Skip to main content
SpringerLink
Log in

COMPOSV: compound feature extraction and depthwise separable convolution-based online signature verification

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Online signature verification (OSV) is a predominantly used verification framework, which is intended to authenticate the legitimacy of a test signature by learning the writer specific signing characteristics. The significant adoption of OSV in critical applications like E-Commerce, M-Payments, etc., emphasizes on a framework which addresses critical requirements: (1) The framework should be competent to classify a test signature with few training samples, as minimum as one per user and with the least number of features extracted per signature, and (2) The framework should accurately classify a test signature of an unseen user. Even though several OSV frameworks are proposed based on various advanced techniques, still there is a necessity for a holistic OSV framework which is able to accomplish the abovementioned requirement criteria. To realize the above requirements, we present a depthwise separable (DWS) convolution-based OSV framework which facilitate the classification of test signature samples from an unseen user. In addition to this, we introduce a novel dimensionality reduction-based feature extraction technique, which decrease the dimensionality of a set of features from 100 to 3 concerning to MCYT-330, MCYT-100 and 47 to 3 with regard to SVC, SUSIG datasets. To appraise the competence of our proposed COMPOSV framework, extensive experiments and ablation studies are conducted on four widely used datasets, i.e., MCYT-100, MCYT-330, SVC and SUSIG. The proposed framework, trained with signature samples of only 10% of users (seen), can classify the signatures of 90% of unseen users with higher accuracy than the frameworks trained with signature samples of all users.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Guru DS, Manjunath KS, Manjunath S, Somashekara M (2017) Interval valued symbolic representation of writer dependent features for online signature verification. Expert Syst Appl 80(7–9):232–243

    Article  Google Scholar 

  2. He L, Tan H, Huang Z (2019) Online handwritten signature verification based on association of curvature and torsion feature with Hausdorff distance. Multimed Tools Appl 23(6):407–418

    Google Scholar 

  3. Keshari R, Singh R, Vatsa M (2019) Guided dropout. In: AAAI conference on artificial intelligence, vol 33. IEEE, pp 4065–4072

  4. Fierrez-Aguilar J, Krawczyk S, Ortega-Garcia J, Jain AK (2005) Fusion of local and regional approaches for on-line signature verification. In: International Conference on Advance Biometric Person Authentication, vol 1. IEEE, pp 188–196

  5. Sekhar V, Doctor A, Viswanath P (2019) Classification of handwritten signatures based on name legibility. In: ICDAR WML (2019) 2nd international workshop on machine learning, vol 6539. IEEE, pp 53–59

  6. Manjunatha K, Manjunath S, Guru D, Somashekara M (2016) Online signature verification based on writer dependent features and classifiers. Pattern Recognit Lett 80(3):129–136

    Article  Google Scholar 

  7. Al-Hmouz R, Pedrycz W, Daqrouq K, Morfeq A, Al-Hmouz A (2019) Quantifying dynamic time warping distance using probabilistic model in verification of dynamic signatures. Soft Comput 23(6):407–418

    Article  Google Scholar 

  8. Khalil M, Moustafa M, Abbas H (2009) Online signature verification using recurrent neural network and length-normalized path signature descriptor. In: 16th IEEE international conference on image processing (ICIP), vol 6539. IEEE, pp 1470–1475

  9. Galbally J, Fiérrez J, Diaz M, Garcia J (2009) Improving the enrollment in dynamic signature verification with synthetic samples. In: International conference document analysis and recognition (ICDAR), vol 6539. IEEE, pp 1295–1299

  10. Guru D, Prakash H (2007) Symbolic representation of on-line signatures. In: International conference on computational intelligence and multimedia applications, vol 1. IEEE, pp 313–317

  11. Sekhar V, Sai Gorthi R, Viswanath P (2019) Online signature verification by few-shot separable convolution based deep learning. In: International conference on document analysis and recognition, vol 2. IEEE, pp 1125–1129

