JPH024035B2 - - Google Patents

Description

[Detailed Description of the Invention] [Technical Field of the Invention] The present invention relates to post-processing of a character recognition device. The present invention relates to a character recognition device that determines a recognition result based on a group of words belonging to a category defined for each field from among candidate characters.

[Conventional technology and problems]

The character recognition device optically scans the information on the form to obtain image information, recognizes multiple candidate characters in each field from the image information, and recognizes from among the multiple candidate characters recognized in each field. There is something that determines the outcome. Conventionally, in the post-processing of character recognition devices that determine such recognition results,
For each field, a character category, such as alphabets, numbers, kana, etc., was specified, and recognition results were determined within that category. However, as the recognition targets become wider, such as kanji and hiragana, there are many cases where recognition results cannot be determined based on character-by-character categories.

[Purpose of the invention]

The present invention solves the above-mentioned problems, and aims to provide a character recognition device that can more accurately determine recognition results even when the recognition target becomes wider.

[Structure of the invention]

To this end, the character recognition device of the present invention has an optical scanning unit that optically scans information on a form to obtain image information, an image storage unit that stores the image information as binary content, and a field on the form. a format information section having format information for each field such as the position and number of characters; a recognition section that reads out the contents stored in the image storage section for each field according to the format information and selects a plurality of candidate characters; In a character recognition device comprising a recognition result determining unit that determines a set of words as a recognition result from among selected candidate characters, and an output unit that outputs the word determined as a recognition result, the format information unit comprises: A category storage means having information specifying a category such as name, address, occupation, product name, etc. in each field, and in which a plurality of words belonging to each of the categories are registered in the recognition result determining section, in each field. a category selection means for selecting a group of words belonging to a category specified by the format information section from the category storage means; a group of words selected by the category selection means from among the plurality of candidate characters selected by the recognition section; The present invention is characterized by comprising a search determining means for searching for a set of words and determining a set of words as a selection result.

[Embodiments of the invention]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention;
FIG. 2 is a diagram showing the relationship between fields and categories, and FIG. 3 is a diagram showing an example of correspondence between input characters, recognition results, candidate characters, and categories. In the figure, 1 is an optical scanning section, 2 is an image storage section, 3 is a recognition section, 4 is a format information section, 5 is a category selection means, 6 is a search determination means, 7 is a category storage section,
8 is an output means, 9 is a form, 10 to 12 are fields, 13 to 15 are categories, and 16 is format information.

In FIG. 1, an optical scanning section 1 optically scans and reads information on a form to obtain image information, and the image information is sent to an image storage section 2. The image storage section 2 stores the image information sent from the optical scanning section 1 in binary form. The recognition section 3 refers to the format information in the format information section 4, reads out the contents stored in the image storage section 2 field by field, and selects a plurality of corresponding candidate characters. The format information section 4 has format information and category designation information regarding each field on the form, as will be described later. The category selection means 5 selects a group of words belonging to the category specified by the format information section 4 from the category storage section 7. Categories include, for example, names, addresses, occupations, product names, etc., and the category storage section 7 registers word groups belonging to each category. The search determination means 6 searches for a group of words belonging to the selected category, determines a recognition result from among the plurality of candidate characters extracted by the recognition section 3, and sends the recognition result to the output means 8.

The relationship between fields and categories will be explained with reference to FIG. In FIG. 2, it is assumed that there are fields 10 to 12 on a form 9, and each field is a recognition target field that can be categorized. The categories are field 10 is b, field 11 is a, and field 1 is
2 is C. Based on these matters, the format information 16 includes, for each field, the line position, field position (left and right position), number of characters, reading mode (numbers, alphabets, kana, etc.), and other fields. Information characterizing the field and the category of the field are registered. For example, if the field 10 is a name field, a group of words of the name to be recognized are registered in the category 14.

Next, referring to FIG. 3, the case where A ₀ B ₀ C ₀ is written in the field 10 on the form 9 will be explained. Here, the category of field 10 is b, and the word group of category b includes A ₃ B ₄ C ₅ ,
It is assumed that words such as A ₀ B ₀ C ₀ , A ₁ B ₇ C ₆ , ... are registered. Therefore, in recognition unit 3, for A ₀
A ₀ , A ₃ , A ₂ …, B ₀ and B ₁ , B ₀ , B ₄ , …, C ₀
C ₁ , C ₀ , C ₆ , ... are recognized in order of similarity, and A ₀ B ₁ C ₁ is recognized as the recognition result. Category b is specified in the format information section 4 and sent to the category selection means 5. Therefore, when the word group of category b is selected, the word group of category b is searched. However, since the word A ₀ B ₁ C ₁ is not registered in the word group of category b, the word A ₀ B ₀ C ₀ is searched for the next candidate characters. The recognition result can be determined.

As explained above, there are many fields to be recognized that can be categorized, such as names, addresses, occupations, and product names. The category is stored separately and specified in the field to be recognized. Then, by selecting and searching the words that have been stored separately, more accurate recognition results can be obtained.

〔Effect of the invention〕

As is clear from the above description, according to the present invention, the content written in each field on a form is categorized, words belonging to the categories are registered in advance, and words are searched by selecting each category. As a result, more accurate recognition results can be determined, and since the range of words to be searched is limited, unnecessary searches are reduced, search efficiency is improved, and processing speed is improved.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing one embodiment of the present invention;
FIG. 2 is a diagram showing the relationship between fields and categories, and FIG. 3 is a diagram showing an example of correspondence between input characters, recognition results, candidate characters, and categories. 1... Optical scanning unit, 2... Image storage unit, 3...
recognition section, 4... format information section, 5... category selection means, 6... search determination means, 7... category storage section, 8... output means, 9... form, 10
or 12... field, 13 or 15...
Category, 16...Format information.

Claims (1)

[Claims] 1. Optical scanning unit that optically scans the information on the form to obtain image information; image storage unit that stores the image information as binary content; and formatting of each field, such as field position and number of characters on the form. a format information section having information; a recognition section that reads out the contents stored in the image storage section field by field according to the format information and selects a plurality of candidate characters; and a recognition section that selects a plurality of candidate characters from among the candidate characters selected by the recognition section. In a character recognition device that includes a recognition result determining unit that determines a set of words as a recognition result, and an output unit that outputs the determined word as a recognition result, the format information unit stores name, address, occupation, name, address, occupation, etc. in each field. A category storage means having information specifying a category such as product name, in which a plurality of words belonging to each category are registered in the recognition result determining section, and specified by the format information section in field units. a category selection means for selecting a group of words belonging to a category from the category storage means; a group of words selected by the category selection means from among the plurality of candidate characters selected by the recognition section; A character recognition device characterized by comprising a search determination means for determining a selection result.