Intelligent Analysis for Supporting Veterinary Inspection in Slaughterhouses Based on Computer Vision
DOI:
https://doi.org/10.30681/rbegdr.v8i3.14507Keywords:
Artificial Intelligence, Computer Vision, Convolutional Neural Networks (CNNs), Food Inspection, Recurrent Neural Networks (RNNs), Vision Transformers (ViTs)Abstract
The advancement of artificial intelligence and computer vision technologies has revolutionized veterinary inspection processes in meat processing plants, providing greater precision, efficiency, and food safety. This study aimed to analyze the integrated application of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Vision Transformers (ViTs) in intelligent systems focused on anomaly detection and quality control. The methodology used was an integrative review of publications between 2021 and 2025 in scientific databases. The results indicate that the combination of these architectures enhances visual and predictive analysis, allowing for more reliable and real-time automated decisions. It is concluded that the integration of neural networks represents a significant evolution for the modernization of food inspection, promoting a proactive, autonomous, and data-driven approach.
Downloads
References
ALMJALLY, A.; ALMUKADI, W. S. Deep computer vision with artificial intelligence based sign language recognition to assist hearing and speech-impaired individuals. Scientific Reports, v. 15, art. 32268, 2025. DOI: 10.1038/s41598-025-09106-8. Disponível em: https://www.nature.com/articles/s41598-025-09106-8. Acesso em: 17 out. 2025.
ALVAREZ-GARCÍA, J.; LI, J.; WANG, Y.; et al. Implementing AI to measure meat quality at multiple stages of the beef value chain. International Journal of Food Science & Technology, 2024. Disponível em: https://onlinelibrary.wiley.com/doi/10.1111/ijfs.17205. Acesso em: 17 out. 2025.
ALZAHRANI, S. A. Artificial Intelligence for Skin Lesion Analysis based on Computer
Vision and Deep Learning. 2023. Tese (Doutorado), University of Liverpool. Disponível em: https://livrepository.liverpool.ac.uk/3160728/1/AlzahraniSamah_Apr2023_3160728.pdf. Acesso em: 17 out. 2025.
BLACK, M. T. Application of Multispectral Imaging for Identification of Poultry Carcass Condemnations and Fecal Contamination. 2024. Tese (Doutorado em Engenharia), Auburn University, Auburn, AL. Disponível em:
https://etd.auburn.edu/bitstream/handle/10415/9291/Full%20Thesis.pdf. Acesso em: 17 out. 2025.
BLACK, M. T.; XUE, F.; WANG, J.; et al. Detection of visible and invisible fecal contamination on chicken carcasses using multispectral fluorescence imaging and machine learning to mitigate Salmonella risks. Journal of Food Protection, v. 88, n.10, p.100613. 2025. Disponível em: https://pubmed.ncbi.nlm.nih.gov/40912660/. Acesso em: 17 out. 2025.
DING, H.; HOU, H.; WANG, L.; CUI, X.; YU, W.; WILSON, D. I. Application of
Convolutional Neural Networks and Recurrent Neural Networks in Food Safety. Foods, v. 14, n. 2, art. 247. 2025. Disponível em: https://www.mdpi.com/2304-8158/14/2/247. Acesso em: 17 out. 2025.
DU, Y.; WANG, H.; CUI, W.; ZHU, H.; GUO, Y.; DHAREJO, F. A.; ZHOU, Y. Foodborne disease risk prediction using multigraph structural long short-term memory networks: algorithm design and validation study. JMIR Medical Informatics, v. 9, n. 8, e29433, 2021. Disponível em: https://medinform.jmir.org/2021/8/e29433/. Acesso em: 17 out. 2025.
FERRI, F.; FERRARI, E.; MONTI, M.; et al. Automated detection and imaging of dorsal and lateral skin lesions for welfare assessment in pig carcasses at slaughter. Computers and Electronics in Agriculture, 2024. Disponível em:
https://www.sciencedirect.com/science/article/pii/S0168169924004496. Acesso em: 17 out. 2025.
GAO, J.; AGARWAL, R. AI Test Modeling for Computer Vision System—A Case Study. Computers, v. 14, n. 9, art. 396, 2025. DOI: 10.3390/computers14090396. Disponível em: https://www.mdpi.com/2073-431X/14/9/396. Acesso em: 17 out. 2025.
GENG, Z.; WANG, X.; JIANG, Y.; HAN, Y.; MA, B.; CHU, C. Novel IAPSO-LSTM neural
network for risk analysis and early warning of food safety. Expert Systems with Applications, v. 230, art. 120747, 2023. Disponível em:
https://www.sciencedirect.com/science/article/abs/pii/S0957417423012496. Acesso em: 17 out. 2025.
