Implementation of Artificial Neural Networks Using NVIDIA Digits and OpenCV for Coffee Rust Detection
Edwin Mauricio Torres Caballero, Alicia María Reyes Duke
Abstract
The Central American countries have accounted for millions of dollars of up to 500 million dollars due to coffee rust infections in their coffee plantations; a deadly disease that attacks coffee plants, causing this sequence to dry and completely discard its leaves until it can no longer produce coffee. The detection of this infection at the time, can prevent the spread over coffee fields, but the conventional method involves making recordings and performing visual supervision, so that the same conventional method incurs the spread of the disease; this research aims to train of two neural network, which can detect the presence of coffee rust in coffee plants, use NVIDIA Digits and the OpenCV open library in Visual Studio software to make a comparison between detecting and determining the percentage of precision.