An image co-segmentation algorithm that was presented in ICIP'14. It has been recipient of Top 10% paper award as well.
Following are the instructions for running the code:
Run compile.m [NOTE: Pls comment line 5 of project.h in mexDenseSIFT and SiftFlow folders if you are compiling using visual studio in windows, and uncomment if you are in linux or mac os.] Run main.m for demo Results will be sub-folder named 'segemntation_masks' where images are located.
If you find the code useful, kindly cite the following papers:
[1] K. R. Jerripothula, J. Cai, F. Meng and J. Yuan, "Automatic image co-segmentation using geometric mean saliency", IEEE International Conference on Image Processing (ICIP), Paris, France, 2014, pp. 3277-3281.
[2] K. R. Jerripothula, J. Cai, and J. Yuan, "Group Saliency Propagation for Large-scale and Quick Image Co-segmentation", IEEE International Conference on Image Processing (ICIP), Quebec City, Canada, 2015, pp. 4639-4643.
[3] K. R. Jerripothula, J. Cai, J. Lu and J. Yuan, "Object Co-skeletonization with Co-segmentation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 2017, pp. 6205-6213.