Mostrar el registro sencillo del ítem

dc.contributorFacultad de Ciencias Biologicas y Ambientaleses_ES
dc.contributor.authorPedraza Dorado, Aníbal
dc.contributor.authorBueno García, María Gloria
dc.contributor.authorDéniz Suárez, Óscar
dc.contributor.authorRuiz-Santaquiteria Alegre, Jesús
dc.contributor.authorSánchez Bueno, Carlos
dc.contributor.authorBlanco Lanza, Saúl 
dc.contributor.authorBorrego Ramos, María 
dc.contributor.authorOlenici, Adriana
dc.contributor.authorCristóbal Pérez, Gabriel
dc.contributor.otherEcologiaes_ES
dc.date2018-05-24
dc.date.accessioned2019-01-22T00:40:03Z
dc.date.available2019-01-22T00:40:03Z
dc.date.issued2019-01-22
dc.identifier.citationAnibal Pedraza, Gloria Bueno, Oscar Déniz, Jesus Ruiz-Santaquiteria,Carlos Sanchez, Saul Blanco, Maria Borrego-Ramos, Adriana Olenici,Gabriel Cristobal, "Lights and pitfalls of convolutional neural networks fordiatom identification," Proc. SPIE 10679, Optics, Photonics, and DigitalTechnologies for Imaging Applications V, 106790G (24 May 2018): doi:10.1117/12.2309488es_ES
dc.identifier.urihttp://hdl.handle.net/10612/9312
dc.descriptionP. 1-10es_ES
dc.description.abstractDiatom detection has been a challenging task for computer scientist and biologist during past years. In this work, the new state of art techniques based on the deep learning framework have been tested, in order to check whether they are suitable for this purpose. On the one hand, RCNNs (Region based Convolutional Neural Networks), which select candidate regions and applies a convolutional neural network and, on the other hand, YOLO (You Only Look Once), which applies a single neural network over the whole image, have been tested. The first one is able to reach poor results in out experimentation, with an average of 0.68 recall and some tricky aspects, as for example it is needed to apply a bounding box merging algorithm to get stable detections; but the second one gets remarkable results, with an average of 0.84 recall in the evaluation that have been carried out, and less aspects to take into account after the detection has been performed. Future work related to parameter tuning and processing are needed to increase the performance of deep learning in the detection task. However, as for classification it has been probed to provide succesfully performance.es_ES
dc.languageenges_ES
dc.publisherSPIEes_ES
dc.subjectEcología. Medio ambientees_ES
dc.subject.otherDeep learninges_ES
dc.subject.otherCNNes_ES
dc.subject.otherRCNNes_ES
dc.subject.otherYOLOes_ES
dc.subject.otherDiatoms detectiones_ES
dc.subject.otherWater qualityes_ES
dc.titleLights and pitfalls of convolutional neural networks for diatom identificationes_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.description.peerreviewedSIes_ES


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem