Natural Scene Segmentation Based on Information Fusion and Homogeneity Property

  title={Natural Scene Segmentation Based on Information Fusion and Homogeneity Property},
  author={Heng-Da Cheng and Manasi Datar and Wen Ju},
This paper presents a novel approach to natural scene segmentation. It uses both color and texture features in cooperation to provide comprehensive knowledge about every pixel in the image. A novel scheme for the collection of training samples, based on homogeneity, is proposed. Natural scene segmentation is carried out using a two-stage hierarchical self-organizing map (HSOM). The proposed method confirms that the sample selection based on homogeneity and the selflearning ability and… CONTINUE READING
4 Citations
9 References
Similar Papers


Publications referenced by this paper.
Showing 1-9 of 9 references

Bors,“A variational approach for color image segmentation,

  • A.G.N. Nasios
  • Proceedings of the 17th International Conference…
  • 2004
Highly Influential
3 Excerpts

Texture energy measures

  • K. I. Laws
  • Proccedings of Image Understanding Workshop, pp…
  • 1979
2 Excerpts

Similar Papers

Loading similar papers…