Off-line signature verification

In today’s society signatures are the most accepted form of identity verification. However, they have the unfortunate side-effect of being easily abused by those who would feign the identification or intent of an individual. This thesis implements and tests current approaches to off-line signature verification with the goal of determining the most beneficial techniques that are available. This investigation will also introduce novel techniques that are shown to significantly boost the achieved classification accuracy for both person-dependent (one-class training) and person-independent (two-class training) signature verification learning strategies. The findings presented in this thesis show that many common techniques do not always give any significant advantage and in some cases they actually detract from the classification accuracy. Using the techniques that are proven to be most beneficial, an effective approach to signature verification is constructed, which achieves approximately 90% and 91% on the standard CEDAR and GPDS signature datasets respectively. These results are significantly better than the majority of results that have been previously published. Additionally, this approach is shown to remain relatively stable when a minimal number of training signatures are used, representing feasibility for real-world situations.

[1]  Anil K. Jain,et al.  Goal-Directed Evaluation of Binarization Methods , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Peter Shaohua,et al.  Wavelet – based Off – line Signature Verification , 2007 .

[3]  Robert Sabourin.  Off-Line Signature Verification: Recent Advances and Perspectives , 1997, BSDIA.

[4]  Siyuan Chen,et al.  Machine Learning for Signature Verification , 2006, ICVGIP.

[5]  Hidetoshi Miike,et al.  An off-line signature verification system using an extracted displacement function , 2002, Pattern Recognit. Lett..

[6]  Sebastiano Impedovo,et al.  Verification of Handwritten Signatures: an Overview , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[7]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Lei Zhang,et al.  A Novel Off-Line Signature Verification Based on Adaptive Multi-resolution Wavelet Zero-Crossing and One-Class-One-Network , 2007, ISNN.

[9]  Sargur N. Srihari,et al.  Offline Signature Verification And Identification Using Distance Statistics , 2004, Int. J. Pattern Recognit. Artif. Intell..

[10]  Karolj Skala,et al.  Reimplementation of the Random Forest Algorithm , 2005 .

[11]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[12]  Flávio Bortolozzi,et al.  A comparison of SVM and HMM classifiers in the off-line signature verification , 2005, Pattern Recognit. Lett..

[13]  Sargur N. Srihari,et al.  Machine learning approaches for person identification and verification , 2005, SPIE Defense + Commercial Sensing.

[14]  Bai-ling Zhang.  Off-Line Signature Recognition and Verification by Kernel Principal Component Self-Regression , 2006, 2006 5th International Conference on Machine Learning and Applications (ICMLA'06).

[15]  Anil K. Jain,et al.  On-line signature verification, , 2002, Pattern Recognit..

[16]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[18]  Vallipuram Muthukkumarasamy,et al.  Off-line Signature Verification based on the Modified Direction Feature , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[19]  A. N. Rajagopalan,et al.  Off-line signature verification using DTW , 2007, Pattern Recognit. Lett..

[20]  Luiz Eduardo Soares de Oliveira,et al.  Combining Classifiers in the ROC-space for Off-line Signature Verification , 2008, J. Univers. Comput. Sci..

[21]  Lei Zhang,et al.  A Novel Off-line Signature Verification Based on One-class-one-network , 2007, Third International Conference on Natural Computation (ICNC 2007).

[22]  Sargur N. Srihari,et al.  Gradient-based contour encoding for character recognition , 1996, Pattern Recognit..

[23]  Sargur N. Srihari,et al.  Learning strategies and classification methods for off-line signature verification , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[24]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[25]  Ben M. Herbst,et al.  Offline Signature Verification Using the Discrete Radon Transform and a Hidden Markov Model , 2004, EURASIP J. Adv. Signal Process..

[26]  Sargur N. Srihari,et al.  Properties of Binary Vector Dissimilarity Measures , 2003 .

[27]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[28]  Banshider Majhi,et al.  Novel Features for Off-line Signature Verification , 2006, Int. J. Comput. Commun. Control.

[29]  Siyuan Chen,et al.  Machine Learning for Signature Verification , 2006, ICVGIP.

[30]  Wei Tian,et al.  A New Scheme for Off-line Signature Verification Using DWT and Fuzzy Net , 2007, Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007).

[31]  Abdullah I. Al-Shoshan,et al.  Handwritten Signature Verification Using Image Invariants and Dynamic Features , 2006, International Conference on Computer Graphics, Imaging and Visualisation (CGIV'06).

[32]  Geetha Srikantan,et al.  A multiple feature/resolution approach to handprinted digit and character recognition , 1996, Int. J. Imaging Syst. Technol..

[33]  Bernd Lutterbeck,et al.  Governing Legal Identities Lessons from the History of Seals and Signatures , 2000 .

[34]  Miguel Angel Ferrer-Ballester,et al.  Offline geometric parameters for automatic signature verification using fixed-point arithmetic , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[36]  Matti Pietikäinen,et al.  Robust Texture Classification by Subsets of Local Binary Patterns , 2000, ICPR.

[37]  M. Elif Karsligil,et al.  Off-line signature verification and recognition by Support Vector Machine , 2005, 2005 13th European Signal Processing Conference.

[38]  Ilya Blayvas,et al.  Efficient computation of adaptive threshold surfaces for image binarization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[39]  R. Larkins,et al.  Adaptive Feature Thresholding for off-line signature verification , 2008, 2008 23rd International Conference Image and Vision Computing New Zealand.

[40]  Siyuan Chen,et al.  A New Off-line Signature Verification Method based on Graph , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[41]  J. B. Alonso,et al.  Parameterization of a forgery handwritten signature verification system using SVM , 2004, 38th Annual 2004 International Carnahan Conference on Security Technology, 2004..

[42]  Venu Govindaraju,et al.  Character image enhancement by selective region-growing , 1996, Pattern Recognit. Lett..

[43]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

[44]  Jianying Hu,et al.  Retail applications of signature verification , 2004, SPIE Defense + Commercial Sensing.

[45]  Matti Pietikäinen,et al.  Rotation-invariant texture classification using feature distributions , 2000, Pattern Recognit..