基于邻域灰度值聚类的图像色彩量化  

Image color quantization based on clustering of neighborhood gray level

作　　者：肖满生[1] 吴卫[2] 王宏[2] 

机构地区：[1]湖南工业大学科技学院,湖南株洲412008 [2]湖南工业大学包装设计学院,湖南株洲412008

出　　处：《控制与决策》2013年第6期935-939,共5页Control and Decision

基　　金：湖南省自然科学基金项目(10JJ6089);湖南省教育厅科研重点项目(12A042)

摘　　要：在将图像中的多种颜色或灰度量化成数目较少的颜色或灰度的过程中,存在着计算过于复杂、量化后图像偏差较大等问题,鉴于此,提出基于邻域灰度值聚类的图像色彩量化方法.首先结合邻域像素的灰度和空间信息对像素进行一维灰度化;然后采用基于像素灰度加权系数的改进模糊C均值聚类算法对像素进行聚类.分析和实验表明,该方法可以减少量化计算的复杂度,保持图像的整体层次,量化后图像偏差较小,对图像处理具有一定的实用价值.@@@@For the main problems appearing in the process of reducing the number of either colors or gray level of the image, for example, the computation tends to be too complex and the image deviation tends to be too big, the method of image color quantization based on the clustering of neighborhood gray level is proposed. Firstly, the one-dimensional gray level expression of pixels is carried out by integrating the space and the gray information of the neighborhood pixels. Then the pixels are clustered by using the improved fuzzy -means clustering algorithm. The theoretical analysis and the experiment show that the proposed method can reduce the complexity of the quantization computation and maintain the overall level and the partial details of the image, and the image deviation becomes smaller after the quantization, which has the certain practical value to the imagery processing.

关 键 词：色彩量化 邻域 模糊C均值 灰度加权系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]