Handwritten biometric recognition

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Handwritten biometric recognition should not be confused with Optical character recognition (OCR). While the goal of handwritten biometrics is to identify the author of a given text, the goal of an OCR is to recognize the content of the text, regardless of his author. Handwritten biometric recognition belongs to behavioural biometric systems because it is based on something that the user has learnt to do.

Handwritten biometrics can be split into two main categories:

Static: In this mode, users writes on paper, digitize it through an optical scanner or a camera, and the biometric system recognizes the text analyzing its shape. This group is also known as “off-line”.

Dynamic: In this mode, users writes in a digitizing tablet, which acquires the text in real time. Another possibility is the acquisition by means of stylus-operated PDAs. Dynamic recognition is also known as “on-line”.Dynamic information usually consists of the following information:

  • spatial coordinate x(t)
  • spatial coordinate y(t)
  • pressure p(t)
  • azimuth az(t)
  • inclination in(t)
Example of handwritting of a sequence of digits. Its dynamic information is shown on the right. It is interesting to enphasize that movements in the air are also acquired by the digitizing tablet. These movements can be identified because pressure is equal to zero.
Example of dynamic information of handwritting.

Better accuracies are achieved by means of dynamic systems. Some technological approaches exist.[1][2][3][4][5]

References[edit]

  1. ^ Chapran, J. (2006). "Biometric Writer Identification: Feature Analysis and Classification". International Journal of Pattern Recognition & Artificial Intelligence: 483–503. 
  2. ^ Schomaker, L. (2007). "Advances in Writer Identification and Verification". Ninth International Conference on Document Analysis and Recognition. ICDAR: 1268–1273. 
  3. ^ Said, H. E. S.; TN Tan; KD Baker. "Personal identification based on handwriting". Pattern Recognition 33 (2000): 149–160. doi:10.1016/S0031-3203(99)00006-0. 
  4. ^ Schlapbach, A.; M Liwicki; H Bunke (2008). "A writer identification system for on-line whiteboard data". Pattern recognition 41 (7): 2381–2397. doi:10.1016/j.patcog.2008.01.006. 
  5. ^ Sesa-Nogueras, Enric; Marcos Faundez-Zanuy (2012). "Biometric recognition using online uppercase handwritten text". Pattern recognition 45 (1): 128–144. doi:10.1016/j.patcog.2011.06.002.