Document Type : Research Paper
Authors
- Atefeh Foroozandeh ^{1}
- Ataollah Askari Hemmat ^{} ^{2}^{, 3}
- Hossein Rabbani ^{4}^{, 5}
^{1} Department of Applied Mathematics, Faculty of Sciences and Modern Technology, Graduate University of Advanced Technology, Kerman, Iran.
^{2} Department of Applied Mathematics, Faculty of Mathematics and Computer, Shahid Bahonar University of Kerman, Kerman, Iran.
^{3} Mahani Mathematical Research Center, Shahid Bahonar University of Kerman, Kerman, Iran.
^{4} Department of Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
^{5} Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.
Abstract
Despite the growing growth of technology, handwritten signature has been selected as the first option between biometrics by users. In this paper, a new methodology for offline handwritten signature verification and recognition based on the Shearlet transform and transfer learning is proposed. Since, a large percentage of handwritten signatures are composed of curves and the performance of a signature verification/recognition system is directly related to the edge structures, subbands of shearlet transform of signature images are good candidates for input information to the system. Furthermore, by using transfer learning of some pre-trained models, appropriate features would be extracted. In this study, four pre-trained models have been used: SigNet and SigNet-F (trained on offline signature datasets), VGG16 and VGG19 (trained on ImageNet dataset). Experiments have been conducted using three datasets: UTSig, FUM-PHSD and MCYT-75. Obtained experimental results, in comparison with the literature, verify the effectiveness of the presented method in both signature verification and signature recognition.
Keywords
[2] N.S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression, Amer. Statist., 46 (1992), pp. 175-185.
[3] M. Arathi and A. Govardhan, An efficient offline signature verification system, Int. J. Mach. Learn. Comput., 4 (2014), pp. 533-537.
[4] A.N. Azmi, D. Nasien and F.S. Omar, Biometric signature verification system based on freeman chain code and k-nearest neighbor, Multimedia Tools Appl., 76 (2017), pp. 15341-15355.
[5] Y. Bengio, Learning deep architectures for AI, Found. Trends Mach. Learn., 2 (2009), pp. 1-127.
[6] Y. Bengio and A. Courville, Deep learning of representations, in Handbook on Neural Inf. Process., Springer, (2013), pp. 1-28.
[7] T.A. Bubba, G. Kutyniok, M. Lassas, M. Marz, W. Samek, S. Siltanen and V. Srinivasan, Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography, arXiv:1811.04602v1, 2018.
[8] E.J. Candes and D.L. Donoho, Continuous curvelet transform: I. Resolution of the wavefront set, Appl. Comput. Harmon. Anal., 19 (2005), pp. 162-197.
[9] E.J. Candes and D.L. Donoho, Curvelets: a surprisingly effective nonadaptive representation for objects with edges, Tech. Rep. Department of Statistics, Stanford University, 1999.
[10] C. Cortes and V. Vapnik, Support-vector networks, Mach. Learn., 20 (1995), pp. 273-297.
[11] B. Cozzens and R. Huang, Signature verification using a convolutional neural network, Las Vegas, Nevada, 2017.
[12] I. Daubechies, Ten lectures on wavelets, Soc. Ind. Appl. Math., Philadelphia, 1992.
[13] L. Deng and D. Yu, Deep learning: methods and applications, Found. Trends in Signal Process., 7 (2014), pp. 197-387.
[14] S. Dey, A. Dutta, J. I. Toledo, S K. Ghosh, J. Llados and U. Pal, SigNet: convolutional siamese network for writer independent offline signature verification, CORR, abs/1707.02131, 2017.
[15] M.N. Do and M. Vetterli, The contourlet transform: an efficient directional multiresolution image representation, IEEE Trans. Image Process., 14 (2005), pp. 2091-2106.
[16] M.A. Duval-Poo, F. Odone and E. De Vito, Edges and corners with shearlets, IEEE Trans. Image Process., 24 (2015), pp. 3768-3780.
[17] G. Easley, D. Labate and Wang-Q Lim, Sparse directional image representations using the discrete shearlet transform, J. Appl. Comput. Harmon. Anal., 25 (2008), pp. 25-46.
