A novel signed pressure force function for image segmentation by combining global and local information

Abstract As we all know, it is difficult to deal with the weak boundary and noisy images by using local or global image information. Therefore, this paper proposes a signed pressure force function for image segmentation by combining global and local image information. First, the global and local gray fitted terms are given by using the global and local region information of the image respectively. Then, the global and local terms are linearly combined to construct a mixed signed pressure force function. Finally, the balloon force function is redefined to adaptively change the contour curve evolution rate of the level set. The numerical simulation results show that the proposed algorithm can not only accurately segment weak boundary and multi-target images, but also has a fast segmentation speed and a certain robustness to the noise.