Skip to main content
SpringerLink
Log in

A deep feature warehouse and iterative MRMR based handwritten signature verification method

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Offline handwritten signature verification has been widely used for document forensics and biometrics, and it is a popular issue. Deep learning models have commonly been used to solve this problem. This research has two aims, and they are to present a high accuracy hybrid classification model for forensics and to collect and share a new handwritten signature dataset to contribute document forensics. In this paper, a novel deep signature verification model is presented. This method has three fundamental phases and they are deep feature generation using transfer learning, iterative minimum redundancy maximum relevance (IMRMR) feature selection, and classification phases. In the deep feature extraction phase, 13 pre-trained widely preferred convolutional neural networks (CNN) are selected. These are utilized as feature generators and 1000 features are extracted from each network. By merging the generated features, a feature vector with a length of 13,000 is created. This feature generation network is named Deep Feature Warehouse (DFW) since it uses 13 pre-trained deep feature extractors in the transfer learning model. The most valuable features of the DFW are selected by the proposed IMRMR method and the selected features are forwarded to the classifier. To test the proposed DFW and IMRMR based verification method, we collected a handwritten signature dataset and CEDAR dataset to obtain comparative results. The proposed DFW and ImRMR based document classification method reached 97.16 % classification accuracy on the collected dataset and 100 % accuracy on the CEDAR dataset. We have used two datasets to demonstrate the general classification ability of our proposal. The calculated results and findings obviously demonstrate the effectiveness of the proposed DFW and ImRMR image verification model. According to the results, our model has general success (it has developed on two datasets), and it is a lightweight machine learning model since it uses transfer learning for feature extraction.

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

Similar content being viewed by others

References

  1. Abikoye O, Mabayoje M, Ajibade R (2011) Offline signature recognition & verification using neural network. Int J Comput Appl 35(2):44–51

    Google Scholar 

  2. Agam G, Suresh S (2007) Warping-based offline signature recognition. IEEE Trans Inf Forensics Secur 2(3):430–437

    Article  Google Scholar 

  3. Bouguettaya A, Kechida A, Taberkit AM (2019) A survey on lightweight CNN-based object detection algorithms for platforms with limited computational resources. Int J Inform Appl Math 2(2):28–44

    Google Scholar 

  4. Calik N, Kurban OC, Yilmaz AR, Yildirim T, Ata LD (2019) Large-scale offline signature recognition via deep neural networks and feature embedding. Neurocomputing 359:1–14

    Article  Google Scholar 

  5. Daramola SA, Ibiyemi TS (2010) Offline signature recognition using hidden markov model (HMM). Int J Comput Appl 10(2):17–22

    Google Scholar 

  6. Dey S, Dutta A, Toledo JI, Ghosh SK, Lladós J, Pal U (2017) Signet: Convolutional siamese network for writer independent offline signature verification. arXiv preprint arXiv:170702131

  7. Diaz M, Ferrer MA, Eskander GS, Sabourin R (2016) Generation of duplicated off-line signature images for verification systems. IEEE Trans Pattern Anal 39(5):951–964

    Article  Google Scholar 

  8. Diaz M, Fischer A, Ferrer MA, Plamondon R (2016) Dynamic signature verification system based on one real signature. IEEE Trans Cybern 48(1):228–239

    Article  Google Scholar 

  9. Ding C, Peng H (2005) Minimum redundancy feature selection from microarray gene expression data. J Bioinf Comput Biol 3(02):185–205

    Article  Google Scholar 

  10. Erkmen B, Kahraman N, Vural RA, Yildirim T (2010) Conic section function neural network circuitry for offline signature recognition. IEEE Trans Neural Netw 21(4):667–672

    Article  Google Scholar 

  11. Eskander GS, Sabourin R, Granger E (2013) Hybrid writer-independent–writer-dependent offline signature verification system. IET Biom 2(4):169–181

    Article  Google Scholar 

  12. Ferrer MA, Vargas JF, Morales A, Ordonez A (2012) Robustness of offline signature verification based on gray level features. IEEE Trans Inf Forensics Secur 7(3):966–977

    Article  Google Scholar 

  13. Ferrer MA, Diaz-Cabrera M, Morales A (2014) Static signature synthesis: A neuromotor inspired approach for biometrics. IEEE Trans Pattern Anal 37(3):667–680

    Article  Google Scholar 

  14. Frias-Martinez E, Sanchez A, Velez J (2006) Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition. Eng Appl Artif Intel 19(6):693–704

    Article  Google Scholar 

  15. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc Cvpr IEEE, pp 770–778

  16. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proc Cvpr IEEE, pp 7132–7141

  17. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc Cvpr IEEE, pp 4700–4708

  18. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:160207360

  19. Ismail M, Gad S (2000) Off-line Arabic signature recognition and verification. Pattern Recogn 33(10):1727–1740

    Article  Google Scholar 

  20. Jain AK, Ross A, Prabhakar S (2004) An introduction to biometric recognition. IEEE T Circ Syst Vid 14(1):4–20

    Article  Google Scholar 

  21. Karouni A, Daya B, Bahlak S (2011) Offline signature recognition using neural networks approach. Procedia Comput Sci 3:155–161

