On the Analysis of Neural Networks for Image Processing

Zwaag van der, Berend Jan and Slump, Kees and Spaanenburg, Lambert (2003) On the Analysis of Neural Networks for Image Processing. In: 7th International Conference of Knowledge-based Intelligent Information and Engineering Systems, KES, September 3-5, 2003 , Oxford, UK.

Preview

PDF
335Kb

Abstract:	This paper illustrates a novel method to analyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, we will show analysis results of some feed-forward¿error-back-propagation neural networks for image processing. We will describe them in terms of domain-dependent basic functions, which are, in the case of the digital image processing domain, differential operators of various orders and with various angles of operation. Some other pixel classification techniques are analyzed in the same way, enabling easy comparison.
Item Type:	Conference or Workshop Item
Copyright:	© 2003 Springer
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Signals and Systems (SAS)
Link to this item:	http://purl.utwente.nl/publications/45400
Official URL:	http://dx.doi.org/10.1007/978-3-540-45226-3_130
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 212150