  12. Diaz M, Fischer A, Ferrer MA, Plamondon R (2018) Dynamic signature verification system based on one real signature. IEEE Trans Cybernet 48(3):129–136

    Google Scholar 

  13. Nanni L, Lumini A (2006) Experimental comparison of one-class classifiers for on-line signature verification. Neurocomputing 69(7–9):869–873

    Article  Google Scholar 

  14. Vorugunti C, Prerana M, Guru D, Viswanath P (2019) Osvnet: convolutional siamese network for writer independent online signature verification. In: 15th international conference on document analysis and recognition (ICDAR 2019), vol 6539. IEEE, pp 1470–1475

  15. Li C, Zhang X, Lin F, Wang Z, Liu J, Zhang R, Wang H (2019) A stroke-based RNN for writer-independent online signature verification. In: 15th International Conference on Document Analysis and Recognition (ICDAR), vol 6539. IEEE, pp 526–532

  16. Pirlo G, Cuccovillo V, Diaz-Cabrera M, Impedovo D, Mignone P (2015) Multidomain verification of dynamic signatures using local stability analysis. IEEE Trans Human-Mach Syst 45(6):407–418

    Article  Google Scholar 

  17. Sharma A, Sundaram S (2017) A novel online signature verification system based on GMM features in a DTW framework. IEEE Trans Inf Forensics Secur 12(11):705–718

    Article  Google Scholar 

  18. Nanni L, Lumini A (2006) Advanced methods for two-class problem formulation for on-line signature verification. Neurocomputing 69(3):854–857

    Article  Google Scholar 

  19. Diaz M, Ferrer A, Quintana J (2019) Anthropomorphic features for on-line signatures. IEEE Trans Pattern Anal Mach Intell 41:2807–2819

    Article  Google Scholar 

  20. Impedovo D, Pirlo G (2018) Automatic signature verification in the mobile cloud scenario: survey and way ahead. IEEE Trans Emerg Topics Comput 12(11):1–10

    Google Scholar 

  21. Tang L, Kang W, Fang Y (2018) Information divergence-based matching strategy for online signature verification. IEEE Trans Inf Forensics Secur 13(2):113–127

    Google Scholar 

  22. Kar B, Mukherjee A, Dutta P (2018) Stroke point warping-based reference selection and verification of online signature. IEEE Trans Instrum Meas 67(6):1059–1073

    Google Scholar 

  23. Doroz R, Kudlacik P, Porwika P (2016) Online signature verification modeled by stability oriented reference signatures. Pattern Recognit Lett 84(6):22–28

    Google Scholar 

  24. Lai S, Jin L (2018) Recurrent adaptation networks for online signature verification. IEEE Trans Inf Forensics Secur 23(6):407–418

    Google Scholar 

  25. Lai S, Jin L, Yang W (2019) Online signature verification using recurrent neural network and length-normalized path signature descriptor. In: 14th international conference on document analysis and recognition (ICDAR 2017), vol 6539. IEEE, pp 1470–1475

  26. Rashidi S, Fallah A, Towhidkhah F (2013) Authentication based on pole-zero models of signature velocity. J Med Signals Sens 3(6):195–208

    Google Scholar 

  27. Diaz M, Fischer A, Plamondon R, Ferrer MA (2015) Towards an automatic on-line signature verifier using only one reference per signer. In: International conference on document analysis and recognition (ICDAR), vol 6539. IEEE, pp 631–635

  28. Wu X, Kimur A, Kenji Iwan B, Uchid S, Kashino K (2019) Deep dynamic time warping: end-to-end local representation learning for online signature verification. In: 15th international conference on document analysis and recognition (ICDAR), vol 6539. IEEE, pp 1103–1109

  29. Barkoula K, Economou G, Fotopoulos S (2013) Online signature verification based on signatures turning angle representation using longest common subsequence matching. Int J Doc Anal Recognit 16(11):261–272

