A comparison of neural and statistical techniques in object recognition

The paper reports on an experimental comparison of two visual object recognition methods: a radial basis function network (RBFN) which is an artificial neural network, and a synthetic discriminant function network (SDFN) which classifies objects statistically via analysis with optimal spatial filters. Both methods require training with a set of images representative of the objects to be recognized. A comparative performance analysis was performed after training both networks with the same image sets. The algorithms were implemented on a Pentium-class PC under MS Windows NT 4.0. Training images were captured from a color CCD camera with standard NTSC resolution. Experiments were performed on both methods to determine the number of images per object necessary to train the networks, to estimate the two networks' accuracy of recognition, and to characterize their tolerance to image noise. It was found that when presented with a new image of one of the objects, RBFNs are more accurate at recognition than SDFNs. However, SDFNs are slightly more accurate in the presence of additive noise. Under the conditions of the experiments, RBFNs were found to provide an overall minimum classification accuracy of close to ninety percent.

[1]  S.J.J. Smith,et al.  Empirical Methods for Artificial Intelligence , 1995 .

[2]  D. Casasent,et al.  Minimum average correlation energy filters. , 1987, Applied optics.

[3]  B. V. Vijaya Kumar,et al.  Unconstrained correlation filters. , 1994, Applied optics.

[4]  B. V. Vijaya Kumar,et al.  Minimum-variance synthetic discriminant functions , 1986 .

[5]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[6]  D Casasent,et al.  Multivariant technique for multiclass pattern recognition. , 1980, Applied optics.

[7]  Sudeep Sarkar,et al.  Comparison of Edge Detectors: A Methodology and Initial Study , 1998, Comput. Vis. Image Underst..

[8]  Saleh Zein-Sabatto,et al.  Learning to grasp in unknown environment by reinforcement learning and shaping , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[9]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[10]  Robert Todd Pack,et al.  Ima: the intelligent machine architecture , 1998 .

[11]  I. Stakgold.  Green's Functions and Boundary Value Problems , 1979 .

[12]  A Mahalanobis,et al.  Distance-classifier correlation filters for multiclass target recognition. , 1996, Applied optics.

[13]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[14]  CentresMark,et al.  Regularisation in the Selection of Radial Basis Function , 1995 .

[15]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[16]  Joydeep Ghosh,et al.  Function Emulation Using Radial Basis Function Networks , 1997, Neural Networks.

[17]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[18]  Mark J. L. Orr,et al.  Regularization in the Selection of Radial Basis Function Centers , 1995, Neural Computation.

[19]  Sudeep Sarkar,et al.  Comparison of edge detectors: a methodology and initial study , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.