Fragment restoring method based on genetic algorithm and character identification technology

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and accuracy to a certain degree at the same time, and provide support for the fields of judicial evidence obtaining, historical document restoring and military intelligence obtaining.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The restoration technology of broken paper is often used in the fields of judicial evidence collection, restoration of historical documents, and acquisition of military intelligence.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...

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

Images