Conference Paper2012Cited by 5

Profound impact of artificial neural networks and Gaussian SVM kernel on distinctive feature set for offline signature verification

Sheikh Faisal Miskhat, Mahmud Ridwan, Ehtesham Chowdhury, Saami Rahman, M Ashraful Amin

2012 International Conference on Informatics, Electronics & Vision (ICIEV)

IEEE, pp. 940–945

DOI: 10.1109/iciev.2012.6317439URL

Abstract

Signature (Latin - signare) is a handwritten stylized form of identification of its owner. Often handwritten signatures are generally used in secured identity preservation. An ideal signature recognition system handles image noise as well as that of learning unique patterns in an individual's signature. This paper analyzes the performance of artificial neural network (ANN) architectures and Gaussian support vector machine (SVM) kernel for offline signature recognition scheme that is trained on a distinct feature set extracted from signature images. We investigated the impact of using ANN and SVM on specialized feature set and present comparative analysis of the two. Three distinct features - gradient histogram, dot density and slices were used - yielding testing accuracies of 93.1%, 98% and 85.1% respectively. Using ANN and SVM on this set, a maximum accuracy of 96.57% was achieved over a group of 30 individuals, covering an entire data set of 3000 signatures.

Keywords

  • Gaussian kernel
  • histogram of oriented gradients
  • offline signature verification
  • dot density
  • artificial neural networks
  • handwritten signature recognition
  • Feature extraction
  • biometric identification
  • Support vector machine

CCDS Authors

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Réjean Plamondon, G Lorette. (1989). Automatic signature verification and writer identification — the state of the art. Pattern Recognition, 22(2), 107–131[10.1016/0031-3203(89)90059-9]
  2. 2.Haris Baltzakis, N. Papamarkos. (2001). A new signature verification technique based on a two-stage neural network classifier. Engineering Applications of Artificial Intelligence, 14(1), 95–103[10.1016/s0952-1976(00)00064-6]
  3. 3.Edson Justino, Flávio Bortolozzi, Robert Sabourin. (2004). A comparison of SVM and HMM classifiers in the off-line signature verification. Pattern Recognition Letters, 26(9), 1377–1385[10.1016/j.patrec.2004.11.015]
  4. 4.Andrew J. Viterbi. (2006). A personal history of the Viterbi algorithm. IEEE Signal Processing Magazine, 23(4), 120–142[10.1109/msp.2006.1657823]
  5. 5.Yuan Yan Tang, Tao Yu, Ernest C.M. Lam. (2002). New method for feature extraction based on fractal behavior. Pattern Recognition, 35(5), 1071–1081[10.1016/s0031-3203(01)00095-4]
  6. 6.Marc Parizeau, Réjean Plamondon. (1990). A comparative analysis of regional correlation, dynamic time warping, and skeletal tree matching for signature verification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7), 710–717[10.1109/34.56215]
  7. 7.Yingyong Qi, Bobby R. Hunt. (1994). Signature verification using global and grid features. Pattern Recognition, 27(12), 1621–1629[10.1016/0031-3203(94)90081-7]
  8. 8.Jean-Pierre Drouhard, Robert Sabourin, M. Godbout. (1996). A neural network approach to off-line signature verification using directional PDF. Pattern Recognition, 29(3), 415–424[10.1016/0031-3203(95)00092-5]
  9. 9.Mohamed A. Ismail, Samia Gad. (2000). Off-line arabic signature recognition and verification. Pattern Recognition, 33(10), 1727–1740[10.1016/s0031-3203(99)00047-3]
  10. 10.Ke Han, Ishwar K. Sethi. (1996). Handwritten signature retrieval and identification. Pattern Recognition Letters, 17(1), 83–90[10.1016/0167-8655(95)00094-1]
  11. 11.Vahid Kiani, Reza Pourreza Shahri, Hamid Reza Pourreza. (2009). Offline Signature Verification Using Local Radon Transform and Support Vector Machines. The International Journal of Sport and Society, 3
  12. 12.H. B. Kekre, Vinayak Ashok Bharadi. (2010). Off-Line Signature Recognition Systems. International Journal of Computer Applications, 1(27), 61–70[10.5120/499-815]
  13. 13.Ahmad Puad Ismail, Mohamed A. Ramadan, Talaat S. El‐Danaf, Ahmed H. Samak. (2011). An efficient offline signature identification method based on Fourier Descriptor and chain codes. International Journal of Biomedical Engineering and Technology, 5(1), 1[10.1504/ijbet.2011.038469]
  14. 14.Qun Chang, Qingcai Chen, Xiaolong Wang. (2006). Scaling Gaussian RBF kernel width to improve SVM classification. , 1, 19–22[10.1109/icnnb.2005.1614559]
  15. 15.Xuhong Xiao, Graham Leedham. (2002). Signature verification using a modified Bayesian network. Pattern Recognition, 35(5), 983–995[10.1016/s0031-3203(01)00088-7]
  16. 16.Tonphong Kaewkongka, Kosin Chamnongthai, Bundit Thipakorn. (2003). Off-line signature recognition using parameterized Hough transform. , 1, 451–454[10.1109/isspa.1999.818209]
  17. 17.Shashi Kumar, K B Raja, R.K. Chhotaray, Sabyasachi Pattanaik. (2010). Off-line Signature Verification Based on Fusion of Grid and Global Features Using Neural Networks.
  18. 18.Kshitij Sisodia, S. Mahesh An. (2013). Off-line Handwritten Signature Verification using Artificial Neural Network Classifier.
  19. 19.Mehdi Radmehr, Seyed Mahmoud Anisheh, Mohsen Nikpour, Abbas Yaseri. (2011). Designing an Offline Method for Signature Recognition.
  20. 20.Cemil Öz, Fikret Erçal, Zafer Demir. (2003). Signature recognition and verification with ANN.
  21. 21.Omid Mirzaei, Hassan Irani, Hamid Reza Pourreza. (2011). Offline Signature Recognition using Modular Neural Networks with Fuzzy Response Integration.
  22. 22.Zhong-Hua Quan, De-Shuang Huang, Kunhong Liu, Kwok‐wing Chau. (2007). A Hybrid HMM/ANN Based Approach for Online Signature Verification. IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks, 402–405[10.1109/ijcnn.2007.4370990]

