Natural Image Segmentation with Adaptive Texture and Boundary Encoding

We present a novel algorithm for unsupervised segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. We test our algorithm on two publicly available databases: Berkeley Segmentation Dataset and MSRC Object Recognition Database. It achieves state-of-the-art segmentation results compared to other popular methods.

• Type: Conference
• Year: 2009
• Where: ACCV
• Authors: Shankar Rao, Hossein Mobahi, Allen Y. Yang, Shankar Sastry, Yi Ma
• Keywords: ACCV 2009, Coding Length, Computer Vision, Optimal Segmentation, Unsupervised Segmentation