Building on recent progress in modeling filter response statistics of natural images we integrate a statistical model into a variational framework for image segmentation. Incorporated in a sound probabilistic distance measure the model drives level sets toward meaningful segmentations of complex textures and natural scenes. Since each region comprises two model parameters only the approach is computationally efficient and enables the application of variational segmentation to a considerably larger class of real-world images. We validate the statistical basis of our approach on thousands of natural images and demonstrate that our model outperforms recent variational segmentation methods based on second-order statistics.
Natural image statistics for natural image segmentation
Proceedings Ninth IEEE International Conference on Computer Vision ; 1259-1266 vol.2
2003-01-01
414558 byte
Conference paper
Electronic Resource
English
Natural Image Statistics for Natural Image Segmentation
British Library Online Contents | 2005
|Natural Image Statistics for Natural Image Segmentation
British Library Conference Proceedings | 2003
|Bagging Stochstic Watershed on Natural Color Image Segmentation
British Library Conference Proceedings | 2015
|No-reference image quality assessment based on log-derivative statistics of natural scenes
British Library Online Contents | 2013
|Extreme Runup Statistics on Natural Beaches
HENRY – Federal Waterways Engineering and Research Institute (BAW) | 1987
|