International FAIM Conference 24th : 2014 : San Antonio, TexasUniversity of Texas at San Antonio. Center for Advanced Manufacturing and Lean SystemsTseng, Tzu-Liang (Bill)Zheng, JunHo, Johnny C.Huang, Chun-CheOchoa, Luis A.Lin, YirongChiou, Richard2022-07-112022-07-112014http://dx.doi.org/10.14809/faim.2014.1099https://hdl.handle.net/20.500.12588/1054Paper presented at the Proceedings of the 24th International Conference on Flexible Automation & Intelligent Manufacturing, held May 20-23, 2014 in San Antonio, Texas, and organized by the Center for Advanced Manufacturing and Lean Systems, University of Texas at San AntonioIncludes bibliographical referencesIntense pressures for quality control are experienced by automotive parts suppliers to stay tuned in competitiveness and to build a long-term relationship with automotive manufacturers. The automotive parts suppliers are urged to contribute towards enhancing the overall quality of national car. E-quality is a process through which inspection of the process and quality of the part produced is done online resulting in the improvement of the process and reduction in the amount of time consumed for the overall process. Automated quality control involves using a methodology to classify the parts based on the damages or the dimensions of the features on a part. However, achieving high classification accuracy is not an easy task, especially in area of quality control where small differences in damages or dimensions result in part fall into a different category. And also the traditional 2D vision is not as reliable as 3D measurement due to the limitations of the technology and the structure of a part. In this study, a novel approach which integrates photometric stereo reconstruction and 3D measurement for 3D inspection is presented. The data extracted from brake caliper and lever brake was used as case study to demonstrate the proposed methodology. Results show that the new methodology yielded superior results compared to the traditional inspection approach with very high classification accuracy. Moreover, the proposed approach is capable to archive 3D models of the parts and achieve rapid quality control. This paper forms the basis for solving many other similar problems that occur in many industries.en-USAutomobiles--Brakes--Inspection--Quality controlAutomobile industry and trade--Quality control--AutomationThree-dimensional imagingSurfaces, Models ofComputer vision--Industrial applicationsArticle