Matlab code for Automatic-image-Co-Segmentation-using-GMS

An image co-segmentation algorithm that was presented in ICIP'14. It has been recipient of Top 10% paper award as well.

Most existing high-performance co-segmentation algorithms
are usually complicated due to the way of co-labeling a set of
images and the requirement to handle quite a few parameters
for effective co-segmentation. In this paper, instead of relying on the complex process of co-labeling multiple images, we perform segmentation on individual images but based on
a combined saliency map that is obtained by fusing single image
saliency maps of a group of similar images. Particularly,
a new multiple image-based saliency map extraction,
namely geometric mean saliency (GMS) method, is proposed
to obtain the global saliency maps. In GMS, we transmit
the saliency information among the images using the warping
technique. Experiments show that our method is able to
outperform state-of-the-art methods on three benchmark co-segmentation
datasets.