Relative Comparison of K-means Clustering Segmented Rice Leaves Image Based Nitrogen, Phosphorus, and Potassium Nutrient Deficiency Classification Using Convolutional Neural Network

Rice is the most widely consumed staple food of Bangladesh. Rice plants are extremely affected by the primary nutrient shortage elements like nitrogen, phosphorus, and potassium. The rice leaves are influenced by the deficiency of primary nutrient ingredients, simultaneously. The unhealthy rice leaves are dominated by several colors and patterns. The proposed work in this presented paper aims to identify and classify the nitrogen, phosphorus, and potassium nutrient deficiency in rice leaves image. The experiment is conducted with a k-means clustering algorithm and convolutional neural network. Firstly, the rice leaf images are segmented with multiple K values by the k-means clustering algorithm so that defective leaves are accurately recognized for classification. Secondly, the different segmented images are employed by the classifier algorithm named convolutional neural network. As a result, the various K cluster value gives the accuracy that is 81%, 83%, 88%, 90%, 85%, 85%, and 79% respectively. Finally, the results are compared with respect to the K cluster value and extracted the standard K value from the k-means cluster numbers.