Uniform Information Segmentation

TL;DR

This paper introduces a novel image segmentation method based on information uniformity, producing adaptive segments that better preserve details and simplify images, outperforming existing methods in accuracy and efficiency.

Contribution

The paper presents a new segmentation algorithm that uses information content as a criterion, adapting segment sizes to image complexity and achieving superior performance.

Findings

Outperforms state-of-the-art segmentation methods on benchmarks.

Produces smaller, denser segments in complex regions and larger in homogeneous areas.

Achieves near real-time computational efficiency.

Abstract

Size uniformity is one of the main criteria of superpixel methods. But size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels without losing too much important detail. We propose that a more appropriate criterion for creating image segments is information uniformity. We introduce a novel method for segmenting an image based on this criterion. Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details. Our algorithm is simple and requires just one input parameter - a threshold on the information content. On segmentation comparison benchmarks it proves to be superior to the state-of-the-art. In addition, our method is computationally very efficient, approaching real-time performance, and is easily extensible to three-dimensional image stacks and video volumes.