[18] G. Eskander, R. Sabourin and E. Granger, Hybrid writer-independent-writer-dependent ofﬂine signature veriﬁcation system, IET Biometrics 2(4) (2013), pp. 169-181.
[19] M. Fakhlai, H.R. Pourreza, R. Moarefdost and S. Shadroo, Offline signature recognition based on contourlet transform, Int. Conf. Mach. Learn. Comput., 2009.
[20] J. Fierrez-Aguilar, N. Alonso-Hermira, G. Moreno-Marquez and J. Ortega-Garcia, An off-Line signature verification system based on fusion of local and global information, Int. Workshop Biom. Authentication, (2004), pp. 295-306.
[21] A. Foroozandeh, Y. Akbari, M.J. Jalili and J. Sadri, A novel and practical system for verifying signatures on Persian handwritten bank checks, Int. J. Pattern Recognit. Artif. Intell. (IJPRAI), 26 (2012), pp. 1-27.
[22] C. Freitas et al., Bases de dados de cheques bancarios brasileiros, In XXVI Conferencia Latinoamericana de Informatica, 2000.
[23] Y. Guerbai, Y. Chibani and B. Hadjadji, The effective use of the one-class SVM classifier for handwritten signature verification based on writer-independent parameters, PR, 48(1) (2015), pp. 103-113.
[24] Y. Guo, U. Budak, A. Sengur and F. Smarandache, A retinal vessel detection approach based on shearlet transform and indeterminacy filtering on fundus images, J. Symmetry, 9 (2017).
[25] K. Guo and D. Labate, The construction of smooth parseval frames of shearlets, Math. Model. Nat. Phenom., 8 (2013), pp. 82-105.
[26] L.G. Hafemann, R. Sabourin and L.S. Oliveira, Learning features for offline handwritten signature verification using deep convolutional neural networks, Pattern Recognit., 70 (2017), pp. 163-176.
[27] L.G. Hafemann, R. Sabourin and L.S. Oliveira, Offline handwritten signature verification-literature review, Int. Conf. Image Process. Theory Tool Appl., (2017), pp. 1-8.
[28] L.G. Hafemann, R. Sabourin and L.S. Oliveira, Analyzing features learned for Offline Signature Verification using Deep CNNs, 23rd Int. Conf, Pattern Recognit, (ICPR), (2016), pp. 2989-2994.
[29] L.G. Hafemann, R. Sabourin and L.S. Oliveira, Writer-independent feature learning for Offline Signature Verification using Deep Convolutional Neural Networks, Int. Joint Conf. Neural Netw., (2016), pp. 2576-2583.
[30] S. Hauser and G. Steidl, Fast Finite Shearlet Transform: a tutorial, arXiv:1202.1773v1 [math.NA] 8 Feb 2012.
[31] H. Hezil, R. Djemili and H. Bourouba, Signature recognition using binary features and KNN, Int. J. Biometrics, 10 (2018), pp. 1-15.
[32] M. Kaboli, A Review of transfer learning algorithms, Research Report, Technische Universitat Munchen, 2017.
[33] M.K. Kalera, S. Srihari and A. Xu, Offline signature verification and identification using distance statistics, Int. J. Pattern Recognit. AI., 18 (2004), pp. 1339-1360.
[34] G. Kanghui, G. Kutyniok and D. Labate, Sparse multidimensional representations using anisotropic dilation and shear operators, Int. Conf. Interact. Wavelets and Splines, (2005), pp. 189-201.
[35] H. Khalajzadeh, M. Mansouri and M. Teshnehlab, Persian signature verification using convolutional neural networks, Int. J. Eng. Res. Technol. 1 (2012), pp. 7-12.
[36] M. Khan, A. Jamil, M. Irfan, R. Seungmin and B. Sung, Convolutional neural networks based fire detection in surveillance videos, IEEE Access, 6 (2018), pp. 18174-18183.
[37] N. Kingsbury, Complex wavelets for shift invariant analysis and filtering of signals, Appl. Comput. Harmon. Anal., 10 (2001), pp. 234-253.
