Abstract
Online signature verification is most popular in the field of biometrics and forensics. Due to its popularity and recent demand, the major challenges are to improve its performance and complexity. This paper presents a novel approach for online signature validation based on local weight learning. The different features like, x coordinate, y coordinates time stamp, pen up and down, azimuth, height, pressure, displacement, velocity and acceleration are extracted from online signature. The extracted features are then passed to locally weighted learning classifier algorithms. Our experimentation is performed on local weight learning classifier of a machine learning method. Locally weighted learning classifier is experimentally found to be effective having False acceptance rate and False rejection rate as 1.18 and 0.02, respectively. The proposed methods gives better performance when compared with other well-known existing models for online signature verification. This result demonstrates that the method is suitable for a real-time system.The popular SVC2004 dataset is used in the experiments, which confirms the effectiveness of the proposed method in simultaneously achieving lower false positive and false negative rate.
Similar content being viewed by others
References
Chandra S (2020) Verification of dynamic signature using machine learning approach. Neural Comput Appl:1–21
Chandra S, Singh KK, Kumar S, Ganesh K, Sravya L, Kumar BP (2021) A novel approach to validate online signature using machine learning based on dynamic features. Neural Comput Appl:1–20
Diaz M, Ferrer MA, Impedovo D, Malik MI, Pirlo G, Plamondon R (2019) A perspective analysis of handwritten signature technology. ACM Comput Surveys (CSUR) 51(6):1–39
Englert P (2012) Locally weighted learning. In: Seminar class on autonomous learning systems. Citeseer
Ferrer MA, Diaz-Cabrera M, Morales A (2013) Synthetic off-line signature image generation. In: 2013 International conference on biometrics (ICB), pp 1–7. IEEE
Fierrez J, Ortega-Garcia J, Ramos D, Gonzalez-Rodriguez J (2007) Hmm-based on-line signature verification: feature extraction and signature modeling. Pattern Recogn Lett 28(16):2325–2334
Hafs T, Bennacer L, Boughazi M, Nait-Ali A (2016) Empirical mode decomposition for online handwritten signature verification. IET Biometrics 5(3):190–199
Hussain L, Aziz W, Nadeem S, Abbasi A (2014) Classification of normal and pathological heart signal variability using machine learning techniques. Int J Darshan Inst Eng Res Emerg Technol 3(2):13–18
Impedovo D, Pirlo G (2008) Automatic signature verification: the state of the art. IEEE Trans Syst Man Cybern Part C (Applications and Reviews) 38 (5):609–635
Kumar MM, Puhan NB (2014) Off-line signature verification: upper and lower envelope shape analysis using chord moments. IET Biometrics 3(4):347–354
Okawa M (2019) Template matching using time-series averaging and dtw with dependent warping for online signature verification. IEEE Access 7:81,010–81,019
Oliveira LS, Justino E, Sabourin R (2007) Off-line signature verification using writer-independent approach. In: 2007 International joint conference on neural networks, pp 2539–2544. IEEE
Parziale A, Diaz M, Ferrer MA, Marcelli A (2019) Sm-dtw: stability modulated dynamic time warping for signature verification. Pattern Recogn Lett 121:113–122
Pramanik R, Bag S (2020) Segmentation-based recognition system for handwritten bangla and devanagari words using conventional classification and transfer learning. IET Image Process 14(5):959–972
Riesen K, Schmidt R (2019) Online signature verification based on string edit distance. Int J Document Anal Recogn (IJDAR) 22(1):41–54
Schaal S, Atkeson CG, Vijayakumar S (2000) Real-time robot learning with locally weighted statistical learning. In: Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No. 00CH37065), vol 1, pp 288–293. IEEE
Schneider J, Moore AW (2000) A locally weighted learning tutorial using vizier 1.0, vol. 149. Carnegie Mellon University the Robotics Institute
Shuai M, Xie K, Pu W, Song G, Ma X (2008) An online approach based on locally weighted learning for short-term traffic flow prediction. In: Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems, pp 1–4
Tan H, He L, Huang ZC, Zhan H (2021) Online signature verification based on dynamic features from gene expression programming. Multimed Tools Appl:1–27
Vorugunti CS, Pulabaigari V, Gorthi RKSS, Mukherjee P (2020) Osvfusenet: online signature verification by feature fusion and depth-wise separable convolution based deep learning. Neurocomputing 409:157–172
Wu X, Kimura A, Iwana BK, Uchida S, Kashino K (2019) Deep dynamic time warping: end-to-end local representation learning for online signature verification. In: 2019 International conference on document analysis and recognition (ICDAR), pp 1103–1110. IEEE
Yahyatabar ME, Baleghi Y, Karami MR (2015) Online signature verification: a robust approach for persian signatures
Yahyatabar ME, Ghasemi J (2017) Online signature verification using double-stage feature extraction modelled by dynamic feature stability experiment. IET Biometrics 6(6):393–401
Yang L, Cheng Y, Wang X, Liu Q (2018) Online handwritten signature verification using feature weighting algorithm relief. Soft Comput 22 (23):7811–7823
Yeung DY, Chang H, Xiong Y, George S, Kashi R, Matsumoto T, Rigoll G (2004) Svc2004: first international signature verification competition. In: International conference on biometric authentication, pp 16–22. Springer
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chandra, S., Kumar, V. A novel approach to validate online signature using dynamic features based on locally weighted learning. Multimed Tools Appl 81, 40959–40976 (2022). https://doi.org/10.1007/s11042-022-13159-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13159-6