Performance Improvement of Fake Discrimination using Time Information in CNN-based Signature Recognition

CNN 기반 서명인식에서 시간정보를 이용한 위조판별 성능 향상

  • Received : 2017.12.20
  • Accepted : 2018.01.29
  • Published : 2018.01.31


In this paper, we propose a method for more accurate fake discrimination using time information in CNN-based signature recognition. To easily use the time information and not to be influenced by the speed of signature writing, we acquire the signature as a movie and divide the total time of the signature into equal numbers of equally spaced intervals to obtain each image and synthesize them to create signature data. In order to compare the method using the proposed signature image and the method using only the last signature image, various signature recognition methods based on CNN have been experimented in this paper. As a result of experiment with 25 signature data, we found that the method using time information improves performance in fake discrimination compared to the existing method at all experiments.


CNN;Signature Recognition;Fake Discrimination


  1. Sang Hwan. Park, Seok Lae. Lee, and Chu Hwan. Park, "A Study on the Application Method of Digital Signature to International e-Trade over the Internet," The Journal of Society for e-Business Studies, Vol. 9, No. 3, pp. 227-241, 2004.
  2. Jae-Hun Song and In-Seok Kim, "A Study on the Utilization of Biometric Authentication for Digital Signature in Electronic Financial Transactions: Technological and Legal Aspect," The Journal of Society for e-Business Studies, Vol. 21, no. 4, pp. 41-53, 2016.
  3. Hyunjung Nam, Jaehyun Park, and Euiyoung Cha, "On-Line Signature Verification Using Velocity Vector Feature and Comparing Angles," Journal korea Multimedia society, pp. 549-552, 2007.
  4. Sang-Yeun Ryu, Dae-Jong Lee, Seok-Jong Lee, and Myung-Geun Chun, "On-line signature verification method using local partition matching," Proceedings KFIS Fall Conference, 2003.
  5. Kalera, Meenakshi K., Sargur Srihari, and Aihua Xu, "Offline signature verification and identification using distance statistics," International Journal of Pattern Recognition and Artificial Intelligence, Vol. 18, no. 07, pp. 1339-1360, 2004.
  6. Yong-Hyun Cho. "An Efficient Signature Recognition Based on Histogram Using Statistical Characteristic," JKIIS, Vol. 10, no. 5391, pp. 701, 2010.
  7. Ferr, Miguel A et al, "Robustness of offline signature verifciation based on gray level features," IEEE Transactions on Information Forensics and Security, Vol. 7, No. 3, pp. 966-977, 2012.
  8. Pandey, Ms Vibha, and S. Shantaiya, "Signature verification using morphological features based on artificial neural network," International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, no. 7, 2012.
  9. Sae-Bae Napa and Nasir Memon, "Online signature verification on mobile devices," IEEE Transactions on Information Forensics and Security, Vol. 9, no. 6, pp. 933-947, 2014.
  10. Seung-je Park, Seung-jun Hwang, Jong-pil Na, and Joong-hwan Baek. "On-line Signature Recognition Using Statistical Feature Based Artificial Neural Network," J. Korea Inst. Inf. Commun. Eng.. Vol. 19, no. 1, 106-112 2015.
  11. Beatrice Drott and Thomas Hassan-Reza, "On-line Handwritten Signature Verification using Machine Learning Techniques with a Deep Learning Approach," LTH Master Thesis at the Centre for Mathematical Sciences, 2015.
  12. Seng-soo Nam, Chang-ho Seo, and Dae-seon Choi, "Mobile Finger Signature Verification Robust to Skilled Forgery," Journal of The Korea Institute of Information Security & Cryptology, Vol. 26, no. 5, 2016.
  13. Luiz G. Hafemanna and Robert Sabourina, "Writer-independent Feature Learning for Offine signature Verification using Deep Convolutional Neural Networks," Neural Networks, pp. 2576-2583, 2016.
  14. Luiz G. Hafemanna, Robert Sabourina, and Luiz S. Oliveirab "Learning Features for Offline Handwritten Signature Verification using Deep Convolutional Neural Networks," Pattern Recognition, Vol 16, no. 70, pp. 163-176, 2017.
  15. Rosso, Osvaldo A., Raydonal Ospina, and Alejandro C. Frery, "Classification and verification of handwritten signatures with time causal information theory quantifiers," PIoS one, Vol. 11,no. 12, pp. e0166868, 2016.
  16. Chatterjee Atanu, Mandal S., Rahaman G. A, and Arif, A. S. M, "Fingerprint identification and verification system by minutiae extraction using artificatial neural network," JCIT, Vol. 1, no. 1, pp. 12-16, 2016.
  17. S. Hochreiter and J. Schmidhuber, "Long Short-term Memory," Neural Computation, vol. 9, no.8, pp. 1735-1780, 1997.
  18. Donghyun Lee, Minkyu Lim, Hosung Park and Ji-Hwan Kim, "LSTM RNN-based Korean Speech Recognition System Using CTC," Journal of Digital Contents Society, Vol. 18, no. 1, pp. 93-99, 2017.
  19. B. Shi, X. Bai, and C. Yao, "An end-to-end trainable neural network for image-based sequence recognition and to scene text recognition," arXiv preprint arXiv: 1507.05717, 2015.


Supported by : 한성대학교