BREAKING NEWS
Cloud Server Hosting For Online Businesses
Inexpensive SEO Services
Benefits of Wanting to play Free Online Slot machines
Handwritten biometric recognition

Summary

Handwritten biometric recognition is the process of identifying the author of a given text from the handwriting style. Handwritten biometric recognition belongs to behavioural biometric systems because it is based on something that the user has learned to do.

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.

Static and dynamic recognition edit

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 for handwriting movement analysis usually consists of the following information:

  • spatial coordinate x(t)
  • spatial coordinate y(t)
  • pressure p(t)
  • azimuth az(t)
  • inclination in(t)

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

Difference from OCR edit

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 its author.

References edit

  1. ^ Chapran, J. (2006). "Biometric Writer Identification: Feature Analysis and Classification". International Journal of Pattern Recognition & Artificial Intelligence. 20 (4): 483–503. doi:10.1142/S0218001406004831.
  2. ^ Schomaker, L. (2007). "Advances in Writer Identification and Verification". Ninth International Conference on Document Analysis and Recognition. ICDAR: 1268–1273. Archived from the original on 2021-01-28. Retrieved 2020-10-12.
  3. ^ Said, H. E. S.; TN Tan; KD Baker (2000). "Personal identification based on handwriting". Pattern Recognition. 33 (2000): 149–160. Bibcode:2000PatRe..33..149S. CiteSeerX 10.1.1.408.9131. 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. Bibcode:2008PatRe..41.2381S. 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. Bibcode:2012PatRe..45..128S. doi:10.1016/j.patcog.2011.06.002.