15Investigation of Banana Plant Disease Detection Using Transfer Learning

R. Karthickmanoj1* and S. Aasha Nandhini2

1Department of Electrical and Electronics Engineering, Academy of Maritime Education and Training, Deemed to be University, Chennai, India

2Department of Electronics and Communication Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India

Abstract

Plant disease may severely reduce food supplies, potentially wiping off species variety. Early crop disease identification, using reliable or automated detection methods, can boost food output while decreasing financial losses. Deep learning has significantly improved the identification precision of picture classification and object recognition systems in recent years. As a result, in this research, a pretrained convolutional neural network (CNN) model is used to swiftly identify plant illnesses. The focus of the suggested model was on enhancing the hyper parameters of well-known pre-trained models like Mobile Net, ResNet-152, VGG-19, and Inception v3. The suggested model makes use of the ResNet152 architecture and intricate hidden layers tuned using random search tuning methods on the real-time dataset of banana leaf capture. Classification precision, recall, accuracy, and F1_score were used to assess the suggested model’s efficiency. There was also a comparison with other cutting-edge investigations. According to the findings, ResNet152 performed 98.3% better in classification accuracy tests ...

Get Smart Agritech now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.