Fast Constraint Propagation for Image Segmentation

TL;DR

This paper introduces a fast, selective constraint propagation method for image segmentation that leverages local image properties and graph-based learning to efficiently propagate constraints and improve segmentation quality.

Contribution

It proposes a novel selective constraint propagation approach that reduces computational complexity and enhances segmentation performance using $L_1$-minimization and graph-based algorithms.

Findings

Efficient constraint propagation speeds up image segmentation.

Selective propagation maintains segmentation quality while reducing computation.

Experimental results show improved segmentation accuracy with the proposed method.

Abstract

This paper presents a novel selective constraint propagation method for constrained image segmentation. In the literature, many pairwise constraint propagation methods have been developed to exploit pairwise constraints for cluster analysis. However, since most of these methods have a polynomial time complexity, they are not much suitable for segmentation of images even with a moderate size, which is actually equivalent to cluster analysis with a large data size. Considering the local homogeneousness of a natural image, we choose to perform pairwise constraint propagation only over a selected subset of pixels, but not over the whole image. Such a selective constraint propagation problem is then solved by an efficient graph-based learning algorithm. To further speed up our selective constraint propagation, we also discard those less important propagated constraints during graph-based learning. Finally, the selectively propagated constraints are exploited based on $L_1$-minimization for normalized cuts over the whole image. The experimental results demonstrate the promising performance of the proposed method for segmentation with selectively propagated constraints.