A new approach to signature recognition using the fuzzy method
 Przemysław Kudłacik,
 Piotr Porwik
 … show all 2 hide
Abstract
The paper presents a new fuzzy approach to offline handwritten signature recognition. The solution is based on characteristic feature extraction. After finding signature’s center of gravity a number of lines are drawn through it at different angles. Cross points of generated lines and signature sample, which are further grouped and sorted, are treated as the set of features. On the basis of such structures, obtained from a chosen number of learning samples, a fuzzy model is created, called the fuzzy signature. During a verification phase the level of conformity of an input sample and the fuzzy signature is calculated. The extension in feature extraction as well as proposed fuzzy model has never been employed before. It needs to be emphasized that information stored within the verification system cannot be used to recreate the original signatures collected at the enrolment phase. The fact is particularly valuable for large databases and systems where storage safety is crucial. The solution is very flexible and allows the user to extend an intuitive structure of fuzzy sets by employing dynamic features, making the approach an online method. The results obtained should be still improved, similarly to the case of other known biometric systems related to signature recognition. However, the presented technique can be easily utilized in applications where FAR coefficient should be very low and is more important than FRR ratio.
 Abbas R (2003) Back propagation neural network prototype for off line signature verification. Thesis submitted to RMIT, Melbourne
 AlShoshan AI (2006) Handwritten signature verification using image invariants and dynamic features. In: Proceedings International Conference on computer graphics, Imaging and visualization (CGIV’06), pp 173–176
 Ammar M, Yoshida Y, Fukumura T (1986) A new effective approach for offline verification of signatures by using pressure features. In: Proceedings international conference on pattern recognition, pp 566–569
 Armand S, Blumenstein M, Muthukkumarasamy V (2004) Offline signature verification based on the modified direction feature. In: Proceedings 18th International Conference on pattern recognition (ICPR ’06), vol. 04, pp 509–512
 Audet S, Bansal P, Baskaran S (2006) Offline signature verification using virtual support vector machines. In: ECSE 526—Artificial Intelligence, pp 1–8
 Baltzakis, H, Papamarkos, N (2001) A new signature verification technique based on a twostage neural network classifier. Eng Appl Artif Intell 14: pp. 95103 CrossRef
 Bharadi, VA, Kekre, HB (2010) Offline signature recognition systems. Int J Comput Appl 1: pp. 4856
 Chen S, Shrihari S (2005) Use of exterior contours and shape features in offline signature verification. In: Proceedings of eight International Conference on document analysis and recognition (ICDAR’05), pp 1280–1284
 Coetzer, J, Herbst, BM, Preez, JA (2004) Offline signature verification using the discrete radom transform and a Hidden Markov model. EURASIP J Appl Signal Process 4: pp. 559571 CrossRef
 Czogala, E, Leski, J (2000) Fuzzy and neurofuzzy intelligent systems. Springer, Berlin CrossRef
 Czogala, E, Leski, J (2001) On equivalence of approximate reasoning results using different interpretations of if–then rules. Fuzzy Sets Syst 117: pp. 279296 CrossRef
 Deng P, Yuan H, Liao M, Tyan H (1996) Wavelet based offline signature recognition system. In: Proceedings of 5th Conference on optical character recognition and document Analysis
 Doroz, R, Porwik, P, Para, T, Wrobel, K (2008) Dynamic signature recognition based on velocity changes of some features. Int J Biometrics 1: pp. 4762 CrossRef
 Dullink H, van Daalen B, Nijhuis J, Spaanenburg L, Zuidhof H (1995) Implementing a DSP kernel for online dynamic handwritten signature verification using the TMS320 DSP Family, EFRIE SPRA304
