JPH0652351A - Optical character reader - Google Patents

Abstract

PURPOSE:To easily designate and manage a format of plip in the case of reading it by the optical character reader. CONSTITUTION:Data on the surface of the slip are optically acquired by an image input part 11, and a surrounding frame contained in the input image is detected by a surrounding frame detection part 12. Next, the class of the surrounding frame is judged by a surrounding frame identification part 13 and a recognition part 16 and described contents corresponding to the class of the surrounding frame are extracted from a described content group previously stored in a described content storage part 14. Finally, the recognition part 16 reads characters or images in the detected surrounding frame according to the extracted described contents.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an optical character reading device, and more particularly to an optical character reading device for reading a form such as a slip.

[0002]

2. Description of the Related Art Conventionally, in the use of an optical character reading device for reading a form, the position of each character on the form is prevented in order to prevent erroneous reading due to misalignment of the total amount column or the like or to improve reading performance. It was common to describe the format such as and character type in advance. These tasks are complicated and time consuming.

However, since there is a fixed pattern in the character layout of each item on the form, when a form is newly designed or changed, a similar format is often input.

[0004]

In the conventional optical character reading apparatus for reading a form, when the form such as the character type and position of each character on the form is changed by newly creating or changing the form, a new form is newly created. Must be created. Therefore, one form is required for one type of form, and the number of forms increases each time a form is newly created or changed, and the management method becomes complicated.

Further, when there are many items of the same format in the same form, the same content must be repeatedly specified for all the items, resulting in a complicated format specification.

[0006] Incidentally, for the purpose of reading printed documents and tables,
Although the format is automatically analyzed, it is necessary to correctly discriminate the contents of a normal form and set the characters to 1
There is a problem that the performance of extracting characters character by character is insufficient at this stage.

The object of the present invention is to solve the above-mentioned problems,
An object of the present invention is to provide an optical character reading device capable of reading a form with high operational efficiency by giving information such as character position and character type in advance.

[0008]

An optical character reading apparatus according to the present invention comprises an image input section for optically inputting data on a sheet of paper including a surrounding frame such as a form to obtain an input screen, and an input image on the input image. Of the surrounding frame, a surrounding frame detecting unit for detecting the surrounding frame, a surrounding frame identifying unit for identifying the detected surrounding frame, and a character type or character relating to the characters or images in the surrounding frame corresponding to the type of the surrounding frame. A description content storage unit that stores description content including position information, a description content extraction unit that reads out and extracts the description content in the identified enclosure from the description content storage unit, and the enclosure frame according to the description content. And a recognition unit that extracts a character or an image in the image and performs a reading process.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram of an embodiment of the present invention. In the embodiment shown in FIG. 1, an image input unit 11 that optically captures data on a paper such as a form, a surrounding frame detection unit 12 that detects a surrounding frame included in an input image acquired by the image input unit 11, An enclosing frame identification unit 13 that identifies the type of the enclosing frame that has been detected, a description content storage unit 14 that stores in-frame description content that corresponds to the type of the enclosing frame, and an identification of the enclosing frame that is identified by the enclosing frame identification unit 13. A description content extraction unit 15 for extracting the description content in the box based on the description content storage unit 14;
And a recognition unit 16 that recognizes the described content.

Next, the operation of this embodiment will be described.

The data on the form is optically taken in by the image input section 11, and the enclosing frame detecting section 12 detects whether or not an enclosing frame exists in the input image taken in.

When the surrounding frame is detected, the type of the surrounding frame is determined by the surrounding frame identifying section 13.

When the type of the enclosing frame is determined, the described content extraction unit 15 extracts the described content from the described content storage unit 14 in which the described contents regarding the characters and images described in the enclosed frame are stored in advance. The recognition unit 16 extracts a character or an image from the enclosed frame on the input image for the extracted description content, and performs recognition processing by reading.

FIG. 2 shows an example of a form used in this embodiment. The reading area 22 is surrounded by a box 21 on the paper surface of the form 5, and an identification frame 23 for determining the type of the box 21 is provided at the upper left corner of the box 21.

In the identification frame 23, the description content storage unit 14
An enclosing frame identification code 24 such as “01” assigned to the enclosing frame 21 stored in FIG.

In the description content storage unit 14, the surrounding frame identification code entered in the type frame 23 of the surrounding frame 21 and the character type relating to the character or image in the surrounding frame 21 in which the surrounding frame identification code 24 is written, The description content information such as position information is stored.

The enclosing frame detector 12 detects the position of the enclosing frame on the input image acquired by the image input unit 11, and outputs the position information to the enclosing frame identifying unit 13. It should be noted that the position detection of the surrounding frame by the surrounding frame detection unit 12 can be realized by using a well-known technique, and thus detailed description thereof will be omitted here.

The enclosing frame identifying section 13 is based on the position information of the enclosing frame provided from the enclosing frame detecting section 12 and is surrounded by the enclosing frame 21.
The enclosing frame identification code 24 described in the identification frame 23 is detected. For this purpose, first, the identification frame 23 is detected from the surrounding frame 21 at the storage position input from the surrounding frame detection unit 12. Next, the image data in the identification frame 23 is input to the recognition unit 16, the surrounding frame identification code 24 is read from the image data, and the result is received from the recognition unit 16. The received result is input to the description content extraction unit 15 as a box identification code 24.

In the present embodiment, the enclosing frame identification code 24 is expressed by numbers, but it may be a character of another type or a code such as a bar code. Further, it may be set at any position in the form.

The description content extraction unit 15 includes a surrounding frame identification unit 13
The specified contents of the surrounding frame identification code 24 input from the are read from the description contents storage unit 14, and the description contents information corresponding to the surrounding frame identification code 24 is input to the recognition unit 16.

As described above, the recognizing unit 16 performs a character reading process of the image data in the identification frame 23 extracted by the enclosing frame identifying unit 13, transfers the read result to the enclosing frame identifying unit 13, and extracts the description content. In accordance with the description content extracted by the unit 15, the character or image in the box on the input image is read.

[0023]

As described above, according to the present invention, the position of the surrounding frame on the form is automatically detected, and the format required for extracting the characters and images in the surrounding frame is set by identifying the surrounding frame. Therefore, it is not necessary to create a new format by creating or changing a form, format management is easy, and if there are many items of the same format in the same form, one item can be specified. This has the effect of making it easy to specify.

[Brief description of drawings]

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

FIG. 2 is a diagram showing an example of a form used in the embodiment of FIG.

[Explanation of symbols]

 11 Image Input Unit 12 Enclosed Frame Detection Unit 13 Enclosed Frame Identification Unit 14 Enclosed Content Storage Unit 15 Described Content Extraction Unit 16 Recognition Unit 21 Enclosed Frame 22 Reading Area 23 Identification Frame 24 Enclosed Frame Identification Code

Claims (1)

[Claims] 1. An image input unit for optically inputting data on a sheet including a surrounding frame such as a form to obtain an input image, and a surrounding frame detecting unit for detecting the surrounding frame on the input image. A surrounding frame identification unit that identifies the detected surrounding frame, and a description content storage unit that stores description content including character types and character position information regarding characters and images in the surrounding frame corresponding to the type of the surrounding frame. A description content extracting unit that reads out and extracts the described description content in the identified enclosure from the description content storage unit; and a recognition unit that extracts a character or image in the enclosure according to the description content and performs a reading process. An optical character reading device comprising: