基于形态学分水岭的彩色图像分割  

Color image segmentation based on Morphological Watershed

作　　者：陈宝靖[1] 

机构地区：[1]国网甘肃省电力公司信息通信公司信息通信调度监控中心,兰州730050

出　　处：《自动化与仪器仪表》2015年第2期139-141,共3页Automation & Instrumentation

摘　　要：将数学形态学理论应用到彩色图像处理是当前的研究热点问题。由于彩色图像的高维特性,导致经典的分水岭方法难以直接拓展到彩色图像处理中。已有的方法常常忽略彩色图像的色度信息,因此分割精度较低。本文提出了一种新的方法,该方法首先定义了新的彩色空间,在新的彩色空间下对彩色图像的色调和亮度分量分别进行分割,然后利用饱和度加权以实现各个分量的融合,得到最终的分割结果。实验结果表明,本文提出的新方法能正确分割彩色图像,分割效果明显优于传统的方法。It is a hot topic that applying mathematical morphological theory in color image processing. A color image is represented by high-dimension data which leads to a result that it is difficult to extend watershed approach to color image processing. The existing approaches always omit hue information of color images, and thus the segmentation accuracy is low. In order to address the issue, a new method is proposed in this paper. Firstly, we define a new color space which is suitable for color image segmentation.And then hue and luminance component of color images is segmented separately. Besides, we use saturation to weight each segmentation result and obtain the final segmentation result. The experimental results show that the proposed approach can provide accurate segmentation results. And the effect of segmentation is obviously superior to the traditional approaches.

关 键 词：彩色图像分割 分水岭变换 梯度图像 饱和度 

分 类 号：TP302.4[自动化与计算机技术—计算机系统结构]