轿车流线型曲面缺陷的图像识别与检测方法研究  

Research on image recognition and detection method for streamline curved surface defect of car

作　　者：苗佳[1] 赵永来[1] MIAO Jia;ZHAO Yonglai(Vocational and Technical College of Inner Mongolia Agricultural University,Baotou 014100,China)

机构地区：[1]内蒙古农业大学职业技术学院,内蒙古包头014100

出　　处：《现代电子技术》2017年第20期95-97,100,共4页Modern Electronics Technique

基　　金：国家自然科学基金(41161045)

摘　　要：提出一种基于灰度像素邻域模板匹配的轿车流线型曲面缺陷的图像识别与检测方法,采用图像处理方法进行轿车流线型曲面缺陷识别,提高轿车表面缺陷的智能修复能力。对采集的轿车表面图像进行降噪提纯处理,利用自适应权重均衡分割方法进行图像分割,采用Retinex信息增强方法进行曲面缺陷图像增强处理,结合灰度像素邻域模板匹配方法进行缺陷识别与检测。仿真结果表明,采用该方法进行轿车流线型曲面缺陷的图像识别,检测的准确匹配概率较高,对缺陷部位的定位较准,性能优越。For car′s streamline curved surface defect,an image recognition and detection method based on grayscale pixelneighborhood template matching is put forward in this paper.The image processing method is used to recognize the streamlinecurved surface defect of car to improve the intelligent repair ability of car′s surface defect.The captured surface image of the caris processed with noise reduction and purification.The adaptive weight balanced segmentation method is used for image segmen?tation.The Retinex information enhancement method is adopted to enhance the image with curved surface defect,and combinedwith the grayscale pixel neighborhood template matching method to recognize and detect the defect.The simulation results showthat the method has high accurate?matching probability for detection,precise positioning for defect parts and high performancewhile it is used to recognize the streamline curved surface defect of car.

关 键 词：图像识别 曲面缺陷 图像检测 Retinex信息增强 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]