摘要
现有的边缘检测算法对红外图像进行边缘提取的过程中,容易出现边缘模糊和噪声残留等现象;针对这种现象,提出了一种结合蚁群搜索与边缘检测的红外轮廓提取算法。根据小波变换后各高频子带间的相关性,引入了图像的相关性因子来对图像信号进行分类;并对提取的边缘信号进行基于蚁群算法的边缘检测算法进行边缘提取,来去除其中的噪声信号并对弱边缘信号进行保护。实验结果表明,其实验结果与预期效果基本相符,在不同复杂背景的红外图像中,都具有较好的边缘保护效果与抗干扰能力。
There are edge blur and noise residues in the course of edge extraction for infrared image by existing edge detection algorithm.In response to this phenomenon,an infrared contour extraction algorithm based on ants search and edge detection is put forward.The correlation factor of the image is introduced to classify image signals based on the wavelet transform correlation between each high frequency sub-band.The edge detection algorithm based on ant colony algorithm is used to extract the weak edge signal,then small noise signals are removed and the weak edge signals are protected.Experimental results show that the results are basically consistent with the expected results.It has a good anti-interference ability and edge protective effect in different complex background infrared images.
出处
《激光与红外》
CAS
CSCD
北大核心
2015年第6期722-727,共6页
Laser & Infrared
关键词
边缘检测
蚁群算法
小波变换
相关性
edge detection
ant colony algorithm
wavelet transform
correlation
