Next Article in Journal
Insight in the Crystallization Kinetics of AlPO4-11 Molecular Sieve Using Di-Isopropylamine as Template
Previous Article in Journal
English–Welsh Cross-Lingual Embeddings
Article

Instance Segmentation of Microscopic Foraminifera

1
Department of Mathematics and Statistics, UiT The Arctic University of Norway, 9019 Tromsø, Norway
2
Department of Geosciences, UiT The Arctic University of Norway, 9019 Tromsø, Norway
3
Department of Community Medicine, UiT The Arctic University of Norway, 9019 Tromsø, Norway
*
Author to whom correspondence should be addressed.
Academic Editor: Dibyendu Sarkar
Appl. Sci. 2021, 11(14), 6543; https://doi.org/10.3390/app11146543
Received: 24 May 2021 / Revised: 9 July 2021 / Accepted: 11 July 2021 / Published: 16 July 2021
Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78 on the classification and detection task, and 0.80 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84 and 0.86, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera. View Full-Text
Keywords: foraminifera; instance segmentation; object detection; deep learning foraminifera; instance segmentation; object detection; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Johansen, T.H.; Sørensen, S.A.; Møllersen, K.; Godtliebsen, F. Instance Segmentation of Microscopic Foraminifera. Appl. Sci. 2021, 11, 6543. https://doi.org/10.3390/app11146543

AMA Style

Johansen TH, Sørensen SA, Møllersen K, Godtliebsen F. Instance Segmentation of Microscopic Foraminifera. Applied Sciences. 2021; 11(14):6543. https://doi.org/10.3390/app11146543

Chicago/Turabian Style

Johansen, Thomas H., Steffen A. Sørensen, Kajsa Møllersen, and Fred Godtliebsen. 2021. "Instance Segmentation of Microscopic Foraminifera" Applied Sciences 11, no. 14: 6543. https://doi.org/10.3390/app11146543

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop