We derive real-time global optimization algorithms for several clustering optimization methods used in unsupervised texture segmentation. Speed is achieved by exploiting the topological relation of features to design a multiscale optimization technique, while accuracy and global optimization properties are provided by a deterministic annealing method. Coarse grained costfunctions are derived for both central and sparse pairwise clustering, where the problem of coarsening sparse random graphs is solved by the concept of structured randomization. Annealing schedules and coarse-to-fine optimization are tightly coupled by a statistical convergence criterion derived from computational learning theory. The algorithms are benchmarked on Brodatz-like micro-texture mondrians. Results are presented for an autonomous robotics application.
Multiscale annealing for real-time unsupervised texture segmentation
1998-01-01
845884 byte
Conference paper
Electronic Resource
English
Multiscale Annealing for Real-Time Unsupervised Texture Segmentation
British Library Conference Proceedings | 1998
|Multiscale Annealing for Grouping and Unsupervised Texture Segmentation
British Library Online Contents | 1999
|Unsupervised multiscale image segmentation
IEEE | 1999
|Unsupervised Multiscale Image Segmentation
British Library Conference Proceedings | 1999
|Unsupervised Texture Segmentation with Nonparametric Neighborhood Statistics
British Library Conference Proceedings | 2006
|