On representation and matching of multi-coloured objects
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A new representation for objects with multiple colours-the colour adjacency graph (CAG)-is proposed. Each node of the CAG represents a single chromatic component of the image defined as a set of pixels forming a unimodal cluster in the chromatic scattergram. Edges encode information about adjacency of colour components and their reflectance ratio. The CAG is related to both the histogram and region adjacency graph representations. It is shown to be preserving and combining the best features of these two approaches while avoiding their drawbacks. The proposed approach is tested on a range of difficult object recognition and localisation problems involving complex imagery of non-rigid 3D objects under varied viewing conditions with excellent results.Keywords
This publication has 11 references indexed in Scilit:
- A parallel color algorithm for segmenting images of 3-D scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Reflectance ratio: A photometric invariant for object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Indexing via color histogramsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Structural matching in computer vision using probabilistic relaxationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- The capacity of color histogram indexingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Computing reflectance ratios from an imagePattern Recognition, 1993
- Image segmentation by a parallel, non-parametric histogram based clustering algorithmPattern Recognition, 1990
- Using color for geometry-insensitive segmentationJournal of the Optical Society of America A, 1989
- Color constancy: a method for recovering surface spectral reflectanceJournal of the Optical Society of America A, 1986
- A locally sensitive method for cluster analysisPattern Recognition, 1976