A Segmentation Algorithm of Infrared Image Based on Variational Formulation Level Set Model

Infrared images always have little priori-information and blurry boundaries or even with discontinuous boundaries, and therefore the segmentation of infrared image is very difficult. A variational formulation level set model based on the image global information is obtained, which can detect contours both with and without gradient based on global information and eliminate the re-initialization procedure. The stopping term does not depend on the boundary gradient of the image, which overcomes greatly the over segmentation. This algorithm forces the level set function to be close to a signed distance function, and therefore reduces the number of iterations and the error of re-initialization. The method is used in the segmentation of an infrared image, and the experiment results reveal the effectiveness of the algorithm listed in this paper.