First-order and multi-stage first-order image subsampling using a FANN-based pattern matching method

TitleFirst-order and multi-stage first-order image subsampling using a FANN-based pattern matching method
Publication TypeConference Paper
Year of Publication2000
AuthorsDumitras, A.
Conference NameNeural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Pagination446 -451 vol.5
KeywordsFANN-based pattern matching method, feedforward artificial neural networks, feedforward neural nets, high-order image subsampling, image matching, multistage first-order image subsampling
Abstract

We propose a method for image subsampling using feedforward artificial neural networks (FANN). Our method employs pattern matching in order to extract information about the presence of local edges. This information is then used to select the FANN desired output values during training. We show that, when applied to first-order and high-order image subsampling, our method effectively subsamples both high detail and smooth image areas, consistently outperforming traditional lowpass filtering and subsampling (LPFS) methods

URLhttp://dx.doi.org/10.1109/IJCNN.2000.861510
DOI10.1109/IJCNN.2000.861510

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2020 The University of British Columbia