A spectral method for image co-segmentation

In this paper, we propose a spectral method to address the problem of image co-segmentation. Our idea is motivated by the Normalized Cut algorithm and spectral clustering. By defining a superpixel graph over the given image pair and introducing the successful ideas of Ncut formulation, we successfully transform the co-segmentation problem into a Rayleigh quotient problem, which can be solved by eigen-decomposition. Then we utilize spectral clustering to classify the pixels in each image and obtain the common objects of the image pair. Experimental results have demonstrated the effectiveness of the proposed method.