Towards Segmentation from Multiple Cues: Symmetry and Color
Autor: | Nahum Kiryati, Roy Shor |
---|---|
Rok vydání: | 2001 |
Předmět: | |
Zdroj: | Multi-Image Analysis ISBN: 9783540421221 Theoretical Foundations of Computer Vision |
Popis: | Towards segmentation from multiple cues, this paper demonstrates the combined use of color and symmetry for detecting regions of interest (ROI), using the detection of man-made wooden objects and the detection of faces as working examples. A functional that unifies color compatibility and color-symmetry within elliptic supports is defined. Using this functional, the ROI detection problem becomes a five-dimensional global optimization problem. Exhaustive-search is inapplicable due its prohibitive computational cost. Genetic search converges rapidly and provides good results. The added value obtained by combining color and symmetry is demonstrated. |
Databáze: | OpenAIRE |
Externí odkaz: |