IMAGE-BASED IDENTIFICATION OF SUMATRA BUTTERFLY SPECIES USING DEEP LEARNING
Veredas do Direito · 22.05.2026 · 23 (8) · e236532
DOI: 10.18623/rvd.v23.6532 ↗Kurz gefasst
Fachartikel in der Zeitschrift Veredas do Direito, online erschienen am 22.05.2026. Verfasst von Rico Andrian und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Deep learning has gained momentum in the last decade for image-based species identification. We examine the classification of eight Sumatra butterfly species with a dataset of 800 photos from Gita Persada Butterfly Park using several deep learning architectures. The dataset was separated into training, validation, and testing subsets under controlled experimental circumstances. We evaluated seven architectures employing transfer learning with ImageNet pretrained weights, including convolutional neural networks (CNNs) and a Vision Transformer (ViT). The DenseNet201 model obtained the highest classification accuracy (99.38%), followed by ResNet50 and Xception (98.75%), MobileNet (97.50%), InceptionV3 (95.63%), ViT (93.75%), and EfficientNetB0 (85.63%). The performances of CNN-based models were more stable under the conditions of the present dataset, while MobileNet reached a good trade-off between accuracy and computational efficiency. The results must be viewed from the perspective of a tiny, single-site data collection. This was a controlled study and not a deployable field application as a standard for the identification of butterfly species from images. There was no external validation or field-based assessment. The results, therefore, give initial support for the possibility of deep learning for automated identification of butterfly species, but further validation using bigger and more diverse datasets is needed to determine model generalizability.
Zitieren
APA
Andrian, R., Syarif, A., Lumbanraja, F. R., & Rosa, E. (2026). IMAGE-BASED IDENTIFICATION OF SUMATRA BUTTERFLY SPECIES USING DEEP LEARNING. Veredas do Direito, 23(8), e236532. https://doi.org/10.18623/rvd.v23.6532
Vancouver
Andrian R, Syarif A, Lumbanraja FR, Rosa E. IMAGE-BASED IDENTIFICATION OF SUMATRA BUTTERFLY SPECIES USING DEEP LEARNING. Veredas do Direito. 2026;23(8):e236532. doi:10.18623/rvd.v23.6532
BibTeX
@article{Andrian2026,
author = {Andrian, Rico and Syarif, Admi and Lumbanraja, Favorisen R. and Rosa, Emantis},
title = {IMAGE-BASED IDENTIFICATION OF SUMATRA BUTTERFLY SPECIES USING DEEP LEARNING},
journal = {Veredas do Direito},
year = {2026},
volume = {23},
number = {8},
pages = {e236532},
doi = {10.18623/rvd.v23.6532}
}
EUVIMED