WO1992008203A1 - Handwritten digit recognition apparatus and method - Google Patents

Handwritten digit recognition apparatus and method Download PDF

Info

Publication number
WO1992008203A1
WO1992008203A1 PCT/US1991/003624 US9103624W WO9208203A1 WO 1992008203 A1 WO1992008203 A1 WO 1992008203A1 US 9103624 W US9103624 W US 9103624W WO 9208203 A1 WO9208203 A1 WO 9208203A1
Authority
WO
WIPO (PCT)
Prior art keywords
characters
image
lines
medial axis
line
Prior art date
Application number
PCT/US1991/003624
Other languages
French (fr)
Inventor
David L. Mccubbrey
Original Assignee
Environmental Research Institute Of Michigan
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Environmental Research Institute Of Michigan filed Critical Environmental Research Institute Of Michigan
Priority to DE91915082T priority Critical patent/DE555227T1/en
Priority to JP3514410A priority patent/JPH06501800A/en
Publication of WO1992008203A1 publication Critical patent/WO1992008203A1/en

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B07SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C3/00Sorting according to destination
    • B07C3/10Apparatus characterised by the means used for detection ofthe destination
    • B07C3/14Apparatus characterised by the means used for detection ofthe destination using light-responsive detecting means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/14Image acquisition
    • G06V30/146Aligning or centring of the image pick-up or image-field
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/42Document-oriented image-based pattern recognition based on the type of document
    • G06V30/424Postal images, e.g. labels or addresses on parcels or postal envelopes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S209/00Classifying, separating, and assorting solids
    • Y10S209/90Sorting flat-type mail

