Citation
Allen Yang, John Wright, Shankar Sastry, Yi Ma. "Unsupervised Segmentation of Natural Images via Lossy Data Compression". Technical report, University of California, Berkeley, UCB/EECS-2006-195, December, 2006.

Abstract
In this paper, we cast natural-image segmentation as a problem of clustering texture features as multivariate mixed data. We model the distribution of the texture features using a mixture of Gaussian distributions. However, unlike most existing clustering methods, we allow the mixture components to be degenerate or nearly-degenerate. We contend that this assumption is particularly important for mid-level image segmentation, where degeneracy is typically introduced by using a common feature representation for different textures. We show that such a mixture distribution can be effectively segmented by a simple agglomerative clustering algorithm derived from a lossy data compression approach. Using simple fixed-size Gaussian windows as texture features, the algorithm segments an image by minimizing the overall coding length of all the feature vectors. In terms of a variety of performance indices, our algorithm compares favorably against other well-known image segmentation methods on the Berkeley image database.

Electronic downloads

• EECS-2006-195.pdf · application/pdf · 6046 kbytes
• http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-195.html

• HTML

  Allen Yang, John Wright, Shankar Sastry, Yi Ma. <a
  href="http://chess.eecs.berkeley.edu/pubs/220.html"
  ><i>Unsupervised Segmentation of Natural Images via
  Lossy Data Compression</i></a>, Technical
  report,  University of California, Berkeley,
  UCB/EECS-2006-195, December, 2006.

• Plain text

  Allen Yang, John Wright, Shankar Sastry, Yi Ma.
  "Unsupervised Segmentation of Natural Images via Lossy
  Data Compression". Technical report,  University of
  California, Berkeley, UCB/EECS-2006-195, December, 2006.

• BibTeX

  @techreport{YangWrightSastryMa06_UnsupervisedSegmentationOfNaturalImagesViaLossyDataCompression,
      author = {Allen Yang and John Wright and Shankar Sastry and
                Yi Ma},
      title = {Unsupervised Segmentation of Natural Images via
                Lossy Data Compression},
      institution = {University of California, Berkeley},
      number = {UCB/EECS-2006-195},
      month = {December},
      year = {2006},
      abstract = {In this paper, we cast natural-image segmentation
                as a problem of clustering texture features as
                multivariate mixed data. We model the distribution
                of the texture features using a mixture of
                Gaussian distributions. However, unlike most
                existing clustering methods, we allow the mixture
                components to be degenerate or nearly-degenerate.
                We contend that this assumption is particularly
                important for mid-level image segmentation, where
                degeneracy is typically introduced by using a
                common feature representation for different
                textures. We show that such a mixture distribution
                can be effectively segmented by a simple
                agglomerative clustering algorithm derived from a
                lossy data compression approach. Using simple
                fixed-size Gaussian windows as texture features,
                the algorithm segments an image by minimizing the
                overall coding length of all the feature vectors.
                In terms of a variety of performance indices, our
                algorithm compares favorably against other
                well-known image segmentation methods on the
                Berkeley image database.},
      URL = {http://chess.eecs.berkeley.edu/pubs/220.html}
  }
  

Posted by Allen Yang on 24 Apr 2007.
Groups: chesslocal
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.