Selection of Superior Rice Seed Features Using Deep Learning Method

Abstract

Indonesia is a tropical country, known as an agricultural country, where 88.57% of the population works in the agricultural sector. Indonesia is rich in agricultural products such as rice, soybeans, corn, peanuts, cassava and sweet potatoes. Rice (Oryza sativia L) is one of the most dominant food commodities for the people of Indonesia. The carbohydrate content per 100 g of rice reaches 79.34 grams. The main benefit of rice is as a source of carbohydrates and a source of energy for the body. Seed is one of the factors that act as a carrier of technology in advanced agriculture, therefore the seeds used must be of good quality. Farmers tend to equate rice seeds from their previous harvests, the rice seed classification process is carried out manually through visual observation and soaking rice seeds in a container filled with water, submerged and floating rice seeds are selected for use, and those that float are discarded. But in reality it still produces less than optimal yields, for example rice that is less dense and broken. This research was conducted using the k Nearest Neighbor method which can classify by utilizing GLCM feature extraction which is an image texture analysis technique to produce features or information from image objects by calculating the contrast, energy, homogeneity and correlation values, then the best hyperplane will be displayed for distinguish between the two classes, namely superior and non-superior classes using the SVM model. This study aims to optimize yields with better quality. The results of this study were successfully carried out using k-Nearest Neighbor (k-NN) with Euclidean distance and k=5 got the highest accuracy of 92.85%. Indonesia is a tropical country, known as an agricultural country, where 88.57% of the population works in the agricultural sector. Indonesia is rich in agricultural products such as rice, soybeans, corn, peanuts, cassava and sweet potatoes. Rice (Oryza sativia L) is one of the most dominant food commodities for the people of Indonesia. The carbohydrate content per 100 g of rice reaches 79.34 grams. The main benefit of rice is as a source of carbohydrates and a source of energy for the body. Seed is one of the factors that act as a carrier of technology in advanced agriculture, therefore the seeds used must be of good quality. Farmers tend to equate rice seeds from their previous harvests, the rice seed classification process is carried out manually through visual observation and soaking rice seeds in a container filled with water, submerged and floating rice seeds are selected for use, and those that float are discarded. But in reality it still produces less than optimal yields, for example rice that is less dense and broken. This research was conducted using the k Nearest Neighbor method which can classify by utilizing GLCM feature extraction which is an image texture analysis technique to produce features or information from image objects by calculating the contrast, energy, homogeneity and correlation values, then the best hyperplane will be displayed for distinguish between the two classes, namely superior and non-superior classes using the SVM model. This study aims to optimize yields with better quality. The results of this study were successfully carried out using k-Nearest Neighbor (k-NN) with Euclidean distance and k=5 got the highest accuracy of 92.85%.