Geometrical characterization of 3D defects by artificial vision

In this article, the authors propose a real-time method for the geometrical characterization of defects located on the surface of a 3D object. The algorithm is built from information contained on a 3D grid of the object to be controlled. The efficiency of the characterization method is judging experimentally.

[1]  R. Haralick.  Using perspective transformations in scene analysis , 1980 .

[2]  J. P. Cholley,et al.  Tampoprint inspection by artificial vision , 1993, Proceedings of IECON '93 - 19th Annual Conference of IEEE Industrial Electronics.

[3]  Norio Tagawa,et al.  A solder joint inspection system for surface mounted pin grid arrays , 1993, Proceedings of IECON '93 - 19th Annual Conference of IEEE Industrial Electronics.

[4]  Fatih Kurugollu,et al.  Quality inspection in PCBs and SMDs using computer vision techniques , 1994, Proceedings of IECON'94 - 20th Annual Conference of IEEE Industrial Electronics.

[5]  M. Dhome,et al.  2 - Etalonnage de caméra à partir d'images associées de sphères et de grilles , 1994 .

[6]  C. Fernandez,et al.  Vision system for on-line surface inspection in aluminum casting process , 1993, Proceedings of IECON '93 - 19th Annual Conference of IEEE Industrial Electronics.

[7]  C. Fernandez,et al.  On-line texture analysis for flat products inspection. Neural nets implementation , 1994, Proceedings of IECON'94 - 20th Annual Conference of IEEE Industrial Electronics.