Date & Time: Wednesday, August 18, 2010, 15:45-16:30
Venue: Ramanujan Hall
Title: How linear algebra can reveal the secrets in your face … no more lying about your age!
Speaker:Kate Smith-Miles
Biography: Kate Smith-Miles is a Professor and Head of the School of Mathematical Sciences at Monash University, Australia. She has held Chairs in three disciplines - Mathematical Sciences, Information Technology, and Engineering – and is involved in many cross-disciplinary research projects. Kate obtained a B.Sc.(Hons) in Mathematics and a Ph.D. in Electrical Engineering, both from the University of Melbourne, Australia. She has published 2 books on neural networks and data mining applications, and over 200 refereed journal and international conference papers in the areas of neural networks, combinatorial optimization, intelligent systems and data mining. She is on the editorial board of several international journals including the prestigious IEEE Transactions on Neural Networks, and has been involved in organizing numerous international conferences in the areas of data mining, neural networks, and optimization. She is a frequent reviewer of international research activities including grant applications in Canada, U.K., Finland, Hong Kong, Singapore and Australia, refereeing for international research journals, and PhD examinations. From 2007-2008 she was Chair of the IEEE Technical Committee on Data Mining (IEEE Computational Intelligence Society). In addition to her academic activities, she also regularly acts as a consultant to industry in the areas of optimisation, data mining, and intelligent systems.
Abstract:The mathematical modelling of the human face enables automated (machine) understanding of a person’s identity, mood, gender, and more recently, age. The applications of such an age estimation model include age specific human-computer interaction, as well as security applications such as passport control. In this seminar we use subspace projection methods to build representative subspaces of the aging process, with the minimum reconstruction error used to estimate the age of a previously unseen face. Experimental results show that the performance of our linear algebra method is more accurate compared to the previous data mining approaches, and provides age estimates that are even more accurate that human observes have achieved on this challenging task.