People can recognize many faces with high accuracy. We would like to automate this task, but unfortunately computers do a very bad job in the recognition task. We propose to use an existing approach by Serre et al. (2004) and apply it to the task of face recognition. The assignment includes the selection of a face database, implementation of the algorithm, and experimentation and evaluation of the tests.
References:
Thomas Serre, Lior Wolf and Tomaso Poggio (2004), "A new biologically motivated framework for robust object recognition", CBCL Paper #243/AI Memo #2004-026, Massachusetts Institute of Technology, Cambridge, MA, 2004. |
