{"title":"Flaw detection in vehicular wheel based on anti-geometric diffusion","authors":"Wu Yuan, Huang Qian, Situ Wuchao","doi":"10.1109/ICVES.2005.1563674","DOIUrl":null,"url":null,"abstract":"This paper presents a new method for detecting flaws in vehicular wheel based on anti-geometric diffusion. The classical image-processing methods for flaw detection can not produce a result with satisfaction, because the shape of the flaw can't be outlined exactly and these methods usually can do nothing about the flaw image with unhomogeneous lighting background. A new two-step technique is proposed in the paper. First, we use an anisotropic diffusion model to the flaw image with noise, this step can eliminate the noise and keep the shape of the flaws. Second, we use anti-geometric diffusion to the image, which is the result of first step, this step can track the flaws very accurately though unhomogeneous lighting background may be exist in the flaw image. Using this method, the flaws can be detected with high certainty. Our experiments also give the good results based on this new method.","PeriodicalId":443433,"journal":{"name":"IEEE International Conference on Vehicular Electronics and Safety, 2005.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE International Conference on Vehicular Electronics and Safety, 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICVES.2005.1563674","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This paper presents a new method for detecting flaws in vehicular wheel based on anti-geometric diffusion. The classical image-processing methods for flaw detection can not produce a result with satisfaction, because the shape of the flaw can't be outlined exactly and these methods usually can do nothing about the flaw image with unhomogeneous lighting background. A new two-step technique is proposed in the paper. First, we use an anisotropic diffusion model to the flaw image with noise, this step can eliminate the noise and keep the shape of the flaws. Second, we use anti-geometric diffusion to the image, which is the result of first step, this step can track the flaws very accurately though unhomogeneous lighting background may be exist in the flaw image. Using this method, the flaws can be detected with high certainty. Our experiments also give the good results based on this new method.