No abstract

This paper describes a method for an automatic detection of small dents in car bodies which are not visible until the paintwork. For an automatic error detection, two problems have to be solved: The accuracy of the measurement system has to be on a suficient level and the errors have be detected in the 3-d measurement data.The measuring of the surface shape can be done by an optical 3-d measurement system. This system consists of two cameras and one projector. The problem of error detection is solved by a method based on neural networks. The measurement data of one or more master workpieces is stored in the weights of a neural network. The calculation of the diflerence between the measurement data and the output of the neural network gives the resulting error surface.In this paper, a combination of both technologies is described. This dent detection method is illustrated by an example.

No abstract

No abstract

The monitoring of patients position during treatment in radiotherapy requires suitable real-time visualization tools which provide a maximum of information. Often, only Electronic Portal Images (EPls), which are of poor quality, exist for the dynamical verification of position deviations, whereas static image material of higher quality is available from diagnostics (and treatment planning. A framework for the fusion of static and dynamic multimodal image data is proposed, which is based on the several image sources existing in radior'herapy.