Face recognition is a challenging vision problem, given the infinitely many variations possible in face images. My project will involve extensive computational experimentation with several deep networks on large databases of face images transformed along a variety of dimensions, as defined in the paper Proceedings of the IEEE. The networks will be trained on augmented and unaugmented face databases, and we will try to determine the kind of training set augmentation that yields the best test performance. We may also undertake studies of human performance if existing data are judged to be inadequate for a fair comparison between machine and human observers. The project will, therefore, span the domains of human and machine perception and yield results that enhance our understanding of both.

I am interested in big data and machine learning, so I am excited to work with both in the context of human perception through this SuperUROP. I am excited about the idea of incorporating studies from other fields and intertwining it with computer science as we can always learn more when we broaden our scope. I hope to come out with a deeper understanding of human perception as well as neural networks.