JP2010182219A - Image processing apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a character recognition technique for a form for achieving an increased recognition rate of bar codes while preventing deterioration of performance such as character recognition speed by discriminating image processings in character recognition and in bar code recognition. <P>SOLUTION: An image processing apparatus includes an image binarization part 101 for binarizing a color or grayscale image of a bar-coded form such as a bar-coded slip, a character recognition part 102 for character-recognizing the binary image of the bar-coded form, a bar code recognition part 103 for bar-code-recognizing the color or grayscale image of the bar-coded form, and a recognition result combination part 104 for combining the result of character recognition by the character recognition part and the result of bar code recognition by the bar code recognition part. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, and more particularly to a technique effective when applied to a character recognition technique for a form such as a slip with a barcode.

  According to a study by the present inventor, examples of character recognition technology for forms and the like include technologies described in Patent Documents 1 to 3, for example.

  Patent Document 1 discloses a technique of an optical scanning and recognition system for bar code characters recorded in documents such as bank exchanges and checks.

  Japanese Patent Application Laid-Open No. 2004-228561 discloses a method and system technique for optically scanning and recognizing barcode characters on a document such as a check.

  Patent Document 3 discloses a technique for preventing the barcode image from being deteriorated when an original with a barcode is converted into an electronic document.

JP-A-5-12487 Japanese Patent Laid-Open No. 5-250515 JP 2008-167314 A

  By the way, the techniques of the above-mentioned Patent Documents 1 and 2 have a problem of barcode character recognition, and aim to improve the barcode recognition rate while preventing performance degradation such as character recognition speed as in the present invention. It is not a thing. The technique of Patent Document 3 is to prevent the barcode image from deteriorating when an original document with a barcode is converted into an electronic document. As in the present invention, performance degradation such as character recognition speed is a problem. It is not intended to improve the barcode recognition rate while preventing the problem.

  Further, as a character recognition technique such as a form, there are, for example, the conventional technique 1 for performing character recognition on a black and white binary image, and the conventional technique 2 to which an optional function for performing barcode recognition is added to this technique. .

  The prior art 1 extracts ruled line information and character information from a monochrome binary image input from a scanner, recognizes characters, and outputs the result to a text file. The prior art 2 is an optional product that recognizes a barcode, and the barcode recognition process can recognize not only a monochrome binary image but also a gray scale image. However, since character recognition is processed in monochrome binary, barcode recognition is also processed in monochrome binary.

  Therefore, when the conventional technique 2 is used, it is necessary to input an image in gray scale in order to make it difficult to be affected by the barcode recognition by the barcode printing state. However, in order to improve the processing speed of character recognition, ruled line information and character information are extracted from a black and white binary image and character recognition processing is performed. For this reason, when character recognition is performed, a black and white binary image is used without using a grayscale image, although a case where a barcode cannot be recognized is expected.

  Accordingly, an object of the present invention is to provide a form character recognition technology that realizes an improvement in barcode recognition rate while distinguishing between character recognition and barcode recognition image processing and preventing performance degradation such as character recognition speed. There is.

  The above and other objects and novel features of the present invention will be apparent from the description of this specification and the accompanying drawings.

  Of the inventions disclosed in the present application, the outline of typical ones will be briefly described as follows.

  That is, the outline of a typical one is an image binarization unit that binarizes a color or gray scale image of a barcoded form such as a slip with a barcode, and a character that recognizes a binary image of a barcoded form. A recognition unit, a barcode recognition unit that recognizes a color or grayscale image of a form with a barcode, and a recognition result composition unit that synthesizes the character recognition result of the character recognition unit and the barcode recognition result of the barcode recognition unit. It is characterized by having.

  In such a configuration, first, a color-added or gray-scale image is input from a scanner or a file as a barcode-added form to be recognized. The input color or grayscale image is saved in a storage device such as a memory or a hard disk. The color or grayscale image is converted into a binary image, and the binary image is stored separately from the color or grayscale image. The barcode portion in the form to be recognized is recognized as a color or gray scale image. Character recognition in a form to be recognized is performed using a binary image. Finally, the barcode recognition result and the character recognition result are combined.

  Among the inventions disclosed in the present application, effects obtained by typical ones will be briefly described as follows.

  In other words, the effect obtained by a typical one is that character recognition is performed on a black-and-white binary image, and the barcode is recognized on a color or grayscale image, so that the processing time for character recognition is not increased. When the barcode is blurred due to the mount for printing the code or the printing method, the barcode recognition rate can be improved. As a result, since the barcode recognition rate is improved, the time for performing calibration for correcting errors can be shortened.

