Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198102,
        author = {E.Abinaya and A.Hemavathi and M.Pavithra and B.Rasiba and M.Jenita},
        title = {Morphological feature extraction of microfauna using YOLOv8 and Efficientnet},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10620-10625},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198102},
        abstract = {Agriculture plays a vital role in the economy and food production systems of many countries. Crop productivity and quality are significantly influenced by environmental and biological factors, among which insects play a crucial role. Insects are broadly classified into beneficial insects (pollinators) and harmful insects (pests). Pollinators such as bees and butterflies support plant reproduction through pollination, thereby enhancing crop yield, while pests cause severe damage to crops, leading to reduced productivity and economic losses. In recent years, the rapid increase in pest populations and the decline of beneficial pollinators have posed serious challenges to farmers. A major contributing factor to this issue is the improper identification of insects. Traditional methods of insect identification rely on manual observation and experience, which are often time-consuming and prone to errors. Misidentification can result in the excessive use of pesticides, negatively impacting the environment, soil health, and beneficial insect populations. With advancements in Artificial Intelligence (AI) and Deep Learning, automated systems for accurate insect classification have become feasible. These systems can analyze images and detect complex patterns that are difficult for humans to recognize. This project proposes a web-based application that utilizes deep learning models, specifically EfficientNet and YOLOv8, for the classification of insects into pests and pollinators. In addition to classification, the system provides detailed biological information, including binomial nomenclature, diet, habitat, and taxonomy of the identified insect. The proposed solution aims to assist farmers, researchers, and students by enabling accurate insect identification, reducing unnecessary pesticide usage, and promoting sustainable and environmentally friendly agricultural practices.},
        keywords = {Insect Classification, Agriculture, Deep Learning, Artificial Intelligence, EfficientNet, YOLOv8, Image Processing, Sustainable Farming.},
        month = {April},
        }