Improved Image Segmentation via Cost Minimization of Multiple Hypotheses

TL;DR

This paper introduces a novel image segmentation method that generates multiple hypotheses by varying parameters and then selects the optimal segmentation through a cost minimization process, improving accuracy and robustness.

Contribution

It proposes a new framework that leverages diverse segmentation hypotheses and optimizes selection via cost minimization, enhancing segmentation quality over existing methods.

Findings

Achieves improved segmentation accuracy compared to state-of-the-art algorithms.

Demonstrates robustness to different segmentation kernels.

Effectively balances contour accuracy and hypothesis stability.

Abstract

Image segmentation is an important component of many image understanding systems. It aims to group pixels in a spatially and perceptually coherent manner. Typically, these algorithms have a collection of parameters that control the degree of over-segmentation produced. It still remains a challenge to properly select such parameters for human-like perceptual grouping. In this work, we exploit the diversity of segments produced by different choices of parameters. We scan the segmentation parameter space and generate a collection of image segmentation hypotheses (from highly over-segmented to under-segmented). These are fed into a cost minimization framework that produces the final segmentation by selecting segments that: (1) better describe the natural contours of the image, and (2) are more stable and persistent among all the segmentation hypotheses. We compare our algorithm's performance with state-of-the-art algorithms, showing that we can achieve improved results. We also show that our framework is robust to the choice of segmentation kernel that produces the initial set of hypotheses.