<![CDATA[Ensuring the quality and integrity of halal food products has become increasingly important with the growth of the global halal food industry. Conventional quality control methods, which rely on manual inspection and laboratory testing, are often time-consuming, subjective, and prone to human error. This study aims to develop and evaluate a machine vision system powered by deep learning algorithms to automate quality control processes in halal food production. A convolutional neural network (CNN)-based framework was implemented to classify and detect defects, contamination, and non-halal elements in food products. The system was trained using a dataset of 12,500 labeled images collected from halal-certified production facilities, with data augmentation applied to improve model generalization. Performance metrics, including accuracy, precision, recall, and F1-score, were used to evaluate the system. The results demonstrate that the proposed deep learning model achieved 96.8% classification accuracy, with high precision (95.5%) and recall (97.2%), significantly outperforming conventional machine vision techniques. The findings indicate that deep learning-driven machine vision can provide fast, reliable, and scalable quality control, supporting compliance with halal standards while reducing operational costs. This research highlights the potential of artificial intelligence to modernize quality assurance systems in halal food industries. ]]>
Copyrights © 2025
