Learning a classification model for segmentation
Ren, X.
Malik, J.
Comput. Sci. Div., California Univ., Berkeley, CA, USA;
This paper appears in: Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on
Publication Date: 13-16 Oct. 2003
On page(s): 10-17 vol.1
Location: Nice, France,
ISBN: 0-7695-1950-4
INSPEC Accession Number: 8301589
Digital Object Identifier: 10.1109/ICCV.2003.1238308
Current Version Published: 2008-04-03
Abstract
We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is over-segmented into super-pixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightness and good continuation. Information-theoretic analysis is applied to evaluate the power of these grouping cues. We train a linear classifier to combine these features. To demonstrate the power of the classification model, a simple algorithm is used to randomly search for good segmentations. Results are shown on a wide range of images.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
