JP2007011529A - Method for determining character recognition position in ocr processing - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To make it unnecessary to execute format setting based on software in each document format, to perform character recognition without being influenced by variation in character positions of image data and to automatically search the positions of characters to be recognized. <P>SOLUTION: A reference character string to be a reference is selected from image data of a routine document, and the coordinates of the range of the reference character string and the coordinates of an OCR character recognition target range corresponding to the reference character string are specified by a user interface of a computer system to search the image data in each page. When the reference character string can not be searched for, the range of the reference character string is moved on the image data by changing the value of the coordinates around the coordinates, a character string coincident with the reference character string on the image data is searched, and correspondingly to the movement of the range of the reference character string, the coordinates of the OCR character recognition target range corresponding to the reference character string are moved. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  According to the present invention, when image data obtained by scanning a standard document on a paper medium from a scanner is character-recognized by OCR processing, or an electronic document that has already been processed into image data in PDF format is subjected to OCR processing, The present invention relates to a method for determining a character recognition position in OCR processing for determining a character recognition position for OCR processing.

  In the OCR processing, the character recognition position (range) on the reference image data (reference position) is pre-formatted by software (form layout setting), and the reference image data on the actually captured image data is displayed. A character at a position (range) corresponding to the character recognition position is OCR-recognized. However, if an error occurs between the character recognition position on the actually captured image data and the character recognition position on the reference image data, character recognition may not be performed in the OCR process.

  For example, as shown in FIGS. 1A and 1B, the image data read and processed by the scanner is formed with an inclination with respect to a reference position (reference image data). If the character string to be recognized on the reading surface (target character string) is out of the range (position) formatted with respect to the reference position, character recognition in the OCR process cannot be performed. For this reason, as shown in FIG. 1C, the inclination of the image data that has been read is corrected within a certain range by the document capture processing and OCR processing functions of the scanner. However, even after this correction, if the character string that is the target of image data recognition falls outside the range that is formatted with respect to the reference position, character recognition in the OCR process cannot be performed.

  Further, as shown in FIGS. 2A and 2B, the image data itself processed by software is formed so as to deviate in the vertical and horizontal directions with respect to the reference position (reference image data). As a result, if the character string to be recognized on the original reading surface of the image data (target character string) is out of the range formatted with respect to the reference position, character recognition in the OCR process cannot be performed. For example, such errors occur due to differences in software margin settings and magnification settings, and when such errors occur, it is difficult to correct image data.

  Furthermore, in image data created in large quantities by various methods, the error with respect to the reference position (reference image data) is not constant, and cannot be handled by the method of fixedly formatting the conventional document format. There was a problem.

  When OCR processing is performed by mechanically reading a large number of standard documents, character position irregularities occur in the process of creating image data and electronic text, and many corrections and additional inputs have occurred due to misrecognition of OCR processing. Met. For this reason, there has been a strong demand for development of a document that contributes to digitization of documents, which has been impossible with conventional OCR processing, by improving the recognition rate of characters in OCR processing to reduce correction work and additional input work. .

  The present invention has been made in view of the above circumstances, eliminates the need for software-based format settings for each document format, and allows character recognition without being affected by variations in the character position of image data. Another object of the present invention is to provide a method for determining a character recognition position in the OCR process so that a character position to be recognized can be automatically searched.

In order to achieve the above object, a method for determining a character recognition position in OCR processing according to the present invention selects a reference character string as a reference for search from image data of a standard document, coordinates of the range of the reference character string, and the reference The coordinates of the target range for OCR character recognition corresponding to the character string are set by the user interface of the computer system, and the image data is searched for each page.
In this way, by setting the character recognition position in the OCR process through the user interface of the computer system, it is possible to eliminate the need for format setting by software for each document format.

  The reference character string is moved around the image data by changing the value of the coordinates around the coordinates of the range of the reference character string, and a character string that matches the reference character string on the image data is searched. It is preferable to do.

