Abstract
Understanding handwritten documents is a vital and challenging problem that attracts many researchers in the fields of forensic and authentication science. This paper presents an offline system for text-independent writer identification of handwritten documents. The system extracts a handwritten connected component contour, which in turn is divided into segments of specific length. The system utilizes the concept of a bag of features in the writer recognition domain and considers handwritten contour segments to extract two conceptually simple and effective structural features. These features are the contour point curve angle and the CONtour point CONcavity/CONvexity. The system uses the proposed features to train a k-means clustering algorithm to construct a codebook of size K. The method then uses occurrence histograms of the extracted features in the codebook to create a final feature vector for each handwritten document. The effectiveness of the proposed features is evaluated in the writer identification domain using two widely used classification methods: the nearest neighbor and the support vector machine techniques. The proposed writer identification is evaluated on two large and public datasets from different language domains, the Arabic KHATT and English IAM datasets. The experimental results show that the proposed system outperforms state-of-the-art methods on the IAM dataset and provides competitive results on the KHATT dataset with respect to the identification rate.
Publisher
Public Library of Science (PLoS)
Reference71 articles.
1. Writer Identification using Deep Learning with FAST Keypoints and Harris Corner Detector;A Semma;Expert Systems with Applications,2021
2. Writer identification of arabic text using statistical and structural features;SM Awaida;Cybernetics and Systems,2013
3. Gibbons M, Yoon S, Cha S-H, Tappert C, editors. Evaluation of biometric identification in open systems. International Conference on Audio-and Video-Based Biometric Person Authentication; 2005: Springer.
4. Zaher AA, Abu-Rezq A, editors. A hybrid ANN-based technique for signature verification. Proceedings of the 4th WSEAS International Conference on COMPUTATIONAL INTELLIGENCE, Universitatea Politehnica, Bucharest, Romania; 2010.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献