    Article  Google Scholar 

  30. Guru D, Prakash H (2009) Online signature verification and recognition: an approach based on symbolic representation. IEEE Trans Pattern Anal Mach Intell 31(6):407–418

    Article  Google Scholar 

  31. Chakraborty D, Narayanan V, Ghosh A (2019) Integration of deep feature extraction and ensemble learning for outlier detection. Pattern Recogn 89(10):161–171

    Article  Google Scholar 

  32. Ansari A, Hanmandlu M, Kour J, Singh A (2014) Online signature verification using segment-level fuzzy modelling. IET Biometrics 3(2):113–127

    Article  Google Scholar 

  33. Maiorana E, Campisi P, Fierrez J, Garcia J, Neri A (2010) Cancelable templates for sequence-based biometrics with application to on-line signature recognition. IEEE Trans Man Machine Cybern 40(3):525–538

    Google Scholar 

  34. Yang L, Cheng Y, Wang X, Liu Q (2018) Online handwritten signature verification using feature weighting algorithm relief. Soft Comput 22(6):1059–1073

    Article  Google Scholar 

  35. Sekhar V, Mukherjee P, Guru D, Viswanath P (2019) Online signature verification based on writer specific feature selection and fuzzy similarity measure. In: Workshop on media forensics, CVPR vol. 65. IEEE, pp 88–95

  36. Xinghua X, Xiaoyu S, Fangun L, Jungang Z, Zhili C, Xiaofu M (2018) Discriminative feature selection for on-line signature verification. Pattern Recognit 74(10):422–433

    Google Scholar 

  37. Alaei A, Pal S, Pal U, Blumenstein M (2017) An efficient signature verification method based on an interval symbolic representation and a fuzzy similarity measure. IEEE Trans Inf Forensics Secur 12(11):1–13

    Article  Google Scholar 

  38. Sae-Bae N, Memon N (2014) Online signature verification on mobile devices. IEEE Trans Inf Forensics Secur 9(6):933–947

    Article  Google Scholar 

  39. Liu Y, Yang Z, Yang L (2015) online signature verification based on DCT and sparse representation. IEEE Trans Cybern 45(11):2498–2511

    Article  Google Scholar 

  40. Impedovo D, Pirlo G, Diaz M, Ferrer M (2019) Weighted direct matching points for user stability model in multiple domains: A proposal for on-line signature verification. In: 15th international conference on document analysis and recognition (ICDAR), vol 6539. IEEE, pp 1320–1326

  41. Tolosana R, Rodriguez R, Fierrez J, Ortega-Garcia J (2017) Biometric signature verification using recurrent neural networks. In: 14th international conference on document analysis and recognition (ICDAR), vol 6539. IEEE, pp 1295—-1299

  42. Yilmaz M, Ozturk K (2018) Hybrid user-independent and user-dependent offline signature verification with a two-channel CNN. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW), vol 6539. IEEE, pp 526–534

  43. Wu X, Kimura A, Uchida S, Kashino K (2019) Prewarping siamese network: learning local representations for online signature verification. In: IEEE international conference on acoustics, speech and signal processing, ICASSP, vol 65. IEEE, pp 2467–2471

  44. Wang X, Jiang Y, Luo Z, Cheng-Lin L, Choi H, Kim S (2019) Arbitrary shape scene text detection with adaptive text region representation. In: The IEEE conference on computer vision and pattern recognition (CVPR), vol 65. IEEE, pp 6449–6458

  45. Manabu O (2020) Online signature verification using single-template matching with time-series averaging and gradient boosting. Pattern Recognit 102(107227):1–39

    Google Scholar 

  46. Chandra Sekhar V, Viswanath P, Rama Krishna G, Prerana M (2020) Osvfusenet: online signature verification by feature fusion and depthwise separable convolution based deep learning. Neurocomputing 409:157–172

    Article  Google Scholar 

  47. Chandra Sekhar V, Viswanath P, Prerana M, Abhishek S (2020) Deepfuseosv: online signature verification using hybrid feature fusion and depthwise separable convolution neural network architecture. Biometrics 9:259–268

