Local Features for Forensic Signature Verification

  • Muhammad Imran Malik
  • Marcus Liwicki
  • Andreas Dengel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8158)


In this paper we present a novel comparison among three local features based offline systems for forensic signature verification. Forensic signature verification involves various signing behaviors, e.g., disguised signatures, which are generally not considered by Pattern Recognition (PR) researchers. The first system is based on nine local features with Gaussian Mixture Models (GMMs) classification. The second system utilizes a combination of scale-invariant Speeded Up Robust Features (SURF) and Fast Retina Keypoints (FREAK). The third system is based on a combination of Features from Accelerated Segment Test (FAST) and FREAK. All of these systems are evaluated on the dataset of the 4NSigComp2010 signature verification competition which is the first publicly available dataset containing disguised signatures. Results indicate that our local features based systems outperform all the participants of the said competition both in terms of time and equal error rate.


Signature verification disguised signatures forensic handwriting examination local features GMM SURF FAST FREAK 


  1. 1.
    Plamondon, R., Lorette, G.: Automatic signature verification and writer identification – the state of the art. Pattern Recognition 22, 107–131 (1989)CrossRefGoogle Scholar
  2. 2.
    Plamondon, R., Srihari, S.N.: On-line and off-line handwriting recognition: A comprehensive survey. IEEE TPAMI 22, 63–84 (2000)CrossRefGoogle Scholar
  3. 3.
    Impedovo, D., Pirlo, G.: Automatic Signature Verification: The State of the Art. IEEE Trans. on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 38, 609–635 (2008)CrossRefGoogle Scholar
  4. 4.
    Liwicki, M., van den Heuvel, C.E., Found, B., Malik, M.I.: Forensic signature verification competition 4NSigComp2010 - detection of simulated and disguised signatures. In: ICFHR 2010, pp. 715–720 (2010)Google Scholar
  5. 5.
    Malik, M.I., Liwicki, M., Dengel, A.: Evaluation of local and global features for offline signature verification. In: 1st Int. Workshop on Automated Forensic Handwriting Analysis (AFHA), pp. 26–30 (2011)Google Scholar
  6. 6.
    De Stefano, C., Marcelli, A., Rendina, M.: Disguising writers identification: an experimental study. In: IGS 2009, pp. 99–102 (2009)Google Scholar
  7. 7.
    Fiel, S., Sablatnig, R.: Writer Retrieval and Writer Identification Using Local Features. In: DAS 2012, pp. 145–149 (2012)Google Scholar
  8. 8.
    Zhiyi, Z., Lianwen, J., Kai, D., Xue, G.: Character-SIFT: A Novel Feature for Offline Handwritten Chinese Character Recognition. In: ICDAR, pp. 763–767 (2009)Google Scholar
  9. 9.
    Jin, Z., Qi, K.-Y., Chen, K.: SSIFT: An Improved SIFT Descriptor for Chinese Character Recognition in Complex Images. In: CNMT, pp. 1–5 (2009)Google Scholar
  10. 10.
    Song, W., Uchida, S., Liwicki, M.: Comparative Study of Part-Based Handwritten Character Recognition Methods. In: ICDAR 2011, pp. 814–818 (2011)Google Scholar
  11. 11.
    Ta, D.-N., Chen, W.-C., Gelfand, N., Pulli, K.: SURFTrac: Efficient tracking and continuous object recognition using local feature descriptors. In: IEEE C. S. Conf. on Computer Vision and Pattern Recognition, pp. 2937–2944 (2009)Google Scholar
  12. 12.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-Up Robust Features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  13. 13.
    Jeong, K., Moon, H.: Object Detection Using FAST Corner Detector Based on Smartphone Platforms. In: First Int. Conf. on Computers, Networks, Systems and Industrial Engineering (CNSI), pp. 111–115 (2011)Google Scholar
  14. 14.
    Bilinski, P., Bremond, F., Kaaniche, M.B.: Multiple object tracking with occlusions using HOG descriptors and multi resolution images. In: ICDP 2009, pp. 1–6 (2009)Google Scholar
  15. 15.
    Diem, M., Sablatnig, R.: Recognition of Degraded Handwritten Characters Using Local Features. In: ICDAR 2009, pp. 221–225 (2009)Google Scholar
  16. 16.
    Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: 10th Int. Conf. on Computer Vision, pp. 1508–1515 (2005)Google Scholar
  17. 17.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: 7th Int. Conf. on Computer Vision, pp. 1150–1157 (1999)Google Scholar
  18. 18.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: 4th Alvey Vision Conf., pp. 147–151 (1988)Google Scholar
  19. 19.
    Alahi, A., Ortiz, R., Vandergheynst, P.: FREAK: Fast Retina Keypoint. In: CVPR 2012, pp. 510–517 (2012)Google Scholar
  20. 20.
    Otsu, N.: A threshold selection method from gray-level histograms. Automatica 111, 285–296 (1975)Google Scholar
  21. 21.
    Marti, U.-V., Bunke, H.: Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. IJPRAI 110(15), 65–90 (2001)Google Scholar
  22. 22.
    Marithoz, J., Bengio, S.: A comparative study of adaptation methods for speaker verification. In: Int. Conf. on Spoken Language Processing, pp. 581–584 (2002)Google Scholar
  23. 23.
    Liwicki, M.: Evaluation of Novel Features and Different Models for Online Signature Verification in a Real-World Scenario. In: 14th Conf. of Int. Graphonomics Society, pp. 22–25 (2009)Google Scholar
  24. 24.
    Schlapbach, A., Liwicki, M., Bunke, H.: A Writer Identification System for On-line Whiteboard Data. PR 41(7), 2381–2397 (2008)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Muhammad Imran Malik
    • 1
  • Marcus Liwicki
    • 1
    • 2
  • Andreas Dengel
    • 1
  1. 1.German Research Center for Artificial Intelligence (DFKI GmbH) KaiserslauternGermany
  2. 2.University of FribourgSwitzerland

Personalised recommendations