Definitions

  • the technical field of the present invention relates to optical character recognition and more particularly recognition of handwritten digits.
  • optical character recognition deals with the problem of separating and indicating printed or written characters.
  • the document is scanned in some fashion to produce a electrical image of the marks of the document. This image of the marks is analyzed by computer to produce an indication of each character of the document. It is within the current state of the art to produce relatively error free indication of many typewritten and printed documents. The best systems of the prior art are capable of properly distinguishing a number of differing type fonts.
  • unconstrained handwritten characters have not been successfully located and recognized by present optical systems.
  • the problem of properly reading unconstrained handwritten characters is difficult because of the great variability of the characters.
  • One person may not write the same character exactly the same every time.
  • the variability between different persons writing the same character is even greater than the variability of a single person.
  • handwritten text is often not cleanly executed.
  • characters may overlap horizontally. Loops and descenders may overlap vertically.
  • Two characters may be connected together, strokes of one character may be disconnected from other strokes of the same character.
  • the individual written lines may be on a slant or have an irregular profile.
  • the different parts of the handwriting may also differ in size. Thus recognition of handwritten characters is a difficult task.
  • the receiving post office recognizes that there is no matching address or addressee in that ZIP code.
  • the mail must then be resorted and redirected to the proper post office. Because of the high expense associated with misdirected mail, it is more desirable to have an automated system reject a piece of mail if the system cannot determine the ZIP code with an extremely high degree of accuracy. The rejected pieces of mail can then be hand sorted at the sending station or other measures can be taken to eliminate or reduce the cost of the misdelivery.
  • Sorting of handwritten mail is an area having a unique set of characteristics.
  • address lines or individual character boxes which would be useful in regularizing the recognition task, are ruled out.
  • the ZIP code employed in a majority of handwritten destination addresses provides all the information needed for the primary sorting operation.
  • Most handwritten ZIP codes are formatted with 5 digits while some handwritten ZIP codes use the longer 9 digit ZIP code. This information is relatively constrained because the ZIP code consists of only 5 or 9 digits.
  • the ZIP code is usually located at the end of the last line of the destination address or sometimes is by itself on the last line.
  • the group of numerals comprising the ZIP code must first be successfully located as a group.
  • a computer system is designed to locate a ZIP code from an digitized address block.
  • the address block can be derived from an addressed envelope, postcard or other label through optical scanning.
  • the digitized address block is comprised of pixels arranged in a matrix.
  • the digital address block is binary with pixels either being part of the foreground image or part of the background.
  • the computer system includes a mechanism for computing horizontal distances between sequential but separated pixels of the foreground image that are in the same row. The computer system subsequently compiles and determines a first significant peak in occurrences of distances which is designated as the interstroke distance.
  • the foreground image represents character strokes of the address block.
  • the strokes are arranged into words based on the interstroke distance.
  • the words are then formatted into groupings, i.e. blocks.
  • the interline vertical connections between different lines of the address block are broken via horizontal erosion of the strokes.
  • the word blocks are then skeletonized down to a horizontal skeleton.
  • a subsystem dilates the resulting horizontal skeleton vertically into boxes with each box having a uniform height and then dilates the boxes horizontally such that boxes overlapping in the horizontal direction are merged together to form line images.
  • the line images are labeled (i.e., numbered) uniquely from the top of the image, to produce line numbers.
  • Another subsystem determines each line image's medial axis and superimposes the line-numbered medial axis onto the original digitized address block.
  • the computer system then bleeds the line number label from each medial axis to identify all strokes connected to the medial axis. Strokes that are connected to two horizontal axes are divided to either the line above or the line below.
  • the mechanism identifies foreground image pixels not connected to any medial axis and excludes these pixels from a subsequent line count.
  • the desired last line that is large enough to contain a ZIP code is then selected and possible wording splits of the last line are determined from interstroke distances and the identified foreground image pixels that do not touch any medial axis. One wording split is selected and a word from the split is identified as the ZIP code location.
  • a mechanism for creating a bounding box of the digitized address block is provided and operations are directed to only pixels within the bounding box to reduce the computer operating time. Furthermore, the pixels within the bounding box are down sampled further reducing computer time while still rendering the needed calculations and processing.
  • the computer system incorporates a parallel processing system. Computational time is hence reduced to acceptable levels while the expense of a sufficiently powerful general computer is avoided.
  • the invention relates to a computer system and method for locating a predetermined group of pixels within a larger selection of pixels forming character images derived from handwriting or machine printing characters.
  • the computer system calculates horizontal distances between separated foreground image pixels in the same row to determine a first peak of distance lengths that is labeled the interstroke distance.
  • the computer system separates the address block image into separate line images using the interstroke distances to form blocks, erodes the blocks horizontally to break interline strokes, skeletonizes the blocks, and subsequently dilates the skeletonized blocks to form lines of the handwritten image.
  • a group of pixels in a particular line is then selected by use of the interstroke distances and identified foreground pixels that do not have a connection to any medial axis of any respective line.
  • FIGURE 1 illustrates, in flow chart form, the process of ZIP code location employed in the preferred embodiment of the present invention
  • FIGURE 2 schematically illustrates a sample address block and its bounding box
  • FIGURE 3 is an enlarged view of the address block in the bounding box schematically illustrating the horizontal distances between two sequential but separated pixels of the foreground image;
  • FIGURE 4 schematically illustrates the arranging of strokes into word blocks based upon the interstroke distance shown in FIGURE 3;
  • FIGURE 5 schematically shows the breaking of the descenders and vertical connections between the lines and the formation of convex hulls
  • FIGURE 6 schematically illustrates skeletonization of the convex hulls
  • FIGURE 7 illustrates the vertically dilated word box areas dilated horizontally into lines and the formed medial axis of each line;
  • FIGURE 8 illustrates superimposing the medial axis of each line shown in FIGURE 7 onto the original bounded down-sampled address block shown in FIGURE 2 and bleeding the characters from the medial axes;
  • FIGURE 9 illustrates a selection of the last line as determined by the previous steps;
  • FIGURE 10 discloses one selected splitting of words
  • FIGURE 11 discloses an alternative selected splitting of words
  • FIGURE 12 discloses a preferred selected word chosen for the ZIP code
  • FIGURE 13 discloses a ZIP code correlating to the word being chosen in FIGURE 12;
  • FIGURE 14 discloses in block diagram form the morphological computer employed in the preferred embodiment of the present invention
  • FIGURE 15 illustrates in block diagram form one of the neighborhood processing stages of the morphological computer illustrated in FIGURE 14.
  • a ZIP code location system of the present invention implementing the method illustrated in Figure 1 is capable of locating a ZIP code within an address block.
  • Figures 2-13 provide an exemplary illustration of the steps diagrammed in Figure 1 and reference will be made to this example as the description of Figure 1 proceeds. The handwritten fictional sample shown in figure
  • the shown example has several common problems that posed problems for various prior art systems.
  • the "J” in the "John” in the first line extends below the medial axis in the second line.
  • the "P” in the middle initial actually is connected to the "n” in the line below.
  • the "S” and the “t” in the middle line extend below the top of the ZIP code in the line below.
  • the lower part of the "S” is furthermore connected with the extender of the first "0” in the ZIP code.
  • the second “NY” is angled such that the top of the “NY” is vertically located above the bottom of the "S,” “t,” and the “r” in the word “Street” in the line above.
  • the word “Main” is positioned significantly higher with regard to the word “Street” such that this line of the address is significantly wavy.
  • the letters also vary in size, e.g., compare the two capital “M's.”
  • the letters have extra loops, e.g., the "M” in “Main,” the initial "P” and the first "0” in the ZIP code.
  • the strokes are relatively jagged and the ZIP code is unevenly separated by the intrusion of the "t” and the wider spacing between the second "0” and the “7.”
  • a digitized address block 21 as shown in Figure
  • the block 21 forms input 20 into the system.
  • the block 21 can originally be obtained from an optical scan or can be previously digitized and stored on disk or other computer storage techniques.
  • the address block 21 is inputted in digitized form in an array of pixels that are horizontally and vertically spaced into rows and columns.
  • the address block pixels can have background states or image states.
