Automatic color image segmentation using CSIFT and Graph Cuts

In this paper, we propose a new automatic color image segmentation method using Colored Sift (CSIFT) and Graph Cuts. Color provides valuable information in object segmentation and recognition tasks. However, color information is vulnerable to be affected by shadows and highlights. CSIFT is a stable and distinctive feature with respect to variations in the photometrical imaging conditions. It has been demonstrated that the CSIFT is more robust than the conventional SIFT with respect to color and photometrical variations. On the other hand, Graph Cuts is proposed as a segmentation method of a detailed object region. But it is necessary to give seeds manually. In our method, the object is recognized first by CSIFT interest points. After that, the object region is cut out by Graph Cuts using CSIFT interest points as seeds.