Abstract
Defective citrus fruits are manually sorted at the moment, which is a time-consuming and cost-expensive process with unsatisfactory accuracy. In this paper, we introduce a deep learning-based vision system implemented on a citrus processing line for fast on-line sorting. For the citrus fruits rotating randomly on the conveyor, a convolutional neural network-based detector was developed to detect and temporarily classify the defective ones, and a SORT algorithm-based tracker was adopted to record the classification information along their paths. The true categories of the citrus fruits were identified through the tracked historical information, resulting in high detection precision of 93.6%. Moreover, the linear Kalman filter model was applied to predict the future path of the fruits, which can be used to guide the robot arms to pick out the defective ones. Ultimately, this research presents a practical solution to realize on-line citrus sorting featuring low costs, high efficiency, and accuracy.
Highlights
Citrus is an important agricultural commodity produced in 140 countries, with the annual worldwide production estimated at over 110 million tons in the period 2016–2017 (Nazirul et al, 2017)
We aim to develop a vision system based on deep learning, which can be implemented directly on a citrus processing line and perform fast on-line citrus sorting
The focus of this study is to develop a novel vision system to realize fast on-line citrus sorting
Summary
Citrus is an important agricultural commodity produced in 140 countries, with the annual worldwide production estimated at over 110 million tons in the period 2016–2017 (Nazirul et al, 2017). Damage to the citrus fruits can be caused by various issues, including insects in the field, bad practice in harvesting, infection penetration through injuries, or evolution of previous diseases during post-harvest storage (Holmes and Eckert, 1999; Burks et al, 2005). These diverse types of defects generate very different symptoms on their external appearance, making it challenging to develop non-destructive sorting methods with both high accuracy and efficiency.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
