Performance Analysis of ResNet50 Architecture based Pest Detection System

The objective of this research work is to categorize and identify various plant diseases at their earliest stages. Due to the late 20th century’s dramatic expansion in human population, there is an enormous demand for crops, fruits, and vegetables that much exceeds availability. Due to plant disease and pests, nearly more than 30% of crops are lost. Pests have a direct negative influence on crops because they eat the plants, spread illnesses, and open the door for bacterial, viral, and fungal growth. The illnesses and pests can be located by professionals using a visual check. However, it is quite expensive to continually consult professionals to treat sickness. Advance discovery of pests can help in reducing disease transmission to crops nearby, which is advantageous given the wastage factor. Artificial intelligence and algorithms of machine learning can be utilized for early detection. The identifying and categorization of various plant ailments may be done using deep learning techniques like Convolution Neural Network and Resnet. To identify and categorize the plant illness at an early stage, the suggested approach employs an object detection and picture recognition model. For the locally prevalent plant diseases brought on by pests, this model has been specifically trained to operate more accurately. This study assists in developing a creative solution to the problem and lessens harm to crops, vegetables, and fruits by identifying and eradicating pests early on.