基于光谱色的迷彩主色提取方法

针对采用聚类方法进行数码迷彩设计时存在提取主色的色度不稳定问题,提出一种基于光谱色的主色聚类中心确定算法。在建立CIE-XYZ系统的基础上对颜色的种类进行划分。将图像颜色从RGB空间转化到XYZ颜色空间,然后通过CIE-XYZ系统计算每一像素颜色的主波长、色纯度,并以主波长、色纯度为标准,选取初始聚类中心的颜色来代表背景图像的主色。实验结果表明:该算法实现的时间复杂度低,执行效率高。

Extraction Method of Dominant Colors of Pattern Painting Based on Spectrum Colors

Aiming at the chromaticity instability problem in the process of main-color extraction using clustering methods in digital camouflage design, this paper proposes an algorithm for determining the clustering center of dominant color based on spectral colors. On the basis of the CIE-XYZ system, the color type is classified by chromaticity. The image color space should be transformed from RGB to XYZ. The main wavelength and the color purity for each pixel are calculated in the CIE-XYZ system. Here the initial clustering center of the dominant color is selected for representing the dominant color of the background image. Experimental results show that the algorithm has low time complexity as well as high efficiency.