Online Signature Verification using Deep Representation: A new Descriptor

This paper presents an accurate method for verifying online signatures. The main difficulty of signature verification come from: (1) Lacking enough training samples (2) The methods must be spatial change invariant. To deal with these difficulties and modeling the signatures efficiently, we propose a method that a one-class classifier per each user is built on discriminative features. First, we pre-train a sparse auto-encoder using a large number of unlabeled signatures, then we applied the discriminative features, which are learned by auto-encoder to represent the training and testing signatures as a self-thought learning method (i.e. we have introduced a signature descriptor). Finally, user's signatures are modeled and classified using a one-class classifier. The proposed method is independent on signature datasets thanks to self-taught learning. The experimental results indicate significant error reduction and accuracy enhancement in comparison with state-of-the-art methods on SVC2004 and SUSIG datasets.

[1]  Y. Baleghi,et al.  Online signature verification: A Persian-language specific approach , 2013, 2013 21st Iranian Conference on Electrical Engineering (ICEE).

[2]  M. Fathy,et al.  Online signature verification based on feature representation , 2015, 2015 The International Symposium on Artificial Intelligence and Signal Processing (AISP).

[3]  Leszek Rutkowski,et al.  New method for the on-line signature verification based on horizontal partitioning , 2014, Pattern Recognit..

[4]  D. Mohamad,et al.  Online Signature Verification Using Probablistic Modeling and Neural Network , 2012, 2012 Spring Congress on Engineering and Technology.

[5]  Karim Faez,et al.  Matching between Important Points using Dynamic Time Warping for Online Signature Verification , .

[6]  A. Fallah,et al.  Authentication based on signature verification using position, velocity, acceleration and Jerk signals , 2012, 2012 9th International ISC Conference on Information Security and Cryptology.

[7]  Endra,et al.  Online Signature Verification on Mobile Devices , 2015 .

[8]  George D. C. Cavalcanti,et al.  Off-line Signature Verification: An Approach Based on Combining Distances and One-class Classifiers , 2010, 2010 22nd IEEE International Conference on Tools with Artificial Intelligence.

[9]  Tieniu Tan,et al.  DeepIris: Learning pairwise filter bank for heterogeneous iris verification , 2016, Pattern Recognit. Lett..

[10]  Mahmood Fathy,et al.  A novel approach for Finger Vein verification based on self-taught learning , 2015, 2015 9th Iranian Conference on Machine Vision and Image Processing (MVIP).

[11]  Asghar Fallah,et al.  A new online signature verification system based on combining Mellin transform, MFCC and neural network , 2011, Digit. Signal Process..

[12]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[13]  Hyun Ah Song,et al.  Hierarchical Representation Using NMF , 2013, ICONIP.

[14]  Ling Guan,et al.  On-line signature verification using global features , 2009, 2009 Canadian Conference on Electrical and Computer Engineering.

[15]  Réjean Plamondon,et al.  Handwritten Signature Verification: New Advancements and Open Issues , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[16]  George Economou,et al.  Online signature verification based on signatures turning angle representation using longest common subsequence matching , 2012, International Journal on Document Analysis and Recognition (IJDAR).

[17]  Hyotaek Lim,et al.  An Efficient Online Signature Verification Scheme Using Dynamic Programming of String Matching , 2011, ICHIT.

[18]  Réjean Plamondon,et al.  Synthetic on-line signature generation. Part I: Methodology and algorithms , 2012, Pattern Recognit..

[19]  Congying Han,et al.  Fingerprint Classification Based on Depth Neural Network , 2014, ArXiv.

[20]  Salman Yussof,et al.  Online Handwritten Signature Verification Using Neural Network Classifier Based on Principal Component Analysis , 2014, TheScientificWorldJournal.

[21]  Priyank Jain,et al.  Online Signature Verification Using Energy,Angle and Directional Gradient Feature WithNeural Network , 2013 .

[22]  Hazem M. Abbas,et al.  Enhanced DTW based on-line signature verification , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[23]  Julian Fiérrez,et al.  HMM-based on-line signature verification: Feature extraction and signature modeling , 2007, Pattern Recognit. Lett..

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

[25]  Abdul Quaiyum Ansari,et al.  Online signature verification using segment-level fuzzy modelling , 2014, IET Biom..

[26]  Berrin A. Yanikoglu,et al.  SUSIG: an on-line signature database, associated protocols and benchmark results , 2008, Pattern Analysis and Applications.

[27]  Enrique Cantó,et al.  Embedded System for Biometric Online Signature Verification , 2014, IEEE Transactions on Industrial Informatics.

[28]  Julian Fiérrez,et al.  Synthetic on-line signature generation. Part II: Experimental validation , 2012, Pattern Recognit..

[29]  Marcos Faúndez-Zanuy,et al.  On-line signature recognition based on VQ-DTW , 2007, Pattern Recognit..

[30]  Bernhard Sick,et al.  Online Signature Verification With Support Vector Machines Based on LCSS Kernel Functions , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[31]  A. Lakshmi,et al.  DEEP REPRESENTATIONS FOR IRIS , FACE , AND FINGERPRINT SPOOFING DETECTION , 2017 .

[32]  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).