Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques

Abstract

This thesis is to investigate effective approaches to tackle different problems in computer vision: variational methods are first studied for image processing, illusory contour reconstruction and segmentation as well as their efficiency improvement. Next, we develop variational segmentation methods by stochastic programming, tackling diverse problems with random noises. Third, the fusion approaches integrating varaitional models and deep neural networks are explored for challenging image tasks. These innovative ideas are validated by significant performance gains.