Evaluation of Colour Models for Computer Vision Using Cluster Validation Techniques

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 C r 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 C r is the best choice for the DARwIn-OP platform tested.

[1]  Horst Bunke,et al.  Validation indices for graph clustering , 2003, Pattern Recognit. Lett..

[2]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[3]  Stephan K. Chalup,et al.  The NUbots' Team Description for 2011 , 2004 .

[4]  Lin Padgham,et al.  Techniques for Obtaining Robust, Real-Time, Colour-Based Vision for Robotics , 1999, RoboCup.

[5]  Shamik Sural,et al.  Segmentation and histogram generation using the HSV color space for image retrieval , 2002, Proceedings. International Conference on Image Processing.

[6]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Jing Li Wang,et al.  Color image segmentation: advances and prospects , 2001, Pattern Recognit..

[8]  Michalis Vazirgiannis,et al.  On Clustering Validation Techniques , 2001, Journal of Intelligent Information Systems.

[9]  Peter Stone,et al.  Real-time vision on a mobile robot platform , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  David Budden,et al.  A Novel Approach to Ball Detection for Humanoid Robot Soccer , 2012, Australasian Conference on Artificial Intelligence.

[11]  J. Dunn.  Well-Separated Clusters and Optimal Fuzzy Partitions , 1974 .

[12]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[13]  S. Chalup,et al.  An automated colour calibration system using multivariate Gaussian mixtures to segment HSI colour space , 2008 .

[14]  Gene H. Golub,et al.  Matrix computations , 1983 .

[15]  Hiroaki Kitano,et al.  RoboCup: The Robot World Cup Initiative , 1997, AGENTS '97.

[16]  Manuela M. Veloso,et al.  Fast and inexpensive color image segmentation for interactive robots , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[17]  Hajime Asama,et al.  Development of open humanoid platform DARwIn-OP , 2011, SICE Annual Conference 2011.

[18]  Francisco Azuaje,et al.  Cluster validation techniques for genome expression data , 2003, Signal Process..

[19]  Maurice K. Wong,et al.  Algorithm AS136: A k-means clustering algorithm. , 1979 .

[20]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[21]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[22]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[23]  L. Hubert,et al.  Quadratic assignment as a general data analysis strategy. , 1976 .

[24]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Jonghyun Park,et al.  Color image segmentation using adaptive mean shift and statistical model-based methods , 2009, Comput. Math. Appl..