摘要
为了使多区域分割后的图像边缘更加清晰,提出了一种将边缘检测与分裂合并法相结合的多区域图像分割方法.其基本思想是用边缘检测算子与分裂合并法分别对同一幅图像进行分割,然后应用信息融合技术将经过上述处理后的两幅图像融合,得到新的图像.在进行图像融合时,采用了像素级和特征级两种融合方法.实验结果表明,该算法可将图像明显地分割成多个区域,且边缘清晰,分割效果令人满意.
To make the image edge of multi-region segmentation more legible, a new multi-region segmentation algorithm, which combines edge detection with region splitting and merging, is presented. The basic principle is to segment one image by edge detection operator and splitting and merging algorithm respectively. And then these two images are syncretized to form a new image by data fusion techniques. Two fusion methods based on the pixel and the feature, are applied. Experimental results show that the image is distinctly segmented into multi-regions and the image edge is legible as well. The segmented results are satisfactory.
出处
《应用科技》
CAS
2006年第1期39-42,共4页
Applied Science and Technology
关键词
图像分割
信息融合
边缘检测
分裂合并
Marr算子
image segmentation
data fusion
edge detection
splitting and merging
Marr operator
