Abstract
In this paper, we propose a novel hybrid deep learning based autoencoder-CNN-Softmax architecture aims at obtaining reduced dimension feature set from raw feature set. The reduced feature set forms an input to CNN layers to learn deep global features. These global features are used to train the SoftMax layer for online signature classification. Ability to reduce the noisy features and to discover the hidden corelated features makes the proposed architecture light weight and efficient to use in critical applications like online signature verification (OSV) and to deploy in resource constraint mobile devices. We demonstrate the superiority of our model for feature correlation learning and signature classification by conducting experiments on standard datasets MCYT, SUSIG. The experimentation confirms that the proposed model achieves better accuracy (lower error rates) with a lesser number of features compared to the current state-of-the-art models. The proposed models yield state-of-the-art performance of 0.4% EER on MCYT-100 dataset and 3.47% with SUSIG dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, K., Nyssen, E., Sahli, H.: Multi-stage online signature verification system. Pattern Anal. Appl. 5, 288–295 (2001)
Nanni, L., Lumini, A.: Advanced methods for two-class problem formulation for online signature verification. Neurocomputing. 69, 854–857 (2006)
Nanni, L.: Experimental comparison of one-class classifiers for on-line signature verification. Neuro. Comput. 69, 869–873 (2006)
Van, B.L., Garcia-Salicetti, S., Dorizzi, B.: On using the viterbi path along with HMM likelihood information for online signature verification. IEEE Trans. Syst. Man Cybern. Part B 37(5), 1237–1247 (2007)
Porwik, P., Doroz, R., Orczyk, T.: Signatures verification based on PNN classifier optimised by PSO algorithm. Pattern Recogn. 60, 998–1014 (2016)
Fierrez, J., Ortega-Garcia, J., Ramos, D., Gonzalez-Rodriguez, J.: HMM-based on-line signature verification: feature extraction and signature modeling. Pattern Recogn. Lett. 28(16), 2325–2334 (2007)
Guru, D.S., Prakash, H.N.: Online signature verification and recognition: an approach based on symbolic representation. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1059–1073 (2009)
Napa, S., Nasir, M.: Online signature verification on mobile devices. IEEE Trans. Inf. Forensics Secur. 9, 933–947 (2014)
Cpałka, K., Zalasinski, M., Rutkowski, L.: A new algorithm for identity verification based on the analysis of a handwritten dynamic signature. Appl. Soft Comput. 43, 47–56 (2016)
Sharma, A., Sundaram, S.: An enhanced contextual DTW based system for online signature verification using vector quantization. Pattern Recogn. Lett. 84, 22–28 (2016)
Manjunatha, K.S., Manjunath, S., Guru, D.S., Somashekara, M.T.: Online signature verification based on writer dependent features and classifiers. Pattern Recogn. Lett. 80, 129–136 (2016)
Guru, D.S., Manjunatha, K.S., Manjunath, S., Somashekara, M.T.: Interval valued symbolic representation of writer dependent features for online signature verification. Elsevier J. Expert Syst. Appl. 80, 232–243 (2017)
Alpar, O., Krejcar, O.: Online signature verification by spectrogram analysis. J. Appl. Intell 48, 1189–1199 (2018)
Lai, S., Jin, L., Yang, W.: Online signature verification using recurrent neural network and length-normalized path signature descriptor. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan (2017)
Cpałka, K., Zalasinski, M.: On-line signature verification using vertical signature partitioning. Expert Syst. Appl. 41, 4170–4180 (2014)
Zalasińskia, M., Cpałkaa, K.: A new method for signature verification based on selection of the most important partitions of the dynamic signature. J. Neurocomput. 289, 13–22 (2018)
Xia, X., Song, X., Luan, F., Zheng, J., Chen, Z., Ma, X.: Discriminative feature selection for on-line signature verification. Pattern Recogn. 74, 422–433 (2018)
