Advisor: Dr. Chris Pollett

Description:

Biometrics is the science and technology of measuring and statistically analyzing biological data. In information technology, biometrics refers to technologies for measuring and analyzing human body characteristics for various purposes including user authentication. It can help to recognize individuals based on their physiological or biological characteristics. The use of biometrics can make it possible to overcome the security threats encountered with traditional security methods like passwords which are possible to hack. Authentication by mouse movements tries to replace the traditional initial login password method. It uses mouse patterns created by the user as the identification method for that person. Movements of users are captured beforehand. The user is then asked to authenticate himself/herself by moving a mouse over few random buttons positioned on the screen. If his/her mouse movements match the already recorded mouse movement patterns, then the user is allowed to proceed. The authentication is based on Hidden Markov Models(HMM). If during our research we find that the mouse movements are not unique then the Hidden Markov Models will be used to do a project on video game (Artificial Intelligence). I will write a game like Pac-Man. HMM will be used to learn common patterns a person uses to evade the ghosts in the game.

Schedule:

Deliverables:

The full project will be done when CS298 is completed. The following will be done by the end of CS297:

1. Write a program which records the movements of mouse. Draw a graph between distance covered and time taken to calculate the velocity of mouse.

2. Run a program in background that tracks the mouse movements. Draw a graph which shows the coordinates of the positions where the mouse moves.

3. Isolate regions on the graph where mouse hovers the most.

4. Follow trigram approach to recognise the pattern of mouse clicks.

5. CS297 Final Report.

References:

[CE93] Statistical Language Learning. Eugene Charniak. MIT. 1993.

[PI02] Circuit complexity and Neural Networks. Ian Parberry. MIT 1994

[RA03] Java-Based Internet Biometric Authentication System. Ross A.J & Peter W. McOwan. IEEE Transactions on Pattern and Machine Intelligence. Vol 25(9).Page 1166-1172. 2003.

[HR02] Movement Awareness for Ubiquitous Game Control. Robert Headon & Rupert Curwen. Personal and Ubiquitious Computing. Springer-Verlag. Vol 6. Page 407-415. 2002.

[RS02] Artificial Intelligence.Stuart J.Russell , Peter Norvig. Prentice Hall. 2002