Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Unsupervised online clustering and detection algorithms using crowdsourced data for malaria diagnosis

Autor
Pagès-Zamora, A.; Cabrera-Bean, Margarita; Diaz, C.
Tipus d'activitat
Article en revista
Revista
Pattern recognition
Data de publicació
2019-02-01
Volum
86
Pàgina inicial
209
Pàgina final
223
DOI
https://doi.org/10.1016/j.patcog.2018.09.001 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/124243 Obrir en finestra nova
URL
https://www.sciencedirect.com/science/article/abs/pii/S0031320318303200 Obrir en finestra nova
Resum
Crowdsourced data in science might be severely error-prone due to the inexperience of annotators participating in the project. In this work, we present a procedure to detect specific structures in an image given tags provided by multiple annotators and collected through a crowdsourcing methodology. The procedure consists of two stages based on the Expectation–Maximization (EM) algorithm, one for clustering and the other one for detection, and it gracefully combines data coming from annotators ...
Paraules clau
Crowdsourcing, MalariaSpot, Online EM algorithm, Unreliable annotators, Unsupervised method
Grup de recerca
SPCOM - Grup de Recerca de Processament del Senyal i Comunicacions

Participants