[38] N. Kingsbury, Image processing with complex wavelets, Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci., 357 (1999), pp. 2543-2560.
[39] J.R. Koza, F.H. Bennett, D. Andre and M.A. Keane, Automated design of both the topology and sizing of analog electrical circuits using genetic programming, J. Artificial Intelligence Des., (1996), pp. 151-170.
[40] A. Krizhevsky, I. Sutskever and G.E. Hinton, ImageNet classiﬁcation with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 25 (2012), pp. 1097-1105.
[41] R. Kumar, L. Kundu, B. Chanda and J.D. Sharma, A Writer-independent off-line signature veriﬁcation system based on signature morphology, Proc. Conf. Intell. Interactive Technol. Multimedia, New York, NY, USA, (2010), pp. 261-265.
[42] G. Kutyniok and L. Demetrio, Shearlets: multiscale analysis for multivariate data, Springer New York: Birkhauser, 2012.
[43] G. Kutyniok, W.Q. Lim and R. Reisenhofer, Shearlab 3D: faithful digital shearlet transforms based on compactly supported shearlets, J. ACM Trans. Math. Softw., 42 (2016), pp. 1-42.
[44] G. Kutyniok, M. Shahram and X. Zhuang, ShearLab: a rational design of a digital parabolic scaling algorithm, SIAM J. Imaging Sci., 5 (2012), pp. 1291-1332.
[45] S. Mallat and S. Zhong, Characterization of signals from multiscale edges, IEEE Trans. Pattern Anal. Mach. Intell., 14 (1992), pp. 710-732.
[46] S. Min, B. Lee and S. Yoon, Deep learning in bioinformatics, Briefings in Bioinformatics, 18 (2016), pp. 851-869.
[47] R.A. Mohammed, R.M. Nabi, S.M.R. Mahmood and R.M. Nabi, State-of-the-art in handwritten signature verification system, Int. Conf. Comput. Sci. Comput. Intell., (2015), pp. 519-525.
[48] P.N. Narwade, R.R. Sawant and S.V. Bonde, Offline handwritten signature verification using cylindrical shape context, 3D Res. 9 (2018), https://doi.org/10.1007/s13319-018-0200-0.
[49] S.Y. Ooi, A.B. J. Teoh, Y.H. Pang and B.Y. Hiew, Image-based handwritten signature veriﬁcation using hybrid methods of discrete radon transform, principal component analysis and probabilistic neural network, Appl. Soft Comput., 40 (2016), pp. 274-282.
[50] N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Sys. Man. Cyber., 9 (1979), pp. 62-66.
[51] S.J. Pan and Q. Yang, A survey on transfer learning, IEEE Trans. Knowledge Data Eng., 22 (2010), pp. 1345-1359.
[52] D.N. Perkins and G. Salomon, Transfer of learning, Int. Encyclopedia of Education, 2nd Edition, Oxford, England: Pergamon Press, 1992.
[53] M.R. Pourshahabi, M.H. Sigari and H.R. Pourreza, Offline handwritten signature identification and verification using contourlet transform, Int. Conf. Soft Comput. Pattern Recognit., (2009), pp. 670-673.
[54] L.Y. Pratt, Discriminability-based transfer between neural networks, Advances in Neural Inf. Process. Syst., 5 (1993), pp. 204-211.
[55] S. Rajaraman et al., Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images, (2018), PeerJ 6:e4568; DOI: 10.7717/peerj.4568.
[56] W. Rawat and Z. Wang, Deep convolutional neural networks for image classification: a comprehensive review, Neural Comput., 29 (2017), pp. 2352-2449.
[57] S. Razavian, H. Azizpour, J. Sullivan and S. Carlsson, CNN features off-the-shelf: an astounding baseline for recognition, IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), (2014), pp. 512-519.
[58] J.D. Regele and O.V. Vasilyev, An adaptive wavelet-collocation method for shock computations, Int. J. Comput. Fluid Dyn., 23 (2009), pp. 503-518.
