Bayesian Optimization for Image Segmentation, Texture Flow Estimation and Image Deblurring

Abstract

This thesis addresses three important problems within computer vision: image segmentation, texture flow estimation, and image/video deblurring. While these three topics differ significantly in the underlying parametric models used to formulate the problems, the uniting theme throughout this thesis is the use of a Bayesian optimization framework to solve each specific problem. In particular, we show how each of these problems can be formulated into one of a maximum a posterior (MAP) estimation, where the likelihood and prior probabilities are uniquely defined for each problem. To solve these non-convex optimizations, an alternating optimization algorithm that iteratively solves for model parameters is used. Our experimental results show that this Bayesian approach provides excellent performance that is either on par or superior to the current state-of-the-art for each topicsb respective area. This thesis is organized to begin with an overview on Bayesian formulation of parameter estimation, followed by self-contained chapters for the problems of image segmentation, texture flow estimation, and image/video deblurring. A summary chapter is included to categorically summarize our contributions and discuss future work.