Text identification method and device irrelevant to handwriting

Abstract

The invention discloses a method and a device for identifying text-independent writing, and belongs to the field of computer vision. The method comprises: preprocessing a query wring sample to obtain edge images of the query writing sample; extracting network microstructure characteristics of the query writing sample from the edge images of the query writing sample; calculating a standard difference of the network microstructure characteristics of the query writing sample and the network microstructure characteristics of each reference writing sample; calculating characteristic intervals of the network microstructure characteristics of the query writing sample and the network microstructure characteristics of each reference writing sample through weighing the standard difference; and comparing and ordering the characteristic intervals to obtain a writer candidate list of the query writing sample. The device comprises a preprocessing module, a characteristic extracting module, a weight calculating module, an interval calculating module and a comparing module. The method obtains a writing candidate through comparing intervals of the network microstructure characteristics, and improves accuracy and identifying property of writing identification.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method and device for text-independent handwriting identification. Background technique [0002] Handwriting identification is a technology to identify the identity of the writer by the writing style of handwritten handwriting samples, and it is a kind of biometric identification technology. In the past, handwriting recognition relied on handwriting experts to use professional identification methods. In addition to the identification results being affected by experts' subjective opinions, manual large-scale handwriting retrieval is often inefficient. Therefore, computer automatic handwriting recognition technology has gradually become a new research field. It has a wide range of applications in judicial, commercial and other fields. [0003] Existing computer automatic handwriting identification methods include text-dependent methods and text-independent methods. Among them, th...

AI Technical Summary

Problems solved by technology

[0004] In the existing technology, the handwriting text is spliced ​​into texture blocks by using the texture analysis method. When splicing the texture blocks, the character splicing sequence itself affects the generation of the texture, and the normalization of the characters also has a certain damage to the handwriting texture.

The order of character splicing actually affects the stability of texture features, especially in Chinese handwriting with huge differences in character shapes. Therefore, the handwriting identification performance of the prior art is poor, and the identification accuracy rate is low, thus affecting the general use of handwriting identification methods sex

Images