Inhomogeneity-embedded active contour for natural image segmentation

Active contour model (ACM) is one of the popular methodologies for image segmentation. However, the ACMs developed so far have not shown powerful performance on natural images. The reason is that natural images are rich in color, intensity or texture. The object pixels are often not artifact inhomogeneous, but inherently inhomogeneous. In this paper, we propose an inhomogeneity-embedded active contour (InH_ACM) for natural image segmentation. InH_ACM describes the inhomogeneity in natural images by a pixel inhomogeneity factor and utilizes it for segmentation, unlike most of existing methods that use some averaging convolution to reduce or remove the inhomogeneity in images. Moreover, we build a saliency-inspired framework that can automatically locate the initial contour for InH_ACM to start the evolution. Experimental results on Alpert׳s 100 gray images, MSRA׳s 1000 color images and our collected 300 images where the contained objects are mostly intrinsic inhomogeneous indicate that our proposed InH_ACM can produce reliably satisfactory segmentation in many situations, outperforming most of current popular ACMs.