Journal cover Journal topic
Climate of the Past An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.536 IF 3.536
  • IF 5-year value: 3.967 IF 5-year
  • CiteScore value: 6.6 CiteScore
  • SNIP value: 1.262 SNIP 1.262
  • IPP value: 3.90 IPP 3.90
  • SJR value: 2.185 SJR 2.185
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 71 Scimago H
    index 71
  • h5-index value: 40 h5-index 40
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  09 Jul 2020

09 Jul 2020

Review status
This preprint is currently under review for the journal CP.

A new automated radiolarian image acquisition, stacking, processing, segmentation, and identification workflow

Martin Tetard1, Ross Marchant1,a, Giuseppe Cortese2, Yves Gally1, Thibault de Garidel-Thoron1, and Luc Beaufort1 Martin Tetard et al.
  • 1Aix Marseille Univ, CNRS, IRD, Coll France, INRAE, CEREGE, Aix-en-Provence, France
  • 2GNS Science, Lower Hutt, New Zealand
  • apresent address: School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, Australia

Abstract. Identification of microfossils is usually done by expert taxonomists and requires time and a significant amount of systematic knowledge developed over many years. These studies require manual identification of numerous specimens in many samples under a microscope, which is very tedious and time consuming. Furthermore, identification may differ between operators, biasing reproducibility. Recent technological advances in image acquisition, processing, and recognition now enable automated procedures for this process, from microscope image acquisition to taxonomic identification.

A new workflow was developed for automated radiolarian image acquisition, stacking, processing, segmentation, and identification. The protocol includes a newly proposed methodology for preparing radiolarian microscopic slides. We mount 8 samples per slide, using a recently developed 3D-printed decanter that enable the random and uniform settling of particles, and minimise the loss of material. Once ready, slides are automatically imaged using a transmitted light microscope. About 4000 specimens per slide (500 per sample) are captured in digital images which include stacking techniques to improve their focus and sharpness. Automated image processing and segmentation is then performed using a custom plugin developed for the ImageJ software. Each individual radiolarian image is automatically classified by a convolutional neural network (CNN) trained on a radiolarian database (currently 17,065 images, corresponding to 112 classes) using the software, ParticleTrieur.

The trained CNN has an overall accuracy of about 90 %. The whole procedure, including the image acquisition, stacking, processing, segmentation and recognition, is entirely automated via a LabVIEW interface, and takes approximately 1 hour per sample. Census data count and classified radiolarian images are then automatically exported and saved. This new workflow paves the way for the analysis of long-term, radiolarian-based palaeoclimatic records from siliceous remains-bearing samples.

Martin Tetard et al.

Interactive discussion

Status: open (until 03 Sep 2020)
Status: open (until 03 Sep 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Martin Tetard et al.

Martin Tetard et al.


Total article views: 172 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
94 53 25 172 22 22
  • HTML: 94
  • PDF: 53
  • XML: 25
  • Total: 172
  • BibTeX: 22
  • EndNote: 22
Views and downloads (calculated since 09 Jul 2020)
Cumulative views and downloads (calculated since 09 Jul 2020)

Viewed (geographical distribution)

Total article views: 182 (including HTML, PDF, and XML) Thereof 182 with geography defined and 0 with unknown origin.
Country # Views %
  • 1



No saved metrics found.


No discussed metrics found.
Latest update: 12 Aug 2020
Publications Copernicus
Short summary
Radiolarians are marine micro-organisms that produce a siliceous shell that is preserved in the fossil record, and can be used to reconstruct past climate variability. However, their study is only possible after a time-consuming manual picking of their shells from the sediment followed by their individual identification. We thus develop a new fully automated workflow consisting in microscopic radiolarian image acquisition, image processing, and identification using artificial intelligence.
Radiolarians are marine micro-organisms that produce a siliceous shell that is preserved in the...