Analysis of Neural Networks for Edge Detection

Zwaag van der, Berend Jan and Slump, Kees and Spaanenburg, Lambert (2002) Analysis of Neural Networks for Edge Detection. In: ProRISC 2002, 13th Workshop on Circuits, Systems and Signal Processing, 28-29 November 2002, Veldhoven, the Netherlands.

Preview

PDF
282Kb

Abstract:	This paper illustrates a novel method to analyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, the elements of a feedforward-backpropagation neural network, that has been trained to detect edges in images, are described in terms of differential operators of various orders and with various angles of operation.
Item Type:	Conference or Workshop Item
Copyright:	©STW Technology Foundation
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Signals and Systems (SAS)
Link to this item:	http://purl.utwente.nl/publications/43578
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 206911