题名

Off-Line Chinese-Based Signature Verification Using a Threshold Self-Organizing Map

并列篇名

使用具門檻值之自組織映射辨識靜態中文簽名

DOI

10.29977/JCIIE.200705.0005

作者

馬恆(Heng Ma)；楊文薇(Wen-Wei Yang)；劉家盛(Chia-Cheng Liu)

关键词

靜態中文簽名辨識 ； 放射性分段 ； 特徵萃取 ； 自組織映射 ； Off-line Signature Verification ； Radial Segmentation ； Feature Extraction ； SOM

期刊名称

工業工程學刊

卷期/出版年月

24卷3期（2007 / 05 / 01）

页次

225 - 235

内容语文

英文
中文摘要

我們提出一靜態中文簽名辨識方法使用放射性分段法與Kohonen的自組織映射(SOM)。放射性分段法乃用於簽名之特徵萃取，此法可克服簽名時產生的變異，如使用筆的粗細、簽名的大小與旋轉角度。SOM針對個人真實簽名加以訓練與群聚，並在訓練完成後對每一群組產生一門檻值作為判定測試樣本是否為真實簽名的界限。實驗包含十位受測者與100位偽造者，結果在錯誤拒絕率(FRR)平均為8%，而在錯誤接受率(FAR)平均低於3%。本方法之優點乃在藉由預設群組數的增加，可達成更低錯誤率之彈性。
英文摘要

We propose an approach using a radial segmentation method and Kohonen's SOM (self-organizing map) to resolve the off-line Chinese-based signature verification problem. The radial segmentation method extracts features of a signature in a consistent manner regardless pen thickness, size and rotation. The threshold SOM trains only on genuine signatures of an individual. Verification is achieved by determining if a test signature is within the threshold boundary for a cluster generated. An experiment including 10 subjects and 100 forgers was conducted for testing this approach. As a result, an average false rejection rate (FRR) of 8% and a false acceptance rate (FAR) below 3% are achieved, depending on the number of hidden nodes involved in training. The approach demonstrates the flexibility in choosing error rates of interest and capability in achieving low error rates.
主题分类 工程學 > 工程學總論
参考文献
  1. Abbas R.(1994).Backpropagation Networks Prototypes for Off-line Signature Verification.Master Thesis, Department of Computer Science, RMIT
  2. Bajaj, R.,S. Chaudhury(1997).Signature verification using multiple neural classifiers.Pattern Recognition,30,1-7.
  3. Chiu, H. P,D. C, Tseng(1997).Invariant handwritten Chinese character recognition using fuzzy min-max neural networks.Pattern Recognition Letters,18,481-491.
  4. Deng, P. S.,H. Y. M. Liao,C. W. Ho,H. R. Tyan(1999).Wavelet-based off-line handwritten signature verification.Computer Vision and Image Understanding,76,173-190.
  5. Drouhard, J. P.,R. Sabourin,M. Godbout(1996).A neural network approach to off-line signature verification using directional PDF.Pattern Recognition,29,415-424.
  6. Herbst, B.,H. Coetzer(1998).On an offline signature verification system.27/39-28/43.
  7. Holt, C. M.,A. Stewart,M. Clint,R. H. Perrott(1987).An improved parallel thinning algorithm.Communications of the ACM,30,156-160.
  8. Justino, E. J. R.,A. E. Yacoubi,F. Bortolozzi,R. Sabourin(2000).An off-line signature verification system using HMM and graphometric features.presented at the 4th IAPR International Workshop on Document,10-13.
  9. Khotanzad, A.,J. H. Lu(1990).Classification of invariant image representations using a neural network.IEEE Transactions on Acoustics, Speech, and Signal Processing,38,1028-1038.
  10. McCormack, D. K. R.,B. M. Brown(1993).Neural network signature verification using Haar wavelet and.Fourier transformations SPIE,14-25.
  11. Mizukami, Y,M. Yoshimura,H. Miike,I. Yoshimura(2002).An off-line signature verification system using an extracted displacement function.Pattern Recognition Letters,23,1569-1577.
  12. Sabourin, R.,G. Genest,F. J. Preteux(1997).Off-line signature verification by local granulometric size distributions.IEEE Transactions on Pattern Analysis and Machine Intelligence,19,976-987.
  13. Tseng, D. C.,H. P. Chiu,J. C. Cheng(1996).Invariant handwritten Chinese character recognition using fuzzy ring data.Image and Vision Computing,14,647-657.
  14. Velez, J. F.,A. Sanchez,A. B. Moreno(2003).Robust off-line signature verification using compression networks and positional cuttings.presented at IEEE International Workshop on Neural Networks for Signal Processing, Sep,17-19.
  15. Yang, X.,T. Furuhashi,K. Obata,Y. Uchikawa(1996).Selection of features for signature verification using the genetic algorithm.Computers Industrial Engineering,30,1037-1045.
  16. Zhang, B.,M. Fu,H. Yan(1998).Handwritten signature verification based on neural `gas' based vector quantization.Proceedings of Fourteenth International Conference on Pattern Recognition, Aug,17/1862-20/1864.
print cancel