Design of an automated coffee selection system by means of computer vision techniques
No Thumbnail Available
Date
Advisors
Evaluators
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Industrial de Santander
Abstract
Description
En el presente artículo se propone un sistema de visión artificial para la detección del fruto de café apto para producción. Para lograr esta detección se desarrollaron dos algoritmos, uno encargado de clasificar los frutos de café en maduros o no maduros, y otro que detecta la presencia de la plaga de la broca. Para el primero se extrajeron características de color y se usó un clasificador bayesiano. Por otra parte, el algoritmo de detección de brocas busca zonas negras en la imagen, esto debido a que la evidencia dejada por esta plaga son orificios en la superficie del fruto. Además, se diseñó un sistema mecánico para el transporte de los frutos de café durante el proceso, y un mecanismo de extracción para separar los frutos, una vez estos sean clasificados por el algoritmo. Los resultados obtenidos mostraron una efectividad del 87%.
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 orunripe state, and the other to detect the presence of the ‘coffee berry borer’. The first one uses a Bayesian Classifier toidentify the color of the fruit, and the second algorithm searches for the holes made by the coffee berry borer on thesurface of the product. Moreover, a mechanical system was designed for the transportation and separation of the coffeefruits. In the first stage, coffees are transported as pictures of them are taken. At the end of this stage, the separationmechanism alters the path of the fruit based on the result of the classifier. The system proposed obtained aneffectiveness of 87%.
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 orunripe state, and the other to detect the presence of the ‘coffee berry borer’. The first one uses a Bayesian Classifier toidentify the color of the fruit, and the second algorithm searches for the holes made by the coffee berry borer on thesurface of the product. Moreover, a mechanical system was designed for the transportation and separation of the coffeefruits. In the first stage, coffees are transported as pictures of them are taken. At the end of this stage, the separationmechanism alters the path of the fruit based on the result of the classifier. The system proposed obtained aneffectiveness of 87%.
Keywords
Selection process, artificial neural networks, binarization, feature extraction, image classification, image color analysis, image segmentation, machine vision, Análisis de color de imágenes, binarización, clasificación de imágenes, extracción de características, fruto de café, proceso de selección, segmentación de imágenes, visión artificial