  It is preferable to move the coordinates of the target range for OCR character recognition corresponding to the reference character string in conjunction with the movement of the reference character string on the image data. As a result, the character position to be recognized by the OCR process can be automatically searched and character recognition by the OCR process can be performed without being affected by the fluctuation of the character position on the image data.

  According to the present invention, for example, even when a document has some distortion, it is possible to perform character recognition by OCR processing. Therefore, it is possible to provide a service that can reduce correction work and additional input work.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
As shown in FIG. 3, the computer system for carrying out the present invention comprises a central processing unit 10, a storage unit 12, a display unit 14, and an input unit 16. Image data (image data) read from a standard document (paper medium) by the scanner 18 or PDF data of a standard document (PDF format) is stored in the storage device 12 of the computer system, and the central processing unit 10 performs OCR processing. Text data obtained from the image data is also stored in the storage device 12.

  As shown in FIG. 4, the image data includes PDF format data (PDF data) obtained by outputting a document document electronically created by a word processor or the like by PDF creation software, and an image obtained by scanning a document document on a paper medium (PDF data). Image data). The image data is information for drawing characters and ruled lines of the original document, and is used for reproducing the original original document on the display device 14 of the computer system and for character recognition in the OCR processing, and is stored as text data after the OCR processing. It is stored in the device 12. One image data is one type of original document format (standard document), and has a data amount corresponding to the amount (for example, the number of original documents) of the original document.

  An example in which the original document shown in FIG. 5 is converted into image data and OCR processing is performed will be described below. When this original document is converted to image data and output to the display device 14, as shown in FIG. 6, the reference character position on the original document and the character position on the image data corresponding to the reference character position are If there is a distortion that cannot be corrected in the document capture stage by the scanner or in the OCR process, and the error when comparing the character positions of the original document and the image data is not constant as one form (standard document), With this format setting (form layout setting using a manuscript document), character recognition is impossible. Therefore, in the present invention, the following processing is performed.

  The processing flow of the present invention is shown in FIG. As shown in FIG. 7, when the process is started, one reference image data from the image data file is output to the display device 14 as input information and displayed. As described above, the image data includes a standard document on a paper medium converted into image data by a scanner function, and a standard document converted into a PDF format electronic document. The image data displayed on the display device 14 is shown in FIG.

  Next, based on the image data displayed on the display device 14, a reference character string serving as a search reference is selected, and the position of the reference character string on the image data is set and stored. Next, the range of the item content that is the target of OCR character recognition corresponding to the reference character string is set and stored. The setting of the reference character string and the setting of the item content range are repeated as many times as the number of character recognition portions in one original document.

  Here, the reference character string means, for example, a fixed item name phrase (character string), and the range of item contents to be subjected to OCR character recognition includes a variable character string corresponding to the reference character string. Means the assumed range. In this example, as shown in FIG. 8, it is assumed that “name” is used as a reference character string, and a character string corresponding to “name”, ie, “Ichiro Suzuki”, is included as an item content range. The example which specified the range to perform is shown.

  Then, as shown in FIG. 9, the character string “name” of the image data displayed on the display device 14 is surrounded by a rectangular frame by the input device 16 of the computer system, and the range is represented by the upper left vertex of the rectangular frame. The coordinates A and the coordinates B of the lower right vertex are obtained by pixel values, the position of the reference character string is set, and this range is stored together with the reference character string obtained by OCR character recognition. Similarly, an assumed range including the character string “Ichiro Suzuki” from the image data displayed on the display device 14 and including the actual name is surrounded by a rectangular frame by the input device 16 of the computer system. The coordinates C of the upper left vertex and the coordinates D of the lower right vertex of the rectangular frame are obtained as pixel values, and the range of the item contents is set and stored. That is, in this example, “name” is selected as the reference character string, the position of the reference character string is set by coordinates A (100, 150) and coordinates B (300, 200), and the range of the item content is set by coordinates C ( 320, 150) and coordinates D (900, 200).