 Edson J, Justino R, Bortolozzi F, Sabourin R (2002) The interpersonal and intrapersonal variability influences on offline signature verification using HMM. In: Proceedings of XV Brazilian Symposium computer graphics and image processing, pp 197–202
 Edson, J, Justino, R, Yacoubi, AE, Bortolozzi, F, Sabourin, R (2000) An offline signature verification system using HMM and graphometric features. DAS 2000: pp. 211222
 Fang B, Wang Y Y (1999) A Smoothness Index Based Approach for Offline Signature Verification, Proceedings of fifth International conference on document analysis and recognition (ICDAR ’99), pp 785–787
 Fasihfar Z, Haddadnia J, (2010) Designing a fuzzy RBF neural network with optimal number of neuron in hidden layer and effect of signature shape for persian signature recognition by Zernike moments and PCA. In: International Conference on web information systems and mining, pp. 188–192
 Ferrer, MA, Alonso, JB, Travieso, CM (2005) Offline geometric parameters for automatic signature verification using fixedpoint arithmetic. IEEE Trans Pattern Anal Mach Intell 27: pp. 993997 CrossRef
 Freire M, Fierrez J, MartinezDiaz M, OrtegaGarcia J (2007) On the applicability of offline signatures to the fuzzy vault construction. In: International Conference document analysis and recognition, pp 1173–1177
 Hamilton D, Whelan J, McLaren A (1995) Low cost dynamic signature verification system. In: Proceeding of IEEE CNF European convention on security and detection, pp 202–206
 Hanmandlu, M, Hafizuddin, MY, Madasu, VK (2005) Offline signature verification and forgery detection using fuzzy modeling. Pattern Recogn 38: pp. 341356 CrossRef
 Huang, K, Yan, H (1997) Offline signature verification based on geometric feature extraction and neural network classification. Pattern Recogn 30: pp. 917 CrossRef
 Impedovo D, Pirlo G (2008) Automatic signature verification: the state of the art. IEEE Trans Syst Man Cybern C Appl Rev 38(5):609–635
 Jain, AK, Flynn, P, Ross, AA (2007) Handbook of biometrics. Springer, New York
 Jain, AK, Ross, A, Prabhakar, S (2002) On line signature verification. Pattern Recogn 35: pp. 29632972 CrossRef
 Johnson AY, Sun J, Bobick A F (2003) Using similarity scores from a small gallery to estimate recognition performance for larger galleries. In: IEEE International Workshop on analysis and modeling of faces and gestures (AMFG2003), pp 100–103
 Kaewkongka T, Chamnongthai K, Thipakom B (1999) Offline signature recognition using parameterized Hough transform. In: Proceedings of fifth International Symposium on signal processing and its applications (ISSPA ’99), vol. 1, pp 451–454
 Kalera, MK, Shrihari, S (2004) Offline signature verification and identification using distance statistics. Int J Pattern Recogn Artif Intell 18: pp. 13391360 CrossRef
 Khalid M, Mokayed H, Yusof R, Ono O (2009) Online signature verification with neural networks classifier and fuzzy inference. In: Proc Third Asia International Conference on modelling, simulation, pp 236–241
 Kudlacik P (2008) Operations on fuzzy sets with piecewiselinear membership function (Polish). Studia Informatica 29 3A(78):91–111
 Kudlacik P (2010) Structure of a knowledge base in the FUZZLIB library (Polish). Studia Informatica 31 2A(89):469–478
 Kudlacik, P (2010) Advantages of an approximate reasoning based on a fuzzy truth value. J Med Inf Technol 15: pp. 5761
 Leclerc, F, Plamondon, R (1994) Automatic signature verification: the state of the art. Int J Pattern Recogn Artif Intell 8: pp. 643660 CrossRef
 Lee S, Pan JC (1992) Offline tracing and representation of signatures IEEE Trans Syst Man Cybern 22(4):755–771
 Lei H, Palla S, Govindraju V (2004) ER2: an intuitive similarity measure for online signature verification. In: Ninth International Workshop on frontiers in handwriting recognition (IWFHR9 2004), pp 191–195
 Łukasiewicz J (1920) O logice trojwartosciowej (in Polish). Ruch filozoficzny5:170–171 (English translation: On threevalued logic. In: Borkowski L (ed.) Selected works by Jan lukasiewicz. NorthHolland, Amsterdam, pp 87–88 (1970))
 Madasu VK, Hanmandlu M, Madasu S (2003) Neurofuzzy approaches to signature verification. In: 2nd National Conference on document analysis and recognition (NCDAR2003)
