首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于HSI空间和颜色纯度的多尺度遥感图像分割算法
引用本文:张龙翔,王春泉.基于HSI空间和颜色纯度的多尺度遥感图像分割算法[J].临沂师范学院学报,2005,27(3):111-114.
作者姓名:张龙翔  王春泉
作者单位:1. 临沂师范学院,信息学院,山东,临沂,276005
2. 山东科技大学,信息科学与工程学院,山东,青岛,266510
摘    要:提出了一种新的考虑到HIS颜色空间和颜色纯度的多尺度遥感影像分割方法.使用HIS颜色空间来取得像素的颜色信息.当饱和度和亮度值较低时,色调值会非常敏感,用颜色纯度作色调值的加权值.不但考虑了像素的属性,还考虑了像素集合的属性.图像先被根据特定尺度分割成不同的区域对象,各个区域对象的平均值和方差值作为区域对象的属性.用区域对象特性和相对位置信息把小的对象合并到大的对象中.

关 键 词:遥感图像分割  HIS颜色空间  颜色纯度  多尺度
文章编号:1009-6051(2005)03-0111-04
修稿时间:2005年5月20日

The Method of Image segmentation based on HIS Color Space and Mutil-scale Characteristics
ZHANG Long-xiang,WANG Chun-quan.The Method of Image segmentation based on HIS Color Space and Mutil-scale Characteristics[J].Journal of Linyi Teachers' College,2005,27(3):111-114.
Authors:ZHANG Long-xiang  WANG Chun-quan
Institution:ZHANG Long-xiang~1,WANG Chun-quan~2
Abstract:A novel method to segment remotely sensed image is proposed considering HIS Color Space, the color purity and Mutil-scale Characteristics. HIS color space is used to express pixel color information. Not only the pixel properties but also the pixel region properties are considered. An image is divided into region. For each region, the mean and variance values can be seen as the pixel region properties. Because the hue value will be very sensitive when the intensity and saturation values are small, the color purity is used as the weight on the hue value. The image segmentation is done with the approach of the combination of region growing based on Mutil-scale Characteristics, and then use features of regions and the relative position information to merge small region into large region.
Keywords:remotely sensed image segmentation  HIS color space  color purity  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号