Scale-constrained Unsupervised Evaluation Method for Multi-scale Image Segmentation

TL;DR

This paper introduces a scale-constrained unsupervised evaluation method for multi-scale image segmentation that adapts to different target scales, improving evaluation accuracy over existing methods.

Contribution

It proposes a novel evaluation approach using regional saliency and merging cost, standardized into spectral distances, tailored for multi-scale segmentation assessment.

Findings

Outperforms four existing unsupervised evaluation methods

Effective in multi-scale segmentation quality assessment

Establishes a relationship between image features and segmentation quality

Abstract

Unsupervised evaluation of segmentation quality is a crucial step in image segmentation applications. Previous unsupervised evaluation methods usually lacked the adaptability to multi-scale segmentation. A scale-constrained evaluation method that evaluates segmentation quality according to the specified target scale is proposed in this paper. First, regional saliency and merging cost are employed to describe intra-region homogeneity and inter-region heterogeneity, respectively. Subsequently, both of them are standardized into equivalent spectral distances of a predefined region. Finally, by analyzing the relationship between image characteristics and segmentation quality, we establish the evaluation model. Experimental results show that the proposed method outperforms four commonly used unsupervised methods in multi-scale evaluation tasks.