Next Article in Journal
A Collision Relationship-Based Driving Behavior Decision-Making Method for an Intelligent Land Vehicle at a Disorderly Intersection via DRQN
Previous Article in Journal
A Trust Management Model for IoT Devices and Services Based on the Multi-Criteria Decision-Making Approach and Deep Long Short-Term Memory Technique
Previous Article in Special Issue
Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization
Article

Automatic Fungi Recognition: Deep Learning Meets Mycology

1
Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, 30100 Pilsen, Czech Republic
2
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, 16636 Prague, Czech Republic
3
Center for Macroecology, Evolution and Climate, Biological Institute, University of Copenhagen, 1165 Copenhagen, Denmark
4
Global Biodiversity Information Facility, 2100 Copenhagen, Denmark
*
Author to whom correspondence should be addressed.
Academic Editor: Mark Shortis
Sensors 2022, 22(2), 633; https://doi.org/10.3390/s22020633
Received: 8 November 2021 / Revised: 3 January 2022 / Accepted: 4 January 2022 / Published: 14 January 2022
(This article belongs to the Special Issue Deep Learning Applications for Fauna and Flora Recognition)
The article presents an AI-based fungi species recognition system for a citizen-science community. The system’s real-time identification too — FungiVision — with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset — Danish Fungi 2020 (DF20) — with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities. View Full-Text
Keywords: fungi; species; classification; recognition; machine learning; computer vision; species recognition; fine-grained; artificial intelligence fungi; species; classification; recognition; machine learning; computer vision; species recognition; fine-grained; artificial intelligence
Show Figures

Figure 1

MDPI and ACS Style

Picek, L.; Šulc, M.; Matas, J.; Heilmann-Clausen, J.; Jeppesen, T.S.; Lind, E. Automatic Fungi Recognition: Deep Learning Meets Mycology. Sensors 2022, 22, 633. https://doi.org/10.3390/s22020633

AMA Style

Picek L, Šulc M, Matas J, Heilmann-Clausen J, Jeppesen TS, Lind E. Automatic Fungi Recognition: Deep Learning Meets Mycology. Sensors. 2022; 22(2):633. https://doi.org/10.3390/s22020633

Chicago/Turabian Style

Picek, Lukáš, Milan Šulc, Jiří Matas, Jacob Heilmann-Clausen, Thomas S. Jeppesen, and Emil Lind. 2022. "Automatic Fungi Recognition: Deep Learning Meets Mycology" Sensors 22, no. 2: 633. https://doi.org/10.3390/s22020633

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