Partition-distance methods for assessing spatial segmentations of images and videos

Abstract

The primary goal of the research on image segmentation is to produce better segmentation algorithms. In spite of almost 50 years of research and development in this field, the general problem of splitting an image into meaningful regions remains unsolved. New and emerging techniques are constantly being applied with reduced success. The design of each of these new segmentation algorithms requires spending careful attention judging the effectiveness of the technique.

This paper demonstrates how the proposed methodology is well suited to perform a quantitative comparison between image segmentation algorithms using a ground-truth segmentation. It consists of a general framework already partially proposed in the literature, but dispersed over several works. The framework is based on the principle of eliminating the minimum number of elements such that a specified condition is met. This rule translates directly into a global optimization procedure and the intersection-graph between two partitions emerges as the natural tool to solve it. The objective of this paper is to summarize, aggregate and extend the dispersed work. The principle is clarified, presented striped of unnecessary supports and extended to sequences of images. Our study shows that the proposed framework for segmentation performance evaluation is simple, general and mathematically sound.