Evaluation of Color Image Segmentation Algorithms Based on Histogram Thresholding
Image segmentation is an essential processing step in texture analysis systems, as its accuracy has a significant impact on the quality of the final analysis result. The downside of texture analysis is that segmentation is one of the most difficult tasks in image processing. In this paper, algorithms for improved color image segmentation are presented. They are all based on a histogram thresholding approach that was developed for monochrome images for it has proven to be very effective. Improvements over the genuine segmentation approach are measured and the best optimization algorithm is determined.
KeywordsReceiver Operating Characteristic Curve Image Segmentation Segmentation Approach Texture Region Monochrome Image
Unable to display preview. Download preview PDF.
- 1.Wilson, R., Spann, M.: Image Segmentation and Uncertainty. Pattern Recognition and Image Processing Series. Research Studies Press Ltd, England (1988)Google Scholar
- 2.Freixenet, J., et al.: Yet Another Survey on Image Segmentation: Region and Boundary Information Integration. In: Proc. 7th European Conference on Computer Vision-Part III, pp. 408–422 (2002)Google Scholar
- 3.Huang, Q., Dom, B.: Quantitative Methods of Evaluating Image Segmentation. In: Proc. ICIP, vol. 3, pp. 53–56 (1995)Google Scholar
- 6.Wilson, R., Knutsson, H., Granlund, G.H.: The Operational Definition of the Position of Line and Edge. In: Proc. ICPR (1982)Google Scholar
- 10.Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
- 11.Hanley, J.A., Mc Neil, B.J.: The Meaning and Use of the Area under the Receiver Operating Characteristic (ROC) Curve. Radiology 1(143), 29–36 (1982)Google Scholar