Online signature recognition


Published on

  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Online signature recognition

  1. 1. TopicsDefinitionsFeature extractionSignature ForgerySignature modelsAdvantages and disadvantages of signature as biometrics
  2. 2. Signature
  3. 3. SignaturesOff-line or static signatures are scanned from paper documents, where they were written in conventional way. Off-line signature analysis can be carried out with a scanned image of the signature using a standard camera or scanner.On-line or dynamic signatures are written with an electronically instrumented device and the dynamic information (pen tip location through time) is usually available at high resolution, even when the pen is not in contact with the paper.
  4. 4. PDA
  5. 5. Signature in Identity Documents
  6. 6. Digitizing Tablet
  7. 7. Pen-Tablet System (WACOM)
  8. 8. Pen-Tablet System –How It Works? The WACOM stylus looks and feels like a pen yet contains no batteries or magnets. Instead it takes advantage of electro-magnetic resonance technology in which radio waves are sent to the stylus and returned for position analysis. In operation, a grid of wires below the screen alternates between transmit and receive modes (about every 20μs):  In transmit mode, the electro-magnetic signal stimulates oscillation in the coil-and capacitor resonant circuit in the pen  In receive mode, the energy of the resonant circuit oscillation in the pen is detected by the antenna grid. This is then analysed to determine position and other information including pressure Since the grid provides the power to the pen through resonant coupling, no batteries are required. Thus there are no consumables that will run down and need to be replaced or that would make the pen top-heavy.
  9. 9. Automatic identificationTraditional means of automatic identification:  Possession-based (credit card, smart card)  Use “something that you have”  Knowledge-based (password, PIN)  Use “something that you know”  Biometrics-based (biometric identifier)  Use something that relies on “what you are”Signature is inherently a combination of knowledge and biometric, the knowledge component (what is written and how it is written) can be chosen, and indeed changed, by the user
  10. 10. Pre-processing  Smoothing: the input signal from a digitizing pen can be very jagged. The pen used can affect the smoothness and the size of the signature.  Segmentation: determination of the beginning and ending of signing.  Signature beginning: first sample where pressure information is not null (first pen-down)  Signature ending: last pen-up. Because few pen-ups can be found in the signature, we have to establish a maximum pen-up duration (e.g. 3 s).
  11. 11. Pre-processingInitial pointalignment: all thesignatures have to bealigned with respect tothe initial point (e.g.the coordinate origin)to make informationindependent from theposition on the tablet.
  12. 12. Pre-processing
  13. 13. Principal structure of signature recognitionsystems
  14. 14. Dynamic Signature
  15. 15. Local and Global FeaturesLocal features x, y coordinates Velocity (v) Acceleration (A) Azimuth Elevation
  16. 16. Local and Global FeaturesGlobal features Signature length, height Total signature time Total pen-down time Total pen-up time Average velocity Maximum velocity Minimum velocity
  17. 17. Forgery Genuine Forgery signatures signatures
  18. 18. Signatures: authentic and skilled forgery
  19. 19. Signature Recognition AdvantagesSignature is a man-made biometric where forgery has been studied extensivelyEnrollment (training) is intuitive and fastSignature verification in general has a fast response and low storage requirementsA signature verification is “independent” of the native language userVery high compression rates do not affect shape of the signature (100-150 bytes)
  20. 20. Signature Recognition DisadvantagesThere is much precedence for using signature to authenticate documents and not for security applicationsA five-dimensional pen may be needed to arrive at the desired accuracy. This makes the hardware costly.Some people have palsies, while others do not have enough fine motor coordination to write consistently
  21. 21. ReferencesDynamic Signatures developed by NSTC subcomittee on Biometrics::Simina Emerich, Eugen Lupu, Corneliu Rusu, “On- line Signature Recognition Approach Based on Wavelets and Support Vector Machines”Jinxu Guo, Jianbin Zheng, Bo Lu, “Research of Online Signature Recognition Based on Energy Feature”