SoilMATe: Soil Macronutrients and pH Level Assessment for Rice Plant through Digital Image Processing Using Artificial Neural Network

Abstract

In this study, digital image processing technique was used to efficiently identify the Macronutrients and pH level of Soil in the farmland of Philippines: (1) Nitrogen, (2) Phosphorus, (3) Potassium and (4) pH. The composition of the system is made of four sections namely, image acquisition, image processing, training system, and result. The Artificial neural network was applied in this study for its features that make it well suited in offering fast and accurate performance for the image processing. The system will base on 448 captured image data, 70% for training, 15% for testing and 15% for validation. Based on the result, the program will generate a report in printed form. Overall, this study identifies the soil macronutrient and pH level of the soil and gives fertilizer recommendation for inbred rice plant and was proven 98.33% accurate.