File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Boundary detection by artificial neural network
Title | Boundary detection by artificial neural network |
---|---|
Authors | |
Keywords | Image processing Parallel processing systems Real time systems |
Issue Date | 1993 |
Citation | Proceedings of the International Joint Conference on Neural Networks, 1993, v. 2, p. 1189-1194 How to Cite? |
Abstract | 'Active contour model - Snake', firstly suggested by Kass et al. in 1988, is a boundary detection scheme, which is known to be very effective for detecting boundary problematic to existing classical schemes. However, the requirement of heavy computation limited its practical application. Neural network, having a massively parallel architecture and being capable of processing huge amount of information in parallel manner, provides an alternative platform for real-time processing. In this paper, the 'Snake' formulation is first mapped to a generalized higher-order Hopfield network and finally a tunneling network, an alternative neural network suggested by Cheung & Lee in 1992, is adopted for the 'Snake' boundary detection scheme. Simulation performed manifests its feasibility and it's found that the solution obtained is better than some existing 'Snake' implementation. |
Persistent Identifier | http://hdl.handle.net/10722/65580 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cheung, Kwokwai | en_HK |
dc.contributor.author | Lee, Tong | en_HK |
dc.contributor.author | Chin, Roland T | en_HK |
dc.date.accessioned | 2010-08-31T07:16:16Z | - |
dc.date.available | 2010-08-31T07:16:16Z | - |
dc.date.issued | 1993 | en_HK |
dc.identifier.citation | Proceedings of the International Joint Conference on Neural Networks, 1993, v. 2, p. 1189-1194 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/65580 | - |
dc.description.abstract | 'Active contour model - Snake', firstly suggested by Kass et al. in 1988, is a boundary detection scheme, which is known to be very effective for detecting boundary problematic to existing classical schemes. However, the requirement of heavy computation limited its practical application. Neural network, having a massively parallel architecture and being capable of processing huge amount of information in parallel manner, provides an alternative platform for real-time processing. In this paper, the 'Snake' formulation is first mapped to a generalized higher-order Hopfield network and finally a tunneling network, an alternative neural network suggested by Cheung & Lee in 1992, is adopted for the 'Snake' boundary detection scheme. Simulation performed manifests its feasibility and it's found that the solution obtained is better than some existing 'Snake' implementation. | en_HK |
dc.language | eng | en_HK |
dc.relation.ispartof | Proceedings of the International Joint Conference on Neural Networks | en_HK |
dc.subject | Image processing | en_HK |
dc.subject | Parallel processing systems | en_HK |
dc.subject | Real time systems | en_HK |
dc.title | Boundary detection by artificial neural network | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.email | Chin, Roland T: rchin@hku.hk | en_HK |
dc.identifier.authority | Chin, Roland T=rp01300 | en_HK |
dc.description.nature | link_to_subscribed_fulltext | en_HK |
dc.identifier.scopus | eid_2-s2.0-0027848490 | en_HK |
dc.identifier.volume | 2 | en_HK |
dc.identifier.spage | 1189 | en_HK |
dc.identifier.epage | 1194 | en_HK |
dc.identifier.scopusauthorid | Cheung, Kwokwai=7402406586 | en_HK |
dc.identifier.scopusauthorid | Lee, Tong=54679920600 | en_HK |
dc.identifier.scopusauthorid | Chin, Roland T=7102445426 | en_HK |