A Numerical Procedure for Supporting Garlic Root Trimming Machines Using Deep Learning Algorithms

Abstract

Smart agricultural machinery is indispensable for modern postharvest. This study introduces an artificial intelligence system to detect and evaluate the root trimming condition of garlics based on garlic images using convolutional neural network algorithms. We aimed to develop a real-time and autonomous classification system of garlic during the root trimming process. The classification considered as three classes namely, good, bad and scratch classes. The system automatically operated when a garlic was placed under the webcam. The analysis results were sent to two replays via serial ports for further automation processes. The classification was instant, and its accuracy was about 96 %. This system has the potential for high-impact applications in agricultural imaging, especially in postharvest machinery.