Enhanced-alignment Measure for Binary Foreground Map Evaluation

Deng-Ping Fan1  Cheng Gong1  Yang Cao1  Bo Ren1  Ming-Ming Cheng Ali Borji2

1CCCE, Nankai University      2CRCV, UCF


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 improvement ranging from 9.08% to 19.65% compared with other popular measures.


If you find our work is helpful, please cite

  title={Enhanced-alignment Measure for Binary Foreground Map Evaluation}, 
  author={Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, Ali Borji}, 
  organization={AAAI Press} 

  title={Structure-measure: A New Way to Evaluate Foreground Maps}, 
  author={Deng-Ping Fan and Ming-Ming Cheng and Yun Liu and Tao Li and Ali Borji}, 
  booktitle={IEEE International Conference on Computer Vision},



2398total visits,11visits today

Leave a Reply

Your email address will not be published. Required fields are marked *