A Literature Review of Image Segmentation Techniques and Matting for the Purpose of Implementing “Grab-Cut”

This literature review attempts to provide a brief overview of some of the most common segmentation techniques, and a comparison between them. It discusses the “Grab-Cut” technique, and reviews some some of the common matting techniques. The graph cut approaches to segmentation can be extended to 3-D data and can be used for segmenting 3-D volumes. Other segmentation techniques use either contour or edge segmentation to perform segmentation. The graph cut techniques use both contour and edge information. The main matting techniques are Poisson matting and probabilistic alpha matting using colour statistics. Poisson matting works directly on the alpha matte of the image, and is interactive. The statistical approach uses Gaussians to model colour statistics in the image and is not interactive.