  • the image states can be the state of thinned components, end points, junctions and "flesh," i.e., the part of the image removed during thinning.
  • the address block 21 is first analyzed for its quality (step 24) which includes noise, dropouts, broken strokes and other image processing defects which can effect analysis of the image. The defects are then quantified and the image is then classified as a certain quality 22.
  • the incoming address block 21 then has noise and dropouts filtered (step 26) to the extent desired.
  • a bounding box 23 as shown in Figure 2 is then determined (step 28) .
  • a bounding box is determined by the most left and right, and the uppermost and lowermost extent of the strokes of the image as shown by example in Figure 2.
  • the image is then down-sampled within the bounding box 23 as indicated by step 30.
  • the bounding box is formed and downsampled to reduce computer time.
  • the address block 21 then has horizontal stroke separation computed (step 32) as schematically shown in Figure 3.
  • the horizontal spacing between two sequential but separated and horizontally aligned is computed. The spacing between different sequential but separated are illustrated by spaces 25, 27, 29 and 31 of differing lengths.
  • the strokes are then arranged into words (step 34) .
  • the words 35 are determined from the interstroke distances 31 and the wider distances 25 and
  • Blocks 35 schematically represent the groupings of each word.
  • the vertical stroke connections between the lines are then broken (step 36) via horizontal dilation and subsequent horizontal erosion of the characters where thin descenders and long extenders 37 of characters are eliminated.
  • the elimination of descenders and extenders 37 break the connections between the two adjacent address lines.
  • Each block of words 35 then is completely separated and these group blocks 35 are then formed into convex hulls 33 about the eroded image.
  • the hulls 33 are then skeletonized as shown in step 38 into skeletal segments 39 as shown in Figure 6.
  • the blocks 35 are then further grouped horizontally into address lines. This is accomplished by dilating the skeletonized segments 39 vertically from the skeletal segments 39 to form boxed areas 41 of uniform vertical thickness. As shown in Figure 7, the boxed areas 41 are then dilated horizontally such that any horizontal overlap of one area 41 with an adjacent area 41 is filled in as indicated in areas 43.
  • the next step 44 is to label strokes according to line number.
  • Step 44 Based on the bleeding, the punctuation, and the 5 interstroke distances, the strokes are grouped into words within the lines shown in step 44. We now have line grouped word candidates. Step 46 now either discards impossibly small lines or merges the small lines together as indicated in step 48 if there is a horizontal overlap
  • the last or lowest line 57 as indicated in Figure 9 is selected as shown in step 49.
  • the last line however does not include the lowest extension of the "t" in "Street” in the line above nor will it include any of the part of the first "0" above the point
  • the last line 57 is split into words as shown in step 50.
  • Figure 10 indicates a splitting into three words with "NY" before the punctuation mark 55 forming one word 59, the second "NY" forming a word 61 after the punctuation
  • the split is a result of the slightly larger distances between the second "0" and the "7."
  • the word split shown in Figure 10 is preferred over the word split shown in Figure 11.
  • the word 63 is then selected as being the location of the ZIP code and as shown in Figure 12.
  • Step 52 provides that the corresponding characters 69 for word 63 are shown in full resolution as illustrated in Figure 13. Based upon the class of the image quality as indicated in step 22, noise, blobs and dropouts within the word 63 are repaired as indicated in step 70. The blobs and noise are labeled in step 72 and the image pixels in word 63 are shown on a screen in step
  • the ZIP code is then transferred to a digit separator in step 76 in which the group of ZIP code digits can then be segmented, and the digits are then analyzed recognized by step 78 with a digit recognizer. If per chance a 9 digit ZIP code is used, the 9 digit ZIP code is detected and the digit separator then determines 9 digits rather than 5 digits.
  • the computer system used with the ZIP code location process is preferably a morphological type computer which is preferably constructed in accordance with U.S. Patent No. 4,167,728 issued September 11, 1979 to Sternberg and entitled “Automatic Image Processor” and is commercially known by the mark “Cytocomputer.”
  • the teachings of U.S. Patent No. 4,167,728 are incorporated herein by reference. Briefly, the construction is described in conjunction with Figures 14 and 15.
  • the overall construction of the morphological computer 70 is illustrated in Figure 14 and the construction of a single neighborhood processing stage 80 is illustrated in Figure 15.
  • the morphological computer 70 includes of a pipeline of a plurality of neighborhood processing stages 80, 82...84.
  • the first neighborhood processing stage 80 receives as its input a data stream corresponding to individual pixels of a binary image as the incoming address block in a raster scan fashion.
  • the image of the incoming address block includes data corresponding to individual pixels arranged in a plurality of rows and columns.
  • the raster scan data stream consists of pixels in order starting with the top row of the left-most pixel to the right-most pixel, followed by the next row in left to right order followed by each succeeding row in similar fashion.
  • the neighborhood processing stage 80 in turn produces an output stream of data also corresponding to individual pixels of a transformed image in a raster scan sequence. Each pixel of this output data stream corresponds to a particular pixel of the input data stream, the neighborhood processing stage 80 forms each pixel of the output data stream based upon the value of the corresponding input pixel and the values of the 8 neighboring pixels. Thus, each pixel of the output data stream corresponds to the neighborhood of a corresponding input pixel.
  • the output of each neighborhood processing stage 80,82... is supplied to the input of the next following stage.
  • the output of the last neighboring processing stage 84 forms the output of the morphological computer 70.
  • each neighborhood processing stage 80,82 ... 84 has a unique digital address.
  • the transformation controller 90 specifies a particular address on address line 92 and then specifies a command corresponding to a particular transformation on command line 94.
  • the neighborhood processing stage 80,82... 84 having the specified address stores the command. Each stage then performs the transformation corresponding to its last received command.
  • FIG. 15 illustrates in further detail the construction of an exemplary neighborhood processing stage 80.
  • the neighborhood processing stage 80 operates in conjunction with the delay line formed of pixel elements 100-108 and shift register delay lines 110 and 112. Pixel elements 100-108 are each capable of storing the bits corresponding to the data of a single pixel of the input image.
  • Shift register delay lines 110 and 112 have a length equal to three less than the number of pixels within each line of the image. The length of the shift register delay lines 110 and 112 are selected to ensure that pixel elements 100, 103 and 106 store data corresponding to pixels vertically adjacent in the input image. Likewise, the data and pixel elements 101, 104, 107 correspond to vertically adjacent pixels and the data in pixel elements 102, 105, 108 correspond to vertically adjacent pixels.
  • Pixel data is supplied in raster scan fashion to the input of the neighborhood processing stage 80.
  • the pixel is first stored in pixel element 100.
  • the pixel stored in pixel element 100 is shifted to the pixel element 101 and the new pixel is stored in pixel element 100. Receipt of the next pixel shifts the first pixel to pixel element 102, the second pixel to pixel element 101 and the just received pixel stored in pixel element 100.
  • This process of shifting data along the delay line continues in the direction of the arrows appearing in Figure 15. Once the pixel reaches pixel element 108, it is discarded upon receipt of the next pixel.
  • the neighborhood processing stage 80 operates by presenting appropriate pixel data to combination circuit 114.
  • pixel elements 100-108 store a 3 x 3 matrix of pixel elements which are adjacent in the original image. If pixel element 104 represents the center pixel, then pixel elements 100, 101, 102, 103, 105, 106, 107, 108 represent the eight immediately adjacent pixels.
  • This combination circuit 114 forms some combination of the nine pixels. Such combinations could take many forms.
  • the pixel output data may have more or fewer bits than the input data depending on the combination formed. It is also feasible that combination circuit 114 may form comparisons between one or more of the pixels or between a pixel and a constant received from transformation controller 90. The essential point is that combination circuit 114 forms an output pixel from some combination of the pixels stored in the pixel elements 100-108.
  • Each neighborhood processing stage 80,82 ... 84 forms a neighborhood operation on the received image data as fast as that data can be recalled from memory.
  • Each stage requires only a fixed delay related to the line length of the image before it is producing a corresponding output pixel stream at the same rate as it receives pixels. Dozens, hundreds or even thousands of these neighborhood processing stages can be disposed in the chain. While each neighborhood processing stage performs only a relatively simple function, the provision of long chains of such stages enables extensive image operations within a short time frame.
  • location of the ZIP code does require a complex and extensive computation due to the number of problems that are inherent in handwritten ZIP codes such as descenders, slanted lines, and jagged lines, irregular spacings, broken strokes, interconnected characters and lines and ink blots and other image noise.
  • the hardware system such as the one described is needed to provide the computational capacity to work on a typical handwritten address block to locate the ZIP code within that block.

