Mostrar el registro sencillo del documento
Design of an on-line multispectral Coffee fruit classification and sorting system using narrowband LEDs and MCU
dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional |
dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional |
dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional |
dc.contributor.advisor | Osorio Londoño, Gustavo Adolfo |
dc.contributor.author | Manrique Naranjo, Leonardo |
dc.date.accessioned | 2020-08-05T23:11:17Z |
dc.date.available | 2020-08-05T23:11:17Z |
dc.date.issued | 2020 |
dc.identifier.citation | Manrique, L. Design of an on-line multispectral coffee fruit classification and sorting system using narrowband LEDs and MCU. Maestría en Ingeniería - Automatización Industrial 2020 |
dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/77947 |
dc.description.abstract | La tendencia creciente de cafés especiales abre la posibilidad de generación de ingresos adicionales para los productores de café Colombianos, quienes han sido golpeados recientemente por condiciones de mercado, cambio climático, incremento de costo de suministros y resultados de la violencia entre otras razones. Un requerimiento clave para cafés especiales, sin importar el método de post-producción utilizado, es el uso exclusivo de frutos de café completamente maduros, los cuales pueden ser rojos o amarillos; todos los frutos verdes deben ser removidos. El diseño propuesto en esta tesis es el resultado de una investigación de mercado tanto financiera como técnica, e implementa un sensor de color discreto de bajo costo, así como LEDs disponibles comercialmente controlados por un procesador de alto desempeño de arquitectura ARM Cortex-M4, ejecutando algoritmos de clasificacion derivados de técnicas entrenamiento supervisado optimizados para micro controladores, obteniendo un ensamble electrónico de costo inferior a US$100 en volúmenes altos. El trabajo se enfoca en la capacidad discriminante aumentada del sensor, la cual se obtiene gracias al análisis de diferentes configuraciones de fuentes de luz de banda angosta a través de métodos de computación intensiva. Si bien múltiples clasificadores son utilizados, el model resultante obtiene una certeza superior al 99% utilizando un clasificador LDA tipo ensamble, a una tasa de clasificación mayora 10 frutos por segundo o 72 Kg por hora en un factor de forma portátil, utilizando solo 3 tipos de LEDs discretos y un conversor de luz a frecuencia. |
dc.description.abstract | The growing trend of specialty coffees brings the possibility of increased income for Colombian coffee producers, who have been recurrently hit by market conditions, climate change, supplies cost increase and aftermath of violence. A key requirement for specialty coffee, regardless of the post-production method to use, is the exclusive use of ripe coffee fruits, which could be red or yellow; all green fruits must be removed. The design proposed in this thesis is the result of a financial and technical market research, and implements a low-cost discrete color sensor and commercially available LEDs system controlled by a high-performance Cortex-M4 core MCU, running algorithms derived from supervised learning techniques optimized for a MCU, achieving an electrical assembly of under US$100 when manufactured in high volumes. This work focuses on the increased discriminant capacity of the sensor, achieved by examining different narrowband light source configurations through intensive computing methods. While multiple classifiers are studied, the resulting model achieves an accuracy over 99% using an ensemble LDA, at a rate of more than 10 fruits per second or 72 Kg per hour in a portable form-factor, by using only 3 discrete LEDs and a light to frequency converter. |
