Normalized cuts and image segmentation

TLDR

The authors propose a novel global criterion, the normalized cut, to solve the perceptual grouping problem by treating image segmentation as a graph partitioning task that captures the overall impression of an image. The normalized cut criterion balances inter‑group dissimilarity and intra‑group similarity, and can be efficiently optimized using a generalized eigenvalue problem. Applying this method to static images and motion sequences yielded encouraging segmentation results.

Abstract

We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph partitioning problem and propose a novel global criterion, the normalized cut, for segmenting the graph. The normalized cut criterion measures both the total dissimilarity between the different groups as well as the total similarity within the groups. We show that an efficient computational technique based on a generalized eigenvalue problem can be used to optimize this criterion. We applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging.