Team

• Akshay Uttamani, auttamani@cs.wisc.edu
• Ankit Aggarwal, ankit@cs.wisc.edu
• Vaibhav Patel, vaibhav@cs.wisc.edu

Project Details:

Abstract

The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. In this paper, we re-implement the two famous interactive image segmentation methods - GrabCut and Lazy snapping. GrabCut is an approach based on optimization by graph-cut which combines both types of information i.e. color. It is an iterative version of the optimization that is used to simplify substantially the user interaction needed for a given quality. Lazy Snapping, is another interactive image cutout tool that separates coarse and fine scale processing, making object specification and detailed adjustment easy. Moreover, it provides instant visual feedback, snapping the cutout contour to the true object boundary efficiently despite the presence of ambiguous or low contrast edges. Also, some improvements are suggested to these algorithms and results are compared and explained at the end.
• Report [pdf_file ]
• Codes [folder ]