Texture regimes for entropy-based multiscale image analysis

Authors:
Sylvain Boltz;Frank Nielsen;Stefano Soatto
Affiliations:
Laboratoire d'Informatique, École Polytechnique, Palaiseau Cedex, France and UCLA Vision Lab, University of California, Los Angeles, Los Angeles, CA;Laboratoire d'Informatique, École Polytechnique, Palaiseau Cedex, France;Laboratoire d'Informatique, École Polytechnique, Palaiseau Cedex, France
Venue:
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Year:
2010

Citing 7
Cited 2

Minimax entropy principle and its application to texture modeling

Neural Computation
Scale-Space Theory in Computer Vision

Scale-Space Theory in Computer Vision
Mean Shift Based Clustering in High Dimensions: A Texture Classification Example

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Statistical Region Merging

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Statistical Approach to Material Classification Using Image Patch Exemplars

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation with nonparametric neighborhood statistics

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

IEEE Transactions on Signal Processing

Object detection with feature stability over scale space

Journal of Visual Communication and Image Representation
Scale selection for supervised image segmentation

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an approach to multiscale image analysis. It hinges on an operative definition of texture that involves a "small region", where some (unknown) statistic is aggregated, and a "large region" within which it is stationary. At each point, multiple small and large regions co-exist at multiple scales, as image structures are pooled by the scaling and quantization process to form "textures" and then transitions between textures define again "structures." We present a technique to learn and agglomerate sparse bases at multiple scales. To do so efficiently, we propose an analysis of cluster statistics after a clustering step is performed, and a new clustering method with linear-time performance. In both cases, we can infer all the "small" and "large" regions at multiple scale in one shot.