It is a figure for demonstrating the structure and operation | movement of an image processing apparatus of Embodiment 1 of this invention. FIG. 5 is a diagram for explaining an example in which a barcode is input as a grayscale image and a monochrome binary image in the image processing apparatus according to the first embodiment of the present invention. It is a figure for demonstrating the structure and operation | movement of an image processing apparatus of Embodiment 2 of this invention. In the image processing apparatus of Embodiment 2 of this invention, it is a figure for demonstrating the process sequence of a position calculation part. It is a figure for demonstrating the example of a recognition information definition file in the image processing apparatus of Embodiment 2 of this invention. It is a figure for demonstrating the structure and operation | movement of an image processing apparatus of Embodiment 3 of this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that components having the same function are denoted by the same reference symbols throughout the drawings for describing the embodiment, and the repetitive description thereof will be omitted.

  In the following embodiments, a barcoded slip will be described as an example of a barcoded form to be recognized. However, the present invention is not limited to this.

(Embodiment 1)
An image processing apparatus according to Embodiment 1 of the present invention will be described with reference to FIGS. 1 and 2. FIG. 1 is a diagram for explaining the configuration and operation of the image processing apparatus according to the first embodiment. FIG. 2 is a diagram for explaining an example in which a barcode is input in a grayscale image and a monochrome binary image.

  First, the configuration of the image processing apparatus according to the first embodiment will be described with reference to FIG.

  The image processing apparatus according to the first embodiment includes an image binarization unit 101 that binarizes a color or grayscale image of a barcoded slip, and a character recognition unit 102 that recognizes characters of the binary image of a barcoded slip. And a barcode recognition unit 103 that recognizes a color or grayscale image of a slip with a barcode, and a recognition result synthesis unit 104 that synthesizes a character recognition result and a barcode recognition result. Each of these functional units is realized by a program executed by a CPU (not shown) in the image processing apparatus, and is a functional block by software.

  In addition, the image processing apparatus includes data input from the scanner 300 and processing results obtained by the functional units of the image binarization unit 101, the character recognition unit 102, the barcode recognition unit 103, and the recognition result synthesis unit 104. A storage device 150 (150a to 150d) such as a memory or a hard disk for storing data is also provided.

  Next, the operation of the image processing apparatus according to the first embodiment will be described with reference to FIG.

  First, a slip with a barcode is input from the scanner 300, and a color or gray scale image is created on the storage device 150a. At this time, the input method may be input from an image file instead of the scanner 300.

  Subsequently, the image binarization unit 101 binarizes the color or grayscale image of the slip with barcode. At this time, the binary image of the slip with barcode and the color or grayscale image are stored separately in the storage devices 150b and 150c. In addition, regarding the binarization of the image by the image binarization unit 101, any processing method may be used.

  Then, the character recognition unit 102 performs character recognition on the black and white binary image of the barcode attached slip.

  On the other hand, the barcode recognition unit 103 recognizes the barcode on the color or gray scale image of the slip with barcode. By using a color or grayscale image having a large amount of information for the binary image, an improvement in the barcode recognition rate is expected. Note that any method may be used for the barcode recognition processing method of the barcode recognition unit 103.

  Finally, the character recognition result obtained by the character recognition unit 102 and the barcode recognition result obtained by the barcode recognition unit 103 are combined with the recognition result by the recognition result synthesis unit 104 and stored in the storage device 150d. This recognition result is output. The recognition result may be in a text format, or may be in an XML format that holds position information in addition to the recognition result.

  Here, the effect of performing barcode recognition on a color or gray scale image will be described with reference to FIG. FIG. 2 shows an example in which a barcode is input as a grayscale image and a black and white binary image. (A) is an input example using a grayscale image, and (b) is an input example using a black and white binary image.

  In FIG. 2, when comparing the grayscale image of (a) and the black and white binary image of (b), the width of (b) is not uniform and jagged compared to (a). I understand. For this reason, when a monochrome binary image is input, the barcode recognition rate is lower than when a grayscale image is input. Therefore, in the first embodiment, the barcode recognition rate is improved by applying a case where a color or grayscale image is input.

  As described above, according to the image processing apparatus of the first embodiment, the image binarizing unit 101, the character recognizing unit 102, the barcode recognizing unit 103, the recognition result synthesizing unit 104, and the like are configured. Character recognition is performed on images, and barcodes are recognized on color or grayscale images, so that the barcodes are blurred due to the printing method of slips with barcodes without increasing the character recognition processing time. In such a case, an improvement in the barcode recognition rate can be expected. As a result, since the barcode recognition rate is improved, the time for performing calibration for correcting errors can be shortened.

