Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.
Próximo SlideShare
Signature recognition
Signature recognition
Cargando en…3
18 de 26

Sign verification

  1. 1. Signature Verification using Grid based feature extraction Aniket Sahasrabuddhe Anurag D. Y. Patil College Of Engineering Shashank Akurdi, Pune Sushant Saurav
  2. 2. Presentation Agenda  Introduction  Existingtechniques  Proposed work  Algorithms  Mathematical model  Advantages & disadvantages  Conclusion
  3. 3. Introduction  Computers are largely used in almost each and every field.  Thesecurity measures to be used must be cheap, reliable and un-intrusive to the authorized person.
  4. 4. Importance of Signature  Transaction  Individuals less likely to object  Biometric
  5. 5. Types of signature Identification  Offline Signature Verification  deals with shape only  Online signature Verification  deals with dynamic features like speed, pen pressure, directions, stroke length, and when the pen is lifted from the paper
  6. 6. Existing systems and limitations  UsingVariable Length Segmentation and Hidden Markov Models  New extreme points warping technique  Wavelet Transform Based Global Features • Percentage of error occurrence is high • It has heavy computational load • Optimal performance not guaranteed
  7. 7. Challenging tasks  Differentiating between the parts of the signature that vary with each signing.  The signature can vary substantially over an individual’s lifetime.
  8. 8. Proposed Work  Signature Acquisition  Signature Pre-processing  Feature Extraction  Signature Verification Fig 1 System Architecture
  9. 9. Signature Acquisition  Signature is acquired from the user. Fig.2 Sample Signatures
  10. 10. Signature Pre-processing Function of the preprocessor Image resizing Image binarizing Image thinning Image normalizing
  11. 11. Feature Extraction Fig.3 Grid over pre-processed signature image Fig.4 Matrix corresponding to the above grid
  12. 12. Signature Verification Fig.5 Signature Verification
  13. 13. Applications  Banking,  Passport office,  And any other places which require identification !
  14. 14. Advantages  Low error rate.  Forgery is detected even when the forger has managed to get a copy of the authentic signature.  Fast and simple training.  Cheap hardware.  Little storage requirements.
  15. 15. Use Case Diagram
  16. 16. Class Diagram
  17. 17. Activity Diagram
  18. 18. Component Diagram
  19. 19. Sequence Diagram
  20. 20. Collaboration Diagram
  21. 21. State Diagram
  22. 22. Requirements & Technologies The hardware component we are using here is a scanning device(WEBCAM), high RAM for better results and good processor. • Operating System: Windows XP or Higher • NetBeans IDE 7.0 • SDK - J2SE • Intel core 2 duo processor • 2.1 GHZ, 1 GB RAM
  23. 23. Conclusion  The pre-processed signature i.e. resized, binarized, thinned and rotation normalized signature is segmented into grid of size 10x20 cells where each cell is having 100 pixels.  The system does not need any special hardware like tablet, fingerprint verification or iris scanning systems.  It requires only low cost webcams  The database used for the verification will not be large.
  24. 24. References  Muhammed Nauman Sajid “Vital Sign: Personal Signature based Biometric Authentication System”, Bs degree thesis, Pakistan Institute of Engineering and Applied sciences, sept 2009.  K. Yasuda, D. Muramatsu, and T. Matsumoto, “Visual-based online signature verification by pen tip tracking”, Proc. CIMCA 2008, 2008, pp. 175–180.  D.Muramatsu, M. Kondo, M. Sasaki, S. Tachibana, and T. Matsumoto. “A markov chain monte carlo algorithm for bayesian dynamic signature verification”. IEEE Transactionson Information Forensics and Security, 1(1):22–34, March,2006.  Satoshi Shirato, D. Muramatsu, and T. Matsumoto, “camera-based online signature verification: Effects of camera positions.” World Automation congress2010 TSI press.  D. Muramatsu, K. Yasuda, S. Shirato, and T. Matsumoto. “Visual-based online signature verification using features extracted from video”, Journal of Network and Computer Applications Volume 33, Issue 3, May 2010, Pages 333-341.
  25. 25. Cont.  M. E. Munich and P. Perona. “Visual identification by signature tracking.” IEEE Trans. Pattern Analysis and MachineIntelligence, 25(2):200–217, February 2003.  F.A.Afsar, M. Arif and U. Farrukh, “Wavelet Transform Based Global Features for Online Signature Recognition”, Proceeding of IEEE International Multi- topic Conference INMIC, pp. 1-6 Dec. 2005.  Charles E. Pippin, “Dynamic Signature Verification using Local and Global Features”, Georgia Institute of Technology, July 2004.  Hao Feng and Chan Choong Wah, “Online Signature Verification Using New Extreme Points Warping Technique”, Pattern Recognition Letters, vol. 24, pp. 2943-2951, Dec. 2003.  F.A. Afsar, M. Arif and U. Farrukh, “Wavelet Transform Based Global Features for Online Signature Recognition”, Proceeding of IEEE International Multi- topic Conference INMIC, pp. 1-6 Dec. 2005.
  26. 26. Thank You