 Majhi, B, Reddy, Y, Babu, D (2006) Novel features for offline signature verification. Int J Comput Commun control 1: pp. 1724
 Mamdani, EH, Assilan, S (1975) An experiment in linguistic synthesis with a fuzzy logic controller. Int J Man Mach Stud 20: pp. 113 CrossRef
 Muramatsu, D, Matsumoto, T (2007) Effectiveness of pen pressure, azimuth, and altitude features for online signature verification. Lect Notes Comput Sci Adv Biom 4642: pp. 503512 CrossRef
 Nalwa, V (1997) Automatic online signature verification. Proc IEEE Trans Biometrics 85: pp. 215239
 Nassery P, Faez K(1998) Signature pattern recognition using moments invariants and a new fuzzy LVQ model. IEICE Trans Inf Syst E81D(12):1483–1493
 Porwik, P, Wrobel, K (2008) Signature preprocessing based on Walsh coefficients. J Med Inf Technol 12: pp. 5761
 Quek C, Zhou RW (2002) Antiforgery: a novel pseudoouter product based fuzzy neural network driven signature verification system. Pattern Recogn Lett 23(14):1795–1816
 Rhee T, Cho S (2001) On line signature recognition using model guided segmentation and discriminative feature selection for skilled forgeries. In: Proceedings of Sixth International Conference on document analysis and recognition, pp 645–649
 Sabourin, R, Genest, G, Preteux, FJ (1997) Offline signature verification local granulometric size distributions. IEEE Trans Pattern Anal Mach Intell 19: pp. 976988 CrossRef
 Shafiei M, Rabiee HR (2003) A new online signature verification algorithm using variable length segmentation and Hidden Markov models. In: Proceedings of seventh International Conference on document analysis and recognition (ICDAR 2003), vol 1, pp 443–446
 SVC2004 signature database http://www.cse.ust.hk/svc2004/
 Takagi, T, Sugeno, M (1985) Fuzzy identification of systems and its applications to modelling and control. IEEE Trans Syst Man Cybern 15: pp. 116132 CrossRef
 Tanabe K, Yoshihara M, Kameya H, Mori S, Omata S, Ito T (2001) Automatic signature verification based on the dynamic feature of pressure. In: Proceedings of sixth international conference on document analysis and recognition (ICDAR 2001), pp 1045–1049
 Tian W, Qiao Y, Ma Z (2007) A New scheme for offline signature verification using DWT and fuzzy net. In: 8th ACIS International Conference on software engineering, artificial intelligence, networking, and parallel/distributed computing, pp 30–35
 Velez JF, Sanchez A, Moreno AB, Esteban JL (2007) Introducing fuzziness on snake models for offline signature verification: a comparative study. In: International Conference on intelligent systems design and applications, pp 843–848
 Velez, JF, Sanchez, A, Moreno, AB, Esteban, JL (2009) Fuzzy shapememory snakes for the automatic offline signature verification problem. Fuzzy Sets Syst 160: pp. 182197 CrossRef
 Xuhua Y, Takashi F, Obata K, Uchikawa Y (1995) Constructing a high performance signature verification system using a GA method. in: IEEE Conference ANNES, pp 170–173
 Zadeh, LA (1965) Fuzzy sets. Inf Control 8: pp. 338353 CrossRef
 Zakaria, R, Wahab, AF, Ali, JM (2010) Confidence fuzzy interval in verification of offline handwriting signature. Eur J Sci Res 47: pp. 455463
 Zhang B (2006) Offline signature recognition and verification by kernel principal component selfregression. In: Proceedings of 5th International Conference on machine learning and applications (ICMLA’06), pp 28–33
 Title
 A new approach to signature recognition using the fuzzy method
 Open Access
 Available under Open Access This content is freely available online to anyone, anywhere at any time.
 Journal

Pattern Analysis and Applications
Volume 17, Issue 3 , pp 451463
 Cover Date
 20140801
 DOI
 10.1007/s1004401202839
 Print ISSN
 14337541
 Online ISSN
 1433755X
 Publisher
 Springer London
 Additional Links
 Topics
 Keywords

 Signature recognition
 Fuzzy sets
 Fuzzy system
 Industry Sectors
 Authors

 Przemysław Kudłacik ^{(1)}
 Piotr Porwik ^{(1)}
 Author Affiliations

 1. Institute of Computer Science, University of Silesia, Katowice, Poland