Offline signature verification using factorized graph matching

Rahman, A.B.M. Ashikur

dc.contributor.author	Rahman, A.B.M. Ashikur
dc.date.accessioned	2020-09-23T09:32:12Z
dc.date.available	2020-09-23T09:32:12Z
dc.date.issued	2018-11-15
dc.identifier.citation	[1] M. B. Y lmaz and B. Yan ko glu, \Score level fusion of classi ers in o -line signature veri cation," Information Fusion, vol. 32, pp. 109{119, 2016. [2] J. Ruiz-del Solar, C. Devia, P. Loncomilla, and F. Concha, \O ine signature veri cation using local interest points and descriptors," in Iberoamerican Congress on Pattern Recognition, pp. 22{29, Springer, 2008. [3] M. I. Malik, M. Liwicki, A. Dengel, S. Uchida, and V. Frinken, \Automatic signature stability analysis and veri cation using local features," in Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on, pp. 621{626, IEEE, 2014. [4] B. R. Ghosh, S. Banerjee, S. Dey, S. Ganguli, and S. Sarkar, \O -line signature veri cation system using weighted complete bipartite graph," in Business and Information Management (ICBIM), 2014 2nd International Conference on, pp. 109{113, IEEE, 2014. [5] C. Y. Suen, Q. Xu, and L. Lam, \Automatic recognition of handwritten data on cheques{fact or ction?," Pattern Recognition Letters, vol. 20, no. 11-13, pp. 1287{1295, 1999. [6] H. Baltzakis and N. Papamarkos, \A new signature veri cation technique based on a two-stage neural network classi er," Engineering applications of Arti cial intelligence, vol. 14, no. 1, pp. 95{103, 2001. [7] A. El-Yacoubi, E. Justino, R. Sabourin, and F. Bortolozzi, \O -line signature veri cation using hmms and cross-validation," in NEURAL NETWORKS SIG- NAL PROCESS PROC IEEE, vol. 2, pp. 859{868, 2000. [8] E. J. Justino, A. El Yacoubi, F. Bortolozzi, and R. Sabourin, \An o -line signature veri cation system using hmm and graphometric features," in Proc. of the 4th international workshop on document analysis systems, pp. 211{222, 2000. [9] A. C. Verma, D. Saha, and H. Saikia, \Forgery detection in o ine handwritten signature using global and geometric features," IJCER, vol. 2, no. 2, pp. 182{188, 2013. 37 [10] W. F. Nemcek and W. C. Lin, \Experimental investigation of automatic signature veri cation," IEEE Transactions on Systems, Man, and Cybernetics, no. 1, pp. 121{126, 1974. [11] M. R. Pourshahabi, M. H. Sigari, and H. R. Pourreza, \O ine handwritten signature identi cation and veri cation using contourlet transform," in 2009 In- ternational Conference of Soft Computing and Pattern Recognition, pp. 670{673, IEEE, 2009. [12] J. Coetzer, O -line signature veri cation. PhD thesis, Stellenbosch: University of Stellenbosch, 2005. [13] P. S. Deng, H.-Y. M. Liao, C. W. Ho, and H.-R. Tyan, \Wavelet-based o -line handwritten signature veri cation," Computer vision and image understanding, vol. 76, no. 3, pp. 173{190, 1999. [14] R. Zouari, R. Mokni, and M. Kherallah, \Identi cation and veri cation system of o ine handwritten signature using fractal approach," in Image Processing, Applications and Systems Conference (IPAS), 2014 First International, pp. 1{4, IEEE, 2014. [15] M. B. Yilmaz, B. Yanikoglu, C. Tirkaz, and A. Kholmatov, \O ine signature veri cation using classi er combination of hog and lbp features," in Biometrics (IJCB), 2011 international joint conference on, pp. 1{7, IEEE, 2011. [16] Y. Serdouk, H. Nemmour, and Y. Chibani, \Combination of oc-lbp and longest run features for o -line signature veri cation," in Signal-Image Technology and Internet-Based Systems (SITIS), 2014 Tenth International Conference on, pp. 84{88, IEEE, 2014. [17] Y. Serdouk, H. Nemmour, and Y. Chibani, \Orthogonal combination and rotation invariant of local binary patterns for o -line handwritten signature veri cation," [18] J. Hu and Y. Chen, \O ine signature veri cation using real adaboost classi er combination of pseudo-dynamic features," in Document Analysis and Recognition (ICDAR), 2013 12th International Conference on, pp. 1345{1349, IEEE, 2013. [19] J. Vargas, M. Ferrer, C. Travieso, and J. B. Alonso, \O -line signature veri cation based on grey level information using texture features," Pattern Recognition, vol. 44, no. 2, pp. 375{385, 2011. [20] I. S. Abuhaiba, \O ine signature veri cation using graph matching," Turkish Journal of Electrical Engineering & Computer Sciences, vol. 15, no. 1, pp. 89{ 104, 2007. 