Three types of information stored in the above settings, including the reference character string, the coordinates of the reference character string range, and the coordinates of the item content range corresponding to the reference character string, which are subject to OCR character recognition, are stored in the original document. One item of information is stored in the computer system.
In this example, a case is described in which only one character recognition portion is included in one original document. However, when there are two or more character recognition portions, reference character string setting (reference character string setting) is performed. The selection and setting of the range) and the setting of the item content range are repeatedly stored for the number of character recognition portions.

  As described above, the reference character string and the item content range are set and stored in the computer system, and then the image data read sequentially from the image data file is searched for each page. First, a reference character string in image data is searched using the reference character string as a key. In this example, the reference character string is searched for a character string that matches the reference character string on the image data while turning the range specified on the image data around the coordinates obtained at the position of the reference character string. ing. This makes it possible to perform character recognition by OCR processing without being affected by fluctuations in character positions on the image data.

That is, as shown in FIG. 10, in some image data, the position of the character string that matches the reference character string may be different from the position of the reference character string set as described above. In this case, the range of the rectangular reference character string set as described above is moved from the center to the outer peripheral direction, for example, by changing it in units of one pixel from the center while turning and moving the rectangle. The component in is recognized by OCR characters, and a reference character string (in this example, the character “name”) is searched. The search for the reference character string is not limited to this example. For example, the range of the reference character string may be changed in units of several pixels and turned.
If the reference character string cannot be detected from the image data and the search range is exceeded, the processing of the target item is terminated and the process moves to the next item when the search range is exceeded.

  The range of the item content is captured for the image data in which the reference character string is detected. That is, when the character string is detected, the difference in coordinates moved from the starting point is obtained, and the coordinates of the range of the item content corresponding to the reference character string are moved in proportion to the difference in coordinates, thereby the OCR character. The range of the item content (position of “Ichiro Suzuki” in FIG. 10) that is the recognition target range is captured. At this time, the coordinates of the target range for OCR character recognition in one item are determined. Thereby, the position of the character to be recognized by the OCR process can be automatically searched.

  Next, OCR character recognition of the character string within the range of the item content captured as described above is performed, and the result of OCR character recognition is converted into text and stored. When all items set for one image data are completed, the text data obtained from the image data is stored in the computer system. This completes the processing for one image data.

  As described above, according to this example, it is not necessary to perform format setting by software for each original form, and character recognition can be performed without being affected by fluctuations in the character position of image data. The position of the power should be searched automatically.

FIG. 6 is a diagram illustrating a state in which an image data is tilted due to a physical tilt of the document in the document reading process and is further corrected by a correction process. It is a figure which shows the state from which the position shift | offset | difference occurred in image data itself with the function and use conditions of image data creation processing software. FIG. 2 is a diagram illustrating an example of a computer system for carrying out the present invention. It is a figure which shows the relationship between the manuscript document and image data in the computer system for implementing this invention. It is a figure which shows the example of the fixed form document which converts into image data and recognizes an OCR character. It is a figure which shows an example which displayed the fixed form document shown in FIG. 5 by image data processing. It is a control flow figure of the present invention. It is a figure which shows the example which sets a reference character string and an item range based on the image data displayed on the display apparatus. It is a figure attached | subjected to description of the example which memorize | stores the coordinate of the range of a reference | standard character string, and the coordinate of the range of item content with the reference | standard character string. It is a figure attached | subjected to description of the search of a character string.

Explanation of symbols

10 Central Processing Unit 12 Storage Unit 14 Display Unit 16 Input Unit 18 Scanner

Claims (3)

  A reference character string serving as a search reference is selected from the image data of the fixed form document, and the coordinates of the range of the reference character string and the coordinates of the target range of OCR character recognition corresponding to the reference character string are determined by the user interface of the computer system. A method for determining a character recognition position in OCR processing, characterized by setting and searching image data page by page.   The range of the reference character string is moved on the image data by changing the value of the coordinate around the coordinates, and a character string that matches the reference character string on the image data is searched for. A method for determining a character recognition position in the OCR processing according to Item 1.   3. The method for determining a character recognition position in OCR processing according to claim 2, wherein the coordinates of the target range for OCR character recognition corresponding to the reference character string are moved in conjunction with the movement of the range of the reference character string. .

Images