RTF-RCNN: An Architecture for Real-Time Tomato Plant Leaf Diseases Detection in Video Streaming Using Faster-RCNN.

Area of Science:

• Agricultural Science
• Computer Vision
• Plant Pathology

Background:

• Tomato crops are vital globally, but susceptible to leaf diseases causing significant yield loss (40-60%).
• Effective disease detection mechanisms are essential for tomato production and food security.
• Traditional methods and earlier machine learning models show limitations in real-time disease identification.

Purpose of the Study:

• To develop and evaluate an advanced model for real-time detection of tomato plant leaf diseases.
• To compare the performance of the proposed model against existing techniques like AlexNet and Convolutional Neural Network (CNN).
• To enhance the accuracy and efficiency of plant disease diagnosis using image and video analysis.

Main Methods:

• Implementation of the real-time faster region convolutional neural network (RTF-RCNN) model.
• Utilizing both static images and real-time video streams for disease detection.
• Performance evaluation using key metrics: precision, accuracy, and recall, compared to AlexNet and CNN.

Main Results:

• The proposed RTF-RCNN model achieved a high accuracy of 97.42%.
• RTF-RCNN demonstrated superior performance compared to AlexNet (96.32%) and CNN (92.21%).
• The model effectively processed both image data and real-time video for disease identification.

Conclusions:

• The RTF-RCNN model offers a highly accurate and efficient solution for real-time tomato plant disease detection.
• This advanced deep learning approach can significantly aid farmers in timely disease management, reducing crop losses.
• The study highlights the potential of RTF-RCNN in agricultural applications for automated crop health monitoring.