JPH0362286A - Document reading system - Google Patents

Abstract

PURPOSE:To extract the presence/absence of a control line and the information on an editing control code by recognizing the partial control line patterns of both the initiation and the termination of a control line in order to decide the control contents and outputting a control code. CONSTITUTION:A character line including a control line is extracted. A control line part area is detected by separating the area S of the character line and the area T of the control line from the character line including the control line based on the peak width of projection. Thus it is possible to decrease the problem points in terms of the editing job efficiency and the health which are porduced when the text part of an existing document ins read independently of the document eiditing task when a document is produced based on an existing uncoded document.

Description

DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a document reading method, and particularly to a document reading method useful for automatic document reading and editing.

(Prior Art) With the diversification of information processing systems, various data input methods are required, and character recognition technology is also being put into practical use as a powerful data input method. However, current character recognition technology is far inferior to humans in terms of character reading performance, and various improvements have been made. One direction of improvement is to improve the recognition performance of individual characters, and another direction is to improve the reading ability of individual documents.

In recent years, with the spread of Japanese word processors, a variety of printed documents have been created in offices, and four people can easily determine and read text parts, figures, tables, etc. from the various documents.

However, the current character recognition device (hereinafter referred to as OCR: 0ptic)
(abbreviation for Character Reader)), the format of the document is determined in advance, or the operator specifies the text part, reads only the specified text part, and encodes only the characters to create an electronic document. limited to things.

Therefore, in order to create a document based on an uncoded existing document, it is necessary to read the text part of the existing document, create a coded electronic document, and then edit the electronic document. .

(Problem to be solved by the invention) When editing, information such as deleted parts, changed parts, lexical strength parts, character type part designations such as double-width characters and half-width characters is required on existing documents or copies thereof. is written, and the operator edits it while looking at the editing document, but the work is done by visually searching for the editing part on the paper.
Editing is an unnatural process that involves using a keyboard while looking at a display, which poses a work problem in that editing efficiency is low unless the person is an expert, and even for an expert, it is a heavy burden and can lead to fatigue, which is a health problem. There is a problem.

The purpose of the present invention is to solve the problem of work efficiency in editing operations that occurs when reading the text part of the existing document and editing the document are performed independently when creating a document based on an uncoded existing document. An object of the present invention is to provide a document reading method that reduces health problems and health problems by automating or semi-automating document editing.

(Means for Solving the Problems) In order to solve the above-mentioned problems, a document reading method according to the present invention includes a document image storage unit that stores document images provided as a two-dimensional grid array, and a document image storage unit that stores document images provided as a two-dimensional grid array. a character line processing unit that reads the document image signal and separates character lines including control lines drawn below the character lines; and a character line that stores each character line image separated by the character line processing unit. an image storage unit, a control line detection unit that detects the presence or absence of the control line from the character line image, and detects a character line area and a control line area if the control line exists; Separate characters to extract individual character patterns, detect whether or not a control line is drawn in each character pattern, and extract character information and parts including each individual character pattern and the presence or absence of a control line corresponding to each individual pattern. a character separation unit that outputs a control line pattern; a control code recognition unit that determines control content by recognizing partial control line patterns at the start and end of the control line and outputs a control code; and a control code recognition unit that recognizes each character pattern. It consists of a character recognition unit that processes and outputs recognition results, character information, and control codes.

(Operation) The principle and operation of the present invention will be explained below with reference to the drawings.

FIG. 2 shows a printed document image containing control lines. Conventionally, this control line has been deleted as unnecessary information by preprocessing of image processing.

An example of this is shown in FIG. 3(b).

As shown in FIG. 3(a), by obtaining horizontal projection information from the document image, clues for determining the position of character lines in the document can be obtained. Large peaks in the projection information indicate character lines, and narrow, relatively low peaks indicate the presence of control lines. Conventionally, character lines are extracted excluding control lines by detecting the width of the peak, as shown in FIG. 3(b). In contrast, in the present invention, character lines are extracted including control lines, as shown in FIG. 3(c).

The method of detecting the control line area is as shown in Figure 4.
This can be achieved by separating the character line area S and the control line area T from the width of the projection peak from the character line including the control line.

FIG. 5 shows the relationship between each individual character and the control line. From a character line S that does not include a control line, perform character separation using, for example, projection onto the horizontal axis and find the separation position,
Furthermore, the region T of the control line is also separated using the separation position. The presence or absence of a control line is determined for each of the separated control line areas, and the character on which the control line is drawn is determined. In FIG. 5, the three characters A, B, and C are the characters on which control lines are drawn. Thereafter, character patterns that do not include control lines are recognized, and character information including the recognition results and the presence or absence of control lines is output.

FIG. 9 is a diagram showing an example of a control line. By recognizing the control line drawn under each individual character pattern, it is possible to determine whether the part is to be deleted, changed, emphasized, or changed character type. As a result, not only the character code of the document but also the control line information can be automatically input into the information processing system, making it possible to support editing operations.

