An introduction to vision through image segmentation using graph cuts based on MRF

Abstract

This report explores image segmentation using graph cuts. The image is viewed as a MRF and a combinatorial optimization on the labels. In due process we also explore techniques that can be applied to make the problem easier, challenges faced and general representational issues. The report comes from a computer science background and builds up knowledge on prominent signal processing ideas and vision techniques.

Topics

6 Figures and Tables

Download Full PDF Version (Non-Commercial Use)