Cited By

  1. 1.Faiza Eba Batool, Muhammad Attique, Muhammad Sharif, Kashif Javed, Muhammad Nazir, Aaqif Afzaal Abbasi, Zeshan Iqbal, Naveed Riaz. (2020). Offline signature verification system: a novel technique of fusion of GLCM and geometric features using SVM. Multimedia Tools and Applications, 83(5), 14959–14978[10.1007/s11042-020-08851-4]
  2. 2.Murat Taskiran, Zehra Gulru Cam. (2017). Offline signature identification via HOG features and artificial neural networks. , 000083–000086[10.1109/sami.2017.7880280]
  3. 3.K. N. Pushpalatha, Aravind Kumar Gautham, D. R. Shashikumar, K. B. Shiva Kumar, Rupam Das. (2013). Offline Signature Verification with Random and Skilled Forgery Detection Using Polar Domain Features and Multi Stage Classification-Regression Model. International Journal of Advanced Science and Technology, 59, 27–40[10.14257/ijast.2013.59.03]
  4. 4.K.N. Pushpalatha, Supreeth S. Prajwal, A.K. Gautam, K.B. Shiva Kumar. (2014). Offline signature verification based on contourlet transform and textural features using HMM. , 1–6[10.1109/icraie.2014.6909124]
  5. 5.Xiaokang Ding, Lei Yan, Jinhao Liu, Jianlei Kong, Zheng Yu. (2013). Obstacles Detection Algorithm in Forest based on Multi-sensor Data Fusion. Journal of Multimedia, 8(6)[10.4304/jmm.8.6.790-795]
← All publications