• Aishwarya Borade
• Sonali Patil
• Anjali Giri
• Akshada Dani
• Damini Patil

The agricultural sector has a huge capacity to address food needs and provides wholesome, nutritious food. Insects damage a significant portion of the crops and degrade their quality, making finding agricultural insects challenging for farmers.The primary cause of crop quality decline are insects. And decrease harvest efficiency. It's critical to keep track of insects and assess useful and harmful insects. Early detection of insect attacks in agriculture is essential. Which will help farmers plan pest control and action against harmful insects. A computer vision and image analysis-based system can detect and classify crop insects more accurately and quickly at an early stage, assisting farmers to increase the yield of crop. This paper proposes a Yolov5 model architecture that detects and categorizes insects on crops. The objective is to solve the problem of identifying and classifying insects present in agricultural crops. To extract more properties of insects, we use multiscale training with a fully convolutional network.

Insect classification, insect detection, Yolov5, image processing, Machine learning

"Intelligent detection and classification of insects in agricultural farm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.k359-k366, May-2023, Available :http://www.jetir.org/papers/JETIR2305A50.pdf

"Intelligent detection and classification of insects in agricultural farm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppk359-k366, May-2023, Available at : http://www.jetir.org/papers/JETIR2305A50.pdf