Abstract

A computer system and a method for a mail sorting operation in which the computer system determines the location of the ZIP code within a digital image of an address block (20) from a piece of mail. An interstroke distance is calculated for the image and the strokes of the image are thinned (38) to enhance vertical separation between the lines of the address block. A medial axis for each line is determined and the medial axis is superimposed upon the digital image. A bleeding operation is conducted on the digital image from the medial axis at which data bits that do not connect to the medial axis are notated as punctuation and interlinear connected strokes are then divided between the two lines. The last line which is determined to be large enough to contain a ZIP code based on bounding box size is then selected. Alternate splits of words are formed and the best split is selected (50) in which the last formed group is detected to be the ZIP code.

Description

HANDWRITTEN DIGIT RECOGNITION APPARATUS & METHOD
Technical Field of the Invention
The technical field of the present invention relates to optical character recognition and more particularly recognition of handwritten digits.
Background of the Invention
There are many instances where it would be useful or desirable to provide a computer readable form of a document not available in a compatible computer readable form. Normally it is the case that the document is not available in machine readable form because the document was handwritten or typewritten and thus no computer readable form exists, or because the computer readable form is not available. In some instances there is a "foreign11 document, i.e. an existing computer readable form but the document was produced on an incompatible computer system. In some instances, such as facsimile transmission, a simple optical scan of the document can produce the required form. In most instances the form most useful for later use and decision making is a separate indication of each character of the document.
The field of optical character recognition deals with the problem of separating and indicating printed or written characters. In optical character recognition, the document is scanned in some fashion to produce a electrical image of the marks of the document. This image of the marks is analyzed by computer to produce an indication of each character of the document. It is within the current state of the art to produce relatively error free indication of many typewritten and printed documents. The best systems of the prior art are capable of properly distinguishing a number of differing type fonts.
On the other hand, unconstrained handwritten characters have not been successfully located and recognized by present optical systems. The problem of properly reading unconstrained handwritten characters is difficult because of the great variability of the characters. One person may not write the same character exactly the same every time. The variability between different persons writing the same character is even greater than the variability of a single person. In addition to the variability of the characters themselves, handwritten text is often not cleanly executed. Thus characters may overlap horizontally. Loops and descenders may overlap vertically. Two characters may be connected together, strokes of one character may be disconnected from other strokes of the same character. Further, the individual written lines may be on a slant or have an irregular profile. The different parts of the handwriting may also differ in size. Thus recognition of handwritten characters is a difficult task.
An example of a field where recognition of handwritten characters would be very valuable is in mail sorting. Each piece of mail must be classified by destination address. Currently, a large volume of typewritten and printed mail is read and sorted using prior art optical character recognition techniques. Presently, approximately 15% of current U.S. mail that is hand addressed. Present technology uses automated conveyer systems to present these pieces of mail, one at a time, to an operator who views the address and enters a code for the destination. This is the most labor intensive, slowest and consequently most expensive part of the entire mail sorting operation. Furthermore, it is expensive to misidentify a ZIP code and send the piece of mail to the wrong post office. Once the mail is forwarded to the receiving post office, the receiving post office recognizes that there is no matching address or addressee in that ZIP code. The mail must then be resorted and redirected to the proper post office. Because of the high expense associated with misdirected mail, it is more desirable to have an automated system reject a piece of mail if the system cannot determine the ZIP code with an extremely high degree of accuracy. The rejected pieces of mail can then be hand sorted at the sending station or other measures can be taken to eliminate or reduce the cost of the misdelivery.
Sorting of handwritten mail is an area having a unique set of characteristics. First, due to the problem of user acceptance it is not feasible to place further constraints on the address. Thus address lines or individual character boxes, which would be useful in regularizing the recognition task, are ruled out. On the other hand, there already exists a relatively constrained portion of the current address. The ZIP code employed in a majority of handwritten destination addresses provides all the information needed for the primary sorting operation. Most handwritten ZIP codes are formatted with 5 digits while some handwritten ZIP codes use the longer 9 digit ZIP code. This information is relatively constrained because the ZIP code consists of only 5 or 9 digits. In addition the ZIP code is usually located at the end of the last line of the destination address or sometimes is by itself on the last line.
Various systems have been devised to recognize handwritten digits. However, many of these systems assume that the digits are already located and isolated and the problem is only to determine which numeral the handwritten digit represents. Often these systems require the digits to be written inside individual boxes.
In order for a computer to analyze and recognize the handwritten numerals in a hand-written ZIP code in an address block typically appearing on an envelope, the group of numerals comprising the ZIP code must first be successfully located as a group.
Even though the above mentioned constraints on the ZIP code in the form of number of digits and location exist, previous attempts to locate the ZIP code have encountered problems. The same problems that exist in general for successful recognition of handwriting also pose problems for locating the ZIP code. Previous attempts to count lines of a handwritten address block have been stymied by loops, descenders, line slant or other line irregularities.
What is needed is a highly reliable system to correctly locate the ZIP code in an address block before analysis of the digits of the ZIP code.
Summary of the Invention
In accordance with one aspect of the invention, a computer system is designed to locate a ZIP code from an digitized address block. The address block can be derived from an addressed envelope, postcard or other label through optical scanning. The digitized address block is comprised of pixels arranged in a matrix. Preferably the digital address block is binary with pixels either being part of the foreground image or part of the background. The computer system includes a mechanism for computing horizontal distances between sequential but separated pixels of the foreground image that are in the same row. The computer system subsequently compiles and determines a first significant peak in occurrences of distances which is designated as the interstroke distance. In the foreseen application, the foreground image represents character strokes of the address block. The strokes are arranged into words based on the interstroke distance. The words are then formatted into groupings, i.e. blocks. The interline vertical connections between different lines of the address block are broken via horizontal erosion of the strokes. The word blocks are then skeletonized down to a horizontal skeleton. A subsystem dilates the resulting horizontal skeleton vertically into boxes with each box having a uniform height and then dilates the boxes horizontally such that boxes overlapping in the horizontal direction are merged together to form line images. The line images are labeled (i.e., numbered) uniquely from the top of the image, to produce line numbers. Another subsystem then determines each line image's medial axis and superimposes the line-numbered medial axis onto the original digitized address block.
Desirably, the computer system then bleeds the line number label from each medial axis to identify all strokes connected to the medial axis. Strokes that are connected to two horizontal axes are divided to either the line above or the line below. The mechanism identifies foreground image pixels not connected to any medial axis and excludes these pixels from a subsequent line count. The desired last line that is large enough to contain a ZIP code is then selected and possible wording splits of the last line are determined from interstroke distances and the identified foreground image pixels that do not touch any medial axis. One wording split is selected and a word from the split is identified as the ZIP code location.
Preferably a mechanism for creating a bounding box of the digitized address block is provided and operations are directed to only pixels within the bounding box to reduce the computer operating time. Furthermore, the pixels within the bounding box are down sampled further reducing computer time while still rendering the needed calculations and processing.
Preferably the computer system incorporates a parallel processing system. Computational time is hence reduced to acceptable levels while the expense of a sufficiently powerful general computer is avoided.
In accordance with a broader aspect of the invention, the invention relates to a computer system and method for locating a predetermined group of pixels within a larger selection of pixels forming character images derived from handwriting or machine printing characters. The computer system calculates horizontal distances between separated foreground image pixels in the same row to determine a first peak of distance lengths that is labeled the interstroke distance. The computer system separates the address block image into separate line images using the interstroke distances to form blocks, erodes the blocks horizontally to break interline strokes, skeletonizes the blocks, and subsequently dilates the skeletonized blocks to form lines of the handwritten image. A group of pixels in a particular line is then selected by use of the interstroke distances and identified foreground pixels that do not have a connection to any medial axis of any respective line.
Brief Description of the Drawings
Reference now is made to the accompanying drawings in which: FIGURE 1 illustrates, in flow chart form, the process of ZIP code location employed in the preferred embodiment of the present invention;
FIGURE 2 schematically illustrates a sample address block and its bounding box;
FIGURE 3 is an enlarged view of the address block in the bounding box schematically illustrating the horizontal distances between two sequential but separated pixels of the foreground image; FIGURE 4 schematically illustrates the arranging of strokes into word blocks based upon the interstroke distance shown in FIGURE 3;
FIGURE 5 schematically shows the breaking of the descenders and vertical connections between the lines and the formation of convex hulls;
FIGURE 6 schematically illustrates skeletonization of the convex hulls;
FIGURE 7 illustrates the vertically dilated word box areas dilated horizontally into lines and the formed medial axis of each line;
FIGURE 8 illustrates superimposing the medial axis of each line shown in FIGURE 7 onto the original bounded down-sampled address block shown in FIGURE 2 and bleeding the characters from the medial axes; FIGURE 9 illustrates a selection of the last line as determined by the previous steps;
FIGURE 10 discloses one selected splitting of words; FIGURE 11 discloses an alternative selected splitting of words;
FIGURE 12 discloses a preferred selected word chosen for the ZIP code; FIGURE 13 discloses a ZIP code correlating to the word being chosen in FIGURE 12;
FIGURE 14 discloses in block diagram form the morphological computer employed in the preferred embodiment of the present invention; and FIGURE 15 illustrates in block diagram form one of the neighborhood processing stages of the morphological computer illustrated in FIGURE 14.
Detailed Description of the Preferred Embodiment
A ZIP code location system of the present invention implementing the method illustrated in Figure 1 is capable of locating a ZIP code within an address block. Figures 2-13 provide an exemplary illustration of the steps diagrammed in Figure 1 and reference will be made to this example as the description of Figure 1 proceeds. The handwritten fictional sample shown in figure
2 illustrates several problems that may occur in a handwritten address. The handwritten sample is only an example and it should be understood that the same below described method is equally applicable to other handwritings that can be quite distinctive and very different from the one shown.
The shown example has several common problems that posed problems for various prior art systems. The "J" in the "John" in the first line extends below the medial axis in the second line. Furthermore, the "P" in the middle initial actually is connected to the "n" in the line below. The "S" and the "t" in the middle line extend below the top of the ZIP code in the line below. The lower part of the "S" is furthermore connected with the extender of the first "0" in the ZIP code. The second "NY" is angled such that the top of the "NY" is vertically located above the bottom of the "S," "t," and the "r" in the word "Street" in the line above. The word "Main" is positioned significantly higher with regard to the word "Street" such that this line of the address is significantly wavy. The letters also vary in size, e.g., compare the two capital "M's." Furthermore, the letters have extra loops, e.g., the "M" in "Main," the initial "P" and the first "0" in the ZIP code. Furthermore, the strokes are relatively jagged and the ZIP code is unevenly separated by the intrusion of the "t" and the wider spacing between the second "0" and the "7." A digitized address block 21 as shown in Figure
