Texture Detection Using Neural Networks Trained on Examples of One Class

Authors:
Vic Ciesielski;Vinh Phuong Ha
Affiliations:
School of Computer Science and Information Technology, RMIT University, Melbourne, Australia 3001;School of Computer Science and Information Technology, RMIT University, Melbourne, Australia 3001
Venue:
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Year:
2009

Citing 8
Cited 0

One-class svms for document classification

The Journal of Machine Learning Research
Improving image retrieval performance by inter-query learning with one-class support vector machines

Neural Computing and Applications
Estimating the Support of a High-Dimensional Distribution

Neural Computation
An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification

Expert Systems with Applications: An International Journal
Image retrieval: Ideas, influences, and trends of the new age

ACM Computing Surveys (CSUR)
Combatting financial fraud: a coevolutionary anomaly detection approach

Proceedings of the 10th annual conference on Genetic and evolutionary computation
Texture Image Segmentation Based on Improved Wavelet Neural Network

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Texture segmentation by genetic programming

Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an approach to finding regions of a texture of interest in arbitrary images. Our texture detectors are trained only on positive examples and are implemented as autoassociative neural networks trained by backward error propagation. If a detector for texture T can reproduce an n ×n window of an image with a small enough error then the window is classified as T. We have tested our detectors on a range of classification and segmentation problems using 12 textures selected from the Brodatz album. Some of the detectors are very accurate, a small number are poor. The segmentations are competitive with those using classifiers trained with both positive and negative examples. We conclude that the method could be used for finding some textured regions in arbitrary images.