Limited receptive area neural classifier for texture recognition of mechanically treated metal surfaces

Authors:
O. Makeyev;E. Sazonov;T. Baidyk;A. Martín
Affiliations:
Department of Electrical and Computer Engineering, Clarkson University, Potsdam, NY 13699, USA;Department of Electrical and Computer Engineering, Clarkson University, Potsdam, NY 13699, USA;Lab of Micromechanics and Mechatronics, CCADET, National Autonomous University of Mexico (UNAM), Cd. Universitaria, Mexico, D.F., 04510, Mexico;Lab of Micromechanics and Mechatronics, CCADET, National Autonomous University of Mexico (UNAM), Cd. Universitaria, Mexico, D.F., 04510, Mexico
Venue:
Neurocomputing
Year:
2008

Citing 6
Cited 2

Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons

International Journal of Computer Vision
One-class texture classifier in the CCR feature space

Pattern Recognition Letters
An Experimental Comparison of Non-Parametric Classifiers for Time-Constrained Classification Tasks

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Flat image recognition in the process of microdevice assembly

Pattern Recognition Letters
Backpropagation applied to handwritten zip code recognition

Neural Computation
Handbook of Parametric and Nonparametric Statistical Procedures

Handbook of Parametric and Nonparametric Statistical Procedures

Image recognition with neural classifiers in micromechanics and agriculture

NN'09 Proceedings of the 10th WSEAS international conference on Neural networks
Investigation of efficient features for image recognition by neural networks

Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

The limited receptive area (LIRA) neural classifier is proposed for texture recognition of mechanically treated metal surfaces. It may be applied in systems that have to recognize position and orientation of complex work pieces during micromechanical device assembly as well as in surface quality inspection systems. The performance of the proposed classifier was tested on a specially created image database with four texture types corresponding to metal surfaces after milling, polishing with sandpaper, turning with lathe and polishing with file. The promising recognition rate of 99.8% was obtained.