(Embodiment 2)
An image processing apparatus according to a second embodiment of the present invention will be described with reference to FIGS. FIG. 3 is a diagram for explaining the configuration and operation of the image processing apparatus according to the second embodiment. FIG. 4 is a diagram for explaining the processing procedure of the position calculation unit. FIG. 5 is a diagram for explaining an example of the recognition information definition file.

  First, the configuration of the image processing apparatus according to the second embodiment will be described with reference to FIG.

  The image processing apparatus according to the second embodiment is different from the first embodiment in that a position calculating unit 105 that calculates a character recognition position and a barcode recognition position is added. In other words, the image processing apparatus according to the second embodiment includes a binary image of a slip with a barcode in addition to the image binarization unit 101, the character recognition unit 102, the barcode recognition unit 103, and the recognition result synthesis unit 104. Then, a recognition information definition file (stored in the storage device 150e) that defines character recognition positions, barcode recognition positions, and the like is input, and a position calculation unit 105 that calculates a character recognition position and a barcode recognition position. It is comprised including. This position calculation unit 105 is also a functional block by software.

  Next, the operation of the image processing apparatus according to the second embodiment will be described with reference to FIG.

  First, a slip with a barcode is input from the scanner 300, and a color or gray scale image is created on the storage device 150a. At this time, the input method may be input from an image file instead of the scanner 300.

  Subsequently, the image binarization unit 101 binarizes the color or grayscale image of the slip with barcode. At this time, the binary image of the slip with barcode and the color or grayscale image are stored separately in the storage devices 150b and 150c. In addition, regarding the binarization of the image by the image binarization unit 101, any processing method may be used.

  Further, a binary image of a slip with a barcode and a recognition information definition file that defines a character recognition position, a barcode recognition position, and the like are input from the storage device 150e. The position recognized by the barcode is calculated. The recognition position information of characters and barcodes stored in the recognition information definition file may be absolute position information with the origin at the top left of the binary image of the barcoded slip, etc., but how is this position information expressed? It doesn't matter if you use any method. The method for calculating the position may be absolute position information with the origin at the upper left of the binary image, but any calculation method may be used.

  An example of this recognition information definition file will be described with reference to FIG. The recognition information definition file recognizes recognition targets such as characters and barcodes, the position of the rectangular area to be recognized, the recognition information consisting of line type information on the top, bottom, left and right of the rectangular area, and information for detecting displacement The reference area information added to the information is stored.

  Here, the processing procedure of the position calculation unit 105 will be described with reference to FIG. The position calculation unit 105 includes a recognition information definition file input unit 201, a reference area detection unit 202, and a recognition information movement unit 203.

  The recognition information definition file input unit 201 inputs the recognition information from the recognition information definition file shown in FIG. 5 and superimposes it on the binary image of the barcoded slip.

  The reference area detection unit 202 detects the reference area in the binary image of the barcoded slip using information on the reference area in the recognition information definition file.

  In the recognition information moving unit 203, the position information of the recognition information in the recognition information definition file includes the position information of the reference area in the recognition information definition file and the position information of the detection result of the reference area in the binary image of the slip with barcode. Are added to calculate the recognition information for the binary image of the barcoded slip.

  A plurality of reference areas may be set. When a plurality of reference areas are set, the recognition area can be enlarged or reduced in consideration of the shift amount of each position information.

  If it is not necessary to shorten the processing time or there is no recognition information definition file, the barcode recognition position may be the entire binary image of the barcoded slip.

  As described above, the processing of the position calculation unit 105 is executed.

  Returning to FIG. 3, the character recognition unit 102 performs character recognition on the binary image of the barcoded slip based on the calculation result of the position calculation unit 105. If there is no recognition information definition file or there is no character to be recognized, character recognition need not be performed.

  On the other hand, the barcode recognition unit 103 uses the barcode recognition position obtained by the position calculation unit 105 for the color or gray scale image of the slip with barcode based on the calculation result of the position calculation unit 105. To recognize the barcode. By using a color or grayscale image having a large amount of information for the binary image, an improvement in the barcode recognition rate is expected. Note that any method may be used for the barcode recognition processing method of the barcode recognition unit 103.

  Finally, the character recognition result obtained by the character recognition unit 102 and the barcode recognition result obtained by the barcode recognition unit 103 are combined with the recognition result by the recognition result synthesis unit 104 and stored in the storage device 150d. , Output the recognition result. The recognition result may be in a text format, or may be in an XML format that holds position information in addition to the recognition result.

  As described above, according to the image processing apparatus of the second embodiment, as in the first embodiment, an improvement in the barcode recognition rate can be expected without increasing the character recognition processing time. As a result, the time for performing calibration to correct errors can be shortened. Furthermore, according to the second embodiment, the position calculation unit 105 is added, and the barcode recognition is performed using the barcode recognition position obtained by the position calculation unit 105, thereby further improving the barcode. The recognition rate can be improved.

