EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A structured literature review of computer vision methods for insect identification

Sudha Cheerkoot-Jalim iD, Camille Simon-Chane iD, Zarine Cadersaib iD, Zahra Mungloo-Dilmohamud, Aymeric Histace, Kavi Kumar Khedo, Leckraj Nagowah iD, Denis Sereno iD

Journal of Insect Science · 2026

DOI: 10.1093/jisesa/ieag050 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of Insect Science, 2026. Verfasst von Sudha Cheerkoot-Jalim und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information, Communication and Digital Technologies, University of Mauritius, Réduit, Mauritius. Hauptthemen laut MEDLINE: Insecta, Image Processing, Computer-Assisted, Entomology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union, HORIZON-MSCA-2021-SE-01.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated image-based identification of adult insects is increasingly critical to biodiversity monitoring, pest management, and vector surveillance, yet practical deployment remains limited by data scarcity, field variability, and fine-grained taxonomic challenges. We conducted a PRISMA-guided literature review of computer-vision methods for insect classification and identification. A Web of Science Core Collection search (31 August 2024) retrieved 930 records; after deduplication (n = 2) and screening, 230 articles underwent full-text quality assessment using weighted criteria for taxonomy/methods, image capture, computational technique, sample size, and performance evaluation. Of these, 111 high-quality studies met inclusion thresholds. Data were extracted on taxonomic coverage, optical devices and experimental settings, algorithms and pipelines, datasets, and outcome metrics. Deep learning dominated the field; You Only Look Once variants were common for detection and ResNet/EfficientNet/MobileNet for classification; occasional hybrids combined Convolutional Neural Network (CNN) features with traditional classifiers. CNN-based and 1-stage detectors outperformed hand-crafted pipelines; transformers and self-supervised pre-training showed promise with limited labels. Despite strong laboratory performance, generalization to field conditions was hindered by illumination, occlusion, and pose variability. Public datasets were scarce and geographically skewed, limiting reproducibility and equitable benchmarking. Taxonomic coverage concentrated on Lepidoptera, Diptera, Hemiptera, and Coleoptera. We recommend advancing the field through comprehensive reporting beyond overall accuracy, the design of lifecycle-aware and domain-adapted models validated under field conditions, the establishment of diverse benchmarks with standardized imaging protocols, and the development of interpretable architectures suitable for deployment in embedded trapping systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

InsectaImage Processing, Computer-AssistedEntomologyAnimalsConvolutional Neural NetworksClassification AlgorithmsDetection AlgorithmsDeep Learning

Stichwörter der Autor:innen

AIentomologysurveillance

Autor:innen und Institutionen

  • Faculty of Information, Communication and Digital Technologies, University of Mauritius, Réduit, Mauritius.
  • ETIS UMR 8051, CY Cergy Paris University, ENSEA, CNRS, Cergy, France.
  • InterTryp IRD-CIRAD, Université de Montpellier, Montpellier, France.
  • GoInsEct: Global Entomology and Infectiology Research Group, Montpellier, France.

ORCID-Profile: Sudha Cheerkoot-Jalim, Camille Simon-Chane, Zarine Cadersaib, Leckraj Nagowah, Denis Sereno

Förderung

  • European Union
  • HORIZON-MSCA-2021-SE-01

Zitieren

APA

Cheerkoot-Jalim, S., Simon-Chane, C., Cadersaib, Z., Mungloo-Dilmohamud, Z., Histace, A., Khedo, K. K., Nagowah, L., & Sereno, D. (2026). A structured literature review of computer vision methods for insect identification. Journal of Insect Science. https://doi.org/10.1093/jisesa/ieag050

Vancouver

Cheerkoot-Jalim S, Simon-Chane C, Cadersaib Z, Mungloo-Dilmohamud Z, Histace A, Khedo KK, et al. A structured literature review of computer vision methods for insect identification. Journal of Insect Science. 2026. doi:10.1093/jisesa/ieag050

BibTeX
@article{CheerkootJalim2026,
  author = {Cheerkoot-Jalim, Sudha and Simon-Chane, Camille and Cadersaib, Zarine and Mungloo-Dilmohamud, Zahra and Histace, Aymeric and Khedo, Kavi Kumar and Nagowah, Leckraj and Sereno, Denis},
  title = {A structured literature review of computer vision methods for insect identification},
  journal = {Journal of Insect Science},
  year = {2026},
  doi = {10.1093/jisesa/ieag050}
}
Kostenlos starten →