Development of Tomato Leaf Disease Detection using Single Shot Detector (SSD) Mobilenet V2
Purpose – To create a software prototype for the tomato leaf disease detection model to identify the tomato leaf condition and detect and identify the disease present in it.
Methodology – Using the TensorFlow 2 Object Detection API, the object detection model used is the Single Shot Detector (SSD) MobileNetV2 Object Detection model. The feature extractor used is the pre-trained TF2 MobileNetV2 model with the ImageNet dataset providing trained weights that allows feature extraction. Combining the pre-trained TF2 MobileNetV2 and Convolutional Neural Network (CNN) for SSD, the result object localization and image classification with SSD, and feature extractor pre-trained model.
Result – When training the model, at the 1300th step out of 6000 steps, the learning rate spiked from 0 to 0.7999. It then stabilized from 0.7999 and gradually decreased to 0.7796. After training, the total loss of the model is 46.95% for evaluation and 45.32% for training results. The average recall of the model is 94.51%, and the map of the model is 92.45%.
Conclusion – Using TF2 MobileNetV2 as the pre-trained feature extractor and, adding it with SSD layers was developed to detect the tomato leaf condition. The model can recognize a healthy tomato leaf, a tomato leaf with bacterial spot, and a tomato leaf with yellow leaf curl virus correctly 94.51% of the time, with a mean average precision of the model at 92.45%.
Recommendation – The prototype can be improved by increasing the number of tomato leaf image datasets and expanding the types of tomato leaf diseases. A mobile application for real-time plant detection can improve its user-friendliness and usability.
Practical Implications – The prototype can help farmers and consumers identify tomato leaf diseases, enabling them to introduce early cures, mitigation, or prevention of tomato plant diseases. Hence, help increase in production and harvest of healthy tomato fruits.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited.