AGRINOVA EDGE: DEEP LEARNING-BASED MULBERRY DISEASE INTELLIGENCE

Using deep learning and mobile technology the work presents a workable advanced AI mulberry leaf disease diagnosis system. In addition, automatically accurately and instantly detecting mulberry leaf diseases developed system effectively addresses the shortcomings of traditional disease identification techniques. Using a labelled dataset, we trained a CNN model and used TensorFlow Lite to optimize it for mobile device deployment for effective on-device inference. The trained models are incorporated into an Android mobile app which allows users to snap a picture of a leaf or choose an image from the gallery to instantly obtain the disease prediction its degree of confidence and treatment suggestions. Since the entire system is mobile it can be used in remote and rural agricultural locations and operates offline with post-response time and data privacy. The system performs well in classifying both healthy and sick mulberry leaves under various backgrounds according to the experiment results. It can be an easy- to-use tool for farmers and agricultural advisors because of its portability and user-friendly interface. In summary the prototype systems overall performance is dependable and economical offering a helpful technique for enhancing crop management and lowering crop loss while also introducing cutting-edge artificial intelligence techniques into agriculture.  

1.           S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk and D. Stefanovic, “Deep Neural Networks- Based Recognition of Plant Diseases by Leaf Image Classification”, Computational Intelligence and Neuroscience vol 2016, pp. 1–11-2016. 2.           Mohanty S. P, Hughes D. P, and Salathe M, “Using Deep Learning for Image Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, pp. 1–10- 2016. 3.           I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. Cambridge, MA: MIT Press, 2016. 4.           TensorFlow Documentation, “TensorFlow: An End-to-End Open-Source Machine Learning Platform”. Available: https://www.tensorflow.org. 5.           TensorFlow Lite Documentation, “Deploy machine learning models on mobile and edge devices”. Available: https://www.tensorflow.org/lite. 6.                Kaggle, “Plant Disease Image Datasets” accessed  January  2020.  Available: https://www.kaggle.com. 7.                OpenCV Documentation, “Open-Source Computer Vision Library”. Available: https://opencv.org. 8.                Android Developers, “Android Application Development Documentation”.   Available: https://developer.android.com. 9.                Chollet F, Deep Learning with Python, Manning Publications Press, 2018. 10.            Available: https://code.visualstudio.com Visual Studio Code Documentation, VS Code for Python Development.