Repairing Bad Co-segmentation using Its Quality
Evaluation and Segment Propagation
 
Abstract

In this paper, we improve co-segmentation performance by repairing bad segments based on their quality evaluation and segment propagation. Starting from co-segmentation results of the existing co-segmentation method, we first perform co-segmentation quality evaluation to score each segment. Good segments can be filter out based on the scores. Then, a propagation method is designed to transfer good segments to the rest bad ones so as to repair the bad segmentation. In our method, the quality evaluation is implemented by the measurements of foreground consistency and segment completeness. Two propagation methods such as global propagation and local region propagation are then defined to achieve the more accurate propagation. We verify the proposed method using four state-of-the-arts cosegmentation methods and two public datasets such as ICoseg dataset andMSRC dataset. The experimental results demonstrate the effectiveness of the proposed quality evaluation method. Furthermore, the proposed method can significantly improve the performance of existing methods with larger intersection-overunion score values.

 
Paper
 
Hongliang Li, Fanman Meng, Bing Luo, Shuyuan Zhu, "Repairing Bad Co-segmentation using Its Quality Evaluation and Segment Propagation," IEEE Transactions on Image Processing, Accepted for publication, May, 2014.  [PDF]  
 
Results
 
The segmentation results of the proposed method based on [ICCV2011].The results of Hall-red and Cheetah in ICoseg dataset and Signs and Faces in MSRC dataset are displayed. For each block, the original images, the initial segments and our segments are shown from the top row to the bottom row, respectively.
 
The segmentation results by the proposed method based on [Kim CVPR2012].The results of Monks and Sox in ICoseg dataset and Trees and Cows in MSRC dataset are displayed. For each block, the original images, the initial segments and our segments are shown from the top row to the bottom row, respectively.
 
 
Downloads
 
1. Source Code (MATLAB)
 
   Source code will be downloaded from Here
 
Acknowledgments
 
 
This work was partially supported by NSFC (No. 61271289), The Ph.D. Programs Foundation of Ministry of Education of China (No. 20110185110002), and National High Technology Research and Development Program of China (863 Program, No. 2012AA011503).