(Example) Next, the present invention will be explained with reference to the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention.

The document image storage unit 1 stores document images converted into electrical signals by an image input means or the like.

The character line processing unit 2 reads the document image signal as the signal 11 from the document image storage unit 1, extracts the character line area including the control line as explained in the operation section, and outputs it as the character line image signal 12. This will be explained in detail later.

The character line image storage section 3 stores the character line image signal 12.

The control line detection unit 4 reads a character line image from the character line image storage unit 3 as a signal 13, checks the presence or absence of a control line, and if a control line exists, separates the character line and control line as explained in the section of the operation. It detects the position of the control line, outputs the position Nl1l of the start and end of the control line as a signal 14, and outputs a flag signal indicating that the control line does not exist when the control line does not exist. will be described later.

The character separation section 5 reads the character line image signal 13 from the character line image storage section 3, reads the control line start and end position signals 14 from the control line detection section 4, and performs character separation as explained in the section of operation. The area of the control line is separated using the position coordinates obtained as a result of character separation, and it is determined whether or not each separated area contains a control line. Information, position information, etc. are output as a signal 15, and each portion 111Jtl line pattern is output as a signal 16, details of which will be described later.

The control code recognition unit 6 scans the series of partial control line patterns from left to right, recognizes the shape of the leftmost partial control line pattern and the shape of the rightmost partial control line pattern, determines a control code, and outputs the control code as a signal 17. The details of the output will be described later.

The character recognition unit 7 performs character recognition processing on each individual character pattern sent as a signal 15, information on the presence or absence of a control line, position information, etc., and uses the obtained recognition results or Candidate character types, information on the presence or absence of the f11# line, control code information, position information, etc. are sent to signal 1.
Output as 8.

Note that various individual character recognition processing methods have been proposed, and the present invention is not limited to any particular method.

FIG. 6 is a diagram for explaining in detail an example of the configuration of the character line processing section 2. As shown in FIG.

The horizontal projection extraction unit 21 inputs the document image signal 11 and outputs a horizontal projection histogram obtained by scanning in the horizontal direction as a signal 121.

The projection storage unit 22 stores the projection histogram output as the signal 121.

The local maximum/minimum detection unit 23 receives the signal 12 from the projection storage unit 22.
2, reads the horizontal projection histogram, detects local maximum values, local minimum values, and their position coordinates within a global range, and detects the sequence of local maximum values, local minimum values, and their position coordinates from top to bottom as signal 123. The next output is around j.

The peak width detection unit 24 reads the signal 123, detects a peak from the series of maximum values and minimum values, calculates the width of the peak from the coordinates of the upper end and the coordinate of the lower end of each peak, and calculates the coordinates of the upper end and lower end of each peak. and the width are output as a signal 124 in order from the top.

The character line detecting unit 25 reads the coordinates of the top and bottom ends of each peak and the width of the peak as a signal 124, and when a small peak is adjacent to a peak with a large width, the top @ coordinate of the large peak and the bottom coordinate of the small peak. are determined as the upper and lower vIJ coordinates of the character line and output as signal 125, and when a large peak is adjacent to a large peak, the coordinates of the upper and lower ends of the upper large peak are determined as the upper and lower coordinates of the character line. The coordinates are determined and output as a signal 125, and this processing is performed for all peaks from top to bottom in order. Note that threshold processing may be used to determine whether a peak is a large peak or a small peak.

The character line extraction unit 26 reads the document image signal 11 and the signal 125 indicating the upper and lower coordinates of each character line, and sequentially outputs a rectangular area determined by the upper and lower coordinates of each character line as a character line image signal 12. do.

FIG. 7 is a diagram for explaining in detail an example of the elliptical command of the control line detection section 4.

The horizontal projection extraction unit 41 reads the character line image signal 13 and outputs a horizontal projection histogram obtained by scanning it in the horizontal direction as a signal 141, and has the same function as the horizontal extraction unit 21. .

The projection storage unit 42 stores the projection histogram output as the signal 141.

The peak detection section 43 performs the same processing as the maximum/minimum detection section 23 and the peak width detection section 24 to check for the presence or absence of a small peak, and outputs the upper @ coordinate and the lower end coordinate as a signal 143 when a small peak exists. , when a small peak does not exist, a flag indicating its absence is outputted as a signal 14.

FIG. 8 is a diagram for explaining in detail an example of the configuration of the character separating section 5. As shown in FIG.

The area M unit 51 reads the character line image signal 13 and the signal 14 regarding the presence or absence of a control line or the position coordinates, and
When a Jal line exists, the character line image is divided into a character line area and a control line area, and a character line area image signal 150 and a control line area image signal 154 are output, and when a control line does not exist, the entire character line image is divided into a character line area and a control line area. is output as a character line area image signal 150, and an image in which all pixel values are cleared is output as a control line area image signal 154.

