Implementation of Convolutional Neural Networks for Eyeglass Product Image Retrieval: A Comparative Study of ResNet-50 and MobileNetV2

Handri Taufik; Sajarwo Anggai; Taswanda Taryo

Authors

Handri Taufik Master’s Program in Informatics Engineering, Postgraduate Program, Pamulang University
Sajarwo Anggai Master’s Program in Informatics Engineering, Postgraduate Program, Pamulang University
Taswanda Taryo Master’s Program in Informatics Engineering, Postgraduate Program, Pamulang University

Keywords:

CBIR, CNN, ResNet50, MobileNetV2, Cosine Similarity

Abstract

The increasing similarity among eyewear product designs poses significant challenges for conventional text-based search systems, highlighting the need for effective Content-Based Image Retrieval (CBIR) approaches. This study proposes a CNN-based CBIR system for eyeglass frame and sunglasses retrieval, employing a comparative analysis of ResNet50 and MobileNetV2 as feature extractors. The dataset comprises 4,500 gallery images and 300 query images, with feature similarity measured using cosine similarity and accelerated through FAISS indexing. Experimental results indicate that ResNet50 achieves higher recall (0.0622), demonstrating its ability to capture more complex visual features. In contrast, MobileNetV2 provides superior ranking performance, achieving an mAP of 0.6091 and an MRR of 0.1427, outperforming ResNet50 (mAP of 0.5019 and MRR of 0.0713), while also reducing feature extraction time (0.1348 s versus 0.2023 s). These findings suggest that ResNet50 is more suitable for accuracy-oriented retrieval tasks, whereas MobileNetV2 is better suited for real-time and resource-constrained applications.

References

L. Zheng, Y. Yang, and Q. Tian, “SIFT meets CNN: A decade survey of instance retrieval,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 5, pp. 1224–1244, 2017.

M. W. Sardjono, V. Ramadhan, M. Cahyanti, and E. R. Swedia, “Klasifikasi Bentuk Bingkai (Frame) Kacamata Menggunakan CNN dengan Arsitektur Inception V3 dan Augmented Reality Berbasis Android,” J. Syst. Comput. Eng., vol. 5, no. 2, pp. 204–218, 2024.

A. Babenko and V. Lempitsky, “Aggregating local deep features for image retrieval,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1269–1277.

T. S. Warongan, S. R. U. A. Sompie, and A. Jacobus, “Penerapan Metode Content-Based Image Retrieval untuk Pengenalan Jenis Bunga,” J. Tek. Inform., vol. 13, no. 3, 2018.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, 2017.

A. Gordo, J. Almazan, J. Revaud, and D. Larlus, “End-to-end learning of deep visual representations for image retrieval,” Int. J. Comput. Vis., vol. 124, no. 2, pp. 237–254, 2017.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.

J. Liang, “Image classification based on RESNET,” in Journal of Physics: Conference Series, IOP Publishing, 2020, p. 12110.

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.

W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F. E. Alsaadi, “A survey of deep neural network architectures and their applications,” Neurocomputing, vol. 234, pp. 11–26, 2017.

Y. Gulzar, “Fruit image classification model based on MobileNetV2 with deep transfer learning technique,” Sustainability, vol. 15, no. 3, p. 1906, 2023.

D. R. Fauzi, “Comparison of CNN Models Using EfficientNetB0, MobileNetV2, and ResNet50 for Traffic Density with Transfer Learning,” J. Intell. Syst. Technol. Informatics, vol. 1, no. 1, pp. 22–30, 2025.

S. Karnila, S. Irianto, and R. Kurniawan, “Face recognition using content based image retrieval for intelligent security,” Int. J. Adv. Eng. Res. Sci., vol. 6, no. 1, pp. 91–98, 2019.

M. R. M. Ariefwan, I. Diyasa, and K. M. Hindrayani, “InceptionV3, ResNet50, ResNet18 and MobileNetV2 performance comparison on face recognition classification,” Literasi Nusant., vol. 4, pp. 1–10, 2021.

S. Aras and A. Setyanto, “Deep Learning Untuk Klasifikasi Motif Batik Papua Menggunakan EfficientNet dan Trasnfer Learning,” Insect (Informatics Secur. J. Tek. Inform., vol. 8, no. 1, pp. 11–20, 2022.

J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with GPUs,” IEEE Trans. Big Data, vol. 7, no. 3, pp. 535–547, 2019.

F. Loekman, “Sistem Manajemen Inventori Dengan Pengenalan Barang Secara Otomatis Menggunakan Metode Convolutional Neural Network,” Teknika, vol. 12, no. 1, pp. 47–56, 2023.