Wang, J., He, H., Danil, V., Prokhorov, A.: Folded neural network autoencoder for dimensionality reduction. In: International Neural Network Society Winter Conference INNS-WC 2012 (2012)
Yanikoglu, B., Kholmatov, A.: Online signature verification using Fourier descriptors. EURASIP J. Adv. Signal Process. 1, 260516 (2009)
Mishra, A., Reddy, S., Mittal, A., Hema Murthy, A.: A generative model for zero shot learning using conditional variational autoencoders. In: International Conference on Pattern Recognition CVPR (2018)
David, A., Chih-Peng, C., Wen-Hsiao, P., Hsueh-Ming, H.: An auto encoder-based learned image compressor: description of challenge proposal by NCTU. In: CVPR, Salt lake, USA (2018)
Yildirim, O., San Tan, R., Rajendra Acharya, U.: An efficient compression of ECG signals using deep convolutional autoencoders. Elsevier J. Cogn. Syst. Res. 52, 198–211 (2018)
Adem, K., Kiliçarslan, S., Cömert, O.: Classification and diagnosis of cervical cancer with softmax classification with stacked autoencoder. Elsevier J. Expert Syst. Appl. 115, 557–564 (2019)
Trumble, M., Gilbert, A., Hilton, A., Collomosse, J.: Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 800–816. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_48
Anupriya, G., Angshul, M.: Discriminative autoencoder for feature extraction: application to character recognition. Neural Process. Lett. 49, 1–13 (2018)
Chen, J., Cheng Wua, Z., Zhang, J.: Driver identification based on hidden feature extraction by using adaptive non negativity-constrained auto encoder. Appl. Soft Comput. J. 74, 1–9 (2019)
Narasimhan, M.G., Kamath, S.: Dynamic video anomaly detection and localization using sparse denoising auto encoders. Multimedia Tools Appl. 77, 13173–13195 (2018)
Nath, A., Karthikeyan, S.: Enhanced prediction of recombination hotspots using input features extracted by class specific auto encoders. J. Theor. Biol. 444, 73–82 (2018)
Pathirage, C.S., Li, J., Li, L., Hao, H., Liu, W., Ni, P.: Structural damage identification based on auto encoder neural networks and deep learning. Eng. Struct. 172, 13–28 (2018)
Feng, S., Duarte, M.: Graph auto encoder-based unsupervised feature selection with broad and local data structure preservation. Elsevier J. Neuro. Comput. 000, 1–14 (2018)
Deng, Y., Sander, A., Faulstich, L., Denecke, K.: Towards automatic encoding of medical procedures using convolutional neural networks and auto encoders. Elsevier J. Artif. Intell. Med. 93, 29–42 (2019)
Ibrahim, M.S., Mori, G.: Hierarchical relational networks for group activity recognition and retrieval. In: 5th European Conference on Computer Vision (ECCV), 8–14 September 2018
Yan, Z., Zhao, Z., Jie, Q., Li, Z., Bing, L., Fanzhang, L.: Semi-supervised local multi-manifold isomap by linear embedding for feature extraction. Pattern Recogn. 76, 662–678 (2018)
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Ortega-Garcia, J.: Exploring recurrent neural networks for on-line handwritten signature biometrics. IEEE Access 6, 5128–5138 (2018)
Yuen, C.T., Lim, W.L., Tan, C.S., Goi, B.M., Wang, X., Ho, J.H., Probabilistic model for dynamic signature verification system, J. Appl. Sci. Eng. Technol. 3, 1318–1322 (2011)
Pirlo, G., Cuccovillo, V., Cabrera, M.D., Impedovo, D., Mignone, P.: Multidomain verification of dynamic signatures using local stability analysis. IEEE Trans. Hum. Mach. Syst. 45, 805–810 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Vorugunti, C.S., Pulabaigari, V. (2019). A Deep Learning Architecture Based Dimensionality Reduction and Online Signature Verification. In: Sundaram, S., Harit, G. (eds) Document Analysis and Recognition. DAR 2018. Communications in Computer and Information Science, vol 1020. Springer, Singapore. https://doi.org/10.1007/978-981-13-9361-7_10
Download citation
DOI: https://doi.org/10.1007/978-981-13-9361-7_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9360-0
Online ISBN: 978-981-13-9361-7
eBook Packages: Computer ScienceComputer Science (R0)