Aspects of 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 originate at the image acquisition and are mainly due to the projection of the world by the optical system, and the sampling and quantization in spatial and temporal dimensions which are necessary to obtain a digitized image. 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, the useful information about the scene can often be transformed such that it is conserved in some way in the image series. In this context, image fusion is the technique of reconstructing the useful information about a scene by means of sophisticated processing of an image series. That way, information can be gained that is not directly conceivable in a single image.