An approach for improve the recognition of defects in coffee beans using retinex algorithms

Rel Guzmán Apaza; Christian E. Portugal-Zambrano; Juan Carlos Gutierrez Caceres; César A. Beltrán-Castañón

doi:10.1109/CLEI.2014.6965102

An approach for improve the recognition of defects in coffee beans using retinex algorithms

Rel Guzmán Apaza, Christian E. Portugal-Zambrano, Juan Carlos Gutierrez Caceres, César A. Beltrán-Castañón

Departamento Académico de Ingeniería de Sistemas e Informática

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

5 Scopus citations

Abstract

This paper describes the development of a system for evaluating the quality of coffee focused on the pre-processing of digital images using an algorithm based on the retinex theory called multi-scale retinex with color restoration (MSRCR). A dataset of images of coffee beans are collected and others techniques for image enhancement are compared, then a color gray-level coocurrence matrix (CGLCM) technique is used for features extraction and a Support Vector Machine (SVM) is used to evaluate results with a set of prepared data, these results shows a good visual quality and better accuracy in classification for MSRCR techniques compared with others, finally conclusions and future works are presented.

Original language	English
Title of host publication	Proceedings of the 2014 Latin American Computing Conference, CLEI 2014
Editors	Pablo Ezzatti, Andrea Delgado
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479961306
DOIs	https://doi.org/10.1109/CLEI.2014.6965102
State	Published - 21 Nov 2014
Event	2014 40th Latin American Computing Conference, CLEI 2014 - Montevideo, Uruguay Duration: 15 Sep 2014 → 19 Sep 2014

Publication series

Name	Proceedings of the 2014 Latin American Computing Conference, CLEI 2014

Conference

Conference	2014 40th Latin American Computing Conference, CLEI 2014
Country/Territory	Uruguay
City	Montevideo
Period	15/09/14 → 19/09/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

CGLCM
coffee beans
Computer vision
image enhancement
industrial quality
MSRCR
retinex
SVM

Access to Document

10.1109/CLEI.2014.6965102

Cite this

Apaza, R. G., Portugal-Zambrano, C. E., Gutierrez Caceres, J. C., & Beltrán-Castañón, C. A. (2014). An approach for improve the recognition of defects in coffee beans using retinex algorithms. In P. Ezzatti, & A. Delgado (Eds.), Proceedings of the 2014 Latin American Computing Conference, CLEI 2014 [6965102] (Proceedings of the 2014 Latin American Computing Conference, CLEI 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLEI.2014.6965102

Apaza, Rel Guzmán ; Portugal-Zambrano, Christian E. ; Gutierrez Caceres, Juan Carlos et al. / An approach for improve the recognition of defects in coffee beans using retinex algorithms. Proceedings of the 2014 Latin American Computing Conference, CLEI 2014. editor / Pablo Ezzatti ; Andrea Delgado. Institute of Electrical and Electronics Engineers Inc., 2014. (Proceedings of the 2014 Latin American Computing Conference, CLEI 2014).

@inproceedings{3c1c16785ab247d588fee694cdb75158,

title = "An approach for improve the recognition of defects in coffee beans using retinex algorithms",

abstract = "This paper describes the development of a system for evaluating the quality of coffee focused on the pre-processing of digital images using an algorithm based on the retinex theory called multi-scale retinex with color restoration (MSRCR). A dataset of images of coffee beans are collected and others techniques for image enhancement are compared, then a color gray-level coocurrence matrix (CGLCM) technique is used for features extraction and a Support Vector Machine (SVM) is used to evaluate results with a set of prepared data, these results shows a good visual quality and better accuracy in classification for MSRCR techniques compared with others, finally conclusions and future works are presented.",

keywords = "CGLCM, coffee beans, Computer vision, image enhancement, industrial quality, MSRCR, retinex, SVM",

author = "Apaza, {Rel Guzm{\'a}n} and Portugal-Zambrano, {Christian E.} and {Gutierrez Caceres}, {Juan Carlos} and Beltr{\'a}n-Casta{\~n}{\'o}n, {C{\'e}sar A.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; null ; Conference date: 15-09-2014 Through 19-09-2014",

year = "2014",

month = nov,

day = "21",

doi = "10.1109/CLEI.2014.6965102",

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

series = "Proceedings of the 2014 Latin American Computing Conference, CLEI 2014",

