Efficient commercial classification of agricultural products using convolutional neural networks

Abstract

Agricultural products, as essential commodities, are among the most sought - for items in superstores. Barcode is usually utilized to classify and regulate the price of products such as ornamental flowers in such stores. However, the use of barcodes on some fragile agricultural products such as ornamental flowers can be damaged and lessen their life length. Moreover, it is time - consuming and costly and may lead to the pro duction of massive waste and damage to the environment and the admittance of chemical materials into food products that can affect human health. Consequently, we aimed to design a classifier robot to recognize ornamental flowers based on the related produc t image at different times and surrounding conditions. Besides, it can increase the speed and accuracy of distinguishing and classifying the products, lower the pricing time, and increase the lifetime due to the absence of the need for movement and changin g the position of the products. According to the datasheets provided by the robot that is stored in its database, we provide the possibility of identifying and introducing the product in different colors and shapes. Also, due to the preparation of a standa rd and small database tailored to the needs of the robot, the robot will be trained in a short time (less than five minutes) without the need for an Internet connection or a large hard drive for storage the data. On the other hand, by dividing each input p hoto into ten different sections, the system can, without the need for a detection system, simultaneously in several different images, decorative flowers in different conditions, angles and environments, even with other objects such as vases, detects very fast with a high accuracy of 97%.