Learning for Facial Analysis: Issues of real-time performance and prior models
Speaker: Vinay Kumar , Center for Biological and Computational Learning & Department of Brain and Cognitive Sciences, MIT
Date: November 21 2000
Analysis of faces is an important vision problem that can be used to develop enabling technology for intelligent man-machine interfaces. We investigate a learning-based approach to facial analysis. We raise two critical issues in this approach:
1. Real Time performance: We describe a trainable system capable of tracking faces and facial features like eyes and nostrils and estimating basic mouth features such as degrees of openness and smile in real time. In developing this system, we have addressed the twin issues of image representation and algorithms for learning. We have used the invariance properties of image representations based on Haar wavelets to robustly capture various facial features. Similarly, unlike previous approaches this system is entirely trained using examples and does not rely on a priori (hand-crafted) models of facial features.
2. Prior Models of Faces: Prior models may be important for designing facial analysis systems to exploit constraints in facial appearances. We describe a method for estimating the parameters of a linear morphable model (LMM) that models mouth images. The method uses a learning-based approach to estimate the LMM parameters directly from the images of the object class (in this case mouths). Thus this method can be used to bypass current computationally intensive methods that use analysis by synthesis, for matching objects to morphable models. The estimation of LMM parameters could possibly have application to other problems in vision. We investigate one such application, namely viseme recognition.
See other events that are part of Brains & Machines Seminar Series Fall 2000
See other events happening in November 2000