<![CDATA[Coconut oil quality assessment is important for ensuring product safety, commercial value, and consumer acceptance; however, conventional laboratory-based evaluation methods are often time-consuming, costly, and impractical for real-time applications. This study proposes a real-time coconut oil quality classification system using smartphone imaging integrated with a Convolutional Neural Network (CNN) model. A total of 60 coconut oil images were collected under controlled conditions and categorized into High Quality, Medium Quality, and Low Quality classes. The dataset underwent preprocessing stages including resizing, normalization, and augmentation before CNN training and evaluation. Experimental results showed that the proposed model achieved an accuracy of 93.33%, precision of 93.20%, recall of 92.80%, and F1-score of 93.00%, demonstrating reliable multi-class classification performance. In addition, the system achieved an average real-time prediction time of approximately 0.82 seconds per image on a smartphone device, indicating fast and efficient mobile-based implementation. The findings confirm that smartphone imaging combined with deep learning provides a portable, low-cost, non-destructive, and practical solution for intelligent coconut oil quality monitoring in food and agricultural applications.]]>
Copyrights © 2026