dc.format.extent | 97 |
dc.format.mimetype | application/pdf |
dc.language.iso | eng |
dc.rights | Derechos reservados - Universidad Nacional de Colombia |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.subject.ddc | 600 - Tecnología (Ciencias aplicadas) |
dc.title | Design of an on-line multispectral Coffee fruit classification and sorting system using narrowband LEDs and MCU |
dc.title.alternative | Diseño de un Sistema en Línea de Clasificación y Selección de Frutos de Café Usando LEDs de Banda Estrecha y MCUs |
dc.type | Otro |
dc.rights.spa | Acceso abierto |
dc.description.additional | Thesis submitted in partial ful llment for the requirements for degree of MSc in Engineering - Industrial Automation. -- Research line: Signal and Image Analysis and Recognition, Electronic Design. |
dc.type.driver | info:eu-repo/semantics/other |
dc.type.version | info:eu-repo/semantics/acceptedVersion |
dc.publisher.program | Manizales - Ingeniería y Arquitectura - Maestría en Ingeniería - Automatización Industrial |
dc.contributor.researchgroup | Percepción y Control Inteligente (PCI) |
dc.description.degreelevel | Maestría |
dc.publisher.department | Departamento de Ingeniería Eléctrica y Electrónica |
dc.publisher.branch | Universidad Nacional de Colombia - Sede Manizales |
dc.relation.references | Acosta, Luis J.: Colombia to examine selling coffee at its own price, ignoring New York market. In: Reuters (2019) |
dc.relation.references | Akmalia, Dina ; Saputro, Adhi H. ; Handayani, Windri: A Non-Destruction Measurement System based on Hyperspectral Imaging for Sugar Content in Banana. In: IEEEE (2017) |
dc.relation.references | Arcila, J.: Sistemas de Producci´on - Densidad de siembra y productividad de los cafetales. Cenicafe, 2011 |
dc.relation.references | Betancur, J. A.: Segmentaci´on de frutos de cafe mediante m´etodos de crecimiento de regiones. In: Rev.Fac.Nal.Agr.Medellin.Vol.59, No.1 (2006), S. 3311{3333 |
dc.relation.references | Comercio, Industria y T. d.: Informacion: Perfiles EconA~3micosDepartamentales − MinCIT − Caldas:https://www.mincit.gov.co/getattachment/7f87532c-4073-497d-96329eafc29376b0/C 2019 [6] Dahl, Russ: Light-Emitting Diodes: A Primer. https://www.photonics.com/Article.aspx?AID=36706. Version: 2019 |
dc.relation.references | E. Alvarez, F. Alvarez M. T.: Propiedades f´ısico-mecanicas del fruto y del sistema fruto-pedunculo del caf´e variedad Colombia. 1999 |
dc.relation.references | Farfan, F.: Sistemas de Producci´on - Caf´es Especiales. Cenicafe, 2011 |
dc.relation.references | Feiping Nie, Yangqing Jia Changshui Z. Shiming Xiang X. Shiming Xiang ; Yan, Shuicheng: Trace ratio criterion for feature selection. In: AAAI, Volume 2 (2008), S.671{676 |
dc.relation.references | Fen, Dai ; Tiansheng, Hong ; Kun, Zhang ; Ya, Hong: Nondestructive detection of pesticide residue on longan surface. In: IEEE (2010) |
dc.relation.references | Fleuret, FranA¸cois: Fast binary feature selection with conditional mutual information. In: The Journal of Machine Learning Research (2004), S. 5:1531{1555 |
dc.relation.references | FNC: La Gente del Cafe - Estadisticas Caficultores. http://www.cafedecolombia.com/particulares/es/la tierra del cafe/la gente del cafe Version: 2010 |
dc.relation.references | FNC: Estad´ısticas Cafeteras. https://federaciondecafeteros.org/wp/estadisticas-cafete Version: 2020 |
dc.relation.references | FNC: Precio del Caf´e en Colombia, visited February 24th 2020. https://federaciondecafeteros.org/static/files/precio cafe.pdf. Version: 2020 |
dc.relation.references | G. I. Puerta, Q.: Influencia de los granos de caf´e cosechados verdes, en la calidad fisica y organol´eptica de la bebida. 2000 |