    Article  Google Scholar 

  22. Khoshdeli M, Cong R, Parvin B (2017) Detection of nuclei in H&E stained sections using convolutional neural networks. In: IEEE EMBS International Conference on Biomedical & Health Informatics (BHI). IEEE, New York, pp 105-108

  23. Kim Y (2014) Convolutional neural networks for sentence classification. arXiv preprint arXiv:14085882

  24. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Adv Neur In, pp 1097–1105

  25. LeCun Y, Jackel L, Bottou L, Brunot A, Cortes C, Denker J, Drucker H, Guyon I, Muller U, Sackinger E (1995) Comparison of learning algorithms for handwritten digit recognition. In: International conference on artificial neural networks, Perth, Australia, pp 53-60

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

    Article  Google Scholar 

  27. Ortega-Garcia J, Fierrez-Aguilar J, Simon D, Gonzalez J, Faundez-Zanuy M, Espinosa V, Satue A, Hernaez I, Igarza J-J, Vivaracho C (2003) MCYT baseline corpus: a bimodal biometric database. IEE Proc Vis Image Signal Process 150(6):395–401

    Article  Google Scholar 

  28. Özyurt F (2020) A fused CNN model for WBC detection with MRMR feature selection and extreme learning machine. Soft Computing 24(11):8163–8172

    Article  Google Scholar 

  29. Özyurt F (2020) Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures. The Journal of Supercomputing 76(11):8413–8431

    Article  Google Scholar 

  30. Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks. In: European conference on computer vision, Springer, Berlin, pp 525-542

  31. Ruiz V, Linares I, Sanchez A, Velez JF (2020) Off-line handwritten signature verification using compositional synthetic generation of signatures and Siamese Neural Networks. Neurocomputing 374:30–41

    Article  Google Scholar 

  32. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proc Cvpr IEEE, pp 4510–4520

  33. Şenol C, Yıldırım T (2005) Signature verification using conic section function neural network. In: International Symposium on Computer and Information Sciences, Springer, Berlin, pp 524-532

  34. Sheng W, Chen S, Xiao G, Mao J, Zheng Y (2015) A biometric key generation method based on semisupervised data clustering. IEEE Trans Syst Man Cy-S 45(9):1205–1217

    Article  Google Scholar 

  35. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556

  36. Srihari SN, Xu A, Kalera MK (2004) Learning strategies and classification methods for off-line signature verification. In: Ninth International Workshop on Frontiers in Handwriting Recognition, Kokubunji, Japan, IEEE, pp 161-166

  37. Suryani D, Irwansyah E, Chindra R (2017) Offline signature recognition and verification system using efficient fuzzy kohonen clustering network (EFKCN) algorithm. Procedia Comput Sci 116:621–628

    Article  Google Scholar 

  38. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proc Cvpr IEEE, pp1–9

  39. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proc Cvpr IEEE, pp 2818–2826

  40. Tolosana R, Vera-Rodriguez R, Ortega-Garcia J, Fierrez J (2015) Preprocessing and feature selection for improved sensor interoperability in online biometric signature verification. IEEE Access 3:478–489

    Article  Google Scholar 

  41. Vivaracho-Pascual C, Simon-Hurtado A, Manso-Martinez E, Pascual-Gaspar JM (2016) Client threshold prediction in biometric signature recognition by means of Multiple Linear Regression and its use for score normalization. Pattern Recogn 55:1–13

    Article  Google Scholar 

  42. Vivaracho-Pascual C, Simon-Hurtado A, Manso-Martinez E (2017) Using the score ratio with distance-based classifiers: A theoretical and practical study in biometric signature recognition. Neurocomputing 248:57–66

    Article  Google Scholar 

  43. Xia X, Xu C, Nan B (2017) Inception-v3 for flower classification. In: 2017 2nd International Conference on Image, Vision and Computing (ICIVC), IEEE, New York, pp 783-787

  44. Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proc Cvpr IEEE, pp 6848–6856

  45. Zhao, H. H., & Liu, H. (2020). Multiple classifiers fusion and CNN feature extraction for handwritten digits recognition. Granular Computing, 5(3), 411-418.

Download references

Author information

Authors and Affiliations

  1. Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey

    Turker Tuncer & Sengul Dogan

  2. Department of Management Information, College of Management, Sakarya University, Sakarya, Turkey

    Emrah Aydemir

  3. Department of Software Engineering, College of Engineering, Firat University, Elazig, Turkey

    Fatih Ozyurt

Authors
  1. Turker Tuncer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Emrah Aydemir
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fatih Ozyurt
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sengul Dogan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Turker Tuncer.

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

Tuncer, T., Aydemir, E., Ozyurt, F. et al. A deep feature warehouse and iterative MRMR based handwritten signature verification method. Multimed Tools Appl 81, 3899–3913 (2022). https://doi.org/10.1007/s11042-021-11726-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11726-x

Keywords

Search

Navigation