Lights and pitfalls of convolutional neural networks for diatom identification

DSpace/Manakin Repository

Lights and pitfalls of convolutional neural networks for diatom identification

Show full item record

Title: Lights and pitfalls of convolutional neural networks for diatom identification
Author: Pedraza, Aníbal;Bueno, Gloria;Déniz, Óscar;Ruiz-Santaquiteria Alegre, Jesús;Sánchez Bueno, Carlos;Blanco Lanza, Saúl;Borrego Ramos, María;Olenici, Adriana;Cristóbal Pérez, Gabriel
xmlui.dri2xhtml.METS-1.0.item-contributor: Facultad de Ciencias Biologicas y Ambientales
xmlui.dri2xhtml.METS-1.0.item-area: Ecologia
Abstract: Diatom 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.
xmlui.dri2xhtml.METS-1.0.item-desfisica: P. 1-10
xmlui.dri2xhtml.METS-1.0.item-peerreviewed: SI
Publisher: SPIE
xmlui.dri2xhtml.METS-1.0.item-citation: Proceedings of SPIE, 2018, vol. 10679, 106790G
URI: http://hdl.handle.net/10612/9312
Date: 2018-05-24
xmlui.dri2xhtml.METS-1.0.item-tipo: info:eu-repo/semantics/article
Subject: Ecología. Medio ambiente
xmlui.dri2xhtml.METS-1.0.item-palclave: Deep learning
CNN
RCNN
YOLO
Diatoms detection
Water quality
Exportar referencia a Refworks:


Files in this item

Files Size Format View
Lights and pitfalls....pdf 3.459Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Search DSpace


Advanced Search

Browse

My Account

Statistics