Framework to Detect NPK Deficiency in Maize Plants Using CNN

Abstract

A balanced level of nutrients is very essential for healthy growth of plants. Deficiency of nutrients inhibits the growth of plants. It is needed to detect the infertile plants for the deficiency of nutrients at the early stage, so that proper fertilizers can be provided. In this paper, a framework is proposed by utilizing the images of nutrient-deficit leaves w.r.t. nitrogen (N), phosphorus (P), and potassium (K) of maize plant. A set of images contributes for bunch of dataset to be used as the training dataset. It is a non-invasive way of detecting nutrient deficiency in plants. The collected authentic training dataset of images is used to train the Inception V3 Convolutional Neural Network (CNN) model. The Inception V3 CNN uses transfer learning technique which is a research problem in machine learning. It concentrates on collecting the knowledge acquired while solving one problem and applying it to solve a related another problem. Therefore, features of maize leaf are extracted by the initial pretrained layers of CNN. Accurate and effective results are provided by speeding up the working of CNN. The given test image of maize leaf is provided to the trained CNN model which detects the nutrient deficiency in maize leaf as nitrogen, phosphorous, or potassium deficient accordingly. This framework can be applied in agricultural development in order to help farmers and to increase agricultural productivity.