Local versus global evaluation of a cooperative fusion system for 3D image interpretation

Abstract

Information fusion approaches are more and more used in complex applications in which there is a real need to take into account several kinds of information simultaneously. Fusion systems become complex because they involve all the information treatment chain steps (from the extraction to the decision). A global evaluation of the fused result does not allow the end-users to adjust the numerous parameters and to efficiency interact with the system. This paper proposes a local approach to evaluate the mission completeness of each subpart of the fusion systems. For this, the main mission of each subpart needs to be well formulated and then, a mission achievement measurement will allow to quantify the performance of the subpart according to its objective and independently to the method used inside the subparts. The proposed measurement is based on an histograms comparison and the approach is then illustrated on a real cooperative fusion system devoted to 3D tomographic image interpretation.