Classification of Wrist Accessories: Advanced Watches with Logistic Regression, SVM, and Deep Features from Inception V3 and VGG-19
DOI:
https://doi.org/10.26905/jtmi.v11i1.15571Keywords:
Wristwatch classification, Deep Learning, Inception V3, Logistic RegressionAbstract
This study proposes a hybrid classification framework for wrist accessories (Analog, Automatic, Digital, and Smartwatches) by combining deep learning-based feature extraction (Inception V3 and VGG-19) with traditional classifiers (Logistic Regression and SVM). The Inception V3 + Logistic Regression model achieved the highest performance, with 95% accuracy and an AUC of 0.999. t-SNE visualization revealed distinct clusters for Digital and Smartwatches, while Analog and Automatic categories exhibited partial overlap, indicating challenges in distinguishing visually similar classes. The findings underscore the effectiveness of deep features in improving classification accuracy. Practical applications include retail inventory management, counterfeit detection, and e-commerce product sorting, highlighting the model's real-world adaptability and scalability. This approach demonstrates the potential of hybrid techniques in enhancing automated classification systems for wrist accessories.
Downloads
References
Chen, Z., Liu, Y., & Wang, T. (2023). Data Augmentation for Wearable Product Classification Using CNNs. IEEE Access, 11, 17845–17855.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR).
Garg, D., Singh, M., & Kaur, R. (2022). Vision-based Smartwatch Identification Using Deep Learning. Procedia Computer Science, 198, 734–741.
Khandelwal, A., Patel, V. M., & Singh, R. (2022). A Survey on Multimodal Deep Learning for Computer Vision and Pattern Recognition. Pattern Recognition, 121, 108194.
Hakim, A. N., Wibowo, A., & Prasetyo, Y. E. (2025). Analisis Kombinasi Klasifikasi Machine Learning dengan Teknik Seleksi Fitur untuk Model Analisis Kinerja Dosen. Jurnal Teknologi dan Manajemen Informatika (JTMI), 24(2), 285–296.
Hameed, M. M., Mahmood, M., & Kim, K. (2022). Combining Deep Features and Traditional Classifiers for Improved Medical Image Classification. Computers in Biology and Medicine, 145, 105406.
Ismail, M. H., Hussain, M., & Khan, S. (2023). Hybrid Feature Extraction for Improved Image Classification Using CNN and Traditional Machine Learning. Multimedia Tools and Applications, 82, 1–19.
Mursyid, R., Zulkarnain, Z., & Rahmawati, L. (2021). Perbandingan Model Deep Learning untuk Klasifikasi Sentimen. Jurnal Teknologi dan Manajemen Informatika (JTMI), 7(2), 95–112.
Nguyen, H. T., Pham, M. H., & Le, N. D. (2023). Hybrid Deep Learning Approach for Retail Product Image Classification. Journal of Imaging, 9(1), 15.
Pasaribu, D. H., Situmorang, M. M., & Arifin, R. (2023). Pemanfaatan Metode Convolutional Neural Network (CNN) dengan Transfer Learning untuk Klasifikasi Citra Rumah Adat Malaka. Jurnal Teknologi dan Manajemen Informatika (JTMI), 9(2), 91–98.
Sabbir, M. M., Islam, M. M., & Hasan, M. M. (2021). Deep Transfer Learning for Image-Based Product Recognition Using SVM. Sensors, 21(9), 3208.
Saini, H., & Sikka, G. (2021). Fine-Grained Visual Categorization for Wrist-Worn Devices Using Deep Convolutional Networks. Multimedia Tools and Applications, 80, 27107–27126.
Wang, Y., Zhang, X., & Li, P. (2022). Lightweight and Efficient CNN Feature Integration with SVM for Image Classification Tasks. Applied Intelligence, 52(4), 4123–4137.
Zhao, H., Jiang, H., Jia, Y., & Wang, H. (2021). Deep Feature Fusion and SVM for Fine-Grained Image Classification. IEEE Access, 9, 134250–134261.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
(1)Â Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the journal.
(2) Publisher of JTMI: Jurnal Teknologi dan Manajemen Informatika is University of Merdeka Malang.
(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.
