提取目标背景的主色是迷彩设计中的重要步骤，通常采用的颜色聚类算法具有监督性的缺陷. 为此，提出一种基于色度直方图的、无监督的颜色聚类算法. 该算法采用CIE 1931色度系统建立色度直方图，根据像素点在该坐标系的分布规律自动生成聚类中心. 逐一计算像素点与各聚类中心的色度的欧氏距离，将像素点与最近的聚类中心归于一类. 实验结果表明，采用该聚类算法能够准确提取主色，自动分割彩色图像，且比普通聚类算法的时间效率更优.
In camouflage design, extracting the dominant color from target background is an important step. A drawback of common color clustering methods is the requirement of supervision. This paper proposes an unsupervised color clustering algorithm based on the chromaticity histogram. The chromaticity histogram is established according to the CIE 1931 system. The cluster center is automatically generated based on the distribution of pixels in the coordinate system. Euclidean distances in the chroma space are calculated one by one between pixels and each cluster center. These pixels are clustered around the
nearest clustering center. Experimental results show that the proposed clustering algorithm can accurately extract the dominant color, and automatically segment the color image. In addition, the algorithm uses less time in image segmentation than common algorithms.
[1] 喻钧，初苗，田少辉，胡志毅. 迷彩设计中背景图像聚类方法的比较[J]. 应用科学学报，2009, 27(5): 475-479.
YU Jun, CHU Miao, TIAN Shao Hui, HU Zhi Yi. Comparison and analysis for image clustering methods of camouflage design [J]. Journal of Applied Sciences, 2009, 27(5): 475-479. (in Chinese)
[2] YANG Y, GUO L, WANG T, et al. Unsupervised multiphase color–texture image segmentation based on variational formulation and multilayer graph [J]. Image and Vision Computing, 2014, 32(2): 87-106.
[3]吕明磊，刘冬梅，曾志勇. 一种改进的K-means聚类算法的图像检索方法[J].计算机科学，2013,40(8): 285-288.
LV Ming Lei, LIU Dong Mei, ZENG Zhi Yong. Novel image retrieval method of improved K-means clustering algorithm [J]. Computer Science, 2013, 40(8): 285-288. (in Chinese)
[4] 张春凯，王丽君. 基于遗传算法的一种改进的 K-均值聚类算法[J]. 计算机工程与应用，2012, 48(26): 144-147.
ZHANG Chun Kai, WANG Li Jun. Improved K-means clustering algorithm based on genetic algorithm [J]. Computer Engineering and Application, 2012, 48 (26): 144-147. (in Chinese)
[5] 何月，申铉京，龙建武，等. 基于塔形信息的空间约束FCM图像分割算法[J]. 计算机工程，2011, 37(22): 209-210, 214.
HE Yue, SHEN Xuan Jing, LONG Jian Wu, et al. Image segmentation algorithm for spatial constraints FCM based on pyramid information [J]. Computer Engineering, 2011, 37(22): 209-210, 214. (in Chinese)
[6] JUNG C R. Unsupervised multiscale segmentation of color images [J]. Pattern Recognition Letters, 2007, 28(4): 523-533.
[7] CELIK T, TJAHJADI T. Unsupervised colour image segmentation using dual-tree complex wavelet transform [J]. Computer Vision and Image Understanding, 2010, 114(7): 813-826.
[8] 陈坤，马燕，刘俊. 一种自适应无监督彩色图像分割方法[J]. 小型微型计算机系统，2013, 34(4): 887-891.
CHEN Kun, MA Yan, LIU Jun. An adaptive unsupervised method toward color image segmentation [J]. Journal of Chinese Computer System, 2013, 34(4): 887-891.
[9] 袁兴生，王正志，项凤涛. 基于视锥细胞色适应生理机制的颜色恒常性计算[J]. 中国图象图形学报，2013, 18(5): 537-544.
YUAN Xing Sheng, WANG Zheng Zhi, XIANG Feng Tao. Color constancy algorithm based on biological mechanism: color adaptation of cone cells [J]. Journal of Image and Graphics, 2013, 18(5): 537-544. (in Chinese)
[10] TANAKA S, MOON C H, FUKUDA M, et al. Three-dimensional visual feature representation in the primary visual cortex[J]. Neural Networks, 2011, 24(10): 1022-1035.
[11] NIXON M, AGUADO A S. Feature extraction and image processing [M]. Access Online via Elsevier, 2008.
[12] SCHANDA Janos. Colorimetry: understanding the CIE system [M]. [S/l.]: Wiley-Interscience, 2007.
[13] 徐洋，郭冬霄，程安宇，等. 基于CIE1931的颜色识别方法研究[J].电视技术，2012, 36( 5): 126-130.
XU Yang, GUO Dong Xiao, CHENG An Yu. Research on color distinguish technology based on CIE1931[J]. Video Application and Project, 2012, 36(5): 126-130. (in Chinese)
[14] 喻钧，刘飞鸿，王占锋，等. 基于光谱色的迷彩主色提取方法[J]. 兵工自动化，2014, 33(1): 72-75.
YU Jun, LIU Fei Hong, WANG Zhan Feng. Extraction method of dominant colors of pattern painting based on spectrum colors [J]. Ordnance Industry Automation, 2014, 33(1): 72-75. (in Chinese)
