Owuor7/Ghana-crop-disease-detection-

# Crop Disease Detection for Sub-Saharan Africa # Introduction In Sub-Saharan Africa, crop diseases and pests are responsible for up to a 40% reduction in crop yields each year, posing a significant threat to food security and economic stability. With agriculture employing over 60% of the population and contributing roughly 23% of the region's GDP, these losses are especially detrimental. The increasing prevalence of crop diseases, driven by climate change and limited access to advanced agricultural technologies, has severely impacted key crops. Diseases such as tomato leaf curl virus and pepper blight are leading to major yield reductions, putting millions of livelihoods at risk. This project aims to develop a machine learning solution capable of accurately detecting and identifying diseases in three essential crops: corn, pepper, and tomato. By providing an accessible and reliable disease detection tool, this project hopes to support subsistence farmers in diagnosing crop issues early, minimizing losses, and enhancing food security in the region. #Objective The primary objectives of this project are to: Accurately Detect Multiple Diseases: Identify different diseases in corn, pepper, and tomato crops with high precision. The model will aim to generalize well to various conditions, even detecting previously unseen diseases. Deploy Efficiently on Edge Devices: Optimize the model for performance on low-cost smartphones, which are commonly used by subsistence farmers in Sub-Saharan Africa, enabling easy and quick disease identification in the field. By combining data insights with advanced machine learning, this project aims to deliver a solution that enhances crop productivity, sustainability, and food security for millions in the region. #Exploratory Data Analysis (EDA) The project begins with a comprehensive Exploratory Data Analysis (EDA) phase. This step is crucial to understand the patterns, distributions, and potential outliers in the dataset, which include …