From BoVW to VLAD with KAZE features: Offline signature verification considering cognitive processes of forensic experts

Abstract The widespread use of handwritten signatures for identity authentication has resulted in a need for automated verification systems. However, there is room for improvement in the performance of automated systems compared to human analysis, particularly that of forensic document examiners (FDEs), under a wide range of conditions. As any inaccuracy in analysis can cause serious problems, further research is required to improve performance. In this study, to improve the performance of offline signature verification under various writing conditions, new approaches using feature encoding methods of a bag-of-visual words (BoVW) and a vector of locally aggregated descriptors (VLAD) are adopted. The proposed method considers current knowledge about the cognitive processes used by FDEs to improve performance. The proposed method incorporates an approach based on BoVW and VLAD with local features to mimic the cognitive processes of FDEs for feature extraction. In addition, KAZE features detected in strokes and background space are employed as local features to enhance discriminative power. The performance of the proposed approach is demonstrated using the publicly-available CEDAR and MCYT-75 signature datasets.

[1]  Doug Rogers,et al.  A Consideration of signature complexity using simulators' gaze behaviour , 2012 .

[2]  Volkmar Frinken,et al.  Automatic Signature Stability Analysis and Verification Using Local Features , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[3]  Harish Srinivasan,et al.  On the Discriminability of the Handwriting of Twins , 2008, Journal of forensic sciences.

[4]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[5]  Manabu Okawa,et al.  Offline writer verification using pen pressure information from infrared image , 2013, IET Biom..

[6]  Loris Nanni,et al.  An On-Line Signature Verification System Based on Fusion of Local and Global Information , 2005, AVBPA.

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

[8]  R. Nadarajan,et al.  A Fuzzy Hybrid Framework for Offline Signature Verification , 2013, PReMI.

[9]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[10]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[11]  Woo Chaw Seng,et al.  A review of biometric technology along with trends and prospects , 2014, Pattern Recognit..

[12]  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).

[13]  Marcus Liwicki,et al.  Man vs. Machine: A comparative analysis for Signature Verification , 2014 .

[14]  Julian Fierrez,et al.  Off-line Signature Verification Using Contour Features , 2008, ICFHR 2008.

[15]  Umapada Pal,et al.  Off-line signature verification using G-SURF , 2012, 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA).

[16]  Manabu Okawa,et al.  Text and User Generic Model for Writer Verification Using Combined Pen Pressure Information From Ink Intensity and Indented Writing on Paper , 2015, IEEE Transactions on Human-Machine Systems.

[17]  Javier Ruiz-del-Solar,et al.  Offline Signature Verification Using Local Interest Points and Descriptors , 2008, CIARP.

[18]  Adrien Bartoli,et al.  KAZE Features , 2012, ECCV.

[19]  Babak Nadjar Araabi,et al.  Deep Multitask Metric Learning for Offline Signature Verification , 2016, Pattern Recognit. Lett..

[20]  Michael J. Allen,et al.  Foundations of Forensic Document Analysis: Theory and Practice , 2015 .

[21]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

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

[23]  Manabu Okawa,et al.  Vector of locally aggregated descriptors with KAZE features for offline signature verification , 2016, 2016 IEEE 5th Global Conference on Consumer Electronics.

[24]  Jan Seaman Kelly,et al.  Scientific examination of questioned documents , 2006 .

[25]  Manabu Okawa,et al.  OŒine writer veriˆcation based on forensic expertise: Analyzing multiple characters by combining the shape and advanced pen pressure information , 2017 .

[26]  Limin Wang,et al.  Computer Vision and Image Understanding Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice , 2022 .

[27]  Bryan Found,et al.  Visual Attention and Expertise for Forensic Signature Analysis , 2006, Journal of forensic sciences.

[28]  Bryan Found,et al.  An Insight into Forensic Document Examiner Expertise for Discriminating Between Forged and Disguised Signatures , 2008, Journal of forensic sciences.

[29]  Sargur N. Srihari,et al.  Role of automation in the examination of handwritten items , 2014, Pattern Recognit..

[30]  Arun Ross,et al.  50 years of biometric research: Accomplishments, challenges, and opportunities , 2016, Pattern Recognit. Lett..

[31]  Manabu Okawa,et al.  Offline Signature Verification Based on Bag-of-VisualWords Model Using KAZE Features and Weighting Schemes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[32]  Hassiba Nemmour,et al.  New off-line Handwritten Signature Verification method based on Artificial Immune Recognition System , 2016, Expert Syst. Appl..

[33]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Ying Wen,et al.  Text-independent writer identification using SIFT descriptor and contour-directional feature , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[35]  Jesús Francisco Vargas-Bonilla,et al.  Off-line signature verification based on grey level information using texture features , 2011, Pattern Recognit..

[36]  Manabu Okawa,et al.  User generic model for writer verification using multiband image scanner , 2013, 2013 IEEE International Conference on Technologies for Homeland Security (HST).

[37]  Cordelia Schmid,et al.  Aggregating Local Image Descriptors into Compact Codes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  B. H. Shekar,et al.  Local Morphological Pattern Spectrum Based Approach for Off-line Signature Verification , 2013, PReMI.

[39]  Andrew Beng Jin Teoh,et al.  Image-based handwritten signature verification using hybrid methods of discrete Radon transform, principal component analysis and probabilistic neural network , 2016, Appl. Soft Comput..

[40]  Savvas A. Chatzichristofis,et al.  Image moment invariants as local features for content based image retrieval using the Bag-of-Visual-Words model , 2015, Pattern Recognit. Lett..

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

[42]  Sung-Hyuk Cha,et al.  Individuality of handwriting. , 2002, Journal of forensic sciences.

[43]  Manabu Okawa,et al.  Off-Line Writer Verification Using Shape and Pen Pressure Information , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.