Normalized cuts and image segmentation¶
Why this mattered¶
TBD
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.
Related¶
- cite → Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images — Normalized cuts cites Gibbs-distribution image restoration as prior work connecting image segmentation to graph-based probabilistic energy formulations.
- enables → Selective Search for Object Recognition — Normalized cuts supplied graph-based image segmentation concepts that selective search adapted for hierarchical region grouping into object proposals.
- cite ← Selective Search for Object Recognition — Selective Search uses graph-based image segmentation ideas related to normalized cuts as a foundation for generating candidate object regions.
- enables ← Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images — Gibbs-distribution image restoration enables normalized cuts by importing probabilistic energy formulations for spatial coherence in image labeling.