Project Abstract

The timely and accurate detection of plant leaf diseases is crucial in securing agricultural productivity, ensuring food security, and promoting sustainable farming practices worldwide. However, conventional manual methods for disease identification are often imprecise, time-consuming, and require a lot of labor, hence the urgent need for efficient and scalable solutions that use advanced technologies. This study proposes the creation of a comprehensive smart agriculture system that seamlessly integrates image processing and deep learning techniques to automate the process of leaf disease detection and classification among multiple plant species. The project’s unique approach combines cutting-edge Machine Learning (ML) algorithm, like convolutional neural networks (CNN), with robust cloud computing infrastructure and user-friendly interfaces tailored specifically for farmers. Using a data-driven methodology, which includes acquiring high-quality leaf image datasets, preprocessing, augmentation, and model training, the system is expected to provide accurate and generalizable disease detection models capable of giving real-time insights and recommendations to farmers. Preliminary findings indicate the potential for reliable identification and classification of a wide range of leaf diseases, empowering farmers to make informed decisions, optimize farming practices, mitigate crop losses, and ultimately enhance yields and agricultural productivity. If successful, this research will provide a thorough and useful solution to the long-standing problem of plant disease detection, bridging the gap between modern technology and agricultural practices and opening up access to sophisticated machine learning tools and cloud computing resources, supporting the efficient and sustainable development of agriculture on a global scale.

Keywords: Data Science, Neural Network, cloud computing

 Conference Details

Session: Presentation Stream 28 at Presentation Slot 3

Location: GH001 at Wednesday 8th 13:30 – 17:00

Markers: Neil Carter, Gary Tam

Course: MSc Advanced Computer Science, Masters PG

Future Plans: I’m looking for work