Rice variety identification system based on drone images to support seed certification process

Abstract

Utilization of technology can be a solution in the process of supervising certified seeds, especially at the stage of field inspection, which is faster and more efficient. This study aimed to develop a drone image-based rice variety system to support the inspection process for seed certification. The research was conducted from March – July 2022. The rice plants of IPB 3S and Inpari 32 varieties located in Karawang, West Java were observed for their agronomic characteristics. The images of the two varieties were taken using a drone and augmented and cropped. The overall image obtained was 80% used as training data, 20% as data validation, and 10% as test data. The variety identification system was built using a model by applying the convolutional neural network (CNN) algorithm. The performance of the model was observed through accuracy, precision, recall, and F1-Score. All agronomic characters justified that the two varieties used were different. This study produced three CNN models that could accurately identify the varieties of IPB 3S and Inpari 32 with an accuracy rate of 99.52% to 100%. Drone imaging is prospective for field inspection process of seed certification.
 Keywords: CNN, deep learning, image processing, seed production, unmanned aerial vehicle