Fragment restoring method based on genetic algorithm and character identification technology

A character recognition and genetic algorithm technology, applied in the field of fragment recovery based on genetic algorithm and character recognition technology

Active Publication Date: 2014-11-12
JINAN UNIVERSITY
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, to provide a fragment restoration method based on genetic algorithm and character recognition technology, and to solve the splicing and restoration of shredded paper of text documents processed by shredders

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
  • Fragment restoring method based on genetic algorithm and character identification technology
  • Fragment restoring method based on genetic algorithm and character identification technology
  • Fragment restoring method based on genetic algorithm and character identification technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] like figure 1 As shown, the fragment recovery method based on genetic algorithm and character recognition technology in this embodiment mainly includes the following steps:

[0087] 1. Establishment of English character database;

[0088] 2. Character recognition;

[0089] 3. Branch clustering technology;

[0090] 4. In-line splicing technology;

[0091] 5. Splicing between lines.

[0092] The above steps are further analyzed in conjunction with specific technical solutions below:

[0093] 1. Establishment of English character database

[0094] The objects of the English character database established in this embodiment are 26 uppercase and lowercase English letters (52 characters in total) in different fonts and font sizes. At the beginning of the establishment of the English character database, all character images used to establish the database will be binarized (the processing threshold is 205).

[0095] First, through the character extraction technology of the...

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 invention discloses a fragment restoring method based on the genetic algorithm and the character identification technology. The method comprises the following steps that S1, an English character database is built, and a grayscale matrix of each character is obtained through the character obtaining technology; S2, the characters are identified, and whether the characters needing to be identified are cut or not is judged; S3, fragments are clustered according to lines, line clustering is based on the character identification technology and datum line distance information, and the line clustering process is completed through clustering vectors, clustering centers and clustering distances; S4, after the line clustering technology is executed, the fragments in each line are spliced through the inline splicing technology; S5, fragment splicing is conducted through the interline splicing technology. The fragment restoring method can be widely applied to restoring of longitudinally and transversely cut fragments generated by various paper shredders, guarantee efficiency and accuracy to a certain degree at the same time, and provide support for the fields of judicial evidence obtaining, historical document restoring and military intelligence obtaining.

Description

technical field [0001] The invention relates to the research field of fragment restoration, in particular to a fragment restoration method based on genetic algorithm and character recognition technology. Background technique [0002] The restoration technology of broken paper is often used in the fields of judicial evidence collection, restoration of historical documents, and acquisition of military intelligence. However, in the face of a huge number of fragments, the efficiency of manual restoration is low. It is necessary to develop automatic splicing technology with high restoration efficiency. Improve the work efficiency of the demand side and maximize the acquisition of high-accuracy information from scraps of paper [0003] Shredded paper is currently divided into three parts, which are ① hand-torn pieces with irregular edges, ② strip-shaped pieces shredded by a shredder, and ③ horizontal and vertical pieces shredded by a shredder. For the first type of fragments, sch...

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): G06K9/20G06F17/30
Inventor 樊锁海许荷东庄子炜郑晶
Owner JINAN UNIVERSITY
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