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

editor = "Pablo Ezzatti and Andrea Delgado",

booktitle = "Proceedings of the 2014 Latin American Computing Conference, CLEI 2014",

address = "Estados Unidos",

}

Apaza, RG, Portugal-Zambrano, CE, Gutierrez Caceres, JC & Beltrán-Castañón, CA 2014, An approach for improve the recognition of defects in coffee beans using retinex algorithms. in P Ezzatti & A Delgado (eds), Proceedings of the 2014 Latin American Computing Conference, CLEI 2014., 6965102, Proceedings of the 2014 Latin American Computing Conference, CLEI 2014, Institute of Electrical and Electronics Engineers Inc., 2014 40th Latin American Computing Conference, CLEI 2014, Montevideo, Uruguay, 15/09/14. https://doi.org/10.1109/CLEI.2014.6965102

An approach for improve the recognition of defects in coffee beans using retinex algorithms. / Apaza, Rel Guzmán; Portugal-Zambrano, Christian E.; Gutierrez Caceres, Juan Carlos et al.

Proceedings of the 2014 Latin American Computing Conference, CLEI 2014. ed. / Pablo Ezzatti; Andrea Delgado. Institute of Electrical and Electronics Engineers Inc., 2014. 6965102 (Proceedings of the 2014 Latin American Computing Conference, CLEI 2014).

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

TY - GEN

T1 - An approach for improve the recognition of defects in coffee beans using retinex algorithms

AU - Apaza, Rel Guzmán

AU - Portugal-Zambrano, Christian E.

AU - Gutierrez Caceres, Juan Carlos

AU - Beltrán-Castañón, César A.

PY - 2014/11/21

Y1 - 2014/11/21

N2 - This paper describes the development of a system for evaluating the quality of coffee focused on the pre-processing of digital images using an algorithm based on the retinex theory called multi-scale retinex with color restoration (MSRCR). A dataset of images of coffee beans are collected and others techniques for image enhancement are compared, then a color gray-level coocurrence matrix (CGLCM) technique is used for features extraction and a Support Vector Machine (SVM) is used to evaluate results with a set of prepared data, these results shows a good visual quality and better accuracy in classification for MSRCR techniques compared with others, finally conclusions and future works are presented.

AB - This paper describes the development of a system for evaluating the quality of coffee focused on the pre-processing of digital images using an algorithm based on the retinex theory called multi-scale retinex with color restoration (MSRCR). A dataset of images of coffee beans are collected and others techniques for image enhancement are compared, then a color gray-level coocurrence matrix (CGLCM) technique is used for features extraction and a Support Vector Machine (SVM) is used to evaluate results with a set of prepared data, these results shows a good visual quality and better accuracy in classification for MSRCR techniques compared with others, finally conclusions and future works are presented.

KW - CGLCM

KW - coffee beans

KW - Computer vision

KW - image enhancement

KW - industrial quality

KW - MSRCR

KW - retinex

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=84919431178&partnerID=8YFLogxK

U2 - 10.1109/CLEI.2014.6965102

DO - 10.1109/CLEI.2014.6965102

M3 - Contribución a la conferencia

AN - SCOPUS:84919431178

T3 - Proceedings of the 2014 Latin American Computing Conference, CLEI 2014

BT - Proceedings of the 2014 Latin American Computing Conference, CLEI 2014

A2 - Ezzatti, Pablo

A2 - Delgado, Andrea

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 15 September 2014 through 19 September 2014

ER -

Apaza RG, Portugal-Zambrano CE, Gutierrez Caceres JC, Beltrán-Castañón CA. An approach for improve the recognition of defects in coffee beans using retinex algorithms. In Ezzatti P, Delgado A, editors, Proceedings of the 2014 Latin American Computing Conference, CLEI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 6965102. (Proceedings of the 2014 Latin American Computing Conference, CLEI 2014). doi: 10.1109/CLEI.2014.6965102

An approach for improve the recognition of defects in coffee beans using retinex algorithms

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this