Open AccessA Deep Learning Method for Chinese writer Identification with Feature Fusion
Author(s) -
Yang Xu,
Yuehui Chen,
Yi Cao,
Yawen Zhao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1883/1/012142
Subject(s) - handwriting , computer science , feature (linguistics) , artificial intelligence , pattern recognition (psychology) , identification (biology) , block (permutation group theory) , feature extraction , pixel , intelligent character recognition , set (abstract data type) , writing style , feature vector , speech recognition , image (mathematics) , mathematics , linguistics , philosophy , botany , geometry , character recognition , biology , programming language
Writer identification is one of the research hotspots of computer vision and pattern recognition, and it is of great significance in the fields of judicial authentication, file security protection, historical document analysis, and so on. However, many problems are still challenging due to the different writing sources, the common features of learning local features, and the implicit features of handwriting style. This paper uses the fusion of depth features and manual features to obtain handwriting style features from handwriting pictures. Firstly, the handwriting picture is pre-treatment and divided into small pixel blocks, and then the depth feature and LPQ feature information are extracted from each pixel block, and the depth features are reduced by PCA, and then the local features are encoded into global features through the Vlad algorithm. So far, the depth global feature and the LPQ global feature of a page of handwriting pictures are obtained, and the two features are combined as the global feature vector of the page of handwriting. And our method has achieved good results on the CASIA-HWDB data set.