Electronic identification method for handwritten characters

Abstract

The invention relates to an electronic identification method for handwritten characters. The electronic identification method includes the following steps: S11, obtaining pattern information of the handwritten characters in a preset parting line answer sheet or a blank area, wherein a parting line is a solid parting line section or an electronic virtual parting line section, and the handwritten characters include English letters, Arabic numerals and punctuation marks; S12, conducting geometric correction on the pattern information to obtain correction characters; S13, conducting matching identification according to characteristics of the correction characters. The electronic identification method is applied to the answer sheet identification field, can be used for accurately parting handwritten English characters and the Arabic numerals, solves the handwritten parting problem, and enables application of off-line handwriting recognition to be possible. According to the electronic identification method, as the characteristic of the English characters can be rapidly extracted through the simple and rapid character characteristic extraction method, the method can be applied to devices with limited calculation capacity, and the application range of handwritten identification is greatly enlarged.

Description

technical field [0001] The invention relates to the technical field of image recognition processing of answer sheets, in particular to an electronic recognition method of handwritten characters. Background technique [0002] In the prior art, the answer sheet can recognize the graphics filled with 2B pencils, but cannot recognize the handwritten content. However, the ability to recognize individual content in the prior art is also based on normative writing or special training writing forms; because everyone's writing habits are different. As a result, the segmentation of English characters has become a difficult point in handwriting recognition. The existing methods cannot accurately segment English characters and letters in different situations. The current English character feature extraction method mainly extracts the geometric information or geometric features of the characters, and then These features are classified and processed, but due to the different habits of eac...

AI Technical Summary

Problems solved by technology

[0002] In the prior art, the answer sheet can recognize the graphics filled with 2B pencils, but cannot recognize the handwritten content. However, the ability to recognize individual content in the prior art is also based on normative writing or special training writing forms; because everyone's writing habits are different. As a result, the segmentation of English characters has become a difficult point in handwriting recognition. The existing methods cannot accurately segment English characters and letters in different situations. The current English character feature extraction method mainly extracts the geometric information or geometric features of the characters, and then These features are classified and processed, but due to the different habits of each person, these methods need to train each person's handwriting fonts, which cannot guarantee good applicability, so they cannot be applied to the field of answer sheets, and cannot be used in handwriting recognition in answer scoring. aspect application

Images