Image Segmentation using Sparse Subset Selection

TL;DR

This paper introduces a novel image segmentation approach using sparse subset selection that automatically determines the number of segments and efficiently groups superpixels, achieving high-quality results.

Contribution

The paper proposes a convex model and ADMM-based algorithm for image segmentation that automatically determines the optimal number of regions from superpixel features.

Findings

Achieves competitive segmentation quality on benchmark datasets.

Automatically determines the number of segments without prior specification.

Offers a computationally efficient solution with parallelizable ADMM iterations.

Abstract

In this paper, we present a new image segmentation method based on the concept of sparse subset selection. Starting with an over-segmentation, we adopt local spectral histogram features to encode the visual information of the small segments into high-dimensional vectors, called superpixel features. Then, the superpixel features are fed into a novel convex model which efficiently leverages the features to group the superpixels into a proper number of coherent regions. Our model automatically determines the optimal number of coherent regions and superpixels assignment to shape final segments. To solve our model, we propose a numerical algorithm based on the alternating direction method of multipliers (ADMM), whose iterations consist of two highly parallelizable sub-problems. We show each sub-problem enjoys closed-form solution which makes the ADMM iterations computationally very efficient. Extensive experiments on benchmark image segmentation datasets demonstrate that our proposed method in combination with an over-segmentation can provide high quality and competitive results compared to the existing state-of-the-art methods.