2 forms input 20 into the system. The block 21 can originally be obtained from an optical scan or can be previously digitized and stored on disk or other computer storage techniques. The address block 21 is inputted in digitized form in an array of pixels that are horizontally and vertically spaced into rows and columns. The address block pixels can have background states or image states. The image states can be the state of thinned components, end points, junctions and "flesh," i.e., the part of the image removed during thinning. The address block 21 is first analyzed for its quality (step 24) which includes noise, dropouts, broken strokes and other image processing defects which can effect analysis of the image. The defects are then quantified and the image is then classified as a certain quality 22. The incoming address block 21 then has noise and dropouts filtered (step 26) to the extent desired. A bounding box 23 as shown in Figure 2 is then determined (step 28) . A bounding box is determined by the most left and right, and the uppermost and lowermost extent of the strokes of the image as shown by example in Figure 2. The image is then down-sampled within the bounding box 23 as indicated by step 30. The bounding box is formed and downsampled to reduce computer time. The address block 21 then has horizontal stroke separation computed (step 32) as schematically shown in Figure 3. The horizontal spacing between two sequential but separated and horizontally aligned is computed. The spacing between different sequential but separated are illustrated by spaces 25, 27, 29 and 31 of differing lengths. Common printing and handwriting provides that there is a common range of spacing between most adjacent vertical strokes as indicated by the stroke distances labeled 31. Significantly smaller gap distances occur less often than stroke distance 31. Distances approximately equal to the gap distance 25 between horizontally adjacent image words occur less often than smaller stroke distances. In addition, horizontal gaps that are slightly greater than the stroke distance 31 decrease in number such that the computer can calculate a first peak of stroke distances approximately equal to distance 31 which are labeled an interstroke distance.
With the calculated interstroke distance 31 for address block 21 as a guide, the strokes are then arranged into words (step 34) . The words 35 are determined from the interstroke distances 31 and the wider distances 25 and
29 in Figure 3. The result of the grouping step 34 is shown in Figure 4. Blocks 35 schematically represent the groupings of each word. The vertical stroke connections between the lines are then broken (step 36) via horizontal dilation and subsequent horizontal erosion of the characters where thin descenders and long extenders 37 of characters are eliminated. The elimination of descenders and extenders 37 break the connections between the two adjacent address lines.
Each block of words 35 then is completely separated and these group blocks 35 are then formed into convex hulls 33 about the eroded image. The hulls 33 are then skeletonized as shown in step 38 into skeletal segments 39 as shown in Figure 6. As shown in step 40, the blocks 35 are then further grouped horizontally into address lines. This is accomplished by dilating the skeletonized segments 39 vertically from the skeletal segments 39 to form boxed areas 41 of uniform vertical thickness. As shown in Figure 7, the boxed areas 41 are then dilated horizontally such that any horizontal overlap of one area 41 with an adjacent area 41 is filled in as indicated in areas 43. The next step 44 is to label strokes according to line number. This is accomplished by determining a medial axis 45 for each line 1, 2 and 3 shown in Figure 7 and superimposing the line-numbered medial axis 45 onto the original down-sampled image of the address block 21 as shown in Figure 8. A line number bleeding process based on connectivity is performed. The bleeding process starts at the line-numbered medial axis. Any lettering that is directly connected to the medial axis or any stroke that is connected to a stroke that is in turn touching the medial axis will be identified as belonging to that medial axis of either lines l, 2 or 3. For example, the descender of the "t" in the word "street," even though it is below the top of the "0" and the top of the "7" of the third line will be identified as part of the second line. The "r" in "Mr.," even though situated below the medial axis 44 will be identified as part of the first line since it is connected to the "M" and the line number bleeding will occur from the "M" into the "r." The bleeding also helps define letters of two different lines that are connected to each other. The extender for the "P" in the middle initial and the extender of the "n" in "Main" are connected as are and the "S" in the word "Street" and the "0" in the third line are connected. These characters are divided apart by the bleeding of the respective letters. The bleeding of the different lines meet at points 51. By definition any image pixel above point 51 is identified with the upper character and any image pixel below the point 51 is identified with the lower character. The period 53 and comma 55 are not connected to any axis and are therefor be left unlabeled and designated as punctuation marks.
Based on the bleeding, the punctuation, and the 5 interstroke distances, the strokes are grouped into words within the lines shown in step 44. We now have line grouped word candidates. Step 46 now either discards impossibly small lines or merges the small lines together as indicated in step 48 if there is a horizontal overlap
10 detected between these lines. The last or lowest line 57 as indicated in Figure 9 is selected as shown in step 49. The last line however does not include the lowest extension of the "t" in "Street" in the line above nor will it include any of the part of the first "0" above the point
15 51.
The last line 57 is split into words as shown in step 50. Figure 10 indicates a splitting into three words with "NY" before the punctuation mark 55 forming one word 59, the second "NY" forming a word 61 after the punctuation
20 mark 55 and before the relatively large gap 27 as shown in Figure 3. The "10073" forms a third word 63. Alternative splits are also performed as shown in Figure 11. The alternate four-word splitting has the "100" in one word labeled 65 and the "73" is in a second word labeled 67.
25 The split is a result of the slightly larger distances between the second "0" and the "7." However, due to other constraints, for example, the size of the word 67 being too small for a ZIP code in and of itself based on interstroke distances, the word split shown in Figure 10 is preferred over the word split shown in Figure 11. The word 63 is then selected as being the location of the ZIP code and as shown in Figure 12.
Step 52 provides that the corresponding characters 69 for word 63 are shown in full resolution as illustrated in Figure 13. Based upon the class of the image quality as indicated in step 22, noise, blobs and dropouts within the word 63 are repaired as indicated in step 70. The blobs and noise are labeled in step 72 and the image pixels in word 63 are shown on a screen in step
74. The ZIP code is then transferred to a digit separator in step 76 in which the group of ZIP code digits can then be segmented, and the digits are then analyzed recognized by step 78 with a digit recognizer. If per chance a 9 digit ZIP code is used, the 9 digit ZIP code is detected and the digit separator then determines 9 digits rather than 5 digits.
The computer system used with the ZIP code location process is preferably a morphological type computer which is preferably constructed in accordance with U.S. Patent No. 4,167,728 issued September 11, 1979 to Sternberg and entitled "Automatic Image Processor" and is commercially known by the mark "Cytocomputer." The teachings of U.S. Patent No. 4,167,728 are incorporated herein by reference. Briefly, the construction is described in conjunction with Figures 14 and 15. The overall construction of the morphological computer 70 is illustrated in Figure 14 and the construction of a single neighborhood processing stage 80 is illustrated in Figure 15.
In general, the morphological computer 70 includes of a pipeline of a plurality of neighborhood processing stages 80, 82...84. The first neighborhood processing stage 80 receives as its input a data stream corresponding to individual pixels of a binary image as the incoming address block in a raster scan fashion. The image of the incoming address block includes data corresponding to individual pixels arranged in a plurality of rows and columns. The raster scan data stream consists of pixels in order starting with the top row of the left-most pixel to the right-most pixel, followed by the next row in left to right order followed by each succeeding row in similar fashion.
The neighborhood processing stage 80 in turn produces an output stream of data also corresponding to individual pixels of a transformed image in a raster scan sequence. Each pixel of this output data stream corresponds to a particular pixel of the input data stream, the neighborhood processing stage 80 forms each pixel of the output data stream based upon the value of the corresponding input pixel and the values of the 8 neighboring pixels. Thus, each pixel of the output data stream corresponds to the neighborhood of a corresponding input pixel. The output of each neighborhood processing stage 80,82... is supplied to the input of the next following stage. The output of the last neighboring processing stage 84 forms the output of the morphological computer 70.
The particular transformation or neighborhood operation performed by each neighborhood processing stage 80,82 ... 84 is controlled by transformation controller 90. Each neighborhood processing stage 80,82...84 has a unique digital address. The transformation controller 90 specifies a particular address on address line 92 and then specifies a command corresponding to a particular transformation on command line 94. The neighborhood processing stage 80,82... 84 having the specified address stores the command. Each stage then performs the transformation corresponding to its last received command.
Figure 15 illustrates in further detail the construction of an exemplary neighborhood processing stage 80. The neighborhood processing stage 80 operates in conjunction with the delay line formed of pixel elements 100-108 and shift register delay lines 110 and 112. Pixel elements 100-108 are each capable of storing the bits corresponding to the data of a single pixel of the input image.
An eight bit or sixteen bit pixel in most foreseeable uses would suffice since standard dilation and skeletonization need to define each pixel in one of five states; background, thinned components, end points, junctions, and "flesh." Shift register delay lines 110 and 112 have a length equal to three less than the number of pixels within each line of the image. The length of the shift register delay lines 110 and 112 are selected to ensure that pixel elements 100, 103 and 106 store data corresponding to pixels vertically adjacent in the input image. Likewise, the data and pixel elements 101, 104, 107 correspond to vertically adjacent pixels and the data in pixel elements 102, 105, 108 correspond to vertically adjacent pixels.
Pixel data is supplied in raster scan fashion to the input of the neighborhood processing stage 80. The pixel is first stored in pixel element 100. Upon receipt of the following pixel, the pixel stored in pixel element 100 is shifted to the pixel element 101 and the new pixel is stored in pixel element 100. Receipt of the next pixel shifts the first pixel to pixel element 102, the second pixel to pixel element 101 and the just received pixel stored in pixel element 100. This process of shifting data along the delay line continues in the direction of the arrows appearing in Figure 15. Once the pixel reaches pixel element 108, it is discarded upon receipt of the next pixel. The neighborhood processing stage 80 operates by presenting appropriate pixel data to combination circuit 114. Note that once the shift delay lines 112 and 110 are filled, pixel elements 100-108 store a 3 x 3 matrix of pixel elements which are adjacent in the original image. If pixel element 104 represents the center pixel, then pixel elements 100, 101, 102, 103, 105, 106, 107, 108 represent the eight immediately adjacent pixels. This combination circuit 114 forms some combination of the nine pixels. Such combinations could take many forms. The pixel output data may have more or fewer bits than the input data depending on the combination formed. It is also feasible that combination circuit 114 may form comparisons between one or more of the pixels or between a pixel and a constant received from transformation controller 90. The essential point is that combination circuit 114 forms an output pixel from some combination of the pixels stored in the pixel elements 100-108.
The advantage of the arrangement of Figures 14 and 15 for image operations is apparent. Each neighborhood processing stage 80,82 ... 84 forms a neighborhood operation on the received image data as fast as that data can be recalled from memory. Each stage requires only a fixed delay related to the line length of the image before it is producing a corresponding output pixel stream at the same rate as it receives pixels. Dozens, hundreds or even thousands of these neighborhood processing stages can be disposed in the chain. While each neighborhood processing stage performs only a relatively simple function, the provision of long chains of such stages enables extensive image operations within a short time frame. As known from the above description, location of the ZIP code does require a complex and extensive computation due to the number of problems that are inherent in handwritten ZIP codes such as descenders, slanted lines, and jagged lines, irregular spacings, broken strokes, interconnected characters and lines and ink blots and other image noise. The hardware system such as the one described is needed to provide the computational capacity to work on a typical handwritten address block to locate the ZIP code within that block.
Variations and modifications of the present invention are possible without departing from the scope and spirit of the invention as defined in the appended claims.

