摘要
按照仿生学原理,通过分析人眼的阈值亮度比曲线和weber比曲线,将图像根据背景亮度 划分为低暗区、中间区和高亮区,分别采用不同的公式计算边缘阈值。仿真表明,该方法能够根据边缘所处背景亮度自适应地选择阈值,从而检测出与人的主观视觉更为一致的图像边缘。
An image can be divided into low dark area, middle area and high bright area through analyzing threshold intensity function curves and Weber's law according to bionics principle and background brightness. The edge thresholds for the different areas are calculated according to the different equations, respectively. In this method simulation shows that the edge thresholds can be adaptively selected according to the located backgrounds, thus the image edge that is more consistent with human subjective vision can be detected.
出处
《光电工程》
CAS
CSCD
北大核心
2004年第2期59-62,共4页
Opto-Electronic Engineering
基金
国家973项目资助(2001CB309403)
关键词
边缘检测
图像分割
视觉模型
计算机视觉
Edge detection
Image segmentation
Visual model
Computer vision
