Object Recognition Using Multidimensional Receptive Field Histograms

This paper presents a technique to determine the identity of objects in a scene using 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. In this paper we describe the mathematical foundations of the technique and present the results of experiments which compare robustness and recognition rates for di erent local neighborhood operators and histogram similarity measurements.

• Type: Conference
• Year: 1996
• Where: ECCV
• Authors: Bernt Schiele, James L. Crowley
• Keywords: Computer Vision, ECCV 1996, Histogram Similarity Measurements, Linear Neighborhood Operators, Local Neighborhood Operators, Probable Objects