Invariant object recognition using a neural template classifier

Abstract This paper describes an efficient two-stage neural network for invariant object recognition. It consists of a feature extractor trained by an ART-like fast saturation learning scheme and a delta-rule trained classifier. Objects, represented as edge strength maps derived from raw input images, are scaled to a normalized size and rotated in discrete steps to generate a sequence of localized input feature vectors. The network outputs identify the object and permit the calculation of a confidence level. Experiments show that the system works well even when there is noise and occlusion.

[1]  R. Wilson,et al.  Finite Prolate Spheroidal Sequences and their Applications II: Image Feature Description and Segmentation , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Bernard Widrow,et al.  Layered neural nets for pattern recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[3]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[4]  George Papadourakis,et al.  Object recognition using invariant object boundary representations and neural network models , 1992, Pattern Recognit..

[5]  R. Shepard,et al.  Mental Images and Their Transformations , 1982 .

[6]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[7]  Yehoshua Y. Zeevi,et al.  The Generalized Gabor Scheme of Image Representation in Biological and Machine Vision , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Alireza Khotanzad,et al.  Classification of invariant image representations using a neural network , 1990, IEEE Trans. Acoust. Speech Signal Process..

[9]  S. Marshall,et al.  Review of shape coding techniques , 1989, Image Vis. Comput..

[10]  Azriel Rosenfeld,et al.  Multiresolution image processing and analysis , 1984 .

[11]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[12]  Rafael M. Inigo,et al.  Multistaged neural network architecture for position invariant shape recognition , 1990, Other Conferences.

[13]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[14]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[15]  Elie Bienenstock,et al.  A neural network for invariant pattern recognition. , 1987 .

[16]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[17]  David C. Hogg.  Shape in machine vision , 1993, Image Vis. Comput..

[18]  James L. Crowley,et al.  A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[20]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[21]  Pascal Fua,et al.  Computational strategies for object recognition , 1992, CSUR.

[22]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

[23]  Rama Chellappa,et al.  A unified approach to boundary perception: edges, textures, and illusory contours , 1993, IEEE Trans. Neural Networks.

[24]  Daniel A. Pollen,et al.  Visual cortical neurons as localized spatial frequency filters , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[25]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[26]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[27]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[28]  S. Kung,et al.  VLSI Array processors , 1985, IEEE ASSP Magazine.

[29]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[30]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[31]  Stephen Grossberg,et al.  Invariant recognition of cluttered scenes by a self-organizing ART architecture: CORT-X boundary segmentation , 1989, Neural Networks.