- Title
- Evaluation of colour models for computer vision using cluster validation techniques
- Creator
- Budden, David; Fenn, Shannon; Mendes, Alexandre; Chalup, Stephan
- Relation
- RoboCup 2012: Robot Soccer World Cup XVI. Proceedings of the 16th Annual RoboCup International Symposium (Mexico City, Mexico 18-24 June, 2012) p. 261-272
- Publisher Link
- http://dx.doi.org/10.1007/978-3-642-39250-4
- Publisher
- Springer Verlag
- Resource Type
- conference paper
- Date
- 2013
- Description
- Computer vision systems frequently employ colour segmentation as a step of feature extraction. This is particularly crucial in an environment where important features are colour-coded, such as robot soccer. This paper describes a method for determining an appropriate colour model by measuring the compactness and separation of clusters produced by the k-means algorithm. RGB, HSV, YC b Cr and CIE L*a*b* colour models are assessed for a selection of artificial and real images, utilising an implementation of the Dunn's-based cluster validation index. The effectiveness of the method is assessed by qualitatively comparing the relative correctness of the segmentation to the results of the cluster validation. Results demonstrate a significant variation in segmentation quality among colour spaces, and that YC b Cr is the best choice for the DARwIn-OP platform tested.
- Subject
- image segmentation; colour representations; colour space analysis; clustering; cluster validation; pattern recognition
- Identifier
- http://hdl.handle.net/1959.13/1057761
- Identifier
- uon:16255
- Identifier
- ISBN: 9783642392498
- Language
- eng
- Reviewed
- Hits: 1979
- Visitors: 2436
- Downloads: 1
| Thumbnail | File | Description | Size | Format |
|---|