Classification of Robusta Coffee Fruits at Different Maturation Stages Using Colorimetric Characteristics

Costa, Anderson Gomide; Sousa, Daniela A. G. de; Paes, Juliana Lobo; Cunha, João Paulo Barreto; Oliveira, Marcus Vinícius Moraes de

doi:10.1590/1809-4430-eng.agric.v40n4p518-525/2020

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, it categorizes them according to their defects as normal, black, sour, broken, very long berry, and small. Costa et al [7] obtained colorimetric variables using the RGB, CIE L*a*b*, and HSV models combined with the Kmeans technique to classify coffee fruits. They reduced the colorimetric variables using Principal Component Analysis.…”

Section: Related Workmentioning

confidence: 99%

Enhancing green coffee quality assessment through deep learning

Pereira Neto,

Sousa,

Moreira

et al. 2023

Anais Do XVIII Workshop De Visão Computacional (WVC 2023)

View full text Add to dashboard Cite

Coffee is the world’s most consumed commodity beverage, vital for the Brazilian market. Assessing coffee bean quality through visual features is essential for market value. However, human-based visual analysis has limitations. Deep neural networks, particularly CNNs, offer a promising solution by automating this process. In this work, we propose an evaluation of deep learning models and training strategies to classify green coffee beans automatically. We evaluate four CNN architectures: AlexNet, ResNet-50, MobileNet V3, and EfficientNet B4. After a hyperparameter optimization step, the models were fine-tuned, and we evaluated the impact of data augmentation strategies on the classification performance through the USK-Coffee dataset. EfficientNet B4 excels, achieving 0.8844 accuracy when trained with data augmentation. Our findings showcase deep learning’s potential for coffee quality assessment, aiding professionals in classifying and guaranteeing coffee quality and value.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing green coffee quality assessment through deep learning

Pereira Neto,

Sousa,

Moreira

et al. 2023

Anais Do XVIII Workshop De Visão Computacional (WVC 2023)

View full text Add to dashboard Cite

show abstract

“…Fakta seperti ini mengindikasikan bahwa jenis klon dan metode panen yang dilakukan oleh petani setempat di OKU Selatan tidak berdampak nyata terhadap atribut sensori yang dihasilkan, dan hasil ini sesuai dengan hasil analisis ragam multivariat seperti yang ditampilkan pada Tabel 3. Tidak adanya pengaruh yang nyata dari perlakuan pemanenan dan pengolahan berlawanan dengan hasil penelitian Montavon et al (2003), Rodrigues et al (2015), Tarigan & Towaha (2017), Costa et al (2020), Hidayat et al (2021), dan Rabelo et al (2021) yang menyatakan adanya hubungan yang positif antara tingkat kematangan buah (buah merah) dengan kandungan kimia dan kualitas kopi. Hasil penelitian lainnya menunjukkan bahwa buah kopi yang dipanen merah lebih cepat berkecambah karena buah tersebut telah matang secara fisiologis (Saefudin & Wardiana, 2013), yang mengindikasikan telah tercapainya kondisi maksimum komponen kimia yang terkandung didalamnya.…”

Section: Pengelompokkan Perlakuan Berdasarkan Metode Analisis Klasterunclassified

Pemetaan Atribut Sensori Kopi Kobura Berdasarkan Perbedaan Cara Panen dan Pengolahan di Tingkat Petani

Randriani

Tarigan

Wardiana

2021

J. tanam. industri dan penyegar

View full text Add to dashboard Cite

<p><em>In general, Kobura coffee farmers in South Ogan Komering Ulu (OKU) harvest coffee with the criteria of red fruit and a mixture of red and green, while the processing method is a dry process. However, the sensory attributes of these activities are not yet known. This study aims to map the sensory qualities of Kobura coffee at the farmer level based on differences in harvesting and processing methods. The research was carried out in Banding Agung District, South OKU Regency, and the Coffee and Cocoa Bioindustry Laboratory, Balittri, Sukabumi, from March to December 2019. The design used was a completely randomized design with 3 treatment factors and two replications. The first factor was three clones of Kobura coffee (Kobura 1, 2, 3), the second factor was two harvesting methods (red and mix of red + green fruit), and the third factor is two processing methods (dry and wet). The variable observed were the sensory attributes analyzed by multivariate analysis of variance, principal component analysis, cluster analysis, and path analysis. The results showed that the harvesting and processing methods of Kobura coffee at the farmer level in South OKU did not significantly affect the sensory. Furthermore, each cluster's harvesting and processing methods were evenly distributed because the proportion between red and green fruit was not clearly identified in the mixed fruit harvest. Superior genetic and optimal altitude factors make Kobura coffee categorized into Fine Robusta with a final score of 81.13-85.75. The final score is directly and dominantly influenced by mouthfeel (body), flavor, overall, and fragrance, respectively.</em></p>

show abstract

“…Adicionalmente, también se han llevado a cabo investigaciones en el sector de la caficultura a partir de técnicas de aprendizaje supervisado con el fin de obtener patrones del grano. Por ejemplo: Mediante redes neuronales convolucionales (CNN) se clasificaron los granos de café verde a través sus defectos (Pinto et al, 2017); Por regresión de mínimos cuadrados se obtiene la predicción de componentes como sacarosa, cafeína y trigonelina en granos de café verde (Caporaso et al, 2017); Se realiza la clasificación de tres especies de granos de café por medio el procesamiento de imágenes y la implementación de una red neuronal artificial (Arboleda et al, 2018); Se clasifican los frutos de café a través de sus características colorimétricas usando fotografías (Costa et al, 2020), entre otros. No obstante, la mayoría de estos estudios no llegan a implementarse en softwares de fácil uso para los caficultores.…”

unclassified