The character line area image storage unit 52 stores the character line area image 1g No. 1
50 is stored.

The character cutting unit 53 reads the character line area image signal 151 from the character line area image storage unit 52, performs a process of cutting out individual character patterns, and converts the individual character pattern into a signal 15.
2, the position coordinates of the left end and right end of the individual character pattern are output as a signal 153.

The character pattern storage section 54 stores individual character patterns.

The character pattern coordinate storage section 55 stores the position coordinates of the left end and right end of the individual character pattern represented by the signal 153.

The control line area image storage unit 56 stores control line area images.

The control line cutout/detection unit 57 reads the control line area image as the signal 155 from the control line area image storage unit 56, and reads the control line area image as the signal 155 from the character pattern coordinate storage unit 55.
6, read the position coordinates of the left end and right end of each individual character pattern, determine whether or not a control line is drawn at the position corresponding to each individual character pattern as shown in FIG. is outputted as a signal 157, and when a control line exists, the control line area image is divided according to the position coordinates of each individual character pattern to create a partial control line pattern and outputted as a signal 16.

The character pattern information integration unit 58 includes the character pattern storage unit 5
4 reads the individual character pattern as signal 158,
The position information of the individual character pattern is read from the character pattern coordinate storage section 55 as a signal 156, and the information on the presence or absence of a control line is read from the control line extraction/detection section 57 as a signal 15.
7, and output these signals together as a signal 15.

FIG. 10 is a diagram showing an example of the configuration of the control code recognition section 6. As shown in FIG.

The start/end detection section 61 determines whether the sequentially sent partial control line patterns are the start or end of a control line, and outputs a signal 161 if the partial control line pattern is a start or end.

The reference pattern storage unit 62 stores reference control patterns for determining control codes.

The control mark recognition unit 63 inputs the partial control line pattern sent as the signal 161, and uses the reference control pattern registered in the reference pattern storage unit 62 as the signal 16.
2, the control code of the input partial control pattern is determined by pattern recognition processing, and is output as a control code signal 17.

(Effects of the Invention) As explained above, according to the present invention, it is possible to extract not only character position information and recognition results, but also information on the presence or absence of control lines and editing control codes. It is also very useful for realizing automatic reading of documents with semi-automatic editing functions.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is a diagram showing an example of a printed document image including control lines, and FIG.
Figures (a) to (c) each illustrate the processing of a document containing 1lJIl lines, and Figure 4 is a diagram illustrating an example in which the character line area and control line area of a character line image can be separated using a projection histogram. FIG. 5 is a diagram showing an example of detecting the presence or absence of a control line in each individual character pattern by applying the character extraction result to the control line area, and FIG. 6 is a detailed explanation of an example of the configuration of the character line processing section 2. 7 is a block diagram for explaining in detail an example of the configuration of the control line detection unit 4, and FIG. 8 is a block diagram for explaining in detail an example of the configuration of the character portion M unit 5. Figures 9 and 9 show one line of the control line, and Figure 10 shows i! 2 is a block diagram showing an example of the configuration of a II control code recognition section 6. FIG. 1... Document image storage section, 2... Character line processing section, 3.
...Character line image storage section, 4...Control line extraction section, 5
... Character portion 1lIi part, 6... Control code recognition part,
7...Character recognition unit, 21...Horizontal projection extraction unit,
22... Projection storage section, 23... Maximum/minimum detection section,
24...Peak width detection unit, 25...Character line detection unit,
26... Character line extraction unit, 41... Horizontal projection extraction unit, 42... Projection storage unit, 43... Peak detection unit,
51... Area separation section, 52... Character line area image storage section, 53... Character cutting section, 54... Character pattern storage section, 55... Character pattern coordinate storage section, 56.
...Control line area image storage unit, 57...Control line cutout detection unit, 58...Character pattern information integration unit,
61... Start/end detection section, 62... Reference pattern storage section, 63... Control mark recognition section.

Claims (1)

[Claims] A document image storage unit that stores document images given as a two-dimensional grid array; and a document image storage unit that reads the document image signal from the document image storage unit and separates character lines including control lines drawn below the character lines. a character line processing unit that stores each character line image separated by the character line processing unit, a character line image storage unit that stores each character line image separated by the character line processing unit, and detects the presence or absence of the control line from the character line image, a control line detection unit that detects a character line area and a control line area;
Separating characters from the character line image to extract individual character patterns, detecting whether or not a control line is drawn in each character pattern, and detecting the presence or absence of each individual character pattern and the control line corresponding to each individual pattern. a character separator that outputs the included character information and the partial control line pattern;
a control code recognition unit that determines the control content by recognizing partial control line patterns at the start and end of the control line and outputs a control code; and a control code recognition unit that recognizes each character pattern and processes the recognition result, character information, and control code. and a character recognition unit that outputs a character recognition unit.