Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition

Abstract The problem of automatic signature recognition has received little attention in comparison with the problem of signature verification despite its potential applications for accessing security-sensitive facilities and for processing certain legal and historical documents. This paper presents an efficient off-line human signature recognition system based on support vector machines (SVM) and compares its performance with a traditional classification technique, multi-layer perceptrons (MLP). In both cases we propose two approaches to the problem: (1) construct each feature vector using a set of global geometric and moment-based characteristics from each signature and (2) construct the feature vector using the bitmap of the corresponding signature. We also present a mechanism to capture the intrapersonal variability of each user using just one original signature. Our results empirically show that SVM, which achieves up to 71% correct recognition rate, outperforms MLP.

[1]  Ishwar K. Sethi,et al.  Signature identification via local association of features , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[2]  Hyeran Byun,et al.  A Survey on Pattern Recognition Applications of Support Vector Machines , 2003, Int. J. Pattern Recognit. Artif. Intell..

[3]  M. Narasimha Murty,et al.  Off-line signature verification using genetically optimized weighted features , 1999, Pattern Recognit..

[4]  A. Pérez-Hernández,et al.  Simplified Stroke-based Approach for Off-line Signature Recognition , 2004 .

[5]  Ishwar K. Sethi,et al.  Handwritten signature retrieval and identification , 1996, Pattern Recognit. Lett..

[6]  Patrick Gallinari,et al.  An hybrid MLP-SVM handwritten digit recognizer , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[7]  Ioannis Pavlidis,et al.  Off-line recognition of signatures using revolving active deformable models , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[8]  Giuseppe Pirlo,et al.  Automatic Signature Verification: The State of the Art , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[9]  John D. Hobby,et al.  Using Shape and Layout Information to Find Signatures, Text, and Graphics , 2000, Comput. Vis. Image Underst..

[10]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[11]  Venu Govindaraju,et al.  The Role of Holistic Paradigms in Handwritten Word Recognition , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  M. A. Ismail,et al.  Off-line arabic signature recognition and verification , 2000, Pattern Recognit..

[13]  Samy Bengio,et al.  SVMTorch: Support Vector Machines for Large-Scale Regression Problems , 2001, J. Mach. Learn. Res..

[14]  Soo Hyung Kim.  Recognition of Handwritten Korean Address Strings by Tight-Coupling of Minimum Distance Classification and Dictionary-Based Post-Processing , 1998 .

[15]  Guodong Guo,et al.  Face recognition by support vector machines , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[16]  Sukhan Lee,et al.  Offline tracing and representation of signatures , 1992, IEEE Trans. Syst. Man Cybern..

[17]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Teruo Fukumura,et al.  Structural description and classification of signature images , 1990, Pattern Recognit..

[19]  Santiago Vallmitjana,et al.  Methods for invariant signature classification , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[20]  Y. K. Wong,et al.  A smoothness index based approach for off-line signature verification , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[21]  Harris Drucker,et al.  Comparison of learning algorithms for handwritten digit recognition , 1995 .

[22]  Hong Chang,et al.  SVC2004: First International Signature Verification Competition , 2004, ICBA.

[23]  Ishwar K. Sethi,et al.  Local structural association for retrieval and recognition of signature images , 1995, Electronic Imaging.

[24]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[25]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[26]  Ana Belén Moreno,et al.  Robust off-line signature verification using compression networks and positional cuttings , 2003, 2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718).

[27]  Dusan Cakmakov,et al.  Handwritten digit recognition by combining support vector machines using rule-based reasoning , 2001, Proceedings of the 23rd International Conference on Information Technology Interfaces, 2001. ITI 2001..

[28]  Réjean Plamondon,et al.  Automatic Signature Verification: The State of the Art - 1989-1993 , 1994, Int. J. Pattern Recognit. Artif. Intell..

[29]  Claus Bahlmann,et al.  Online handwriting recognition with support vector machines - a kernel approach , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[30]  Carl G. Looney,et al.  Pattern recognition using neural networks: theory and algorithms for engineers and scientists , 1997 .

[31]  H. Baltzakisa,et al.  A new signature verification technique based on a two-stage neural network classifier , 2000 .

[32]  Santanu Chaudhury,et al.  Signature verification using multiple neural classifiers , 1997, Pattern Recognit..

[33]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Edson J. R. Justino,et al.  An off-line signature verification method based on SVM classifier and graphometric features , 2003 .

[35]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[36]  Miguel A. Ferrer,et al.  Signature classification by hidden Markov model , 1999, Proceedings IEEE 33rd Annual 1999 International Carnahan Conference on Security Technology (Cat. No.99CH36303).

[37]  Alisher Kholmatov,et al.  Biometric identity verification using on-line & off-line signature verification , 2003 .

[38]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[39]  Samy Bengio,et al.  Torch: a modular machine learning software library , 2002 .

[40]  Nikolaos Papanikolopoulos,et al.  Signature identification through the use of deformable structures , 1998, Signal Process..

[41]  K. R. Al-Balushi,et al.  Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection , 2003 .

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

[43]  Sharath Pankanti,et al.  Guide to Biometrics , 2003, Springer Professional Computing.