Enhanced-alignment Measure for Binary Foreground Map Evaluation

TL;DR

This paper introduces the E-measure, a novel binary foreground map evaluation metric that combines local pixel details with global image statistics, showing significant improvements over existing measures across multiple datasets.

Contribution

The paper proposes the E-measure, integrating local and global information for more accurate binary foreground map evaluation, outperforming existing measures on various datasets.

Findings

E-measure outperforms existing measures on 4 datasets

Significant improvements in application ranking accuracy

Enhanced correlation with human judgment

Abstract

The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways. These measures consider pixel-level match or image-level information independently, while cognitive vision studies have shown that human vision is highly sensitive to both global information and local details in scenes. In this paper, we take a detailed look at current binary FM evaluation measures and propose a novel and effective E-measure (Enhanced-alignment measure). Our measure combines local pixel values with the image-level mean value in one term, jointly capturing image-level statistics and local pixel matching information. We demonstrate the superiority of our measure over the available measures on 4 popular datasets via 5 meta-measures, including ranking models for applications, demoting generic, random Gaussian noise maps, ground-truth switch, as well as human judgments. We find large improvements in almost all the meta-measures. For instance, in terms of application ranking, we observe improvementrangingfrom9.08% to 19.65% compared with other popular measures.