基于图像高频增强的塑料齿轮黑点缺陷高精度检测方法  

High Precision Detection Method of Plastic Gear Black Spots Defect Based on High Frequency Image Enhancement

作　　者：付泓豪 张岱凌 江澜 陈洪芳[4] Fu Honghao;Zhang Dailing;Jiang Lan;Chen Hongfang(School of Instrument Science and Engineering,Southeast University,Nanjing 211189,China;不详;Faculty of Materials and Manufacturing,Beijing Engineering Research Center of Precision Measurement Technology and Instruments,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]东南大学仪器科学与工程学院 [2]东南大学自动化学院 [3]上海大学中欧工程技术学院 [4]北京工业大学材料与制造学部,北京市精密测控技术与仪器工程技术研究中心

出　　处：《工具技术》2023年第4期132-136,共5页Tool Engineering

基　　金：国家自然科学基金(52175491)。

摘　　要：针对现有塑料齿轮端面黑点缺陷检测方法存在对较小黑点识别困难、误检和检测精度不足等问题,提出一种基于图像高频增强的塑料齿轮黑点缺陷高精度检测方法。对塑料齿轮图像的高低频信息进行提取与分离,再将高频信息乘以一定系数与低频信息线性叠加,实现图像高频部分的增强,从而使齿轮黑点更加突出;利用引导滤波进行降噪处理,将与黑点一同增强的其他无关信息(如纹理、噪声等)进行滤除或模糊,避免造成误检;使用LoG_Blob算法对处理后的图像进行斑点检测,进而获取齿轮黑点信息。实验结果表明,该方法能有效提升塑料齿轮黑点缺陷检测的精度。Aiming at the problems of the existing plastic gear face black spots defect detection methods,such as difficult to identify small black spots and insufficient detection accuracy,a high-precision detection method of plastic gear black point defect based on image high frequency enhancement is proposed.The high and low frequency information of plastic gear image is extracted and separated,and then the high frequency information is multiplied by a certain coefficient and the low frequency information linearly superimposed to enhance the high frequency part of the image,so that the gear black spots is more prominent.Subsequently,guided filtering is used for noise reduction,and other irrelevant information enhanced with black spots such as texture and noise are filtered or blurred to avoid false detection.Finally,the LoG_Blob algorithm is used to detect the speckle of the processed image,and then the black spots information of the gear is obtained.The experimental results show that the method can effectively improve the accuracy of plastic gear black spots defect detection.

关 键 词：塑料齿轮 缺陷检测 图像增强 高低频信息分离 BLOB算法 

分 类 号：TG86[金属学及工艺—公差测量技术] TH741[机械工程—光学工程]