As they allow natural interactions between man and machine without the use of the keyboard, speech and handwriting are increasingly gaining acceptance as input to computer devices. Although speech is better suited for bulk data entry, handwriting is an attractive input medium in noisy acoustic environments, when a quiet operation is desired, or where privacy is a primary concern. Examples of applications where handwriting is the prefered input channel include form filing, personal note taking, document editing, record keeping, and meeting support. To address such application, computer interfaces must include the capability of automatically recognizing natural handwriting.
The scope of this project will focus in one very interesting potential application, tele-banking systems with automatic signature verification. The handwriting data recorded with a electronic tablet or digitizer will be sent to a recognizer that will check the similarity of the customer's signature with the one stored in a central database.
- Hardware: Wacom Tablet Digitizer, Pentium
- Software: Matlab, C, C++
- R. Plamondon and G. Lorette, "Automatic signature verificationand
writer identification, the state of the art", Pattern Recognition, Vol
22, No 2, 1989.
- {L. Yang and B.K. Widjaja and R. Prasad, "Application of Hidden
Markov Models for signature verification", Pattern Recognition, Vol
28, No 2, 1995.
- L. R. Rabiner, "A tutorial on Hidden Markov Models and selected
applications in Speech Recognition, Proceedings of the IEEE, Vol 77,
No 2, 1989.
Back to the home page for CNS/EE248