<![CDATA[Object recognition in images is a major challenge in digital image processing with wide applications, including agriculture. This research aims to develop a Convolutional Neural Network (CNN) model based on the Inception-ResNet-V2 architecture for insect pest classification in agriculture. The dataset contains 1,591 images from 13 pest classes, which were processed through preprocessing stages such as resizing, normalization, and augmentation to enhance data quality and variation. The model training process was conducted for 10 epochs, resulting in an accuracy of 89.52% with a loss of 0.4024. The research results indicate that the CNN model can be used to detect and classify insect pests with a high level of accuracy across several classes. This system is expected to help farmers identify pests more efficiently, support decision-making in pest control, and improve agricultural yields.]]>
Copyrights © 2025
