Issue No. 08 - August (2000 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.868688
<p><b>Abstract</b>—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 <it>normalized cut</it>, for segmenting the graph. The <it>normalized cut</it> 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 have applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging.</p>
Grouping, image segmentation, graph partitioning.
J. Shi and J. Malik, "Normalized Cuts and Image Segmentation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 22, no. , pp. 888-905, 2000.