基于数学形态学的红外图像边缘检测算法  

Edge Detection Algorithm of Infrared Image Based on Mathematical Morphology

作　　者：宁柏隆[1] 李春丽 肖义[1] 

机构地区：[1]重庆邮电大学,重庆400065 [2]大连供水有限公司,辽宁大连116021

出　　处：《电光系统》2012年第1期1-4,共4页Electronic and Electro-optical Systems

摘　　要：针对红外图像受噪声影响较大及传统边缘检测算法对噪声非常敏感的问题，文章提出一种基于多结构双尺度算子的数学形态学检测算法。该方法先用双尺度结构元素对图像进行滤除噪声，再用多结构元素对图像边缘各方向进行检测，通过权值计算将各方向边缘融合得到图像边缘。实验结果表明：该方法不但具有很好的抗噪性，而且还能有效地将边缘提取出来。The noise influence on infrared images is very great and the traditional edge detection algorithm is ver- y sensitive to noise. The paper proposed a mathematical morphology detection method based on multi-structure and double-scale operator. The double-structural elements were used to filter out the noise of the image, while the multi-scale structural elements were used to detect directions of the image edge, and weight-calculation to get the image edge. The experimental results show that this method not only has good noise immunity, hut can also detect effectively the edge of the image.

关 键 词：数学形态学 边缘检测 多尺度 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]