基于改进同态滤波的带钢缺陷亮度不均匀校正算法  

A correction algorithm for uneven brightness of strip steel defects based on improved homomorphic filtering

作　　者：刘源[1] 夏春蕾[1] Liu Yuan;Xia Chunlei(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《电子测量技术》2021年第8期110-114,共5页Electronic Measurement Technology

摘　　要：在带钢表面缺陷自动化检测过程中,由于摄像机本身以及摄像环境的影响,会导致获取的图像出现不均匀的亮度,这对后续的缺陷图像分割和识别有较大的影响。基于此,提出了一种基于改进同态滤波的亮度不均匀校正方法,结合带钢表面缺陷特点对滤波器的截止频率进行重新选择,针对带钢图像的高低频分量采用不同的滤波函数分别进行处理,再用处理后的高低频分量重构得到亮度校正后的图像。实验结果表明,本文改进同态滤波亮度校正后的图像质量更高,用亮度校正后的图像质量参数Q值对其进行评价,该方法的平均Q值达到0.9014,相比其他方法的参数值更高。In the process of automatic strip steel surface defect detection,due to the influence of the camera itself and the camera environment,the acquired images will have uneven brightness,which has a greater impact on the subsequent defect image segmentation and recognition.Based on this,this paper proposes a brightness unevenness correction method based on improved homomorphic filtering,which combines the characteristics of strip surface defects to reselect the cutoff frequency of the filter,and uses different filter functions for the high and low frequency components of the strip image.After processing,the processed high and low frequency components are used to reconstruct the brightness-corrected image.The experimental results show that the improved homomorphic filtering in this paper has higher image quality after brightness correction.The image quality parameter Q value after brightness correction is used to evaluate it.The average Q value of the method reaches 0.9014,which is higher than the parameter values of other methods.

关 键 词：同态滤波 截止频率 亮度不均匀校正 带钢表面缺陷 

分 类 号：TN37[电子电信—物理电子学]