Claims

Claims The embodiments in which an exclusive property or privilege is claimed are defined as follows:
1. A computer system for locating a predetermined group of pixels chosen from a digital pixel image set forth in an array of columns and rows, said digital image forming characters arranged in a plurality of lines, said system characterized by: means for computing horizontal distances between horizontally aligned separated sequential image pixels and determining the first significant peak in occurrences of distances referred to as the interstroke distance; means for eroding horizontally said digital pixel image to enhance vertical separation of said characters in said plurality of lines; means for grouping the characters together into blocks based on the interstroke distance and wider distances between said characters; means for skeletonizing said blocks into lines extending the horizontal length of each block; means for dilating the resulting skeletonized image in a vertical direction to create box areas of uniform vertical thickness; means for dilating said resulting box areas horizontally such that box areas overlapping in the horizontal direction are merged together to form line images; means for determining and labeling the medial axis of each respective line image; means for bleeding the labels from said each medial axis to identify image pixels connected to a medial axis directly or via other image pixels such that two differently labeled characters that are in two different medial axes and are connected together are divided where the bleeding of the two medial axes meet; means for identifying a desired line of said characters and associate possible wording groups from interstroke distance; and means for selecting said predetermined group of image pixels from said possible wording groups by using interstroke distances.
2. A system as defined in claim 1 further characterized by: said characters form an address block; and said predetermined group of image pixels form a ZIP code within the address block.
3. A system as defined in claim 2 further characterized by: said identifying means identifies a last line of said address block large enough to include a ZIP code, and said selecting means selects a last wording group in said desired last line sized large enough to be a ZIP code.
4. A system as defined in claim .1 further characterized by: means for identifying image pixels not connected to any medial axis and thereby not bled by said bleeding means; and said means for selecting said predetermined groups using said image pixels not connected to any medial axis as punctuation.
5. A system as defined in claim 1 further characterized by: means for determining the bounding box of said digital image; and means for down-sampling said digital image within said bounding box.
6. A computer system for locating a desired group of characters chosen from a digital pixel image set forth in an array of columns and rows, said digital pixel image forming characters arranged in a plurality of lines, said system characterized by: means for determining the medial axis of each respective line; means for superimposing each respective medial axis onto said image and bleeding pixels forming said digital image from each medial axis to identify pixels connected to the medial axis either directly or via other pixels such that two characters that are in two different horizontal lines and are connected together are divided where the bleeding of the two medial axes meet; line selecting means for selecting a desired line; group selecting means for selecting said desired group of characters within said desired line.
7. A system as defined in claim 6 further characterized by: said input characters form an address block; and said desired group of characters form a ZIP code within the address block.
8. A system as defined in claim 7 further characterized by: said line selecting means selects the last line of said address block, and group selecting means selects a last group in said desired last line.
9. A system as defined in claim 6 further characterized by: means for determining the bounding box of said digital image; and means for down-sampling said digital image within said bounding box.
10. A system as defined in claim 6 further characterized by: means for identifying image pixels not connected to any medial axis and thereby not bled by said bleeding means; and said means for selecting said desired group using said image pixels not connected to any medial axis as punctuation.
11. A computer system as defined in claim 6 further characterized by: means for computing horizontal distances between horizontally aligned separated image pixels and determining the first significant peak in occurrence of distances referred to as the interstroke distance; and said means for selecting said desired group of characters uses said interstroke distance as a factor to form groups of which one is said desired group.
12. A system as defined in claim 11 further characterized by: means for determining the bounding box of said digital image; and means for down-sampling said digital image within said bounding box.
13. A system as defined in claim 11 further characterized by: means for grouping characters together into blocks based on interstate distance; means for skeletonizing said blocks into lines extending the horizontal length of each block; means for dilating said lines in a vertical direction, creating box areas; means for dilating said resulting box areas horizontally such that box areas overlapping in the horizontal direction are merged together to form line images of each line.
14. A computer system for locating a predetermined group of characters chosen from a digital pixel image set forth in array of columns and rows, said digital pixel image forming characters arranged in a plurality of lines, said system characterized by: means for computing horizontal distances between horizontally aligned separated image pixels and determining the first significant peak in occurrence of distances referred to as the interstroke distance; and means for selecting said predetermined group of characters within one of said plurality of lines by using interstroke distances.
15. A system as defined in claim 14 further characterized by: said input characters form an address block; and said predetermined group of characters form a ZIP code within the address block.
16. A system as defined in claim 14 further characterized by: means for determining the bounding box of said digital pixel image; and means for down-sampling said digital pixel image within said bounding box.
17. A method for locating a desired group of characters chosen from a digital pixel image set forth in an array of columns and rows, said digital pixel image forming characters arranged in a plurality of lines, said process characterized by: computing horizontal distances between horizontally aligned separated image pixels and determining the first significant peak in occurrences of distances referred to as the interstroke distance; eroding horizontally said characters to enhance vertical separation of said characters in said plurality of lines; determining the medial axis of each of said plurality of lines; bleeding said characters from each axis to identify all image pixels connected to a medial axis directly or via other image pixels such that two characters that are in two different lines and are connected together are divided where the bleeding of the two medial axes meet; and selecting said desired group of characters by using said interstroke distances.
18. A method as defined in claim 17 further characterized by: determining a bounding box of said digital pixel image; and down-sampling said digital pixel image within said bounding box before said computing step.
19. A method as defined in claim 17 further characterized by: identifying image pixels not connected to the medial axis of any of said plurality of lines; said selecting step uses said identified image pixels as not being connected to any medial axis as punctuation to assist in selecting said predetermined group of characters.
PCT/US1991/003624 1990-10-31 1991-05-23 Handwritten digit recognition apparatus and method WO1992008203A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
DE91915082T DE555227T1 (en) 1990-10-31 1991-05-23 DETECTION METHOD AND DEVICE OF HANDWRITTEN NUMBERS.
JP3514410A JPH06501800A (en) 1990-10-31 1991-05-23 Handwritten digit recognition device and method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US07/606,578 US5216725A (en) 1990-10-31 1990-10-31 Apparatus and method for separating handwritten characters by line and word
US606,578 1990-10-31

