Design of an automated coffee selection system by means of computer vision techniques
Published 2016-04-27
Keywords
- Selection process,
- artificial neural networks,
- binarization,
- feature extraction,
- image classification
- image color analysis,
- image segmentation,
- machine vision ...More
How to Cite
Abstract
In this Article, it is proposed a computer vision system, which can detect whether a coffee fruit is suitable for production
or not. In order to achieve this detection, two algorithms were developed, one to classify the coffee fruit in the ripe or
unripe state, and the other to detect the presence of the ‘coffee berry borer’. The first one uses a Bayesian Classifier to
identify the color of the fruit, and the second algorithm searches for the holes made by the coffee berry borer on the
surface of the product. Moreover, a mechanical system was designed for the transportation and separation of the coffee
fruits. In the first stage, coffees are transported as pictures of them are taken. At the end of this stage, the separation
mechanism alters the path of the fruit based on the result of the classifier. The system proposed obtained an
effectiveness of 87%.
Downloads
References
- G.I. Puerta, “Cómo garantizar la buena calidad de la bebida del café y evitar los defectos,” Avances Técn. Cenicafé, no. 284, pp. 1-8, Feb, 2001. Disponible en: http://goo.gl/aWImXN
- C.E. Oliveros et al., "Dispositivo hidráulico de bajo impacto ambiental para limpieza y clasificación del café en cereza," Cenicafe, vol. 60, no. 3, pp. 229-238, 2009. Diponible en: http://goo.gl/0cYn7S
- J.A. Díaz, "Diseño de un sistema de selección de café mediante la caracterización de imágenes," ENGI Rev. Electr. Fac. Ing., vol. 1, no. 2, 2013.
- G. Daza, L.G. Sánchez, J.F. Suárez, "Selección de características orientada a sistemas de reconocimiento de granos maduros de café," Scientia et Technica, vol. 1, no. 35, 2007.
- Z. Sandoval, F. Prieto, "Caracterización de café cereza empleando técnicas de visión artificial," Rev. Fac. Nal. Agro. Medellín, vol. 60, no. 2, pp. 4105-4127, 2007.
- L.A. Silva, S. Lizcano, "Evaluación del estado de maduración de la piña en su variedad perolera mediante técnicas de visión artificial," Iteckne, vol. 9, no. 1, 2012.
- F. Guevara, J. Gómez, "A machine vision system for classification of wheat and barley grain kernels," Spanish Journ. of Agr. Res., vol. 9, no. 3, pp. 672-680, 2011.
- Cenicafé. Cultivemos café / Manejo Integrado del Cultivo: Manejo Integrado de la Broca [Pub. en línea]. Disponible en: http://goo.gl/IJVbSf
- R.C. Gonzalez, R. Woods, Digital Image Processing, 3a ed. USA: Prentice Hall, 2008.
- M. Nixon, A. Aguado, Feature Extraction & Image Processing, 2a ed. Londres, UK: Elsevier Ltd., 2008.
- D. Savakar, "Identification and Classification of Bulk Fruits Images using Artificial Neural Networks," Int. Journ. Eng. Innov. Tech. (IJEIT), vol. 1, no. 3, 2012.
- M. Hassoun, Fundamentals of Artificial Neural Networks, MA, USA: A Bradford Book, MIT Press, 1995.
- Z. Sandoval, F. Prieto, "Procesamiento de imágenes para la clasificación de café cereza," Prospectiva, vol. 7, no. 1, pp. 67-73, 2009.
- Inst. for Evidence-Based Health Prof., Edu.,The University of Georgia, "4.6: Receiver Operating Characteristic Curves" en Free Online Course in Evidence-Based Practice [Curso en línea]. Disponible: http://ebp.uga.edu/courses/
- Z. Sandoval, “Caracterización y clasificación de café cereza usando visión artificial,” M.S. thesis, Dept. Electr., Fac. Ing. Arq., Univ.Nal., Manizales, Colombia, Abr. 2005. Disponible en: http://goo.gl /110Q38