Object Recognition Using Multidimensional Receptive Field Histograms and its Robustness to View Point Changes
Bernt Schiele, James L. Crowley · 1995
This chapter presents 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 fields). 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 first part of the chapter summarizes the mathematical foundations of multidimensional Receptive Field Histograms [1] and gives a recognition example on a database of 103 objects. The second part of the chapter describes experiments to evaluate the robustness of multidimensional receptive field histograms to view point changes, using the Columbia image database [2]. In this experiment we examine the performance of different filter combinations, histogram matching functions and design parameter of the multidimensional histograms. 1. Introduction In [1] we generalized the color histogram approach of Swain and Ballard [3] to the use of ...