CVNov 15, 2016

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

arXiv:1611.04850v11 citations
Originality Incremental advance
AI Analysis

This addresses the need for adaptable evaluation in image segmentation applications, but it is incremental as it builds on prior unsupervised methods.

The paper tackles the problem of unsupervised evaluation for multi-scale image segmentation by proposing a scale-constrained method that uses regional saliency and merging cost to assess quality, and it outperforms four existing methods in multi-scale tasks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes