Post-processing approach of character recognition

A character recognition and character technology, applied in the field of computer information processing, can solve the problem of low efficiency and accuracy of correcting typos, and achieve the effects of reducing manual workload, ensuring accuracy, and improving recognition rate and recognition speed.

Inactive Publication Date: 2007-02-21
NEW FOUNDER HLDG DEV LLC +1
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem of low efficiency and accuracy of correcting typos in the prior art when character recognition post-processing is performed, the purpose of the present invention is to provide a method for automatically selecting words by judging all candidate characters of misrecognized characters in the recognition results. How to get the correct characters

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

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Post-processing approach of character recognition
  • Post-processing approach of character recognition
  • Post-processing approach of character recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific implementation manners of the present invention will be described below in conjunction with the accompanying drawings.

[0026] figure 1 A character recognition apparatus for converting a printed document or a handwritten document into text data according to an embodiment of the present invention is shown. Because the OCR recognition device may not be able to accurately recognize some characters in the document, this embodiment introduces a post-processing device to determine the correct character from the recommended multiple candidate characters, thereby improving the recognition rate.

[0027] exist figure 1 Among them, the character recognition device includes an image input unit 11, which can be an image input device such as a scanner, a facsimile machine or a digital camera, and also includes an image data storage unit 12, a layout analysis unit 13, a preprocessing unit 14, an OCR recognition unit 15, A post-processing unit 16 , a recognition result...

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

A post-treatment method after character is identified includes identifying characters in file to obtain candidate character of said character and similarity of candidate character, confirming misidentified character by comparing said similarity with preset threshold, forming seek word to carry out search in known text databank to obtain measurement value of said word, using said value to calculate out weight value of misidentified character seek word, confirming correct character being used to correct misidentified character by comparing weight values of all misidentified character seek words.

Description

technical field [0001] The invention relates to post-processing technology in the field of computer information processing, in particular to a method for correcting recognized typos. Background technique [0002] Post-processing is an important part of the application of OCR (Optical Character Recognition) technology. At present, there are always misrecognized characters in the OCR text recognition results. The application of post-processing algorithms corrects the misrecognized characters to a certain extent. [0003] For typos that occur after recognition, the method of marking is traditionally used, and after marking, it depends on manual correction. Therefore, automatic processing cannot be performed, and thus the workload is very heavy for the staff who process the recognition results in batches. [0004] There is another method in the prior art, as described in the document "A New Method for Chinese Character Recognition Context Processing Based on Combination of Word...

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): G06K9/68
Inventor 杜鹏飞康凯徐剑波
Owner NEW FOUNDER HLDG DEV LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products