dc.relation.references | Gini, CW: Variability and mutability, contribution to the study of statistical distribution and relations. In: Studi Economico{Giuricici della R (1912) |
dc.relation.references | Jeremy Hodges, Aine Q. Fabiana Batista B. Fabiana Batista: Climate Change Threatens to Make Your Morning Brew More Expensive. In: Bloomberg News (2019) |
dc.relation.references | J.J. Carvajal, H.: Colorimetr´ıa del fruto de caf´e (Coffea arabica L.) durante us desarrollo y maduraci´on. In: Rev.Fac.Nal.Agr.Medellin (2011), S. 6229{6240 |
dc.relation.references | Jundong Li, Suhang Wang Fred M. Kewei Cheng C. Kewei Cheng: Feature Selection: A Data Perspective. In: ACM Computing Surveys (2016) |
dc.relation.references | Lewis, David D.: Feature selection and feature extraction for text categorization. In: Proceedings of the workshop on Speech and Natural Language (1992), S. 212{217 |
dc.relation.references | Li, Jing ; Xue, Long ; He, Xiuwen ; Liu, Muhua: Visible and Near infrared reflectance spectroscopy for determining soluble solids content of navel orange. In: IEEE (2011) |
dc.relation.references | Lin, Dahua ; Tang, Xiaoou: Conditional infomax learning: an integrated framework for feature extraction and fusion. In: Computer Vision ECCV (2006), S. 68{82 |
dc.relation.references | Marin-Lopez, S.: Cambios f´ısicos y qu´ımicos durante la maduraci´on del fruto de caf´e (Coffea arabica L. var Colombia). In: Cenicafe (2003), S. 208{225 |
dc.relation.references | Minghua Zhang, Eike L. Adam Hale H. Adam Hale: Feasibility of using remote sensing techniques to detect spider mite damage in stone fruit orchards. In: IEEE (2008) |
dc.relation.references | Montes, N.: La visi´on artificial aplicada al proceso de producci´on de caf´e. Universidad Nacional de Colombia, 2001. { Forschungsbericht |
dc.relation.references | Montes, N.: Real-time classification of coffee fruits using FPGA. Universidad Nacional de Colombia, 2015. { Forschungsbericht |
dc.relation.references | MAnguez ~ , I.: Disappearance of chlorophylls and carotenoids during the ripening of the olive. 1995 |
dc.relation.references | Nila ; Saputro ; Imawan: The prediction system of bruising depth of guava based on VIS-NIR imaging. In: IEEE (2017) |
dc.relation.references | Pedregosa, F. ; Varoquaux, G. ; Gramfort, A. ; Michel, V. ; Thirion, B.; Grisel, O. ; Blondel, M. ; Prettenhofer, P. ; Weiss, R. ; Dubourg, V. ; Vanderplas, J. ; Passos, A. ; Cournapeau, D. ; Brucher, M. ; Perrot, M. ;Duchesnay, E.: Scikit-learn: Machine Learning in Python. In: Journal of Machine Learning Research 12 (2011), S. 2825{2830 |
dc.relation.references | Poltak Sihombing, Sajadin Sembiring Nogar S. Faddly Tommy T. Faddly Tommy: The Citrus Fruit Sorting Device Automatically Based On Color Method By Using Tcs320 Color Sensor And Arduino Uno Microcontroller. In: The 3rd International Conference on Computing and Applied Informatics (2018) |
dc.relation.references | Putra, Rizaldi T. F.: Application of Color Sensor in the Determination of Tomato Fruit Ripeness (Solanum Lycopersicum, L) in Gravitation Type Fruit Sorting Tool. In: Indonesian Journal of Agricultural Research (2019) |
dc.relation.references | Ramos, P. J.: Identificaci´on y clasificaci´on de frutos de caf´e en tiempo real, a traves de la medicion de color. In: Cenicafe (2010), S. 315{326 |
dc.relation.references | Rangkuti ; Saputro ; Imawan: Prediction of soluble solid contents mapping on averrhoa carambola using hyperspectral Imaging. In: IEEE (2017) |
dc.relation.references | Richard O Duda, Peter E H. ; Stork, David G.: Pattern classification. John Wiley & Sons, 2012 |
dc.relation.references | Sandoval, Z.: Caracterizaci´on de caf´e cereza empleando t´ecnicas de visi´on artificial. In: Rev.Fac.Nal.Agr.Medellin (2007), S. 4105{4127 |
