Natural image segmentation with adaptive texture and boundary encoding

  • Authors:

  • Shankar R. Rao;Hossein Mobahi;Allen Y. Yang;S. Shankar Sastry;Yi Ma

  • Affiliations:

  • Coordinated Science Laboratory, University of Illinois at Urbana-Champaign;Coordinated Science Laboratory, University of Illinois at Urbana-Champaign;EECS Department, University of California, Berkeley;EECS Department, University of California, Berkeley;Coordinated Science Laboratory, University of Illinois at Urbana-Champaign

  • Venue:
  • ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

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. Our algorithm achieves state-of-the-art results on the Berkeley Segmentation Dataset compared to other popular methods.