Online Signature Classification Using Modified Fuzzy Min-Max Neural Network with Compensatory Neuron Topology

An Efficient signature recognition system is proposed in this paper. A new approach of application of krawtchouk moment method is used to estimate a set of feature vector which is an informative subset and is used as a input data for MFMCN classifier. Preprocessing step uses Krawtchouk moment, which automatically identifies the useful and common features consistently existing within different signature images of the same person. They are also invariant to shift, rotation, and scale. This moment method reduces the dimensionality of the input signature pattern by eliminating features containing low information or high redundancy. These features are used to recognize the signature using Modified Fuzzy Min-Max Neural Network with Compensatory Neuron (MFMCN). The proposed approach is applied to online signature recognition and experimentally it shows that it produces the excellent result by reducing the computational burden of the recognition system and provides high recognition rates.

[1]  Ronny Martens,et al.  On-line signature verification by dynamic time-warping , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[2]  H. Qjidaa,et al.  Krawtchouk moment feature extraction for neural Arabic handwritten words recognition , 2009, 2009 International Conference on Multimedia Computing and Systems.

[3]  William Turin,et al.  Statistical Methods for On-Line Signature Verification , 1994, Int. J. Pattern Recognit. Artif. Intell..

[4]  Prabir Kumar Biswas,et al.  A Fuzzy Min-Max Neural Network Classifier With Compensatory Neuron Architecture , 2007, IEEE Transactions on Neural Networks.

[5]  Paramesran Raveendran,et al.  Krawtchouk moments as a new set of discrete orthogonal moments for image reconstruction , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[6]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[7]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks. I. Classification , 1992, IEEE Trans. Neural Networks.

[8]  Suh-Yin Lee,et al.  On-line signature verification using LPC cepstrum and neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Réjean Plamondon,et al.  Automatic signature verification and writer identification - the state of the art , 1989, Pattern Recognit..

[10]  V. Matousek,et al.  Signature verification using ART-2 neural network , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[11]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jianying Hu,et al.  A Hidden Markov Model approach to online handwritten signature verification , 1998, International Journal on Document Analysis and Recognition.

[13]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks - Part 2: Clustering , 1993, IEEE Trans. Fuzzy Syst..

[14]  Robert Sabourin,et al.  A neural network approach to off-line signature verification using directional PDF , 1996, Pattern Recognit..

[15]  Gerhard Rigoll,et al.  A systematic comparison between on-line and off-line methods for signature verification with hidden Markov models , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[16]  Bhupendra M. Chaudhari,et al.  Signature recognition using fuzzy min-max neural network , 2009, 2009 International Conference on Control, Automation, Communication and Energy Conservation.

[17]  Yingyong Qi,et al.  Signature verification using global and grid features , 1994, Pattern Recognit..

[18]  Andrzej Bargiela,et al.  General fuzzy min-max neural network for clustering and classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[19]  Anil K. Jain,et al.  On-line signature verification, , 2002, Pattern Recognit..