Publications (1)

Publication Number Publication Date
WO1992008203A1 true WO1992008203A1 (en) 1992-05-14

Family

ID=24428544

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US1991/003624 WO1992008203A1 (en) 1990-10-31 1991-05-23 Handwritten digit recognition apparatus and method

Country Status (6)

Country Link
US (2) US5216725A (en)
EP (1) EP0555227A4 (en)
JP (1) JPH06501800A (en)
CA (1) CA2094706A1 (en)
DE (1) DE555227T1 (en)
WO (1) WO1992008203A1 (en)

Families Citing this family (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3143461B2 (en) * 1990-05-29 2001-03-07 キヤノン株式会社 Character recognition method and character recognition device
US5216725A (en) * 1990-10-31 1993-06-01 Environmental Research Institute Of Michigan Apparatus and method for separating handwritten characters by line and word
JP3361124B2 (en) * 1991-07-30 2003-01-07 ゼロックス・コーポレーション Image processing method and image processing apparatus on two-dimensional image including text
CA2077274C (en) * 1991-11-19 1997-07-15 M. Margaret Withgott Method and apparatus for summarizing a document without document image decoding
CA2077969C (en) * 1991-11-19 1997-03-04 Daniel P. Huttenlocher Method of deriving wordshapes for subsequent comparison
US5321770A (en) * 1991-11-19 1994-06-14 Xerox Corporation Method for determining boundaries of words in text
JP3576570B2 (en) * 1991-11-19 2004-10-13 ゼロックス コーポレイション Comparison method
CA2077970C (en) * 1991-11-19 1999-02-23 Daniel P. Huttenlocher Optical word recognition by examination of word shape
US5825919A (en) * 1992-12-17 1998-10-20 Xerox Corporation Technique for generating bounding boxes for word spotting in bitmap images
JP2933801B2 (en) * 1993-06-11 1999-08-16 富士通株式会社 Method and apparatus for cutting out characters
JP3445394B2 (en) * 1993-12-17 2003-09-08 ゼロックス・コーポレーション How to compare at least two image sections
US5410611A (en) * 1993-12-17 1995-04-25 Xerox Corporation Method for identifying word bounding boxes in text
KR100228618B1 (en) * 1994-05-31 1999-11-01 아끼구사 나오유끼 Method and apparatus for assigning temporary and true labels to digital image
KR100286163B1 (en) * 1994-08-08 2001-04-16 가네꼬 히사시 Address recognition method, address recognition device and paper sheet automatic processing system
US5633957A (en) * 1994-09-16 1997-05-27 Compaq Computer Corporation Method and apparatus for determining positional guidelines of handwritten data
US5647027A (en) * 1994-10-28 1997-07-08 Lucent Technologies Inc. Method of image enhancement using convolution kernels
CA2178959C (en) * 1994-11-14 2000-05-16 Kenneth J. Guzik Method of splitting handwritten input
US5668891A (en) * 1995-01-06 1997-09-16 Xerox Corporation Methods for determining font attributes of characters
US5917941A (en) * 1995-08-08 1999-06-29 Apple Computer, Inc. Character segmentation technique with integrated word search for handwriting recognition
US6246794B1 (en) * 1995-12-13 2001-06-12 Hitachi, Ltd. Method of reading characters and method of reading postal addresses
US5848191A (en) * 1995-12-14 1998-12-08 Xerox Corporation Automatic method of generating thematic summaries from a document image without performing character recognition
US5892842A (en) * 1995-12-14 1999-04-06 Xerox Corporation Automatic method of identifying sentence boundaries in a document image
US5850476A (en) * 1995-12-14 1998-12-15 Xerox Corporation Automatic method of identifying drop words in a document image without performing character recognition
DE19614285C2 (en) * 1996-04-11 1998-11-12 Siemens Ag Procedure for recognizing sequences of digits
US5835638A (en) * 1996-05-30 1998-11-10 Xerox Corporation Method and apparatus for comparing symbols extracted from binary images of text using topology preserved dilated representations of the symbols
US6108444A (en) * 1997-09-29 2000-08-22 Xerox Corporation Method of grouping handwritten word segments in handwritten document images
JPH11144068A (en) * 1997-11-10 1999-05-28 Seiko Epson Corp Method and device for generating and processing character string image
US6337924B1 (en) * 1999-02-26 2002-01-08 Hewlett-Packard Company System and method for accurately recognizing text font in a document processing system
SE0004144L (en) * 2000-11-13 2002-05-14 C Technologies Ab Text Puss Ling
US7221810B2 (en) * 2000-11-13 2007-05-22 Anoto Group Ab Method and device for recording of information
US6912308B2 (en) * 2000-12-01 2005-06-28 Targus Communications Corp. Apparatus and method for automatic form recognition and pagination
US6940617B2 (en) * 2001-02-09 2005-09-06 Matsushita Electric Industrial Co., Ltd. Printing control interface system and method with handwriting discrimination capability
US7415131B2 (en) * 2002-12-24 2008-08-19 Siemens Energy & Automation, Inc. Method and system for image processing
US7072514B1 (en) * 2003-02-06 2006-07-04 The United States Of America As Represented By The National Security Agency Method of distinguishing handwritten and machine-printed images
US7324706B2 (en) * 2004-09-09 2008-01-29 Silicon Optix Inc. System and method for representing a general two dimensional spatial transformation
CN101027679B (en) * 2004-09-09 2010-04-21 奥普提克斯晶硅有限公司 System and method for representing a general two dimensional spatial transformation
US7711192B1 (en) * 2007-08-23 2010-05-04 Kaspersky Lab, Zao System and method for identifying text-based SPAM in images using grey-scale transformation
US7706613B2 (en) * 2007-08-23 2010-04-27 Kaspersky Lab, Zao System and method for identifying text-based SPAM in rasterized images
JP2009199102A (en) * 2008-02-19 2009-09-03 Fujitsu Ltd Character recognition program, character recognition device and character recognition method
TW201015382A (en) * 2008-10-09 2010-04-16 Univ Nat Chiao Tung Virtual input system and method
US9003531B2 (en) * 2009-10-01 2015-04-07 Kaspersky Lab Zao Comprehensive password management arrangment facilitating security
US8863040B2 (en) * 2011-01-04 2014-10-14 Google Inc. Gesture-based selection
EP3185206B1 (en) * 2015-12-22 2018-09-26 Thomson Licensing Methods and systems for image processing of digital images
CN110287904B (en) * 2019-06-27 2021-07-16 武汉中海庭数据技术有限公司 Crowdsourcing data-based lane line extraction method and device and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4481665A (en) * 1980-12-17 1984-11-06 Tokyo Shibaura Denki Kabushiki Kaisha Character segmentation method
US4847912A (en) * 1986-12-23 1989-07-11 Sharp Kabushiki Kaisha Method of detecting a space between words with optical character reader

