Fast color image matting by online active contour model
Xiaomin Xie, Changming Wang, Aijun Zhang · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2015
Compared with gray images, colorful images contain more useful information. In this paper, an online active contour model regarding color image matting is proposed. Using our model, the objects of color images are detected according to their colors. For the proposed model, the new scheme firstly identifies the objects to be segmented by setting the initial contour. Then the new energy functional, which is based on the intensities in each channel, is minimized through an efficient level set formula. Thus less iterations and little calculation time are needed. Finally, the morphological opening and closing operation is adopted for regularization. Experiments results demonstrate the efficiency and effectiveness of the proposed approach, compared with the current active contour models.