Check patentability & draft patents in minutes with Patsnap Eureka AI!

Character recognition method

By using color components and frequency distribution to identify background and non-character lines in OCR technology, non-character lines eliminate images and restore character images, the problem of character recognition in color tables is solved, and high-precision character recognition is achieved.

Inactive Publication Date: 2005-09-14
FUJITSU LTD +1
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, in a color form on which a dividing line, background, guide character, etc. is printed using a color different from the above-mentioned setting color, there is , or when written characters touch or cross these dividers, background or guide characters, the recognition of written characters is disturbed, resulting in a lower character recognition rate
Furthermore, in the case where a background color or solid coloring such as a halftone dot grid is generated in the character recognition target area, character recognition is disturbed, resulting in a decrease in the character recognition rate
[0009] That is, in the conventional OCR technology, it is difficult to highly accurately recognize characters written in a three-dimensional coloring area using a color different from the set color, or similarly, it is difficult to highly accurately recognize characters written in a color different from the set color, Characters positioned near or across dividers, backgrounds, guide characters, etc.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0053] (A) Explanation of the embodiment

[0054] figure 1 The structure of the form recognition device as an embodiment of the present invention is shown; FIGS. 2A, 2B, 2C and 2D respectively illustrate forms recognized by the form recognition device. Figure 2A shows a portion of a form; Figure 2B shows characters on the form; Figure 2C shows the pre-printed portion of the form; and Figure 2D shows the background portion of the form.

[0055] A form recognition device (medium processing device; character recognition device) 1 reads a form (medium) used in a banking institution to recognize characters written in predetermined columns. Specifically, the form recognition apparatus 1 recognizes characters written on a color form, the preprinted portion of which includes ruled-lines formed in a color different from the color of the characters and the set color; background...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention is a character recognition apparatus, which comprises a background discriminating section (13), a non-character line discriminating section (14), a first non-character line removed image creating section (17) that creates a first non-character line removed image, which is an original image from which the non-character line is removed, a first character area discriminating section (15), an enlarged image creating section (16), a second non-character line removed image creating section (17), an interference judgment section (18) that judges whether or not the character and the non-character line interfere with each other in the original image, a character image restoring section (19) that, based on the difference between the color information of character image and the color information of non-character line, restores the character image, a second character area discriminating section (20), and a character recognizing section (21) that digitizes the character area recognized by the second character area discriminating section (20) and recognizes the character, thereby characters written on a color form are recognized at a high accuracy.

Description

technical field [0001] The present invention relates to techniques suitable for processing forms such as in banking institutions; more particularly, to techniques for recognizing characters written in colored forms. Background technique [0002] In banking institutions and the like, an image reading device such as an optical character recognition device (OCR) is used as a device that reads character information written in a form in the form of image data, and then recognizes the image data as characters. By adopting OCR equipment, the efficiency of commercial operations is improved. [0003] In conventional OCR technology, image data on a form is obtained in the form of a monochrome binary image, and then recognized as characters. For example, in the case of a form on which separation lines, guide characters, etc. are printed in predetermined dropout colors such as green and red, the OCR device reads the character recognition target area (filling in characters) in the form ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/40G06V30/10
CPCG06K9/2018G06K2209/01G06K9/346G06K2209/015G06V2201/01G06V30/10G06V30/1429G06V30/155
Owner FUJITSU LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More