On the analysis of neural networks for image processing
(2003) 7th Int. Conference on Knowledge-Based Intelligent Information and Engineering Systems (KES) 2774. p.950-957- 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 win describe them in terms of domain-dependent basic functions, which axe, 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 axe analyzed in the same way, enabling easy comparison.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/294930
- author
- van der Zwaag, BJ ; Slump, K and Spaanenburg, Lambert LU
- organization
- publishing date
- 2003
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Lecture Notes in Computer Science (Knowledge-Based Intelligent Information and Engineering Systems, Proceedings Pt 2)
- volume
- 2774
- pages
- 950 - 957
- publisher
- Springer
- conference name
- 7th Int. Conference on Knowledge-Based Intelligent Information and Engineering Systems (KES)
- conference location
- Oxford, United Kingdom
- conference dates
- 2003-09-03 - 2003-09-05
- external identifiers
-
- wos:000186518100130
- scopus:8344263831
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 978-3-540-40804-8
- DOI
- 10.1007/b12003
- language
- English
- LU publication?
- yes
- id
- ed960317-ac12-4a02-9f06-3db9189326c3 (old id 294930)
- date added to LUP
- 2016-04-01 11:45:25
- date last changed
- 2024-01-03 14:09:52
@inproceedings{ed960317-ac12-4a02-9f06-3db9189326c3, 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 win describe them in terms of domain-dependent basic functions, which axe, 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 axe analyzed in the same way, enabling easy comparison.}}, author = {{van der Zwaag, BJ and Slump, K and Spaanenburg, Lambert}}, booktitle = {{Lecture Notes in Computer Science (Knowledge-Based Intelligent Information and Engineering Systems, Proceedings Pt 2)}}, isbn = {{978-3-540-40804-8}}, issn = {{1611-3349}}, language = {{eng}}, pages = {{950--957}}, publisher = {{Springer}}, title = {{On the analysis of neural networks for image processing}}, url = {{http://dx.doi.org/10.1007/b12003}}, doi = {{10.1007/b12003}}, volume = {{2774}}, year = {{2003}}, }