作者: C. Fernandez , C. Platero , P. Campoy , R. Aracil
DOI: 10.1109/IECON.1993.339356
关键词:
摘要: In this paper an automated visual inspection system is described within a general architecture for the online detection and analysis of surface defects in production continuous flat metallic products. Real-time performance requirements result development high-parallel high-speed image processing. Matrix cameras are used acquisition instead linear ones because appearance. Inspection achieved with 1 mm/sup 2/ resolution. Similarity-based algorithms as well texture have been developed hardware-implemented defect high-textured where, most defects, segmentation can not be by only means threshold techniques. The has applied to cast aluminum inspection, where up fifteen different kinds must detected classified. Online classification attempted formal language theory. >