Online Signature Verification Using Deep Learning and Feature Representation Using Legendre Polynomial Coefficients

  • Amr HefnyEmail author
  • Mohamed MoustafaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 921)


Handwritten signing are one of the most popular behavioral biometrics. They are widely accepted for verification purposes, such as authenticating legal documents and financial contracts. In this paper, Legendre polynomials coefficients are used as features to model the signatures. The classifier used in this paper is deep feedforward neural network and the deep learning algorithm is stochastic gradient descent with momentum. The experimental results show better Equal Error Rate reduction and accuracy enhancement on SigComp2011 Dataset presented within ICDAR 2011 in comparison with state-of-the-art methods.


Online signature Deep learning Machine learning Legendre polynomials 


  1. Bharadi, V.A., Singh, V.I.: Hybrid wavelets based feature vector generation from multidimensional data set for on-line handwritten signature recognition. In: 5th International Conference - Confluence The Next Generation Information Technology Summit (Confluence), pp. 561–568 (2014)Google Scholar
  2. Chang, H., Dai, D., Wang, P., Xu, Y.: Online signature verification using wavelet transform of feature function architecture of an online signature verification system. 11, 3135–3142 (2012)Google Scholar
  3. Fernandes, J., Bhandarkar, N.: Enhanced online signature verification system. Int. J. Emerg. Trends Technol. Comput. Sci. (IJETTCS) 3(6), 205–209 (2014). ISSN 2278-6856Google Scholar
  4. Fierrez-Aguilar, J., Krawczyk, S., Ortega-Garcia, J., Jain, A.K.: Fusion of local and regional approaches for on-line signature verification. In: IWBRS 2005. LNCS, vol. 3781, pp. 188–196 (2005)Google Scholar
  5. Hafemann, L.G., Sabourin, R., Oliveira, L.S.: Learning features for offline handwritten signature verification using deep convolutional neural networks. Pattern Recogn. 70, 163–176 (2017)CrossRefGoogle Scholar
  6. Iranmanesh, V., Ahmad, S.M.S., Adnan, W.A.W., Yussof, S., Arigbabu, O.A., Malallah, F.L.: Online handwritten signature verification using neural network classifier based on principal component analysis. Sci. World J. 2014, 1–9 (2014)CrossRefGoogle Scholar
  7. Jain, A.K., Ross, A.A., Nandakumar, K.: Introduction. In: Introduction to Biometrics, pp. 1–49. Springer (2011)Google Scholar
  8. Kaur, M.R., Choudhary, M.P.: Handwritten signature verification based on surf features using HMM. Int. J. Comput. Sci. Trends Technol. 3(1), 187–195 (2015)Google Scholar
  9. Khalil, M., Moustafa, M., Abbas, H.: Enhanced DTW based on-line signature verification. In: 16th IEEE International Conference on Image Processing (ICIP), pp. 2713–2716 (2009)Google Scholar
  10. Liu, Y., Yang, Z., Yang, L.: Online signature verification based on DCT and sparse representation. IEEE Trans. Cybern. 45(11), 2498–2511 (2015)CrossRefGoogle Scholar
  11. Nagbhidkar, K.P., Bagdi, P.V.: Online signature verification on smart phone using discrete wavelet transforms. IORD J. Sci. Technol. 2(2), 1–6 (2015)Google Scholar
  12. Nanni, L., Maiorana, E., Lumini, A., Campisi, P.: Combining local, regional and global matchers for a template protected on-line signature verification system. Expert Syst. Appl. 37(5), 3676–3684 (2010). Scholar
  13. Parodi, M., Gómez, J.C.: Legendre polynomials based feature extraction for online signature verification. Consistency analysis of feature combinations. Pattern Recogn. 47(1), 128–140 (2014). Scholar
  14. Plamondon, R., Pirlo, G., Impedovo, D.: Online signature verification. In: Handbook of Document Image Processing and Recognition, pp. 917–947. Springer (2014)Google Scholar
  15. Plötz, T., Fink, G.A.: Markov models for offline handwriting recognition: a survey. Int. J. Doc. Anal. Recogn. 12, 269–298 (2009)CrossRefGoogle Scholar
  16. Rúa, E.A., Castro, J.L.A.: Online signature verification based on generative models. IEEE Trans. Syst. Man Cybern. B Cybern. 42(4), 1231–1242 (2012)CrossRefGoogle Scholar
  17. Saffar, M.H., Fayyaz, M., Sabokrou, M., Fathy, M.: Online signature verification using deep representation: a new descriptor. arXiv preprint arXiv:1806.09986 (2018)
  18. Sharma, A., Sundaram, S.: An enhanced contextual DTW based system for online signature verification using vector quantization. Pattern Recogn. Lett. 84, 22–28 (2016)CrossRefGoogle Scholar
  19. Thumwarin, P., Pernwong, J., Matsuura, T.: FIR signature verification system characterizing dynamics of handwriting features (2013).
  20. Yanikoglu, B., Kholmatov, A.: Online signature verification using Fourier descriptors. EURASIP J. Adv. Signal Process. (2009)Google Scholar
  21. Yeung, D.-y., Chang, H., Xiong, Y., George, S., Kashi, R., Matsumoto, T., Rigoll, G.: This is the Pre-published Version SVC2004: First International Signature Verification Competition, pp. 1–7 (2004)Google Scholar
  22. Yu, Q., XingXing, W., Chunjing, X.: Learning Mahalanobis distance for DTW based online signature verification. In: IEEE International Conference on Information and Automation (ICIA), June 2011, pp. 333–338 (2011)Google Scholar
  23. Zalasiński, M., Cpałka, K., Hayashi, Y.: New method for dynamic signature verification based on global features. In: International Conference on Artificial Intelligence and Soft Computing, pp. 231–245. Springer (2014)Google Scholar
  24. Zalasiński, M., Cpałka, K., Rakus-Andersson, E.: An idea of the dynamic signature verification based on a hybrid approach. In: International Conference on Artificial Intelligence and Soft Computing, pp. 232–246. Springer (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Mathematics Department, Faculty of ScienceCairo UniversityGizaEgypt
  2. 2.Computer and Systems Engineering Department, Faculty of EngineeringAin Shams UniversityCairoEgypt

Personalised recommendations