38 [21] A. Ramachandra, K. Pavithra, K. Yashasvini, K. Raja, K. Venugopal, and L. Patnaik, \Cross-validation for graph matching based o ine signature veri cation," in India Conference, 2008. INDICON 2008. Annual IEEE, vol. 1, pp. 17{22, IEEE, 2008. [22] A. Ramachandra, J. Ravi, K. Raja, K. Venugopal, and L. Patnaik, \Signature veri cation using graph matching and cross-validation principle," International Journal of Recent Trends in Engineering, vol. 1, no. 1, p. 57, 2009. [23] \Comparison of the opencv's feature detection algorithms." [Online; accessed 11-April-2018]. [24] E. Bayraktar and P. Boyraz, \Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics," 2017. [25] S . I s k, \A comparative evaluation of well-known feature detectors and descriptors," vol. 3, pp. 1{6, 2014. [26] E. Karami, S. Prasad, and M. Shehata, \Image matching using sift, surf, brief and orb: performance comparison for distorted images," 2017. [27] D. Rivard, E. Granger, and R. Sabourin, \Multi-feature extraction and selection in writer-independent o -line signature veri cation," International Journal on Document Analysis and Recognition (IJDAR), vol. 16, no. 1, pp. 83{103, 2013. [28] G. S. Eskander, R. Sabourin, and E. Granger, \Hybrid writer-independent{ writer-dependent o ine signature veri cation system," IET biometrics, vol. 2, no. 4, pp. 169{181, 2013. [29] L. S. Oliveira, E. Justino, C. Freitas, and R. Sabourin, \The graphology applied to signature veri cation," in 12th Conference of the International Graphonomics Society, pp. 286{290, 2005. [30] L. Batista, E. Granger, and R. Sabourin, \Dynamic selection of generative{ discriminative ensembles for o -line signature veri cation," Pattern Recognition, vol. 45, no. 4, pp. 1326{1340, 2012. [31] E. Ozg und uz, T. S ent urk, and M. E. Karsl gil, \O -line signature veri cation and recognition by support vector machine," in Signal Processing Conference, 2005 13th European, pp. 1{4, IEEE, 2005. [32] E. J. Justino, F. Bortolozzi, and R. Sabourin, \A comparison of svm and hmm classi ers in the o -line signature veri cation," Pattern recognition letters, vol. 26, no. 9, pp. 1377{1385, 2005. [33] D. Bertolini, L. S. Oliveira, E. Justino, and R. Sabourin, \Reducing forgeries in writer-independent o -line signature veri cation through ensemble of classi ers," Pattern Recognition, vol. 43, no. 1, pp. 387{396, 2010. 39 [34] R. Kumar, J. Sharma, and B. Chanda, \Writer-independent o -line signature veri cation using surroundedness feature," Pattern recognition letters, vol. 33, no. 3, pp. 301{308, 2012. [35] L. G. Hafemann, R. Sabourin, and L. S. Oliveira, \O ine handwritten signature veri cation\|literature review," in Image Processing Theory, Tools and Applica- tions (IPTA), 2017 Seventh International Conference on, pp. 1{8, IEEE, 2017. [36] Y. Guerbai, Y. Chibani, and B. Hadjadji, \The e ective use of the one-class svm classi er for handwritten signature veri cation based on writer-independent parameters," Pattern Recognition, vol. 48, no. 1, pp. 103{113, 2015. [37] K. Huang and H. Yan, \O -line signature veri cation based on geometric feature extraction and neural network classi cation," Pattern Recognition, vol. 30, no. 1, pp. 9{17, 1997. [38] B. Shekar, R. Bharathi, J. Kittler, Y. V. Vizilter, and L. Mestestskiy, \Grid structured morphological pattern spectrum for o -line signature veri cation," in Biometrics (ICB), 2015 International Conference on, pp. 430{435, IEEE, 2015. [39] A. Soleimani, B. N. Araabi, and K. Fouladi, \Deep multitask metric learning for o ine signature veri cation," Pattern Recognition Letters, vol. 80, pp. 84{90, 2016. [40] H. Rantzsch, H. Yang, and C. Meinel, \Signature embedding: Writer independent o ine signature veri cation with deep metric learning," in International symposium on visual computing, pp. 616{625, Springer, 2016. [41] E. Rosten, R. Porter, and T. Drummond, \Faster and better: A machine learning approach to corner detection," vol. 32, pp. 105{119, IEEE, 2010. [42] S. M. Smith and J. M. Brady, \Susan: a new approach to low level image processing," in International journal of computer vision, vol. 23, pp. 45{78, Springer, 1997. [43] J. Bresenham, \A linear algorithm for incremental digital display of circular arcs," in Communications of the ACM, vol. 20, pp. 100{106, ACM, 1977. [44] E. Rosten, \Fast corner detection." [Online; accessed 13-September-2018]. [45] D.-T. Lee and B. J. Schachter, \Two algorithms for constructing a delaunay triangulation," International Journal of Computer & Information Sciences, vol. 9, no. 3, pp. 219{242, 1980. [46] G. Levi and T. Hassner, \Latch: learned arrangements of three patch codes," in 2016 IEEE winter conference on applications of computer vision (WACV), pp. 1{9, IEEE, 2016. 40 [47] H. Bay, T. Tuytelaars, and L. Van Gool, \Surf: Speeded up robust features," in European conference on computer vision, pp. 404{417, Springer, 2006. [48] M. Zaslavskiy, F. Bach, and J.