基于视觉感知模型修正的彩色图像边缘检测  

Edge Detection Based on Modified Visual Perceptual Model for Color Image

作　　者：雷涛[1,2] 樊养余[2] 王毅[2] 王小鹏[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070 [2]西北工业大学电子信息学院,陕西西安710072

出　　处：《电子学报》2013年第10期1903-1910,共8页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61202314,No.61261029,No.60903127);中国博士后科学基金(No.2012M521801);甘肃省青年科技研究基金(N2010GS04061)

摘　　要：在彩色图像边缘检测过程中,准确检测低照度区域的细节边缘是一个难题.提出了一种基于视觉感知模型修正的彩色图像边缘检测方法.由于视觉感知彩色空间中的色调分量具有圆形特性,导致伪边缘问题,利用色调距离计算色调图像的梯度以去除伪边缘,并根据饱和度的非线性函数控制色调分量的梯度,最后利用修正的视觉感知模型计算矢量梯度以获取彩色图像的边缘.实验结果表明,新的彩色边缘检测方法较现有方法能提高彩色图像的边缘检测精度,尤其对于低照度区域的细节边缘具有较好的响应.In the process of color image edge detection,it is very difficult for the extraction of detail edges in the areas with low i/luminadon. A novel method of color image edge detection based on modified visual perception model is proposed in this pa- per. Because hue component is represented by circular data, it easily leads to the false edges. Firstly, we use hue distance to calculate the gradient of hue component,and then use non-linear function whose variant is saturation to control the change of gradient of hue component. Finally, the edges of color image can be detected by computing vector gradient in modified visual perceptual model. Ex- perimental results show that the proposed method can obtain higher accuracy of edge detection than the existing approaches. Espe- cially, the gmoosed method has a good response for edge details in areas with low illumination.

关 键 词：边缘检测 彩色图像处理 色调分量 梯度算子 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]