IMAGE FUSION FOR AUTOMATED VISUAL INSPECTION

In automated visual inspection, the evaluation of only one image is often not sufficient to obtain the desired information on a scene. Shortcomings originated from the image acquisi-tion are caused by the projection of the world, the sampling and the quantization in spatial and temporal dimensions. In consequence, image acquisition is always a non-injective mapping. However, by acquiring image series where at least one acquisition parameter has been varied systematically, many relevant properties of the scene can be transferred into features that are in some way conserved in the image series. In this context, image fusion is the technique of gaining useful information about the scene by means of a sophisticated processing of an image series. That way, information can be gained that is not directly con-ceivable in a single image