-P. Vert, \A path following algorithm for the graph matching problem," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2227{2242, 2009. [49] M. Cho, J. Lee, and K. M. Lee, \Reweighted random walks for graph matching," in European conference on Computer vision, pp. 492{505, Springer, 2010. [50] S. Gold and A. Rangarajan, \A graduated assignment algorithm for graph matching," IEEE Transactions on pattern analysis and machine intelligence, vol. 18, no. 4, pp. 377{388, 1996. [51] B. J. van Wyk and M. A. van Wyk, \A pocs-based graph matching algorithm," IEEE transactions on pattern analysis and machine intelligence, vol. 26, no. 11, pp. 1526{1530, 2004. [52] R. Zass and A. Shashua, \Probabilistic graph and hypergraph matching," 2008. [53] M. Leordeanu, M. Hebert, and R. Sukthankar, \An integer projected xed point method for graph matching and map inference," in Advances in neural informa- tion processing systems, pp. 1114{1122, 2009. [54] K.-M. Ng, \A continuation approach for solving nonlinear optimization problems with discrete variables," Doctor Dissertation, Department of Management Science and Engineering of Stanford University, 2002. [55] E. L. Allgower and K. Georg, Introduction to numerical continuation methods, vol. 45. SIAM, 2003. [56] I. M. Bomze and G. Danninger, \A global optimization algorithm for concave quadratic programming problems," SIAM Journal on Optimization, vol. 3, no. 4, pp. 826{842, 1993. [57] J. Maciel and J. P. Costeira, \A global solution to sparse correspondence problems," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 187{199, 2003. [58] M. Frank and P. Wolfe, \An algorithm for quadratic programming," Naval re- search logistics quarterly, vol. 3, no. 1-2, pp. 95{110, 1956. [59] M. Fukushima, \A modi ed frank-wolfe algorithm for solving the tra c assignment problem," Transportation Research Part B: Methodological, vol. 18, no. 2, pp. 169{177, 1984. [60] A. A. Rahman, G. Mostaeen, and M. H. Kabir, \A statistical approach for o ine signature veri cation using local gradient features," in International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE), pp. 1{4, IEEE, 2016. 41 [61] M. Liwicki, M. I. Malik, C. E. Van Den Heuvel, X. Chen, C. Berger, R. Stoel, M. Blumenstein, and B. Found, \Signature veri cation competition for online and o ine skilled forgeries (sigcomp2011)," in International Conference on Doc- ument Analysis and Recognition (ICDAR), pp. 1480{1484, IEEE, 2011. [62] T. Fawcett, \An introduction to roc analysis," in Pattern recognition letters, vol. 27, pp. 861{874, Elsevier, 2006.	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/349
dc.description	Supervised by Prof. Dr. Md. Hasanul Kabir	en_US
dc.description.abstract	Signature veri cation is used in verifying the claimed identity of a person through his/her chosen and previously registered signature. The signature's widespread acceptance by the public and niche applications (validating paper documents and use in banking applications) makes it a desirable biometric. Signature is considered to be a behavioral biometric that encodes the ballistic movements of the signer and as such is di cult to imitate. On the other hand, compared to physical traits such as ngerprint, iris or face, a signature typically shows higher intra-class and time variability. Furthermore, as with passwords, a user may choose a simple signature that is easy to forge. In this work, we present a state-of-the-art o ine signature veri cation system that uses a fusion of complementary features, classi ers and preprocessing techniques, with the aim to explore the limits in signature veri cation accuracy. Here we propose an e cient way to verify the identity of a claimed person. This proposed method uses graph matching for measuring the similarity between two sample signatures. For making it eligible to apply graph matching, features are computed by creating graph representation of the signature image. We propose to use direction information for edge feature to make the method more robust to rotation of the image. This direction is normalized to cope with the intra-class variability. For matching Factorized graph matching is used as it provides faster computation of point-wise correspondence. Based on the a nity score, a statistical approach is made for decision making. For validation Writer-Dependent approach is applied. Extensive experiments have been conducted on a benchmark and publicly available O ine Signature Dataset (ICDAR 2011), where the proposed algorithm achieves approximately 12% average False Acceptance Rate (FAR) for signature veri cation. Furthermore, comparison with other promising works on the aforementioned databases demonstrates the enhanced performance and e ciency of the proposed method	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Computer Science and Engineering, Islamic University of Technology, Gazipur, Bangladesh	en_US
dc.title	Offline signature verification using factorized graph matching	en_US
dc.type	Thesis	en_US