Graph-cut based interactive image segmentation with randomized texton searching

In the paper, we present an interactive image-segmentation method in the framework of graph cut, which incorporates not only traditional color and gradient constraints, but also a new type of texture constraint. Given an image with user-input strokes, we first establish the color and texture prior models of the foreground/background. The texture prior model, which is key to establish the texture constraints, is represented by local binary patterns (LBP) histograms. Then, an energy function composed of color, gradient, and texture terms is formulated. At last, by using graph cut, we minimize the energy function to obtain the foreground. In the energy function, the color and gradient terms have similar forms with traditional methods. The texture term in the function is generated using a proposed randomized texton-searching algorithm. First, the algorithm locates an approximately best representative texton for every unknown pixel as foreground and an approximately best one as background, through randomized searching. Second, it computes the LBP histograms of the two textons as the pixel's foreground/background texture descriptors, respectively. Finally, the distances between the descriptors and the foreground/background prior models are used to formulate the texture term. Experimental results demonstrate that our method outperforms traditional ones. Copyright (C) 2015 John Wiley & Sons, Ltd.