Image Categorization and Semantic Segmentation using Scale-Optimized Textons

@inproceedings{Kang2014ImageCA,
  title={Image Categorization and Semantic Segmentation using Scale-Optimized Textons},
  author={Yousun Kang},
  year={2014}
}
In computer vision research, a texton is a representative dense visual word for the bag-of-keypoints method. It has proven its effectiveness in categorizing materials and in generic object classes. Despite its success and popularity, no report describes a study that has tackled the problem of its scale optimization for given image data and associated object categories. We propose scale-optimized textons to learn the best scale for each object in a scene. We incorporate them into image… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • Nevertheless, across the whole dataset under the same experimental conditions, the proposed method achieved a class average performance of 59.8%, which is better than the 58.6% that was obtained using the state-of-the-art method.

Citations

Publications citing this paper.

Malware Analysis Using Visualized Image Matrices

  • TheScientificWorldJournal
  • 2014
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

A Performance Evaluation of Local Descriptors

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2005
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A multi-scale learning framework for visual categorization

S. Wang, Y. Wang
  • Proc. of the 12th Asian Conference on Computer Vision, Queenstown, New Zealand, LNCS, volume 6492, pages 310–322. Springer-Verlag, November
  • 2011
VIEW 1 EXCERPT

Semantic Segmentation and Object Recognition Using Scene-Context Scale

  • 2010 Fourth Pacific-Rim Symposium on Image and Video Technology
  • 2010
VIEW 2 EXCERPTS

An empirical study of context in object detection

  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
VIEW 2 EXCERPTS

Image Classification using Random Forests and Ferns

  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
VIEW 1 EXCERPT