Automatic Chinese Handwriting Verification Algorithm Using Deep Neural Networks

Handwriting verification is to identify whether a script was written by a person himself or forged. Conventional handwriting verification algorithms are based on feature extraction. However, the features of scripts are highly affected by the writing instrument, the posture, and the force of writing, even if the scripts were written by the same person, the extracted features will be quite different. Moreover, since some writers might not write some strokes clearly or ignore some strokes, not all features can be well extracted in every script. Therefore, in this paper, we apply a deep neural network based algorithm for handwriting verification. With the proposed algorithm, the parts that are really powerful and robust for handwriting verification can be highlighted by the auto-encoder. Then, a very high accurate handwriting verification result can be achieved.

[1]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[2]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[3]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Jian-Jiun Ding,et al.  Automatic Writer Verification Algorithm for Chinese Characters Using Semi-Global Features and Adaptive Classifier , 2018, 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[6]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[7]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[8]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[9]  Yaxin Bi,et al.  KNN Model-Based Approach in Classification , 2003, OTM.

[10]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[11]  Jesús Francisco Vargas-Bonilla,et al.  Off-line signature verification based on grey level information using texture features , 2011, Pattern Recognit..