Results of Laboratory Studies of the Automated Sorting System for Root and Onion Crops

Abstract

The roller and sieve machines most commonly used in Russia for the post-harvest processing of root and tuber crops and onions have a number of disadvantages, the main one being a decrease in the quality of sorting due to the contamination of working bodies, which increases the quantity of losses during sorting and storage. To obtain high-quality competitive production, it is necessary to combine a number of technological operations during the sorting process, such as dividing the material into classes and fractions by quality and size, as well as identifying and removing damaged products. In order to improve the quality of sorting of root tubers and onions by size, it is necessary to ensure the development of an automatic control system for operating and technological parameters, the use of which will eliminate manual sorting on bulkhead tables in post-harvest processing. To fulfill these conditions, the developed automatic control system must have the ability to identify the material on the sorting surface, taking into account external damage and ensuring the automatic removal of impurities. In this study, the highest sorting accuracy of tubers (of more than 91%) was achieved with a forward speed of 1.2 m/s for the conveyor of the sorting table, with damage to 2.2% of the tubers, which meets the agrotechnical requirements for post-harvest processing. This feature distinguishes the developed device from similar ones.

Development of an Optical System with an Orientation Module to Detect Surface Damage to Potato Tubers

“…The algorithm for analyzing the obtained spectral images of potato tubers and apple fruits for the recognition of objects [6,8], their shape, and damage to the products requires the implementation of the following stages of work:…”

“…The definition of the objects of analysis also significantly depends on the technical characteristics of a particular object, such as varietal characteristics, size, the quality of the crop at that time period and the presence or absence of diseases [3][4][5]. At the moment, it is not known a priori which object can be present in the image, but it is known that an object can be an object of a certain class [6][7][8][9]. As a rule, it is necessary to recognize an object with accuracy to the class level, i.e., to attribute the object in question to one of the listed classes or to conclude that this object does not belong to any of them.…”

Development of an automated lighting control system in agricultural premises to save energy resources

“…These include a web interface and a mobile device from which the system is controlled and sensor readings are monitored. The second part is the central controller, which allows the user system to interact with sensors and peripherals [9][10][11][12]. The third part is sensors and peripherals, with the help of which environmental readings are taken.…”

Enhancing Yam Quality Detection Through Computer Vision in Iot and Robotics Applications

“…The accuracies for these openCV systems range from 80 to 100%. Dorokhov et al (2021) and Na 'iyah et al (2020) used computer vision system to detect qualities of more than one tuber crops at a time. Na 'iyah et al (2020) used this technology to develop two models for detecting sweet potatoes and cassava tubers, with accuracies of 97 and 93% respectively.…”

“…Na 'iyah et al (2020) used this technology to develop two models for detecting sweet potatoes and cassava tubers, with accuracies of 97 and 93% respectively. Dorokhov et al (2021) also used this technology to detect the external damages and removal of impurities in onions and potatoes automated Sorting System, with overall accuracy of 91%. Little or no studies had been carried out on yam tuber quality detection using computer vision technology.…”