Deep learning-based detection of wine bottle capsules for contamination prevention

Quality control of wine bottle packaging is crucial for preventing wine contamination and safety hazards, ensuring product integrity, and maintaining the overall quality of the product. The presence of metallic capsules has been demonstrated to significantly reduce airborne contamination, particular...

Full description

Saved in:
Bibliographic Details
Main Authors: Diego Caballero-Ramírez, Guilherme Tortorella, Jorge García-Alcaraz, Emilio Jiménez-Macías, Jorge Limon-Romero, Yolanda Baez-Lopez, Diego Tlapa
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025024582
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850071822837481472
author Diego Caballero-Ramírez
Guilherme Tortorella
Jorge García-Alcaraz
Emilio Jiménez-Macías
Jorge Limon-Romero
Yolanda Baez-Lopez
Diego Tlapa
author_facet Diego Caballero-Ramírez
Guilherme Tortorella
Jorge García-Alcaraz
Emilio Jiménez-Macías
Jorge Limon-Romero
Yolanda Baez-Lopez
Diego Tlapa
author_sort Diego Caballero-Ramírez
collection DOAJ
description Quality control of wine bottle packaging is crucial for preventing wine contamination and safety hazards, ensuring product integrity, and maintaining the overall quality of the product. The presence of metallic capsules has been demonstrated to significantly reduce airborne contamination, particularly from 2,4,6-trichloroanisol (TCA), a major contributor to cork taint. Traditional capsule detection in the wine industry primarily relies on visual inspection, thus prone to human error. Despite the progress of Industry 4.0, the application of artificial intelligence (AI) for automated inspection in the wine industry remains limited. This study evaluates the suitability of deep learning (DL) for inspecting capsules in wine bottles. A dataset of 12,050 images was used to train, test, and validate the performance of YOLOv8, YOLOv9, and YOLOv11 models. All three models demonstrated similar performance, achieving high precision (>96 %), recall (>97 %), and mAP (>98 %). Notably, YOLOv11 exhibited the fastest inference speed, making it a strong candidate for real-time detection. These results demonstrated the feasibility of deep learning (DL) in assisting humans with wine packaging inspection to prevent further airborne contamination and enhance real-time quality control. The proposed approach provides a practical and affordable solution to reduce reliance on manual inspection, particularly for small and medium producers, making inspection processes smarter and more efficient.
format Article
id doaj-art-38d3f346377545e19f1bb1b562871f0e
institution DOAJ
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-38d3f346377545e19f1bb1b562871f0e2025-08-20T02:47:13ZengElsevierResults in Engineering2590-12302025-09-012710638810.1016/j.rineng.2025.106388Deep learning-based detection of wine bottle capsules for contamination preventionDiego Caballero-Ramírez0Guilherme Tortorella1Jorge García-Alcaraz2Emilio Jiménez-Macías3Jorge Limon-Romero4Yolanda Baez-Lopez5Diego Tlapa6Facultad de Ingeniería, Arquitectura y Diseño; Universidad Autónoma de Baja California, Ensenada 21100, MexicoDepartment of Mechanical Engineering, The University of Melbourne, Melbourne 3052, Australia; IAE Business School, Universidad Austral, Buenos Aires 1611, Argentina; Fundacao Dom Cabral, Belo Horizonte, BrazilDepartment of Industrial Engineering and Manufacturing, Institute of Engineering and Technology, Universidad Autónoma de Ciudad Juárez, Juárez 32310, Chihuahua, MexicoDepartment of Electric Engineering, Universidad De La Rioja, Logroño 26004, EspañaFacultad de Ingeniería, Arquitectura y Diseño; Universidad Autónoma de Baja California, Ensenada 21100, MexicoFacultad de Ingeniería, Arquitectura y Diseño; Universidad Autónoma de Baja California, Ensenada 21100, MexicoFacultad de Ingeniería, Arquitectura y Diseño; Universidad Autónoma de Baja California, Ensenada 21100, Mexico; Corresponding author.Quality control of wine bottle packaging is crucial for preventing wine contamination and safety hazards, ensuring product integrity, and maintaining the overall quality of the product. The presence of metallic capsules has been demonstrated to significantly reduce airborne contamination, particularly from 2,4,6-trichloroanisol (TCA), a major contributor to cork taint. Traditional capsule detection in the wine industry primarily relies on visual inspection, thus prone to human error. Despite the progress of Industry 4.0, the application of artificial intelligence (AI) for automated inspection in the wine industry remains limited. This study evaluates the suitability of deep learning (DL) for inspecting capsules in wine bottles. A dataset of 12,050 images was used to train, test, and validate the performance of YOLOv8, YOLOv9, and YOLOv11 models. All three models demonstrated similar performance, achieving high precision (>96 %), recall (>97 %), and mAP (>98 %). Notably, YOLOv11 exhibited the fastest inference speed, making it a strong candidate for real-time detection. These results demonstrated the feasibility of deep learning (DL) in assisting humans with wine packaging inspection to prevent further airborne contamination and enhance real-time quality control. The proposed approach provides a practical and affordable solution to reduce reliance on manual inspection, particularly for small and medium producers, making inspection processes smarter and more efficient.http://www.sciencedirect.com/science/article/pii/S2590123025024582Wine industryQuality controlArtificial intelligenceDeep learningYOLO models
spellingShingle Diego Caballero-Ramírez
Guilherme Tortorella
Jorge García-Alcaraz
Emilio Jiménez-Macías
Jorge Limon-Romero
Yolanda Baez-Lopez
Diego Tlapa
Deep learning-based detection of wine bottle capsules for contamination prevention
Results in Engineering
Wine industry
Quality control
Artificial intelligence
Deep learning
YOLO models
title Deep learning-based detection of wine bottle capsules for contamination prevention
title_full Deep learning-based detection of wine bottle capsules for contamination prevention
title_fullStr Deep learning-based detection of wine bottle capsules for contamination prevention
title_full_unstemmed Deep learning-based detection of wine bottle capsules for contamination prevention
title_short Deep learning-based detection of wine bottle capsules for contamination prevention
title_sort deep learning based detection of wine bottle capsules for contamination prevention
topic Wine industry
Quality control
Artificial intelligence
Deep learning
YOLO models
url http://www.sciencedirect.com/science/article/pii/S2590123025024582
work_keys_str_mv AT diegocaballeroramirez deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT guilhermetortorella deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT jorgegarciaalcaraz deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT emiliojimenezmacias deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT jorgelimonromero deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT yolandabaezlopez deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention
AT diegotlapa deeplearningbaseddetectionofwinebottlecapsulesforcontaminationprevention