Automatic Handwriting Verification and Suspect Identification for Chinese Characters Using Space and Frequency Domain Features

Automatic handwriting verification is to identify whether the script was written by a person himself or forged. Compared to related works about handwriting verification, the proposed algorithm adopts the features in both the time domain and the frequency domain. Moreover, in addition to distinguishing the forged manuscript from the genuine one, the proposed algorithm can also identify the suspect. The proposed algorithm is robust to writing instruments. In addition to the information of the luminance of the script, we also adopt the energy distribution on the 2-D frequency domain, the Pearson product-moment correlation coefficient (PPMCC) with genuine scripts, and vital information on characterized script points. Simulations show that the proposed method outperforms many advanced methods, including the deep-learning based method and manual identification by human beings. The proposed algorithm can well identify the script even if it is forged after several times of practice.

[1]  Zhao Zhang,et al.  Handwriting representation and recognition through a sparse projection and low-rank recovery framework , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[2]  Soo-Chang Pei,et al.  New corner detection algorithm by tangent and vertical axes and case table , 2005, IEEE International Conference on Image Processing 2005.

[3]  A. Khatri,et al.  Offline Handwriting Recognition Using Invariant Moments and Curve Let Transform with Combined SVM-HMM Classifier , 2013, 2013 International Conference on Communication Systems and Network Technologies.

[4]  Christopher Kermorvant,et al.  Dropout Improves Recurrent Neural Networks for Handwriting Recognition , 2013, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[5]  Sriganesh Madhvanath,et al.  Principal component analysis for online handwritten character recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  Chang-Dong Wang,et al.  Off-Line Chinese Handwriting Identification Based on Stroke Shape and Structure , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[7]  K. Anandakumar,et al.  Automated Human Behavior Prediction through Handwriting Analysis , 2010, 2010 First International Conference on Integrated Intelligent Computing.

[8]  Y. S. Cheung,et al.  A knowledge-based stroke-matching method for Chinese character recognition , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[9]  M. Abdulghafour,et al.  Offline Chinese Handwriting Character Recognition through Feature Extraction , 2016, 2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV).

[10]  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).

[11]  Nuran Dogru,et al.  Signature recognition by using SIFT and SURF with SVM basic on RBF for voting online , 2017, 2017 International Conference on Engineering and Technology (ICET).

[12]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[13]  Anil Kumar,et al.  Overlapped Character Recognition: An Innovative Approach , 2016, 2016 IEEE 6th International Conference on Advanced Computing (IACC).

[14]  Dan Ciresan,et al.  Multi-Column Deep Neural Networks for offline handwritten Chinese character classification , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).