一种用于管道缺陷的红外图像混合增强方法  

A Infrared Image Hybrid Enhancement Method for Pipeline Defect

作　　者：何依泽 朱冰[1] He Yize;Zhu Bing(College of Electronic Engineering,Xi’an Shiyou University,Xi’an,Shaanxi 710065,China)

机构地区：[1]西安石油大学电子工程学院,陕西西安710065

出　　处：《石油工业技术监督》2022年第12期1-4,35,共5页Technology Supervision in Petroleum Industry

基　　金：国家自然科学基金重大科研仪器研制项目“重型燃气轮机热障涂层系统的柔性阵列电磁声一体化无损评价仪器”(编号:11927801)。

摘　　要：为了更好地提取图像中的特征,使用深度学习法对管道缺陷进行识别,针对传统图像增强算法的优缺点,提出了一种混合图像增强算法。该方法首先将图像进行频移,然后使用傅里叶变换将其从空间域转换到频率域,利用低通和高通滤波器各自的优点,对原始图像分别进行滤波,得到图像低频灰度平坦部分和高频图像灰度变化幅度大的边缘区域;根据低频和高频部分在整幅图像中的占比,取其反比,对图像的低频部分和高频部分进行不同程度的增强,然后利用傅里叶逆变换将其转换回空间域得到处理后的图像。实验结果表明,该算法增强了原图像的边缘部分,并很好地保留了图像中较为平坦的部分,且未引入明显的振铃现象。In order to extract image features better,pipeline defects are recognized through deep learning.Aiming at the advantages and disadvantages of traditional image enhancement algorithms,a hybrid image enhancement algorithm is proposed.First,the frequency shift of the image is carried out,and then the image is converted from the spatial domain to the frequency domain using Fourier transform.Using the respective advantages of low-pass and high-pass filters,the original image is filtered respectively to obtain the low frequency gray level flat part of the image and the edge area of the image with large change amplitude of high frequency gray level.According to the proportion of low frequency and high frequency parts in the whole image,the low frequency and high frequency parts of the image are enhanced to varying degrees,and then they are converted back to the spatial domain by using the inverse Fourier transform to obtain the processed image.Experimental results show that the algorithm enhances the edge of the original image and preserves the flat part of the image,without introducing obvious ringing phenomenon.

关 键 词：图像增强 频率域 傅里叶变换 低通滤波 高通滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN219[自动化与计算机技术—计算机科学与技术]