    Google Scholar 

  48. Sreevani K, Murthy CA (2017) Bridging feature selection and extraction compound feature generation. IEEE Trans Knowl Data Eng 29(10):757–770

    Article  Google Scholar 

  49. Kaiser L, Gomez A, Chollet F (2018) Depthwise separable convolutions for neural machine translation. In: Sixth international conference on learning representations (ICLR), vol 6539. IEEE, pp 1295–1299

  50. Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Le Cun Y (2014) Overfeat: integrated recognition, localization and detection using convolutional networks. In: Sixth international conference on learning representations (ICLR), vol 6539. IEEE, pp 1295–1299

  51. Bai L, Zhao Y, Huang X (2018) A CNN accelerator on FPGA using depthwise separable convolution. IEEE Trans Circuits Syst II Express Briefs 65(10):1415–1419

    Article  Google Scholar 

  52. Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: The IEEE conference on computer vision and pattern recognition (CVPR), vol 6539. IEEE, pp 1251–1258

  53. Gehring J, Auli M, Grangier D, Yarats D, Dauphin Y (2017) Convolutional sequence to sequence learning. In: 2009 10th international conference on document analysis and recognition, vol 70. ICML, pp 1243–1252

  54. Santos A, de Souza C, Zanchettin C, Macedo D, Oliveir A (2018) Reducing squeezenet storage size with depthwise separable convolutions. In: International joint conference on neural networks (IJCNN), vol 65. IEEE, pp 1–6

  55. Liang H, Wanfu G, Kuo Z, Ping Z, Feng W (2018) Feature selection considering two types of feature relevancy and feature interdependency. Expert Syst Appl 93(10):423–434

    Google Scholar 

  56. Xiaochuan T, Yuanshun D, Yanping X (2019) Feature selection based on feature interactions with application to text categorization. Expert Syst Appl 120(10):207–216

    Google Scholar 

  57. Vorugunti C, Guru D, Viswanath P (2019) An efficient online signature verification based on feature fusion and interval valued representation of writer dependent features. In: IEEE fifth international conference on identity, security and behavior analysis (ISBA), vol 6539. IEEE, pp 53–59

  58. Sharma A, Sundaram S (2018) On the exploration of information from the DTW cost matrix for online signature verification. IEEE Trans Cybern 48(3):129–136

    Google Scholar 

  59. Abhishek S, Suresh S (2016) An enhanced contextual DTW based system for online signature verification using vector quantization. Pattern Recognit Lett 84(6):22–28

    Google Scholar 

  60. Ruben T, Ruben V-R, Julian F, Javier O-G (2017) Biometric signature verification using recurrent neural networks. vol. 41. IEEE, pp 652–657

Download references

Funding

We are grateful to NVidia for donating NVidia Titan X 12 GB GPU card which is used to carryout the extensive experiments conducted in this work.

Author information

Authors and Affiliations

  1. Indian Institute of Information Technology, Sri City, India

    Chandra Sekhar Vorugunti & Viswanath Pulabaigari

  2. Jawaharlal Nehru University, New Delhi, India

    Prerana Mukherjee

  3. Birla Institute of Technology and Science, Pilani, India

    Avinash Gautam

Authors
  1. Chandra Sekhar Vorugunti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Viswanath Pulabaigari
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Prerana Mukherjee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Avinash Gautam
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chandra Sekhar Vorugunti.

Ethics declarations

Conflict of interest

(1) The authors have no relevant financial or non-financial interests to disclose. (2) The authors have no conflicts of interest to declare that are relevant to the content of this article. (3) All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vorugunti, C.S., Pulabaigari, V., Mukherjee, P. et al. COMPOSV: compound feature extraction and depthwise separable convolution-based online signature verification. Neural Comput & Applic 34, 10901–10928 (2022). https://doi.org/10.1007/s00521-022-07018-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07018-6

Keywords

Search

Navigation