(Embodiment 3)
An image processing apparatus according to Embodiment 3 of the present invention will be described with reference to FIG. FIG. 6 is a diagram for explaining the configuration and operation of the image processing apparatus according to the third embodiment.

  The image processing apparatus according to the third embodiment is different from the second embodiment in that the image binarization unit 101 is omitted. That is, the image processing apparatus according to the third embodiment includes a character recognition unit 102, a barcode recognition unit 103, a recognition result synthesis unit 104, and a position calculation unit 105.

  In the operation of the image processing apparatus according to the third embodiment, a barcoded slip is input from the scanner 300, and a color or grayscale image is created on the storage device 150a. At this time, if the scanner 300 has a function of outputting binary images at the same time, the image binarization unit 101 shown in the second embodiment can be omitted. Thereafter, the processing after the processing by the position calculation unit 105 shown in the second embodiment is similarly performed based on the binary image of the barcoded slip stored separately in the storage devices 150b and 150c and the color or gray scale image. To implement.

  As described above, according to the image processing apparatus of the third embodiment, as in the first embodiment, an improvement in the barcode recognition rate can be expected without increasing the character recognition processing time. As a result, the time for performing calibration to correct errors can be shortened. Furthermore, according to the third embodiment, since the image binarization unit 101 can be omitted, the processing time can be further shortened.

  As mentioned above, the invention made by the present inventor has been specifically described based on the embodiment. However, the present invention is not limited to the embodiment, and various modifications can be made without departing from the scope of the invention. Needless to say.

  For example, in each of the embodiments described above, a barcoded slip has been described as an example of a barcoded document to be recognized. However, the present invention is not limited to this, and a barcoded book, etc. It is widely applicable to other forms and printed materials with barcodes.

  The present invention relates to an image processing apparatus, and is particularly suitable for character recognition technology for forms such as slips with barcodes and books with barcodes, and is widely applicable to all printed matter with barcodes. In addition, the input color or grayscale image is output as an image file and saved in a database or the like in association with recognition results such as barcodes and character information, so that it can be used for all image processing technologies that enable image filing. is there.

DESCRIPTION OF SYMBOLS 101 ... Image binarization part, 102 ... Character recognition part, 103 ... Bar code recognition part, 104 ... Recognition result synthetic | combination part, 105 ... Position calculation part,
150 ... storage device,
201 ... Recognition information definition file input unit, 202 ... Reference region detection unit, 203 ... Recognition information moving unit,
300: Scanner.

Claims (4)

An image binarization unit for binarizing a color or grayscale image of a form with a barcode;
A character recognizing unit for recognizing a binary image of the barcoded form;
A barcode recognition unit that recognizes the barcode or color or grayscale image of the form with the barcode;
An image processing apparatus comprising: a recognition result combining unit that combines a character recognition result of the character recognition unit and a barcode recognition result of the barcode recognition unit. The image processing apparatus according to claim 1.
A binary image of the form with a barcode, a recognition information definition file defining a character recognition position and a barcode recognition position;
The recognition information definition file is input, and further includes a position for recognizing characters and a position calculation unit for calculating a position for recognizing a barcode.
The character recognition unit recognizes a character based on the calculation result of the position calculation unit,
The bar code recognition unit recognizes a bar code based on a calculation result of the position calculation unit. The image processing apparatus according to claim 2.
The position calculation unit
A recognition information definition file input unit that inputs recognition information from the recognition information definition file and superimposes it on a binary image of the barcoded form,
A reference area detection unit that detects a reference area in a binary image of the barcode-added form using information on the reference area in the recognition information definition file;
The position information of the recognition information in the recognition information definition file is added with the difference between the position information of the reference area in the recognition information definition file and the position information of the detection result of the reference area in the binary image of the barcoded form. An image processing apparatus comprising: a recognition information moving unit that calculates recognition information for a binary image of the form with a barcode. A binary image of a form with a barcode, a recognition information definition file that defines character recognition positions and barcode recognition positions,
A position calculator that inputs the recognition information definition file and calculates a position for recognizing characters and a position for recognizing barcodes;
Based on the calculation result of the position calculation unit, a character recognition unit for recognizing the binary image of the form with barcode,
Based on the calculation result of the position calculation unit, a barcode recognition unit that recognizes the barcode or color or grayscale image of the barcoded form,
An image processing apparatus comprising: a recognition result combining unit that combines a character recognition result of the character recognition unit and a barcode recognition result of the barcode recognition unit.

Images