基于梯度幅值的自适应边缘检测算法  

A Self-adaptable Method of Edge-detection Based on the Gradient Magnitude

作　　者：刘建磊[1] 赵景秀[1] 李波[1] 

机构地区：[1]曲阜师范大学计算机科学学院,山东日照276826

出　　处：《光电子技术》2007年第3期174-177,共4页Optoelectronic Technology

基　　金：山东教委科技创新项目(J06B05);曲师大校科研基金项目(XJ0607)

摘　　要：提出了一种新的边缘检测算法。根据所提出的梯度幅值计算方法求出整幅图像的梯度幅值均值和图像中所有像素点的梯度幅值相对与均值的方差。由图像的梯度幅值均值和方差计算出图像的最佳阈值。然后根据提出的噪声剔除方法对由最佳阈值判定的初始边缘中的噪声进行剔除。实验结果表明所提出的算法在精确定位边缘的同时也较好地抑制了噪声。This paper present a new method for detection of the edges.The image＇s gradient magnitude mean and the variance of every pixel in the image relative to the gradient magnitude mean are calculated according to the method proposed in the paper.The best threshold value is calculated basing on the the gradient magnitude mean and the variance of the image.Then,the noise is eliminated by the method of eliminating noise proposed in the paper.The experimental results show that the new method could locate the edge accurately,and restrain noise of the images at the same time.

关 键 词：最佳阈值 自适应 边缘检测 梯度幅值 

分 类 号：TN911.73[电子电信—通信与信息系统]