2019
DOI: 10.1016/j.marmicro.2019.01.005
|View full text |Cite
|
Sign up to set email alerts
|

Automated species-level identification of planktic foraminifera using convolutional neural networks, with comparison to human performance

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

4
82
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 66 publications
(97 citation statements)
references
References 22 publications
4
82
0
Order By: Relevance
“…Coulibaly et al [27] applied CNN to identify mildew disease in pearl and developed an approach using transfer learning and feature extraction. Mitra et al [28] trained a CNN-based system to identify six species from microscope digital images and concluded that CNN architecture can provide the 'brain' for a viable robotic picking system. Imamverdiyev and Sukhostat [29] published an interesting geological application of CNN for lithofacies classification by employing different variables.…”
Section: Previous Studies On the Use Of Cnn In Geosciencesmentioning
confidence: 99%
“…Coulibaly et al [27] applied CNN to identify mildew disease in pearl and developed an approach using transfer learning and feature extraction. Mitra et al [28] trained a CNN-based system to identify six species from microscope digital images and concluded that CNN architecture can provide the 'brain' for a viable robotic picking system. Imamverdiyev and Sukhostat [29] published an interesting geological application of CNN for lithofacies classification by employing different variables.…”
Section: Previous Studies On the Use Of Cnn In Geosciencesmentioning
confidence: 99%
“…As a consequence, much research into using deep CNNs to automate image processing tasks in other fields is being performed. In the foraminifera domain, one current approach is using transfer learning with pre-trained ResNet50 and VGG networks to classify foraminifera images coloured according to 3D cues from 16-way lighting (Zhong et al, 2018;Mitra et al, 2019). Hsiang et al constructed a large planktonic foraminifera image set, Endless Forams, using multiple expert input, and then applied transfer learning using the VGG network to compare CNN-based classification with humans (Hsiang et al, 2019).…”
Section: B Deep Cnnsmentioning
confidence: 99%
“…For the trainable dense layers of the network, we use the same configuration as (Zhong et al, 2018;Mitra et al, 2019) consisting of a dropout layer with keep probability 0.05, size 512 dense layer, dropout layer with keep probability 0.15, size 512 dense layer and then a final dense layer with SoftMax activation for the class predictions.…”
Section: Transfer Learningmentioning
confidence: 99%
“…Supervised machine learning methods have previously been used to automate species identification for several microscopic taxa, including coccoliths (Beaufort & Dollfus, ), pollen grains (Gonçalves et al, ; Rodriguez‐Damian et al, ), phytoplankton (Sosik & Olson, ), hymenopterans (Rodner et al, ), diatoms (Urbánková et al, ), and dipterans and coleopterans (Valan et al, ). However, these techniques have only been applied in a limited way (i.e., few species, low sampling, limited image variability, and scope) to modern planktonic foraminifera (Macleod et al, ; Mitra et al, ; Ranaweera et al, ; Zhong et al, ), preventing their use as a general tool in this field. Computer vision provides a way to not only automate a task that relatively few researchers are trained to do (i.e., identify all species in a sample) but to also ensure a level of consistency and, at times, accuracy that can be difficult to achieve with human classifiers due to subjectivity and/or bias.…”
Section: Introductionmentioning
confidence: 99%