[59] J. Sadri, M.J. Jalili, Y. Akbari and A. Foroozandeh, Designing a new standard structure for improving automatic processing of Persian handwritten bank cheques, Int. J. Pattern Anal. Appl. (PAA), 17 (2014), pp .849-862.
[60] M.H. Saffar, M. Fayyaz, M. Sabokrou and M. Fathy, Online signature verification using deep representation: a new descriptor, Int. Comput. Vis. Pattern Recognit. (cs.CV), arXiv:1806.09986.
[61] L. Samuel, Some studies in machine learning using the game of checkers, IBM J. Res. Dev., 3 (1959), pp. 210-229.
[62] J. Schmidhuber, Deep learning in neural networks: an overview, Neural Networks, 61 (2015), pp. 85-117.
[63] M. Sharif, M.A. Khan, M. Faisal, M. Yasmin and S.L. Fernandes, A framework for offline signature verification system: best features selection approach, Pattern Recognit. Lett., 2018.
[64] M.H. Sigari, M.R. Pourshahabi and H. R. Pourreza, Offline handwritten signature identification and verification using multi-resolution Gabor wavelet, Int. J. Biometrics and Bioinform. (IJBB), 5 (2011), pp. 234-248.
[65] K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv 1409.1556, 2014.
[66] A. Soleimani, B.N. Araabi and K. Fouladi, Deep multitask metric learning for offline signature verification, Pattern Recognit. Lett., 80 (2016), pp. 84-90.
[67] A. Soleimani, K. Fouladi and B.N. Araabi, UTSig: a Persian offline signature database, IET Biometrics, 6 (2017), pp. 1-8.
[68] A. Soleimani, K. Fouladi and B.N. Araabi, Persian offline signature verification based on curvature and gradient histograms, 6th Int. Conf. Comput. Knowledge Eng., (2016), pp. 147-152.
[69] H. Srinivasan, S.N. Srihari and M.J. Beal, Machine learning for signature verification, Computer Vision, Graphics and Image Processing, Springer Berlin Heidelberg, (2006), pp. 761-775.
[70] J.L. Starck, F. Murtagh and J. Fadili, Sparse image and signal processing: wavelets, curvelets, morphological diversity, Cambridge University Press, 1st Edition, 2010.
[71] S. Tayeb, M. Pirouz, B. Cozzens, R. Huang, M. Jay, K.Khembunjong and S. Paliskara, Toward data quality analytics in signature verification using a convolutional neural network, IEEE Int. Conf. Big Data, (2017), pp. 2644-2651.
[72] J. Vargas, M. Ferrer, C. Travieso and J. Alonso, Off-line handwritten signature GPDS-960 corpus, Doc. Anal. Recognit., 9th Int. Conf., 2 (2007), pp. 764-768.
[73] K. Weiss, T.M. Khoshgoftaar and D.D. Wang, A survey of transfer learning, J. Big Data, 3 (2016).
[74] N. Xiaopeng, W. Zhiliang and P. Zhigeng, Extreme learning machine based deep model for human activity recognition with wearable sensors, Comput. Sci. Eng., 21 (2018), pp. 16-25.
[75] M.E. Yahyatabar and J. Ghasemi, Online signature verification using double-stage feature extraction modelled by dynamic feature stability experiment, IET Biometrics, 6 (2017), pp. 393-401.
[76] F.Yuan, L-M. Po, M. Liu, X, Xu, W. Jian, K. Wong and K. Cheung, Shearlet based video fingerprint for content-based copy detection, J. Signal Inf. Process., 7 (2016), pp. 84-97.
[77] G. Zaccone, M.R. Karim and Menshawy, Deep learning with TensorFlow, explore neural networks and build intelligent systems with Python, Birmingham, England, Mumbai, India, Packt, 2017.
[78] G. Zhong, L. Wang and J. Dong, An overview on data representation learning: from traditional feature learning to recent deep learning, J. Financ Data Sci., 2 (2016), pp. 265-278.
[79] E.N. Zois, L. Alewijnse and G. Economou, Offline signature verification and quality characterization using poset-oriented grid features, Pattern Recognit., 54 (2016), pp. 162-177.