Synergetic Neural Network Approach for Content-Based Retrieval of Trademarks
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | Proceedings of the Joint Conference on Information Sciences |
Pages | 484-487 |
Volume | 5 |
Publication status | Published - 2000 |
Publication series
Name | |
---|---|
Volume | 5 |
Conference
Title | Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000 |
---|---|
Place | United States |
City | Atlantic City, NJ |
Period | 27 February - 3 March 2000 |
Link(s)
Abstract
A application of synergetic neural network (SNN) for content based retrieval was developed that are robust against noise, partial occlusions and is capable of producing fast response to input queries. The SNN is a top-down self-organizing system, which incorporates many of the basic concepts of synergetics. The system enables to support affine invariant of input queries which are a partial version of the stored patterns. It was observed that the number of visual keywords do not increase even when new trademark images were added to the database.
Citation Format(s)
Synergetic Neural Network Approach for Content-Based Retrieval of Trademarks. / Zhao, Arlene T.; Ip, Horace H.S.; Qi, F. H.
Proceedings of the Joint Conference on Information Sciences. Vol. 5 2000. p. 484-487.
Proceedings of the Joint Conference on Information Sciences. Vol. 5 2000. p. 484-487.
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review