Automatic Fungi Recognition: Deep Learning Meets Mycology
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Automatic Fungi Recognition : Deep Learning Meets Mycology. / Picek, Lukáš; Šulc, Milan; Matas, Jiří; Heilmann-Clausen, Jacob; Jeppesen, Thomas S.; Lind, Emil.
In: Sensors, Vol. 22, No. 2, 633, 2022.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Automatic Fungi Recognition
T2 - Deep Learning Meets Mycology
AU - Picek, Lukáš
AU - Šulc, Milan
AU - Matas, Jiří
AU - Heilmann-Clausen, Jacob
AU - Jeppesen, Thomas S.
AU - Lind, Emil
N1 - Publisher Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Artificial intelligence
KW - Classification
KW - Computer vision
KW - Fine-grained
KW - Fungi
KW - Machine learning
KW - Recognition
KW - Species
KW - Species recognition
U2 - 10.3390/s22020633
DO - 10.3390/s22020633
M3 - Journal article
C2 - 35062595
AN - SCOPUS:85122898591
VL - 22
JO - Sensors
JF - Sensors
SN - 1424-3210
IS - 2
M1 - 633
ER -
ID: 291214411