摘要
基于模式识别技术，提出了一种用于彩色图像量化的新算法──统计聚类算法．并用ＢｏｒｌａｎｄＣ３．０成功地实现了该算法．理论和实验结果分析表明：本算法对彩色图像量化的颜色失其度以及噪声点的控制均优于Ｋ均值算法和ＩＳＯＤＡＴＡ算法。
Based on the pattern recognition technology,this paper proposes a new clustering algorithm for the color image quantization, that is, a statistically clustering algorithm.Using Borland C 3. 0 language, it has successfully come ture for the algorithm to be used as the color image quantization. The theoretical analysis and experimental results show that the effects of the color image quantization,the lack fidelity degree and the processing of noise points provided by the algorithm are better than the K -mean algorithm and ISODATA algorithm.
出处
《广东机械学院学报》
1996年第2期58-62,共5页
Industrial Engineering Journal
关键词
聚类分析
颜色量化
图像处理
cluster analysis
pattern sample
statistics
color quantization
