Skip to Main content Skip to Navigation
Journal articles

A new method to control error rates in automated species identification with deep learning algorithms

Abstract : Processing data from surveys using photos or videos remains a major bottleneck in ecology. Deep Learning Algorithms (DLAs) have been increasingly used to automatically identify organisms on images. However, despite recent advances, it remains difficult to control the error rate of such methods. Here, we proposed a new framework to control the error rate of DLAs. More precisely, for each species, a confidence threshold was automatically computed using a training dataset independent from the one used to train the DLAs. These species-specific thresholds were then used to post-process the outputs of the DLAs, assigning classification scores to each class for a given image including a new class called "unsure". We applied this framework to a study case identifying 20 fish species from 13,232 underwater images on coral reefs. The overall rate of species misclassification decreased from 22% with the raw DLAs to 2.98% after post-processing using the thresholds defined to minimize the risk of misclassification. This new framework has the potential to unclog the bottleneck of information extraction from massive digital data while ensuring a high level of accuracy in biodiversity assessment.
Document type :
Journal articles
Complete list of metadata

Cited literature [53 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-03002261
Contributor : Gérard Subsol <>
Submitted on : Thursday, November 12, 2020 - 5:29:22 PM
Last modification on : Tuesday, March 30, 2021 - 12:26:18 PM
Long-term archiving on: : Saturday, February 13, 2021 - 8:16:09 PM

File

s41598-020-67573-7.pdf
Files produced by the author(s)

Identifiers

Citation

Sébastien Villon, David Mouillot, Marc Chaumont, Gérard Subsol, Thomas Claverie, et al.. A new method to control error rates in automated species identification with deep learning algorithms. Scientific Reports, Nature Publishing Group, 2020, 10 (1), ⟨10.1038/s41598-020-67573-7⟩. ⟨lirmm-03002261⟩

Share

Metrics

Record views

115

Files downloads

80