Hunter, Andrew (1996) Connectionist median filtering networks. Image and vision computing, 14 (4). pp. 277-283. ISSN 0262-8856

Full text not available from this repository. (Request a copy)

Abstract

A family of connectionist rank filtering networks is presented, suitable for real-time median filtering. It is demonstrated that these have low complexity (from O(N2) processing elements and connections for a single output N element filter to O(N2) for a fully parallelised N × N filter). The networks have some unusual requirements in terms of processing elements and topology compared with the standard neural network models. The feasibility of VLSI implementation of the networks is discussed

Item Type:	Article
Additional Information:	A family of connectionist rank filtering networks is presented, suitable for real-time median filtering. It is demonstrated that these have low complexity (from O(N2) processing elements and connections for a single output N element filter to O(N2) for a fully parallelised N × N filter). The networks have some unusual requirements in terms of processing elements and topology compared with the standard neural network models. The feasibility of VLSI implementation of the networks is discussed
Keywords:	Median filtering, Connectionist networks, VLSI implementation
Subjects:	G Mathematical and Computer Sciences > G400 Computer Science
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Rosaline Smith
Date Deposited:	14 Jul 2010 13:18
Last Modified:	18 Jul 2011 16:27
URI:	http://eprints.lincoln.ac.uk/id/eprint/2781

Actions (login required)

View Item