An Active Contour Model Based on Edge and Region Information for Image Segmentation
Wenxiu Zhao, Xiaofang Li · 2023
In this paper, a novel active contour model for image segmentation is proposed, which comprises two components: edge energy and region energy. First, a preprocessing step is performed to obtain a denoised smooth image using an off-the-shelf denoiser, which effectively removes noise and unwanted edges. Then we calculate the gradient of the preprocessed image for the edge detection function. In addition, our model considers both local and global information of the image in the region energy. Specifically, we construct a constraint to minimize the differences between the denoised smooth image and the local fitted image, and design fitting terms of the image intensity inside and outside the target boundary. Extensive experiments indicate that our proposed model can effectively segment images even in the presence of noise and intensity inhomogeneity. Moreover, the segmentation accuracy and robustness of this model are better than those of relevant segmentation models.