JPH04294474A - Optical character reader - Google Patents

Abstract

PURPOSE:To improve the working efficiency of this optical character reader and to shorten a correction time by collectively displaying and collectively correcting characters which can not be recognized. CONSTITUTION:This optical character reader is characteristically provided with a character recognizing part for inputting a character image 9, recognizing the image 9 and forming character data (character string 8), a mark data generating part for forming a mark 10 for each character image 9 which can not recognized by the character recognizing part, a display part for displaying each mark 10 formed by the mark data generating part and the character image 9 which can not be recognized, and a correction part for forming the character data of each character image 9 which can not be recognized based upon correction data for respective marks displayed on the display part at the time of collectively inputting the correction data and correcting the character data obtained by the character recognizing part.

Description

[Detailed description of the invention]

[Object of the invention]

0002

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an optical character reading device for reading characters written on a form or the like.

0003

2. Description of the Related Art An optical character reading device that reads characters written on a document or the like uses a scanner or the like to read a document such as a document, and then based on the character image obtained by this reading operation, the optical character reading device reads characters written on a document or the like. It recognizes characters, creates a character string, and outputs this to the next device.

0004

[Problems to be Solved by the Invention] However, in the conventional optical character reading device described above, each time an unrecognized character is generated by recognition processing of a character image read by a scanner or the like, a A mark is displayed to indicate that the characters are unrecognized, and a request is made to correct these characters by manually inputting them, so when reading a single document, if there are multiple unrecognized characters, only the number of unrecognized characters will be displayed. There was a problem in that unrecognized characters had to be manually corrected by displaying the screens one after another and manually inputting them on each screen, which took too much time.

[0005] In view of the above-mentioned circumstances, the present invention is capable of displaying unrecognized characters all at once and correcting them all at once, thereby improving work efficiency and making corrections possible. It is an object of the present invention to provide an optical character reading device that can reduce time.

[Configuration of the invention]

[0007]

[Means for Solving the Problems] In order to achieve the above object, an optical character reading device according to the present invention includes a character recognition unit that captures a character image and recognizes this character image to generate character data; a mark data generation section that generates a mark for each character image that could not be recognized by the character recognition section; a display section that displays each mark generated by the mark data generation section and the character image that could not be recognized; When correction data for each mark displayed on this display section is input all at once, character data for each character image that could not be recognized is generated based on this correction data and obtained by the character recognition section. The present invention is characterized by comprising a correction section for correcting character data.

[0008]

[Operation] In the above configuration, the character recognition section recognizes character images and generates character data, and the mark data generation section gives marks to each character image that cannot be recognized by the character recognition section. This is displayed on the display section, and when the correction data for each character image indicated by each mark is input all at once, the correction section displays the character data for each character image that could not be recognized by the character recognition section. is generated and the character data obtained by the character recognition section is corrected.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a block diagram showing an embodiment of an optical character reading device according to the present invention.

The optical character reading device shown in this figure has a database 1 in which image data read by a scanner (not shown) is stored, and character images stored in this database 1 are recognized to read character data. , and a display operation section 3 that displays characters recognized by the processing device 2 and corrects the recognition content of the processing device 2 based on input content, 1 recognizes the characters indicated by the character images stored in the CRT of the display operation section 3.
The recognition result of the processing device 2 is displayed on the top, and the recognition result of the processing device 2 is corrected based on the operation contents of the keyboard of the display operation section 3.

The database 1 includes a disk device, etc., stores character images supplied from a scanner, etc., and when a read command is supplied from the processing device 2, reads out the character image specified by the read command. This is supplied to the processing device 2.

The processing device 2 is equipped with a character recognition processing circuit for performing character recognition processing, reads out character images from the database 1, performs recognition processing on them, creates a character data string, and also processes unrecognized character images. After generating mark data indicating these character data strings,
Recognition result screen data is created based on the mark data and character images, and is supplied to the display operation section 3. Then, each time correction data is supplied from this display operation section 3,
After correcting the recognition content using this correction data and correcting the recognition result screen data supplied to the display control section,
When a transfer command is supplied from the display operation section 3, the character data string in the recognition result screen data is supplied to a host computer (not shown).

The display operation section 3 is equipped with a keyboard having various keys, a CRT, etc. for displaying various screens, and when the recognition result screen data is supplied from the processing device 2, the display operation section 3 is provided with The recognition result screen displayed on the screen is displayed on the CRT, and when the keyboard is operated, correction data, transfer commands, etc. are generated according to the content of the operation, and these are supplied to the processing device 2.

Next, the operation of this embodiment will be explained with reference to the flowchart shown in FIG.

First, a character image of the form 5 as shown in FIG. 3 is read by a scanner or the like, and if this is stored in the database 1 (step ST1),
reads the character image from the database 1 and performs recognition processing to create a character data string;
If there is a character image that cannot be recognized among these character images (step ST2), mark data indicating the position of the character image that could not be recognized is generated, and then recognition is performed based on these character data strings, mark data, and character images. Result screen data is created and supplied to the display operation unit 3 to display a recognition result screen 6 on the CRT as shown in FIG. The obtained character string 8 and the mark 10 indicating the position of each unrecognized character image are displayed at once.

[0016] After this, the operator who saw the recognition result screen 6 displayed on the display operation section 3 inputs the correct characters for each mark displayed on the recognition result screen 6, and the corresponding characters are input. When the correction data is output from the display operation section 3, the processing device 2 corrects the recognition content using the correction data, corrects the recognition result screen data supplied to the display operation section 3, and creates a recognition result screen. 6 is corrected (step ST3).

Furthermore, in the above-described operation, when all character images read from the database 1 have been recognized, recognition result screen data is created based on the character images and character data strings, and this is supplied to the display operation section 3. Then, a recognition result screen 6 is displayed on the CRT, and the character image 9 of the form 5 and the character string 8 obtained by recognition are displayed.

Next, when the display operation section 3 is operated and a transfer command is input, the processing device 2 supplies the character data string in the recognition result screen data to the host computer based on the transfer command (step ST4). ).

As described above, in this embodiment, the form 5
When the character image obtained by reading is recognized, the marks 10 corresponding to the unrecognized characters are displayed in a predetermined unit, for example, in one form, and corrections can be made all at once. When there are characters that cannot be used, they can be corrected all at once, thereby improving work efficiency.

[0020]

[Effects of the Invention] As explained above, according to the present invention, when there are unrecognized characters, they can be displayed all at once and corrected at once, thereby improving work efficiency. At the same time, it is possible to shorten the correction time.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing an embodiment of an optical character reading device according to the present invention.

FIG. 2 is a flowchart showing an example of the operation of the optical character reading device shown in FIG. 1;

FIG. 3 is a schematic diagram showing an example of a form read by the optical character reading device shown in FIG. 1;

FIG. 4 is a schematic diagram showing a display example of the optical character reading device shown in FIG. 1;

[Explanation of symbols]

2 Character recognition section, mark data generation section, correction section (processing device) 3 Display section (display operation section) 5 Form 8 Character data (character string) 9 Character image 10 Mark

Claims (1)

[Claims] [Claim 1] A character recognition unit that captures a character image and generates character data by recognizing this character image, and a mark data generation unit that generates a mark for each character image that cannot be recognized by the character recognition unit. A display section that displays each mark generated by this mark data generation section and unrecognized character images, and when correction data for each mark displayed on this display section is input all at once. An optical character reading device comprising: a correction section that generates character data for each character image that could not be recognized based on the correction data and corrects the character data obtained by the character recognition section. .