GONÇALVES, D. N.; WEBER, V. A. M.; PISTORI, J. G. B.; et al. Carcass image segmentation using CNN-based methods. Information Processing in Agriculture, 2021;8(4):603-612. Disponível em: https://dx.doi.org/10.1016/j.inpa.2020.11.004. Acesso em: 17 out. 2025.
GORJI, H. T.; SHAHABI, S. M.; SHARMA, A.; et al. Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses. Scientific Reports, 2022;12:2392. Disponível em: https://www.nature.com/articles/s41598022-06379-1. Acesso em: 17 out. 2025.
HASSAN, S. A.; KHALIL, M. A.; AULETTA, F.; FILOSA, M.; CAMBONI, D.;
MENCIASSI, A.; ODDO, C. M. Contamination Detection Using a Deep Convolutional Neural Network with Safe Machine—Environment Interaction. Electronics, v. 12, n. 20, art. 4260, 2023. Disponível em: https://www.mdpi.com/2079-9292/12/20/4260. Acesso em: 17 out. 2025.
JAMIL, S.; ATA, R. U.; LEE, Y.-D. A Comprehensive Survey of Transformers for Computer Vision. Drones, v. 7, n. 5, 287, 2023. DOI: 10.3390/drones7050287. Disponível em: https://www.mdpi.com/2504-446X/7/5/287. Acesso em: 17 out. 2025.
JEONG, K.; et al. Artificial Intelligence in Meat Processing: A comprehensive review of datadriven applications and future directions. Meat and Muscle Biology, 2025. Disponível em: https://www.iastatedigitalpress.com/mmb/article/id/20157/. Acesso em: 17 out. 2025.
LIM, H.; LEE, S.; KIM, J.; et al. Beef carcass grading with EfficientViT: a lightweight vision transformer approach. Applied Sciences, v.15, n.11, p.6302. 2025. Disponível em:
https://www.mdpi.com/2076-3417/15/11/6302. Acesso em: 17 out. 2025.
LUND, D. H.; DAMM, B. I.; KJELDSEN, A. M.; et al. Using latent class modelling to evaluate the performance of a computer vision system for pig carcass contamination. Preventive Veterinary Medicine, v.246, p.106670. 2025. Disponível em: https://pubmed.ncbi.nlm.nih.gov/40359587/. Acesso em: 17 out. 2025.
LUND, D. H.; DAMM, B. I.; KJELDSEN, A. M.; et al. Comparing computer vision models for detecting chronic pleurisy in pigs. Preventive Veterinary Medicine, v.246, 106701.2025. Disponível em: https://pubmed.ncbi.nlm.nih.gov/41056660/. Acesso em: 17 out. 2025.
SAHA, S.; BASAK, S.; DEMIR, B. Vision transformers on the edge: a comprehensive survey. Neurocomputing, 2025. (Online first). Disponível em:
https://www.sciencedirect.com/science/article/abs/pii/S0925231225012962. Acesso em: 17 out. 2025.
SUN, Z.; et al. Machine learning modelling of human visual motion perception. Nature Machine Intelligence, 2025. DOI: 10.1038/s42256-025-00924-8. Disponível em: https://www.nature.com/articles/s42256-025-00924-8. Acesso em: 17 out. 2025.
WAELEN, R. The power of computer vision – Promise, potential and peril. 2023. Tese (Doutorado), University of Twente. Disponível em: https://research.utwente.nl/en/publications/the-power-of-computer-vision-promise-potentialand-peril. Acesso em: 17 out. 2025.
WANG, Y.; DENG, Y.; ZHENG, Y.; CHATTOPADHYAY, P.; WANG, L. Vision Transformers for Image Classification: A Comparative Survey. Technologies, v. 13, n. 1, 32, 2025. DOI: 10.3390/technologies13010032. Disponível em: https://www.mdpi.com/2227-7080/13/1/32. Acesso em: 17 out. 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Revista Brasileira de Estudos de Gestão e Desenvolvimento Regional

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Esta revista oferece acesso livre imediato ao seu conteúdo, seguindo o princípio de que disponibilizar de forma gratuita, a produção da comunidade científica ao público, proporciona maior democratização do conhecimento. A política é Acesso Aberto.
Adotamos a licença CC Attribution-NonCommercial 4.0, a qual permite o compartilhamento, uso, citação, adaptação, desde que citada fonte e não alterada a licença inicial. O uso da publicação para fins comerciais não é permitido. Dessa maneira não são cobradas nenhum tipo de taxa na revista.