Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits
Citrus fruits are the second most important crop worldwide. One of the most important tasks is sorting, which involves manually separating the fruit based on its degree of maturity, and in many cases, involves a task carried out manually by human operators. A machine vision-based citrus sorting syst...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/18/3891 |
| _version_ | 1797580468896399360 |
|---|---|
| author | Marco Aurelio Nuño-Maganda Ismael Antonio Dávila-Rodríguez Yahir Hernández-Mier José Hugo Barrón-Zambrano Juan Carlos Elizondo-Leal Alan Díaz-Manriquez Said Polanco-Martagón |
| author_facet | Marco Aurelio Nuño-Maganda Ismael Antonio Dávila-Rodríguez Yahir Hernández-Mier José Hugo Barrón-Zambrano Juan Carlos Elizondo-Leal Alan Díaz-Manriquez Said Polanco-Martagón |
| author_sort | Marco Aurelio Nuño-Maganda |
| collection | DOAJ |
| description | Citrus fruits are the second most important crop worldwide. One of the most important tasks is sorting, which involves manually separating the fruit based on its degree of maturity, and in many cases, involves a task carried out manually by human operators. A machine vision-based citrus sorting system can replace labor work for the inspection of fruit sorting. This article proposes a vision system for citrus fruit sorting implemented on a dedicated and efficient Field Programmable Gate Array (FPGA) hardware architecture coupled with a mechanical sorting machine, where the FPGA performs fruit segmentation and color and size classification. We trained a decision tree (DT) using a balanced dataset of reference images to perform pixel classification. We evaluate the segmentation task using a pixel accuracy metric, defined as the ratio between correctly segmented pixels produced by a DT and the total pixels in the reference image segmented offline using Otsu’s thresholding algorithm. The balance between correctly classified images by color or size and their corresponding labels of that color and size evaluates the color and size classification algorithms. Considering these metrics, the system reaches an accuracy of 97% for fruit segmentation, 94% for color classification, and 90% for size classification, running at 60 fps. |
| first_indexed | 2024-03-10T22:50:27Z |
| format | Article |
| id | doaj.art-9e2d2a4e22a2438fa777dcdc683e2af0 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T22:50:27Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9e2d2a4e22a2438fa777dcdc683e2af02023-11-19T10:22:48ZengMDPI AGElectronics2079-92922023-09-011218389110.3390/electronics12183891Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus FruitsMarco Aurelio Nuño-Maganda0Ismael Antonio Dávila-Rodríguez1Yahir Hernández-Mier2José Hugo Barrón-Zambrano3Juan Carlos Elizondo-Leal4Alan Díaz-Manriquez5Said Polanco-Martagón6Intelligent Systems Department, Polytechnic University of Victoria, Ciudad Victoria 87138, Tamaulipas, MexicoIntelligent Systems Department, Polytechnic University of Victoria, Ciudad Victoria 87138, Tamaulipas, MexicoIntelligent Systems Department, Polytechnic University of Victoria, Ciudad Victoria 87138, Tamaulipas, MexicoFacultad de Ingeniería y Ciencias, Universidad Autonoma de Tamaulipas, Ciudad Victoria 87000, Tamaulipas, MexicoFacultad de Ingeniería y Ciencias, Universidad Autonoma de Tamaulipas, Ciudad Victoria 87000, Tamaulipas, MexicoFacultad de Ingeniería y Ciencias, Universidad Autonoma de Tamaulipas, Ciudad Victoria 87000, Tamaulipas, MexicoIntelligent Systems Department, Polytechnic University of Victoria, Ciudad Victoria 87138, Tamaulipas, MexicoCitrus fruits are the second most important crop worldwide. One of the most important tasks is sorting, which involves manually separating the fruit based on its degree of maturity, and in many cases, involves a task carried out manually by human operators. A machine vision-based citrus sorting system can replace labor work for the inspection of fruit sorting. This article proposes a vision system for citrus fruit sorting implemented on a dedicated and efficient Field Programmable Gate Array (FPGA) hardware architecture coupled with a mechanical sorting machine, where the FPGA performs fruit segmentation and color and size classification. We trained a decision tree (DT) using a balanced dataset of reference images to perform pixel classification. We evaluate the segmentation task using a pixel accuracy metric, defined as the ratio between correctly segmented pixels produced by a DT and the total pixels in the reference image segmented offline using Otsu’s thresholding algorithm. The balance between correctly classified images by color or size and their corresponding labels of that color and size evaluates the color and size classification algorithms. Considering these metrics, the system reaches an accuracy of 97% for fruit segmentation, 94% for color classification, and 90% for size classification, running at 60 fps.https://www.mdpi.com/2079-9292/12/18/3891real-time system architectureimage segmentationimage classificationagricultureField-Programmable Gate Array |
| spellingShingle | Marco Aurelio Nuño-Maganda Ismael Antonio Dávila-Rodríguez Yahir Hernández-Mier José Hugo Barrón-Zambrano Juan Carlos Elizondo-Leal Alan Díaz-Manriquez Said Polanco-Martagón Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits Electronics real-time system architecture image segmentation image classification agriculture Field-Programmable Gate Array |
| title | Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits |
| title_full | Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits |
| title_fullStr | Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits |
| title_full_unstemmed | Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits |
| title_short | Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits |
| title_sort | real time embedded vision system for online monitoring and sorting of citrus fruits |
| topic | real-time system architecture image segmentation image classification agriculture Field-Programmable Gate Array |
| url | https://www.mdpi.com/2079-9292/12/18/3891 |
| work_keys_str_mv | AT marcoaurelionunomaganda realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT ismaelantoniodavilarodriguez realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT yahirhernandezmier realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT josehugobarronzambrano realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT juancarloselizondoleal realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT alandiazmanriquez realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits AT saidpolancomartagon realtimeembeddedvisionsystemforonlinemonitoringandsortingofcitrusfruits |