dc.relation.references | SCAP: Best of Panama Auction 2019. https://auction.bestofpanama.org/en/lots/auction/best Version: 2019 |
dc.relation.references | Schiffman, Richard: As Climate Changes, Colombia^aTMs Small Coffee Farmers Pay the Price. In: Yale Environment 360 (2019) |
dc.relation.references | Scholkopft, Bernhard ; Mullert, Klaus-Robert: Fisher discriminant analysis with kernels. In: Neural networks for signal processing IX (1999), S. 267{288 |
dc.relation.references | Sikonja, Marko R. ; Kononenko, Igor: Theoretical and empirical analysis of relief and rrelieff. In: Machine learning (2003), S. 53(1{2):23{69 |
dc.relation.references | Sitti Wetenriajeng Sidehabi, Intan Sari Areni Ingrid N. Ansar Suyuti S. Ansar Suyuti: The Development of Machine Vision System for Sorting Passion Fruit using MultiClass Support Vector Machine. |
dc.relation.references | Sun, Jason ; KA~ 1 4nnemeyer, Rainer ; McGlone, Andrew ; Tomer, Nathan: Fruit orientation in NIR transmission for vascular. In: Crown (2017) |
dc.relation.references | Tamayo, M.A.: Analysis de la capacidad discriminante de características de coloren imágenes multiespectrales de frutos de café, Doctorado en Ingenier´ıa - Autom´atica, Diss., 2018 |
dc.relation.references | Tetsuya Inagaki, Yoshiaki Shimomura Satoru T. Daisuke Nozawa N. Daisuke Nozawa: Three-Fibre-Based Diffuse Reflectance Spectroscopy for Estimation of Total Solid Content in Natural Rubber Latex. In: Journal of Near Infrared Spectroscopy (2016) |
dc.relation.references | Tibshirani, Robert: Regression shrinkage and selection via the lasso. In: Journal of the RoyalStatistical Society (1996) |
dc.relation.references | Wang, Xiao ; Xue, Long ; He, Xiuwen ; Liu, Muhua: Vitamin C Content Estimation of Chilies Using Vis/NIR spectroscopy. In: IEEE (2011) |
dc.relation.references | Wright, Sewall: The interpretation of population structure by fwith special regard to systems of mating. In: Evolution (1965), S. 395{420 |
dc.relation.references | Zuliang Wang, Chuanglue Cao Ting Z. Qi An A. Qi An: Design and Implementation of Automatic Sorting Control System for Melon and Fruit Products. In: Application of Intelligent Systems in Multi-modal Information Analytics (2019) |
dc.rights.accessrights | info:eu-repo/semantics/openAccess |
dc.subject.proposal | Coffee Fruits |
dc.subject.proposal | Frutos de café |
dc.subject.proposal | On-line |
dc.subject.proposal | omnidireccional |
dc.subject.proposal | Omnidirectional |
dc.subject.proposal | inspección |
dc.subject.proposal | Inspection |
dc.subject.proposal | clasificación |
dc.subject.proposal | LDA |
dc.subject.proposal | Sorting |
dc.subject.proposal | LDA |
dc.subject.proposal | Selección de características |
dc.subject.proposal | Procesamiento embebido |
dc.subject.proposal | Feature selection |
dc.subject.proposal | Embedded processing |
dc.subject.proposal | SVC |
dc.subject.proposal | Bosques Aleatorios |
dc.subject.proposal | SVC |
dc.subject.proposal | Random Forests |
dc.subject.proposal | GNB |
dc.subject.proposal | GNB |
dc.subject.proposal | Lasso |
dc.subject.proposal | Lasso |
dc.subject.proposal | clasificadores |
dc.subject.proposal | Classifiers |
dc.subject.proposal | Extracción de características |
dc.subject.proposal | Selección por color |
dc.subject.proposal | Feature extraction |
dc.subject.proposal | Color sorting |
dc.type.coar | http://purl.org/coar/resource_type/c_1843 |
dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa |
dc.type.content | Text |
oaire.accessrights | http://purl.org/coar/access_right/c_abf2 |
Archivos en el documento
Este documento aparece en la(s) siguiente(s) colección(ones)
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.Este documento ha sido depositado por parte de el(los) autor(es) bajo la siguiente constancia de depósito