Találati lista | Tudóstér

001-es BibID:	BIBFORM029656
Első szerző:	Antal Bálint (informatikus)
Cím:	An Ensemble Approach to Improve Microaneurysm Candidate Extraction / Bálint Antal, István Lázár, András Hajdu
Dátum:	2012
Megjegyzések:	In this paper, we present a novel approach to microaneurysm candidate extraction. To strengthen the accuracy of individual algorithms, we propose an ensemble of state-of-the-art candidate extractors. We apply a simulated annealing based method to select an optimal combination of such algorithms for a particular dataset. We also present a novel classification technique, which is based on a parallel ensemble of kernel density estimators. The experimental results show improvement in the positive likelihood rate compared to the individual candidate extractors
ISBN:	978-3-642-25205-1
Tárgyszavak:	Műszaki tudományok Informatikai tudományok könyvfejezet Biomedical image processing Image classification Medical decision-making Pattern recognition Statistics Bio-medical image processing Classification technique Data sets Kernel density estimators Medical decision making Microaneurysms Optimal combination Electronic commerce Image classification Image processing Pattern recognition Simulated annealing Statistics Algorithms
Megjelenés:	e-Business and Telecommunications : 7th International Joint Conference, ICETE, Athens, Greece, July 26-28, 2010 : Revised Selected Papers / eds. Mohammad S. Obaidat, George A. Tsihrintzis, Joaquim Filipe. - p. 378-394. -
További szerzők:	Lázár István (1986-) (programtervező matematikus) Hajdu András (1973-) (matematikus, informatikus)
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: