Tri Mulya Dharma, Ramzi Adriman, Khairun Saddami, Rizka Ramadhana
Traditional methods for assessing beef quality often lack the precision needed to reliably differentiate between fresh and spoiled meat. To address this limitation, this study proposes a deep learning-based classification system supported by a newly developed image dataset of beef samples. The dataset comprises 2,240 balanced images, with 1,120 labeled as fresh and 1,120 as rotten, captured under controlled conditions to ensure consistency. Three pre-trained Convolutional Neural Network (CNN) models-VGG16, ResNet50-V2, and Inception-V3-were evaluated using a transfer learning approach. Among them, VGG16 demonstrated superior performance, achieving an accuracy of 99.46%, precision of 99.29%, sensitivity of 99.64%, and an F1-score of 99.47%. These results highlight the effectiveness of the VGG16 model in classifying beef freshness and demonstrate the potential of the proposed dataset and approach to provide a more objective, accurate, and scalable solution compared to conventional assessment techniques. This study contributes a novel benchmark for future research in meat quality evaluation using artificial intelligence. © 2025 IEEE.
Universitas Syiah Kuala, Banda Aceh, Indonesia; Universitas Syiah Kuala, Department of Electrical and Computer Engineering, Banda Aceh, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock