Year: 2025
Type: article
Abstract: ABSTRACT One of the biggest problems in agriculture is pest infestation, which lowers productivity and causes losses. Conventional pest detection methods are not appropriate for large-scale farming because they are laborious, inaccurate, and expensive. This project uses deep learning and image processing techniques to develop an automated earlier pest type detection system. CNN and ResNet models are used to preprocessed pictures of maize and rice leaves. According to experimental data, the CNN model outperformed the ResNet model in terms of pest classification, with a higher accuracy of 98.7% and a smaller loss. The method encourages sustainable agriculture, lessens the overuse of pesticides, and facilitates early pest identification with preventative measures included. Keywords: Pest Detection, Image Processing, Deep Learning, Pest Classification, CNN, Resnet
DOI: 10.55041/ijsrem52762
Authors: Poornima B H, Sandhya M N, Basavanna M
Institution: Davangere University
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: bronze
OpenAlex ID: W4414556208
FWCI:
Cites:
Cited by:
Related to: