Color Blindness Image Segmentation Using Rho-Theta Space
Segmentation of color information in RGB space is considered as the detection of clouds in rho-theta space. The conversion between RGB space and rho-theta space is first derived. Then the peak detection in the cloud-like rho-theta image is developed for color plane segmentation. The color blindness images are used for illustrations and experiments. Results confirm the feasibility of the proposed method. In addition, the segmentation of pattern and background for a color blindness image is also further demonstrated by means of the spatial distance computation among segmented color planes as well as the traditional K-means algorithm.
KeywordsCloud image Color blindness image Image segmentation K-means Peak detection RGB Rho-theta space
This work was supported in part by the Ministry of Science and Technology, Taiwan, Republic of China, under the grant number MOST103-2221-E-155-040 and MOST105-2221-E-155-063.
- 11.Y.S. Chen, C.Y. Zhou, L.Y. Li, Perceiving stroke information from color-blindness images, in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Budapest, Hungary (2016), pp. 70–73Google Scholar
- 12.Y.S. Chen, L.Y. Li, C.Y. Zhou, Rho-theta parameterization for color blindness image segmentation, in Proceedings of the International MultiConference of Engineers and Computer Scientists, Lecture Notes in Engineering and Computer Science, Hong Kong (2017), pp. 405–409Google Scholar
- 13.I. Omer, M. Werman, Color lines: image specific color representation, in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA (2004), pp. 946–953Google Scholar
- 15.J. MacQueen, Some methods for classification and analysis of multivariate observations, in Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. University of California Press, USA (1967), pp. 281–297Google Scholar