<![CDATA[This study aims to develop an efficient and accurate model for classifying clothing material types using the MobileNetV3 architecture. Clothing material images were collected from open sources and processed through resizing, normalization, and data augmentation. The model was trained using transfer learning and evaluated using accuracy, precision, recall, and F1-score metrics. The evaluation results showed an accuracy of 92%, with the best performance in the silk and polyester categories. However, misclassifications still occurred for materials with similar textures, such as linen and cotton. Compared to previous studies, this approach offers advantages in computational efficiency for mobile and edge computing applications. This research contributes to the development of an automated clothing material classification system to support the textile and fashion industries. Further improvements are needed by enhancing dataset quality and fine-tuning the model to better distinguish materials with visually similar characteristics.]]>
Copyrights © 2025
