Greenhow, Keith and Johnson, Colin G. (2014) Region Based Image Preprocessor for Feed-Forward Perceptron Based Systems. In: Zeng, Zhigang and Li, Yangmin and King, Irwin, eds. Advances in Neural Networks – ISNN 2014 11th International Symposium on Neural Networks. Lecture Notes in Computer Science . Springer, Cham, Switzerland, pp. 414-422. ISBN 978-3-319-12435-3. E-ISBN 978-3-319-12436-0. (doi:10.1007/978-3-319-12436-0_46) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:51436)
PDF
Publisher pdf
Language: English Restricted to Repository staff only |
|
|
|
Official URL: http://dx.doi.org/10.1007/978-3-319-12436-0_46 |
Abstract
In this paper, we investigate the notion that there may be alternate methods, beyond typical rectilinear interpolations such as Bilinear Interpolation, that have a greater suitability for use in visual/image preprocessors for Artificial Neural Networks. We present a novel method for down-sampling image data in preparation for a Feed-Forward Perceptron system assisted by a neural usefulness metric, inspired by those common to pruning algorithms. This new method achieves greater accuracy compared to the same system using by Bilinear Interpolation, and has a reduced computational time.
Item Type: | Book section |
---|---|
DOI/Identification number: | 10.1007/978-3-319-12436-0_46 |
Uncontrolled keywords: | artificial neural networks; preprocessor; image processing; salience; relevance assessment |
Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Depositing User: | Colin Johnson |
Date Deposited: | 04 Nov 2015 10:42 UTC |
Last Modified: | 17 Aug 2022 10:59 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/51436 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):