基于统计滤波的自适应双阈值改进canny算子边缘检测算法  

Adaptive Statistical Filtering Double Threshholds Based On Improved Canny Operator Edge Detection Algorithm

作　　者：段军[1] 高翔[2] 

机构地区：[1]内蒙古科技大学矿业研究院,内蒙古包头014000 [2]内蒙古科技大学信息工程学院,内蒙古包头014000

出　　处：《激光杂志》2015年第1期10-12,共3页Laser Journal

基　　金：国家自然科学基金名称:基于DLPCNN的平稳Contourlet域脑部多模医学图像副合算法研究(61261028)

摘　　要：通过介绍传统Canny算子边缘检测算法的基本原理,针对传统算法中存在的缺陷和问题,提出一种基于统计滤波的自适应双阈值的边缘检测算法;它通过统计滤波去除噪声有效的提高了算法的运算效率同时进一步抑制噪声对边缘检测的影响,以及基于简单统计的阈值选择算法,不再是人工选取阈值而是根据图像自身的特点自动选取合适的阈值,两者结合有效的提高了边缘检测算法的准确度和运算效率;这为图像分割技术的发展奠定了坚实的基础。By using the basic principle of the traditional Canny edge detection algorithm, a-iming at the defects and problems existing in the traditional algorithm, proposed an adaptiv-e statistical filtering algorithm of edge detection based on double threshold;it through statisti-cal filtering to remove noise effectively improves the algorithm’ s opera-tion efficiency and fur-ther inhibit the effect of noise on edge detection, and is based on simple the statistical thres-hold selection algorithm, is no longer a manual selection of threshold but to select the appr-opriate threshold automati-cally according to the characteristics of the image itself, both effec-tively improves the algorithm of edge detection ac-curacy and computational efficiency it laida solid foundation for the development of the technique of image segmentation.

关 键 词：统计滤波 简单统计 双阈值 边缘检测 自适应 CANNY算子 

分 类 号：TN911[电子电信—通信与信息系统]