This paper describes a probabilistic object recognition technique which does not require correspondence matching of images. This technique is an extension of our earlier work (1996) on object recognition using matching of multi-dimensional receptive field histograms. In the earlier paper we have shown that multi-dimensional receptive field histograms can be matched to provide object recognition which is robust in the face of changes in viewing position and independent of image plane rotation and scale. In this paper we extend this method to compute the probability of the presence of an object in an image. The paper begins with a review of the method and previously presented experimental results. We then extend the method for histogram matching to obtain a genuine probability of the presence of an object. We present experimental results on a database of 100 objects showing that the approach is capable recognizing all objects correctly by using only a small portion of the image. Our results show that receptive field histograms provide a technique for object recognition which is robust, has low computational cost and a computational complexity which is linear with the number of pixels.
[1]
Edward H. Adelson,et al.
The Design and Use of Steerable Filters
,
1991,
IEEE Trans. Pattern Anal. Mach. Intell..
[2]
Jitendra Malik,et al.
Computational framework for determining stereo correspondence from a set of linear spatial filters
,
1992,
Image Vis. Comput..
[3]
Max A. Viergever,et al.
General Intensity Transformations and Second Order Invariants
,
1992
.
[4]
Bernt Schiele,et al.
Object Recognition Using Multidimensional Receptive Field Histograms
,
1996,
ECCV.
[5]
Bernt Schiele,et al.
The Robustness of Object Recognition to View Point Changes Using Multidimensional Receptive Field Histograms
,
1996
.