摘要
针对雨刮器表面典型缺陷,比如擦伤、划痕、斑点(凹坑与砂眼)等,提出了一种基于机器视觉的雨刮器表面缺陷检测方法。首先根据CCD采集得到的雨刮器表面图像,对图像采用图像形态学处理与Gabor滤波相结合的方法,构建出图像预处理特定的结构元素,利用其对雨刮器表面纹理噪声进行抑制,并使用伽马灰度图像增强算法增强雨刮器缺陷与背景的对比度,然后采用图像最大熵阈值缺陷分割出雨刮器表面缺陷,最后实现金属雨刮器外壳表面典型缺陷特征提取与分类,并对相关缺陷进行尺寸计算。实验结果表明,文章提出的方法对工业生产中雨刮器表面典型缺陷检测速度达到平均0.724 s/根,具有良好的检测精度,能较好地适应于工业环境中。
Aiming at the common typical surface defects of wiper,such as scratches,spots(pits and sand holes),a method of wiper surface defect detection based on machine vision is proposed.Firstly,according to the surface image of the wiper collected by CCD,the image morphology processing and Gabor filtering method are used to suppress the texture noise of the metal frosting by designing specific structural elements of image preprocessing,and the gamma gray image enhancement algorithm is used to enhance the contrast between the wiper defect and the background.Then,the image maximum entropy threshold defect is used to segment the surface defects of the wiper.Finally,the feature extraction and classification of typical defects on the surface of the metal wiper shell are realized,and the size of the relevant defects is calculated.The experimental results show that the detection speed of the proposed method for typical surface defects of wiper in industrial production reaches an average of 0.724 s/piece,which has good detection accuracy and can be well adapted to the industrial environment.
作者
谢丹
贺福强
何昊
纪家平
XIE Dan;HE Fuqiang;HE Hao;JI Jiaping(College of Mechanical Engineering,Guizhou University,Guiyang 550025)
出处
《计算机与数字工程》
2024年第4期1221-1227,共7页
Computer & Digital Engineering
