1Department of Biotechnology & Microbiology, Noida International University, Greater Noida, Gautam Budh Nagar - 201 310, Uttar Pradesh, India; Orcid Id : 0009-0001-5147-6856
2Department of Information Technology, Sathyabama Institute of Science and Technology, Chennai - 600 119, Tamil Nadu, India; Orcid Id : https://orcid.org/0000-0001-5798-7035
3Department of Agricultural Statistics, Faculty of Agricultural Sciences, Siksha ’O’ Anusandhan (Deemed to be University), Bhubaneswar - 751 030, Odisha, India; Orcid Id : 0000-0001-9335-8455
4Centre for Multidisciplinary Research, Anurag University, Hyderabad - 500 088, Telangana, India; Orcid Id : 0009-0007-8739-6640
5Quantum University Research Center, Quantum University, Roorkee - 247 667, Uttarakhand, India; Orcid Id : 0009-0004-3157-0695
6Centre of Research Impact and Outcome, Chitkara University, Rajpura - 140 417, Punjab, India; Orcid Id : https://orcid.org/0009-0004-6880-8716
Chitkara Centre for Research and Development, Chitkara University, Solan - 174 103, Himachal Pradesh, India
*Corresponding authors’ E-mail : abhinav.mishra.orp@chitkara.edu.in; Orcid Id : https://orcid.org/0009-0005-9856-6727
Online Published on 13 May, 2025.
This study discusses the integration of machine learning in automating insect species classification process, providing an efficient and reliable alternative. By utilizing advanced image processing and machine learning algorithms, we aim to improve the accuracy and speed of insect classification. A diverse dataset of insect wing images, which were subjected to preprocessing techniques to enhance image quality and extract relevant features was collected. Various machine learning models, including supervised and unsupervised algorithms, were trained and evaluated. The results indicate a significant improvement in classification accuracy compared to conventional methods, with deep learning architectures outperforming traditional approaches. Visualizations further illustrate the model’s effectiveness in distinguishing between various insect species based on wing patterns. These findings demonstrate that leveraging machine learning for the classification of insect wing patterns not only enhances accuracy but also streamlines the research process in entomology.
Automation, Biodiversity, Computer vision, Entomology, Image processing, Insect, Machine learning, Species identification, Supervised learning, Wing patterns
