Computer vision grading system for physical quality evaluation of green coffee beans

Portugal-Zambrano, Christian E.; Gutierrez-Caceres, Juan C.; Ramirez-Ticona, Juan; Beltrán, César

doi:10.1109/clei.2016.7833383

Cited by 14 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the prototype for bean selection is in the acceptable range (greater than 80.0%) as well as the report of Herrera et al (2016), who determined a level of effectiveness of 87.0% of an automatic coffee fruit selection system that applied Bayesian algorithms based on the minimum error rule. The results also agree with the research of Portugal-Zambrano et al (2016), where the classification of physical defects of green coffee beans with a computer vision system achieved 98.8% effectiveness using the White-Patch algorithm, color histograms as feature extractor and SVM for the classification task. Oliveira et al (2016) demonstrated that neural networks applied to the evaluation of green coffee bean color articulated to a machine vision system classifying beans into off-white, cane green, green, and blue-green, achieved a generalization error of 1.15% and the Bayesian classifier had 100.0% accuracy of all samples.…”

Section: /7supporting

confidence: 89%

Effectiveness of a cherry coffee sorter prototype with image recognition using machine learning

Coral

Bernales-del-Aguila²,

Benavides-Cuvas³

et al. 2023

Agraria

View full text Add to dashboard Cite

The production of specialty coffees is the main objective of coffee growers worldwide and depends on the selection of optimal grains; however, especially in Latin America, they are processed manually and are influenced by subjectivity. The objective of the article was to verify the effectiveness of a cherry coffee sorting prototype with image recognition using machine learning in real time compared to the traditional method in the Valle Grande Association, Peru. Covolutional neural network processing was used. 24,000 images labeled in the Labellmg program of green, ripe, pinton, over-ripe and dry Catimor grains were trained with the YOLOv3 algorithm. The results describe the mechanical-electronic design and assembly procedure of the prototype with the necessary technical specifications for its replication; In addition, they demonstrate their effectiveness in reducing the selection time by approximately 3 hours, with a precision level of 94.0% in four samples of 100 kg of coffee. It is concluded that the prototype is a potential alternative, reducing cost, saving time and providing a useful tool to guarantee the selection of grains that allow obtaining quality higher than 83 SCAA points.

show abstract

Section: /7supporting

confidence: 89%

Effectiveness of a cherry coffee sorter prototype with image recognition using machine learning

Coral

Bernales-del-Aguila²,

Benavides-Cuvas³

et al. 2023

Agraria

View full text Add to dashboard Cite

show abstract

“…C. E. Portugal-Zambrano et al (2016) focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was developed to capture the images of coffee beans, the software uses a White-Patch algorithm as a image enhancement procedure, color histograms as feature extractor and SVM for the classification task, a database of 1930 images was collected, they used 13 categories of defects described in the SCAA standard of evaluation.…”

Section: Literature R Eviewmentioning

confidence: 99%

Analysis on Artificial Recurrent Neural Network for Sequence Classification of Audio Data

Singh¹,

Singh²,

Kaur³

et al. 2021

Middle East Res J Engr Technol

View full text Add to dashboard Cite

Recurrent neural networks (RNNs) are capable of learning features and long-term dependencies from sequential and time-series data. The RNNs have a stack of non-linear units where at least one connection between units forms a directed cycle. A well-trained RNN can model any dynamical system; however, training RNNs is mostly plagued by issues in learning long-term dependencies. In this paper, we present a survey on RNNs and several new advances for newcomers and professionals in the field. In this paper literature survey on Artificial Recurrent Neural Network has been presented.

show abstract

“…The rotating type classifier has several sieves with different hole diameters. The vibrating type-classifier is mechanically driven from electrical energy to the frame, then proceeds to the sieves section [30,31].…”

Section: Introductionmentioning

confidence: 99%

Design and Performance Test of the Coffee Bean Classifier

Ansar¹,

Sukmawaty²,

Murad³

et al. 2021

Preprint

View full text Add to dashboard Cite

Nowadays, some coffee production centers are still classification manually, so it requires a very long time, a lot of labor, and expensive operational costs. Therefore, the purpose of this research was to design and performance of the coffee bean classifier that can accelerate the process of classification beans. The classifier used consists of three main parts, namely the frame, driving force, and sieves. Research parameters include classifier work capacity, power, specific energy, classification distribution and effectiveness, and efficiency. The results showed that the best operating conditions of the coffee bean classifier was found at a rotational speed of 91.07 rpm and a 16° sieves angle with a classifier working capacity of 38.27 kg/h, the distribution of the seeds retained in the first sieve was 56.77 %, the second sieves was 28.12%, and the third sieves was 15.11%. The efficiency of using a classifier was found at a rotating speed of 91.07 rpm and a sieves angle of 16°. This classifier was simple in design, easy to operate, and can sort coffee beans into three classification, namely small, medium, and large.

show abstract

Computer vision grading system for physical quality evaluation of green coffee beans

Cited by 14 publications

References 24 publications

Effectiveness of a cherry coffee sorter prototype with image recognition using machine learning

Effectiveness of a cherry coffee sorter prototype with image recognition using machine learning

Analysis on Artificial Recurrent Neural Network for Sequence Classification of Audio Data

Design and Performance Test of the Coffee Bean Classifier

Contact Info

Product

Resources

About