Family Cites Families (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3328760A (en) * 1963-12-23 1967-06-27 Rca Corp Character reader for reading machine printed characters and handwritten marks
US3500323A (en) * 1965-12-06 1970-03-10 Ibm Handwritten character recognition apparatus
NL144071B (en) * 1971-07-22 1974-11-15 Nederlanden Staat DEVICE FOR READING AND COMBINED MACHINE AND MANUAL PROCESSING OF SIGNS.
US4024500A (en) * 1975-12-31 1977-05-17 International Business Machines Corporation Segmentation mechanism for cursive script character recognition systems
US4105998A (en) * 1976-03-30 1978-08-08 Fujitsu Limited Pattern recognition processing system
US4066998A (en) * 1976-04-30 1978-01-03 Optical Business Machines, Inc. Method and apparatus for discriminating between characters in character recognition systems
JPS5845305B2 (en) * 1976-11-16 1983-10-08 日本電気株式会社 Address detection device
JPS5827551B2 (en) * 1979-05-18 1983-06-10 日本電信電話株式会社 Online handwritten character recognition method
US4516174A (en) * 1980-03-10 1985-05-07 Ricoh Company, Ltd. Video signal regulating apparatus
NL8006241A (en) * 1980-11-14 1982-06-01 Nederlanden Staat DEVICE FOR AUTOMATIC READING OF CHARACTERS.
JPS57141779A (en) * 1981-02-26 1982-09-02 Nec Corp Character cutout system
JPS5998283A (en) * 1982-11-27 1984-06-06 Hitachi Ltd Pattern segmenting and recognizing system
US4718102A (en) * 1983-01-19 1988-01-05 Communication Intelligence Corporation Process and apparatus involving pattern recognition
DE3480667D1 (en) * 1983-03-01 1990-01-11 Nec Corp CHARACTER SPACE DETERMINATION SYSTEM.
JPS6079485A (en) * 1983-10-06 1985-05-07 Sharp Corp Handwriting character recognition processing device
US4635290A (en) * 1983-12-20 1987-01-06 Nec Corporation Sectioning apparatus and method for optical character reader systems
JPS60136892A (en) * 1983-12-26 1985-07-20 Hitachi Ltd On-line recognition device of hand written graphic
US4731857A (en) * 1984-06-29 1988-03-15 International Business Machines Corporation Recognition system for run-on handwritten characters
JPH0754549B2 (en) * 1984-09-19 1995-06-07 株式会社日立製作所 How to create a standard pattern for pattern matching
US4680803A (en) * 1984-12-17 1987-07-14 Ncr Corporation Method and apparatus for isolating image data for character recognition
US4764972A (en) * 1985-05-23 1988-08-16 Nec Corporation Continuous characters recognition system
US4757549A (en) * 1985-12-12 1988-07-12 International Business Machines Corp. Freehand drawing containing invisible lines
US4817034A (en) * 1986-02-11 1989-03-28 E.S.P. Systems, Inc. Computerized handwriting duplication system
JPH0715703B2 (en) * 1986-05-16 1995-02-22 富士電機株式会社 Character reading method
US5050218A (en) * 1986-08-26 1991-09-17 Nec Corporation Apparatus for recognizing address appearing on mail article
US4876733A (en) * 1986-10-31 1989-10-24 International Business Machines Corporation Method for performing morphic transformations on image data in a general purpose computer
US4797806A (en) * 1987-02-19 1989-01-10 Gtx Corporation High speed serial pixel neighborhood processor and method
US4805228A (en) * 1987-05-04 1989-02-14 The Johns Hopkins University Cellular logic processor
JP2619429B2 (en) * 1987-11-05 1997-06-11 グローリー工業株式会社 How to separate contact characters
FR2657982B1 (en) * 1990-02-02 1992-11-27 Cga Hbs METHOD FOR LOCATING AN ADDRESS ON SORTING ARTICLES, ADDRESSING LABEL AND DEVICE FOR IMPLEMENTING THE METHOD.
US5216725A (en) * 1990-10-31 1993-06-01 Environmental Research Institute Of Michigan Apparatus and method for separating handwritten characters by line and word
US5253304A (en) * 1991-11-27 1993-10-12 At&T Bell Laboratories Method and apparatus for image segmentation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4481665A (en) * 1980-12-17 1984-11-06 Tokyo Shibaura Denki Kabushiki Kaisha Character segmentation method
US4847912A (en) * 1986-12-23 1989-07-11 Sharp Kabushiki Kaisha Method of detecting a space between words with optical character reader

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP0555227A4 *

Also Published As

Publication number Publication date
US5216725A (en) 1993-06-01
EP0555227A4 (en) 1994-06-08
US5544259A (en) 1996-08-06
CA2094706A1 (en) 1992-05-01
JPH06501800A (en) 1994-02-24
EP0555227A1 (en) 1993-08-18
DE555227T1 (en) 1994-04-28

Similar Documents

Publication Publication Date Title
US5216725A (en) Apparatus and method for separating handwritten characters by line and word
US5142589A (en) Method for repairing images for optical character recognition performing different repair operations based on measured image characteristics
US5325447A (en) Handwritten digit normalization method
Pal et al. Script line separation from Indian multi-script documents
US5040226A (en) Courtesy amount read and transaction balancing system
US4903312A (en) Character recognition with variable subdivisions of a character region
US6587572B1 (en) Mail distribution information recognition method and device
EP0385009A1 (en) Apparatus and method for use in image processing
EP0476393A2 (en) Robust prototype establishment in an on-line handwriting recognition system
EP0113410A2 (en) Image processors
US4813078A (en) Character recognition apparatus
US5337370A (en) Character recognition method employing non-character recognizer
JPH05242292A (en) Separating method
US6920247B1 (en) Method for optical recognition of a multi-language set of letters with diacritics
JP3485020B2 (en) Character recognition method and apparatus, and storage medium
JP3388867B2 (en) Address area detecting device and address area detecting method
CN108052955B (en) High-precision Braille identification method and system
CN110516674B (en) Handwritten Chinese character segmentation method and system for text image
Ladwani et al. Novel approach to segmentation of handwritten Devnagari word
JPH04502526A (en) image recognition
JPS60153574A (en) Character reading system
Boraik et al. Characters segmentation from arabic handwritten document images: Hybrid approach
KR20040038384A (en) System for inputting and correcting ancient documents through grouping images of chinese characters
Takru et al. Separation of touching and overlapping words in adjacent lines of handwritten text
Lehal et al. A complete OCR system for Gurmukhi script

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): CA JP

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE DK ES FR GB GR IT LU NL SE

WWE Wipo information: entry into national phase

Ref document number: 2094706

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: 1991915082

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 1991915082

Country of ref document: EP

WWW Wipo information: withdrawn in national office

Ref document number: 1991915082

Country of ref document: EP