Classification of Green coffee bean images basec on defect types using convolutional neural network (CNN)

Pinto, Carlito; Furukawa, Junya; Fukai, Hidekazu; Tamura, Shinichi

doi:10.1109/icaicta.2017.8090980

Cited by 61 publications

(36 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since there is no automated coffee classification and grading across the country, the same sample of coffee will be manually inspected and graded in different centers for the same activity with the same procedures which is costly in terms of human resource, labor, budget, and others. Attempts are made to design an automatic coffee classification to the corresponding growing region to facilitate the sorting, classification and grading of different botanical coffee bean growing areas [5,6,7]. These researchers were used traditional machine learning algorithms to develop and design the classification model using a limited size of datasets.…”

Section: Statement Of the Problemmentioning

confidence: 99%

Developing Ethiopian Yirgacheffe Coffee Grading Model using a Deep Learning Classifier

Arunkumar*,

berihun

2020

IJITEE

View full text Add to dashboard Cite

Coffee grading is the main procedure in producing homogenous local commercial fair system of pricing in the market and export. Grading coffee is a difficult task during the inspection, because it requires training and experience of the experts. In order to tackle grading difficulties in coffee producing industries and corporates have been employed and trained experts. Even if, those experts do not work effectively due to tiredness, costly, time consuming, inconsistency, bias and other factors. Digital image processing techniques based on automatically extracted features have been explored to classify Ethiopian coffee to corresponding quality grade labels. Samples of those coffee beans were taken from Yirgacheffe Coffee Farmers’ Cooperative Union. On average, 228 images were taken from each of three grade values or levels (grade 1, grade 2 and grade 3). The total number of images taken was 684 containing 6138 coffee beans. To extract coffee bean features and build a classification model for grading coffee, the state of art deep learning algorithm called convolutional Neural Network was used. Base on the experimental results classification accuracy obtained with testing coffee bean images for grade 1, grade 2 and grade 3 coffee beans was 99.51%, 97.56%, and 98.04%, respectively with the overall classification accuracy of 98.38%. This shows a promising result, even if, images are captured under the challenging condition without laboratory setup, such as illumination, different resolution, shadow and orientation which affects greatly the performance of the classifier and hence they are the future research direction that needs further investigations of noise removal techniques.

show abstract

Section: Statement Of the Problemmentioning

confidence: 99%

Developing Ethiopian Yirgacheffe Coffee Grading Model using a Deep Learning Classifier

Arunkumar*,

berihun

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…da Silva et al (2017) desenvolveram um aplicativo que utiliza RNAs para qualificar lotes ou marcas de café de um conjunto de sensores baseados em polímeros condutores, desenvolvidos pela Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Pinto et al (2017) desenvolveram um sistema automático de classificação de grãos de café para os produtores rurais. Inicialmente, foi desenvolvido um sistema de processamento de imagens que classifica as imagens dos grãos de café verde em cada tipo de defeito.…”

Section: Estado Da Arteunclassified

Sistema para Classificação de Grãos de Café: Uma Comparação entre Redes Neurais Convolucionais e Processamento Digital de Imagens com MLP

Oliveira

Cardoso

Dias

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

Between 2017 and 2018, 160 million bags of 60kg of coffee were produced in the world. Currently, Brazil occupies the position of largest producer of coffee in the world, with 31.9% of total production. In order to classify a sample of post-harvest coffee beans, this work was based on the comparison between two computational techniques. The first one is the use of Convolutional Neural Networks (CNN) and the second one is the combination of Digital Image Processing methods to extract features to feed an Artificial Neural Network of the Perceptron Multi-layered type (MLP) with the goal of classifying coffee beans. As a result, an overall average accuracy of 96.60% was obtained for CNN, greatly improving on the accuracy obtained by MLP, which was 78.13%. Resumo: Entre os anos de 2017 e 2018 foram produzidas 160 milhões de sacas de 60kg de café no mundo. Atualmente, o Brasil ocupa a posição de maior produtor de café do mundo, com 31,9% da produção total. A fim de classificar uma amostra de grãos de café pós-colheita, este trabalho baseou-se na comparação entre duas técnicas computacionais. A primeiraé a utilização de Redes Neurais Convolucionais (CNN) e a segundaé a junção de métodos de Processamento Digital de Imagens (PDI) para extrair características visando alimentar uma Rede Neural Artificial (RNA) do tipo Perceptron Multicamadas (MLP) com o objetivo de se obter a classificação dos grãos de café. Como resultado, obteve-se uma acurácia média global de 96.60% para a CNN, muito superiorà acurácia obtida pelo método de PDI com MLP, que foi de 78.13%.

show abstract

“…The authors in these papers only consider the color to grade the grain quality by its maturation stages, ignoring important defects such as small, very long berry or broken beans that are considered in the present manuscript and that are not detected by maturation stages identification. In addition, some conferences have reported machine vision systems for the classification of green coffee beans [24], for characterizing coffee beans from different towns [25], for automatic classification of defects in green coffee beans [26], for coffee black beans identification [27] and for the recognition of defects in coffee beans [28].…”

Section: Introductionmentioning

confidence: 99%

“…A low accuracy for the recognition of defects in coffee beans is presented in [28] and a low accuracy for the inspection of fade and broken beans is presented in [24]. Furthermore, in [27] only black beans are identified.…”

Section: Introductionmentioning

confidence: 99%

Quality and Defect Inspection of Green Coffee Beans Using a Computer Vision System

García

Candelo-Becerra²,

Hoyos

2019

Applied Sciences

View full text Add to dashboard Cite

There is an increased industry demand for efficient and safe methods to select the best-quality coffee beans for a demanding market. Color, morphology, shape and size are important factors that help identify the best quality beans; however, conventional techniques based on visual and/or mechanical inspection are not sufficient to meet the requirements. Therefore, this paper presents an image processing and machine learning technique integrated with an Arduino Mega board, to evaluate those four important factors when selecting best-quality green coffee beans. For this purpose, the k-nearest neighbor algorithm is used to determine the quality of coffee beans and their corresponding defect types. The system consists of logical processes, image processing and the supervised learning algorithms that were programmed with MATLAB and then burned into the Arduino board. The results showed this method has a high effectiveness in classifying each single green coffee bean by identifying its main visual characteristics, and the system can handle several coffee beans present in a single image. Statistical analysis shows the process can identify defects and quality with high accuracy. The artificial vision method was helpful for the selection of quality coffee beans and may be useful to increase production, reduce production time and improve quality control.

show abstract

Classification of Green coffee bean images basec on defect types using convolutional neural network (CNN)

Cited by 61 publications

References 15 publications

Developing Ethiopian Yirgacheffe Coffee Grading Model using a Deep Learning Classifier

Developing Ethiopian Yirgacheffe Coffee Grading Model using a Deep Learning Classifier

Sistema para Classificação de Grãos de Café: Uma Comparação entre Redes Neurais Convolucionais e Processamento Digital de Imagens com MLP

Quality and Defect Inspection of Green Coffee Beans Using a Computer Vision System

Contact Info

Product

Resources

About