Abstract.
This paper proposes a hybrid opto-electronic method for the fast automatic verification of handwritten signatures. This method combines several statistical classifiers and consists of three steps. The first step aims to transform the original signatures using the identity and four Gabor transforms. For each image transform, the second step is to intercorrelate the analysed signature with the similarly transformed signatures of the learning database. Finally, the third step performs the verification of the authenticity of signatures by fusing the decisions related to each transform. Image transforms and intercorrelations can be computed in real time using a high-speed optical correlator. The different decisions and their fusion are then digitally performed. The opto-electronic implementation of the proposed method has been simulated on a large database, taking into account the specific constraints of the optical implementation. Satisfactory results have been obtained. Indeed, the proposed system allows the rejection of 62.4% of the forgeries used for the experiments when 99% of genuine signatures are correctly recognized.
Similar content being viewed by others
References
Ramesh VE, Murty MN (1999) Off-line signature verification using genetically optimized weighted features. Pattern Recog 32(2):217-233
Bajaj R, Chaudhury S (1997) Signature verification using multiple neural classifiers. Pattern Recog 30(1):1-7
Murshed NA, Sabourin R, Bortolozzi F (1997) A cognitive approach to off-line signature verification. Int J Pattern Recog Artif Intell 11(5):801-825
O’Callaghan MJ, Perlmutter SH, Wolt B (2000) Single-chip correlator implementation for PCI-bus personal computers. In: Proceedings of SPIE: Optical Pattern Recognition, vol 4043, pp 48-58
Banas DB, Handschy MA, Crandall C (1997) 256x256 ferroelectric liquid crystal spatial light modulator. In: Proceedings of SPIE: Liquid Crystal Materials, Devices, and Applications V, vol 3015, pp 114-124
O’Callaghan MJ, Ward DJ, Perlmutter SH, Ji L, Walker CM (1998) A highly integrated single-chip optical correlator. In: Proceedings of SPIE: Algorithms, Devices and Systems for Optical Information Processing II, vol 3466, pp 157-164
Fasquel JB, Stolz C, Bruynooghe M (2001) Real-time verification of handwritten signatures using a hybrid opto-electronical method. In: Proceedings of the 2nd IEEE R8 - Eurasip symposium on image and signal processing and analysis
Plamondon R, Lorette G (1989) Automatic signature verification and writer identification - the state of art. Pattern Recog 22(2):107-131
Casasent D, Smokelin JS (1994) Real, imaginary, and clutter Gabor filter fusion for detection with redeuced false alarms. Opt Eng 33(7):2255-2263
Cai J, Liu ZQ (2000) Off-line unconstrainted handwritten word recognition. Int J Pattern Recog Artif Intell 14(3):259-280
Dougherty E (1992) An introduction to morphological image processing. SPIE Optical Engineering Press, Bellingham, WA
Vander Lugt A (1964) Signal detection by complex spatial filtering. IEEE Trans Inf Theory IT-10:139-145
Kumar BVKV, Hassebrook L (1990) Performance measures for correlation filters. Appl Opt 29(20):2997-3006
Castleman KR (1996) Digital image processing. Prentice-Hall, Upper Saddle River, NJ
Kloos H, Wittenburg JP (1999) Implementation of real-time SAR systems with a high performance digital signal processor. In: Proceedings of SPIE: Image and Signal Processing for Remote Sensing V, vol 3871, pp 343-347
Yu FTS, Jutamulia S (1998) Optical pattern recognition. Cambridge University Press, Cambridge, UK
Sabourin R, Genest G (1995) Définition et évaluation d’une famille de représentations pour la vérification hors-ligne des signatures. Traitement du signal 12(6):585-596
Sabourin R, Genest G, Prêteux FJ (1997) Off-line signature verification by local granulometric size distributions. IEEE Trans Pattern Anal Mach Intell 19(9):976-988
Guo JK, Doermann D, Rosenfeld A (2001) Forgery detection by local correspondence. Int J Pattern Recog Artif Intell 15(4):579-641
Drouhard JP, Sabourin R, Godbout M (1996) A neural network approach to off-line signature verification using directional PDF. Pattern Recog 29:415-424
Sabourin R (1997) Off-line signature verification: recent advances and perspectives. In: Proceedings of BSDIA’97: Advances in Document Image Analysis, Vol 1339, 1st Brazilian symposium, pp 84-98
Roberge D, Soutar C, Kumar BVKV (1999) Optimal trade-off filter for the correlation of fingerprints. Opt Eng 38(8):106-113
Kumar BVKV (1992) Tutorial survey of composite filter designs for optical correlators. Appl Opt 31(23):4773-4801
Chao TH, Zhou H, Reyes G (2000) 512x512 High-speed Grayscale Optical Correlator. In: Proceedings of SPIE: Optical Pattern Recognition XI, vol 4043, pp 40-45
Casasent D, Ye A (1997) Detection filters and algorithm fusion for ATR. IEEE Trans Image Process 6(1):114-125
Schalkoff RJ (1992) Pattern recognition: statistical, structural and neural approaches. Wiley, New York
Noharet B, Sjöberg H, Buret T (2000) Efficient techniques to implement correlation filters on fast SLMs. In: Proceedings of SPIE: Optics in Computing, vol 4089, pp 743-749
Carrott DT, Mallalley G, Dydyk RB, Mills SA (1998) Third generation miniaturized optical correlator (MROC) module. In: Proceedings of SPIE: Optical Pattern Recognition IX, vol 3386, pp 38-44
Author information
Authors and Affiliations
Corresponding author
Additional information
Received: 19 November 2002, Accepted: 15 June 2004, Published online: 12 August 2004
Correspondence to: J.-B. Fasquel
Rights and permissions
About this article
Cite this article
Fasquel, JB., Bruynooghe, M. A hybrid opto-electronic method for fast off-line handwritten signature verification. IJDAR 7, 56–68 (2004). https://doi.org/10.1007/s10032-004-0128-1
Issue Date:
DOI: https://doi.org/10.1007/s10032-004-0128-1