Abstract

Changing illumination condition can change the result of image segmentation algorithm and reduce the intelligent recognition rate. A novel color image segmentation method robust to illumination variations is presented. The method is applied to the skin segmentation. Based on the hue preserving algorithm, the method reduces the dimensionality of the red-green-blue (RGB) space to one dimension, while keeping the hue of every pixel unchanging before and after space transformation. In the new color space, the skin color model is established using Gaussian model. Experimental results show that the method is robust to illumination variations, and has low computational complexity.

© 2010 Chinese Optics Letters

Transformation of a high-dimensional color space for material classification

Huajian Liu, Sang-Heon Lee, and Javaan Singh Chahl
J. Opt. Soc. Am. A 34(4) 523-532 (2017)

Color constancy enhancement under poor illumination

Jun Liu, Zhenfeng Shao, and Qimin Cheng
Opt. Lett. 36(24) 4821-4823 (2011)

Multi-color space learning for image segmentation based on a support vector machine

Renzheng Zhang, Guodong Chen, Zheng Wang, Wenzheng Chi, Zhenhua Wang, Lining Sun, Guilin Yang, and Yifang Wen
OSA Continuum 2(11) 3050-3065 (2019)

Hue-preserving and saturation-improved color histogram equalization algorithm

Ki Sun Song, Hee Kang, and Moon Gi Kang
J. Opt. Soc. Am. A 33(6) 1076-1088 (2016)

Spectral-reflectance linear models for optical color-pattern recognition

Juan L. Nieves, Javier Hernández-Andrés, Eva Valero, and Javier Romero
Appl. Opt. 43(9) 1880-1891 (2004)