Issue 26, 2024

Computer vision with artificial intelligence for a fast, low-cost, eco-friendly and accurate prediction of beer styles and brands

Abstract

Beer is the most consumed alcoholic beverage worldwide and are highly susceptible to fraudulent processes. Traditional sensory analysis can lack precision. With the growth of Industry 4.0, new techniques using artificial intelligence are being developed to address this issue. This scenario makes it appealing to propose low-cost techniques with broad classification capabilities based on sample fingerprints, such as computer vision (CV). CV involves image acquisition, processing, and classification using machine learning. In this work, a computer vision prototype associated with an artificial neural network was developed to classify beer in terms of style and brand. A total of 111 samples were analyzed in triplicate, with the data separated into training and testing sets. Accuracy and precision above 96% were obtained for the training set and 78% for the test set. The computer vision method proved to be a simple, low-cost, eco-friendly, and fast tool for detecting fraud in the brewing industry.

Graphical abstract: Computer vision with artificial intelligence for a fast, low-cost, eco-friendly and accurate prediction of beer styles and brands

Supplementary files

Article information

Article type
Paper
Submitted
03 Apr 2024
Accepted
10 Jun 2024
First published
12 Jun 2024

Anal. Methods, 2024,16, 4285-4290

Computer vision with artificial intelligence for a fast, low-cost, eco-friendly and accurate prediction of beer styles and brands

J. Victor de Sousa Dutra, M. O. Salles, R. C. Michel and D. L. Vale, Anal. Methods, 2024, 16, 4285 DOI: 10.1039/D4AY00617H

To request permission to reproduce material from this article, please go to the Copyright Clearance Center request page.

If you are an author contributing to an RSC publication, you do not need to request permission provided correct acknowledgement is given.

If you are the author of this article, you do not need to request permission to reproduce figures and diagrams provided correct acknowledgement is given. If you want to reproduce the whole article in a third-party publication (excluding your thesis/dissertation for which permission is not required) please go to the Copyright Clearance Center request page.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements