Robustness of Object Recognition to View Point Changes using Multidimensional Receptive Field Histograms

In SC96] we presented a technique to determine the identity of objects in a scene using multidimensional histograms of the responses of a vector of local linear neighborhood operators (receptive elds). This technique can be used to determine the most probable objects in a scene, independent of the object's position, image-plane orientation and scale. The present paper describes experiments to evaluate the robustness of multidimensional receptive eld histograms to view point changes, using the Columbia image database MN95]. In this experiment we examine the performance of diierent lter combinations, histogram matching functions and design parameter of the multidimensional histograms. The rst part of the paper summarizes the mathematical foundations of multidimensional Receptive Field Histograms. The second part of the paper shows the experimental evaluation of the robustness of the approach to view point changes (3D{rotation).