Computer vision grading system for physical quality evaluation of green coffee beans

Christian E. Portugal-Zambrano; Juan Carlos Gutierrez Caceres; Juan Ramirez-Ticona; Cesar A. Beltran-Castanon

doi:10.1109/CLEI.2016.7833383

Computer vision grading system for physical quality evaluation of green coffee beans

Christian E. Portugal-Zambrano, Juan Carlos Gutierrez Caceres, Juan Ramirez-Ticona, Cesar A. Beltran-Castanon

Departamento Académico de Ingeniería de Sistemas e Informática

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Evaluating the physical defects of green coffee beans are an important process in defining their quality. This evaluation is normally carried out by visual inspection or using traditional instruments which have some limitations. This work is focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was developed to capture the images of coffee beans, the software uses a White-Patch algorithm as a image enhancement procedure, color histograms as feature extractor and SVM for the classification task, a database of 1930 images was collected, we used 13 categories of defects described in the SCAA standard of evaluation. Results of classification achieved a 98.8% of overall detection accuracy, therefore the proposed system proved to be effective in classifying physical defects of green coffee beans. Finally a set of conclusions and future works are presented.

Original language	English
Title of host publication	Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509016334
DOIs	https://doi.org/10.1109/CLEI.2016.7833383
State	Published - 25 Jan 2017
Event	42nd Latin American Computing Conference, CLEI 2016 - Valparaiso, Chile Duration: 10 Oct 2016 → 14 Oct 2016

Publication series

Name	Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016

Conference

Conference	42nd Latin American Computing Conference, CLEI 2016
Country/Territory	Chile
City	Valparaiso
Period	10/10/16 → 14/10/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

coffee beans defects
Grade System
Histogram
Image Enhancement
Retinex
SVM
White Patch

Access to Document

10.1109/CLEI.2016.7833383

Cite this

Portugal-Zambrano, C. E., Gutierrez Caceres, J. C., Ramirez-Ticona, J., & Beltran-Castanon, C. A. (2017). Computer vision grading system for physical quality evaluation of green coffee beans. In Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016 [7833383] (Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLEI.2016.7833383

Portugal-Zambrano, Christian E. ; Gutierrez Caceres, Juan Carlos ; Ramirez-Ticona, Juan et al. / Computer vision grading system for physical quality evaluation of green coffee beans. Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. (Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016).

@inproceedings{d66a8359a04e42bcab484cb833f9276f,

title = "Computer vision grading system for physical quality evaluation of green coffee beans",

abstract = "Evaluating the physical defects of green coffee beans are an important process in defining their quality. This evaluation is normally carried out by visual inspection or using traditional instruments which have some limitations. This work is focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was developed to capture the images of coffee beans, the software uses a White-Patch algorithm as a image enhancement procedure, color histograms as feature extractor and SVM for the classification task, a database of 1930 images was collected, we used 13 categories of defects described in the SCAA standard of evaluation. Results of classification achieved a 98.8% of overall detection accuracy, therefore the proposed system proved to be effective in classifying physical defects of green coffee beans. Finally a set of conclusions and future works are presented.",

keywords = "coffee beans defects, Grade System, Histogram, Image Enhancement, Retinex, SVM, White Patch",

author = "Portugal-Zambrano, {Christian E.} and {Gutierrez Caceres}, {Juan Carlos} and Juan Ramirez-Ticona and Beltran-Castanon, {Cesar A.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; null ; Conference date: 10-10-2016 Through 14-10-2016",

year = "2017",

month = jan,

day = "25",

doi = "10.1109/CLEI.2016.7833383",

language = "Ingl{\'e}s",

series = "Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016",

address = "Estados Unidos",

}

Portugal-Zambrano, CE, Gutierrez Caceres, JC, Ramirez-Ticona, J & Beltran-Castanon, CA 2017, Computer vision grading system for physical quality evaluation of green coffee beans. in Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016., 7833383, Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016, Institute of Electrical and Electronics Engineers Inc., 42nd Latin American Computing Conference, CLEI 2016, Valparaiso, Chile, 10/10/16. https://doi.org/10.1109/CLEI.2016.7833383

Computer vision grading system for physical quality evaluation of green coffee beans. / Portugal-Zambrano, Christian E.; Gutierrez Caceres, Juan Carlos; Ramirez-Ticona, Juan et al.

Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7833383 (Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Computer vision grading system for physical quality evaluation of green coffee beans

AU - Portugal-Zambrano, Christian E.

AU - Gutierrez Caceres, Juan Carlos

AU - Ramirez-Ticona, Juan

AU - Beltran-Castanon, Cesar A.

PY - 2017/1/25

Y1 - 2017/1/25

N2 - Evaluating the physical defects of green coffee beans are an important process in defining their quality. This evaluation is normally carried out by visual inspection or using traditional instruments which have some limitations. This work is focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was developed to capture the images of coffee beans, the software uses a White-Patch algorithm as a image enhancement procedure, color histograms as feature extractor and SVM for the classification task, a database of 1930 images was collected, we used 13 categories of defects described in the SCAA standard of evaluation. Results of classification achieved a 98.8% of overall detection accuracy, therefore the proposed system proved to be effective in classifying physical defects of green coffee beans. Finally a set of conclusions and future works are presented.

AB - Evaluating the physical defects of green coffee beans are an important process in defining their quality. This evaluation is normally carried out by visual inspection or using traditional instruments which have some limitations. This work is focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was developed to capture the images of coffee beans, the software uses a White-Patch algorithm as a image enhancement procedure, color histograms as feature extractor and SVM for the classification task, a database of 1930 images was collected, we used 13 categories of defects described in the SCAA standard of evaluation. Results of classification achieved a 98.8% of overall detection accuracy, therefore the proposed system proved to be effective in classifying physical defects of green coffee beans. Finally a set of conclusions and future works are presented.

KW - coffee beans defects

KW - Grade System

KW - Histogram

KW - Image Enhancement

KW - Retinex

KW - SVM

KW - White Patch

UR - http://www.scopus.com/inward/record.url?scp=85013941924&partnerID=8YFLogxK

U2 - 10.1109/CLEI.2016.7833383

DO - 10.1109/CLEI.2016.7833383

M3 - Contribución a la conferencia

AN - SCOPUS:85013941924

T3 - Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016

BT - Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 10 October 2016 through 14 October 2016

ER -

Portugal-Zambrano CE, Gutierrez Caceres JC, Ramirez-Ticona J, Beltran-Castanon CA. Computer vision grading system for physical quality evaluation of green coffee beans. In Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7833383. (Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016). doi: 10.1109/CLEI.2016.7833383

Computer vision grading system for physical quality evaluation of green coffee beans

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this