Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
Biology · 05.07.2025 · 14 (7) · 816
DOI: 10.3390/biology14070816 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biology, online erschienen am 05.07.2025. Verfasst von Eda Kumru und 6 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Natural and Applied Sciences, Ankara University, Ankara 06830, Türkiye. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Puffballs, a group of macrofungi belonging to the Basidiomycota, pose taxonomic challenges due to their convergent morphological features, including spherical basidiocarps and similar peridial structures, which often hinder accurate species-level identification. This study proposes a deep learning-based classification framework for eight ecologically and taxonomically important puffball species: Apioperdon pyriforme, Bovista plumbea, Bovistella utriformis, Lycoperdon echinatum, L. excipuliforme, L. molle, L. perlatum, and Mycenastrum corium. A balanced dataset of 1600 images (200 per species) was used, divided into 70% training, 15% validation, and 15% testing. To enhance generalizability, images were augmented to simulate natural variability in orientation, lighting, and background. In this study, five different deep learning models (ConvNeXt-Base, Swin Transformer, ViT, MaxViT, EfficientNet-B3) were comparatively evaluated on a balanced dataset of eight puffball species. Among these, the ConvNeXt-Base model achieved the highest performance, with 95.41% accuracy, and proved especially effective in distinguishing morphologically similar species such as Mycenastrum corium and Lycoperdon excipuliforme. The findings demonstrate that deep learning models can serve as powerful tools for the accurate classification of visually similar fungal species. This technological approach shows promise for developing automated mushroom identification systems that support citizen science, amateur naturalists, and conservation professionals.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Natural and Applied Sciences, Ankara University, Ankara 06830, Türkiye.
- Department of Computer Engineering, Faculty of Engineering, Başkent University, Ankara 06790, Türkiye.
- Department of Biology, Faculty of Engineering and Natural Sciences, Osmaniye Korkut Ata University, Osmaniye 80000, Türkiye.
- Institute of Artificial Intelligence, Ankara University, Ankara 06100, Türkiye.
- Department of Computer Engineering, Faculty of Engineering, Ankara University, Ankara 06830, Türkiye.
- Artificial Intelligence and Data Engineering, Ankara University, Ankara 06830, Türkiye.
ORCID-Profile: Mustafa Sevindik, Fatih Ekinci, Mehmet Serdar Güzel, Koray Acici, Ilgaz Akata
Zitieren
APA
Kumru, E., Ugurlu, G., Sevindik, M., Ekinci, F., Güzel, M. S., Acici, K., & Akata, I. (2025). Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures. Biology, 14(7), 816. https://doi.org/10.3390/biology14070816
Vancouver
Kumru E, Ugurlu G, Sevindik M, Ekinci F, Güzel MS, Acici K, et al. Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures. Biology. 2025;14(7):816. doi:10.3390/biology14070816
BibTeX
@article{Kumru2025,
author = {Kumru, Eda and Ugurlu, Güney and Sevindik, Mustafa and Ekinci, Fatih and Güzel, Mehmet Serdar and Acici, Koray and Akata, Ilgaz},
title = {Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures},
journal = {Biology},
year = {2025},
volume = {14},
number = {7},
pages = {816},
doi = {10.3390/biology14070816}
}
EUVIMED