Improving the Efficiency of Counting Defects by Learning RBF Nets with MAD Loss

Authors:
Ewaryst Rafajłowicz
Affiliations:
Institute of Computer Engineering, Control and Robotics, Wrocław University of Technology, Wrocław, Poland 50 370
Venue:
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Year:
2006

Citing 11
Cited 2

Lateral histograms for efficient object location: Speed versus ambiguity

Pattern Recognition Letters
On radial basis function nets and kernel regression: statistical consistency, convergence rates, and receptive field size

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Machine Vision: Theory, Algorithms, Practicalities

Machine Vision: Theory, Algorithms, Practicalities
Fast k-NN Classification Rule Using Metrics on Space-Filling Curves

ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2
MAD Loss in Pattern Recognition and RBF Learning

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Local Correlation and Entropy Maps as Tools for Detecting Defects in Industrial Images

International Journal of Applied Mathematics and Computer Science - Applied Image Processing
Nonlinear Image Processing and Filtering: A Unified Approach Based on Vertically Weighted Regression

International Journal of Applied Mathematics and Computer Science - Applied Image Processing
RBF neural network for probability density function estimation and detecting changes in multivariate processes

ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
Pattern recognition algorithms based on space-filling curves and orthogonal expansions

IEEE Transactions on Information Theory
On the construction and training of reformulated radial basis function neural networks

IEEE Transactions on Neural Networks

MAD Loss in Pattern Recognition and RBF Learning

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Pattern recognition with linearly structured labels using recursive kernel estimator

ICAISC'10 Proceedings of the 10th international conference on Artificial intelligence and soft computing: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The method of using a lateral histogram for evaluating the number of holes (e.g., defects) from images is known to be fast but rather inaccurate. Our aim is to propose a method of improving its performance by learning, but keeping the speed of the original method. This task is accomplished by considering a multiclass pattern recognition problem with linearly ordered labels and a loss function, which measures absolute deviations of decisions from true classes.