Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures

Puffballs, a group of macrofungi belonging to the <i>Basidiomycota</i>, 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 propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Eda Kumru, Güney Ugurlu, Mustafa Sevindik, Fatih Ekinci, Mehmet Serdar Güzel, Koray Acici, Ilgaz Akata
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Biology
Subjects:
Online Access:https://www.mdpi.com/2079-7737/14/7/816
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418579837976576
author Eda Kumru
Güney Ugurlu
Mustafa Sevindik
Fatih Ekinci
Mehmet Serdar Güzel
Koray Acici
Ilgaz Akata
author_facet Eda Kumru
Güney Ugurlu
Mustafa Sevindik
Fatih Ekinci
Mehmet Serdar Güzel
Koray Acici
Ilgaz Akata
author_sort Eda Kumru
collection DOAJ
description Puffballs, a group of macrofungi belonging to the <i>Basidiomycota</i>, 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: <i>Apioperdon pyriforme</i>, <i>Bovista plumbea</i>, <i>Bovistella utriformis</i>, <i>Lycoperdon echinatum</i>, <i>L. excipuliforme</i>, <i>L. molle</i>, <i>L. perlatum</i>, and <i>Mycenastrum corium</i>. 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.
format Article
id doaj-art-ebeac2e58c63418d9b182b080bca16e2
institution Kabale University
issn 2079-7737
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Biology
spelling doaj-art-ebeac2e58c63418d9b182b080bca16e22025-08-20T03:32:24ZengMDPI AGBiology2079-77372025-07-0114781610.3390/biology14070816Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer ArchitecturesEda Kumru0Güney Ugurlu1Mustafa Sevindik2Fatih Ekinci3Mehmet Serdar Güzel4Koray Acici5Ilgaz Akata6Graduate School of Natural and Applied Sciences, Ankara University, Ankara 06830, TürkiyeDepartment of Computer Engineering, Faculty of Engineering, Başkent University, Ankara 06790, TürkiyeDepartment of Biology, Faculty of Engineering and Natural Sciences, Osmaniye Korkut Ata University, Osmaniye 80000, TürkiyeInstitute of Artificial Intelligence, Ankara University, Ankara 06100, TürkiyeDepartment of Computer Engineering, Faculty of Engineering, Ankara University, Ankara 06830, TürkiyeArtificial Intelligence and Data Engineering, Ankara University, Ankara 06830, TürkiyeDepartment of Biology, Faculty of Science, Ankara University, Ankara 06100, TürkiyePuffballs, a group of macrofungi belonging to the <i>Basidiomycota</i>, 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: <i>Apioperdon pyriforme</i>, <i>Bovista plumbea</i>, <i>Bovistella utriformis</i>, <i>Lycoperdon echinatum</i>, <i>L. excipuliforme</i>, <i>L. molle</i>, <i>L. perlatum</i>, and <i>Mycenastrum corium</i>. 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.https://www.mdpi.com/2079-7737/14/7/816puffballdeep learningfungal classificationCNN-transformer hybridimage classification
spellingShingle Eda Kumru
Güney Ugurlu
Mustafa Sevindik
Fatih Ekinci
Mehmet Serdar Güzel
Koray Acici
Ilgaz Akata
Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
Biology
puffball
deep learning
fungal classification
CNN-transformer hybrid
image classification
title Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
title_full Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
title_fullStr Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
title_full_unstemmed Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
title_short Hybrid Deep Learning Framework for High-Accuracy Classification of Morphologically Similar Puffball Species Using CNN and Transformer Architectures
title_sort hybrid deep learning framework for high accuracy classification of morphologically similar puffball species using cnn and transformer architectures
topic puffball
deep learning
fungal classification
CNN-transformer hybrid
image classification
url https://www.mdpi.com/2079-7737/14/7/816
work_keys_str_mv AT edakumru hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT guneyugurlu hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT mustafasevindik hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT fatihekinci hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT mehmetserdarguzel hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT korayacici hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures
AT ilgazakata hybriddeeplearningframeworkforhighaccuracyclassificationofmorphologicallysimilarpuffballspeciesusingcnnandtransformerarchitectures