计算机应用 ›› 2010, Vol. 30 ›› Issue (3): 653-656.

• 图形图像处理 • 上一篇    下一篇

基于色调直方图和区域合并的彩色图像分割算法

冷美萍,鲍苏苏   

  1. 华南师范大学计算机学院
  • 收稿日期:2009-09-06 修回日期:2009-11-01 发布日期:2010-03-14 出版日期:2010-03-01
  • 通讯作者: 冷美萍
  • 基金资助:
    广东省自然科学基金团队项目

Color image segmentation algorithm based on hue level histogram and region merging

  • Received:2009-09-06 Revised:2009-11-01 Online:2010-03-14 Published:2010-03-01
  • Contact: LENG Mei-ping

摘要: 近年来随着机器视觉、模式识别和基于内容的图像检索等技术的不断提高以及彩色图像的大量使用,图像分割特别是彩色图像的分割显示出越来越重要的地位。为此提出了一种快速有效的彩色图像分割方法,主要包括三个步骤:首先将RGB颜色空间转换成HSV空间,把图像中的像素点根据饱和度和亮度划分为奇异点和非奇异点;然后对非奇异点和奇异点分别采用基于色调和灰度直方图进行分割;最后综合这两种分割结果,采用区域合并技术进行合并。实验结果表明,该方法对彩色图像能够有效地提取目标物体,具有一定的鲁棒性。

关键词: 彩色图像分割, 奇异点, 色调直方图, 区域合并

Abstract: In recent years, with the advancement of machine vision, pattern recognition and content-based image retrieve and the wide use of color images, image segmentation, especially color image segmentation, has played a more and more important role. Therefore, a fast and effective segmentation method for color image was proposed, which mainly included three steps. Firstly RGB color space was transformed into HSV space, and image pixels were divided into singular and non-singular points according to their saturation and intensity; then the singular and non-singular points were segmented respectively based on hue level histogram and grey level histogram respectively; finally region merging method was adopted to merge the previous results of segmentation. The experimental results show that this method can effectively extract color image of the object and have certain robustness.

Key words: color image segmentation, singular point, hue level histogram, region merging