A COMPARATIVE ANALYSIS OF THE MOBILENETV2 AND RESNET50 MODELS FOR LIGHT VEHICLE IMAGE CLASSIFICATION

Authors

  • Syahira Nasywa Andina Humaedi Universitas Ibn Khaldun Bogor
  • Adinda Rahmawati Universitas Ibn Khaldun Bogor
  • Elsha Nurdwi Baharsyah Universitas Ibn Khaldun Bogor
  • Hanif Zaidan Sinaga Universitas Ibn Khaldun Bogor

DOI:

https://doi.org/10.54840/jcstech.v6i2.626

Keywords:

Convolutional Neural Network (CNN), MobileNetV2, ResNet50, Image Classification, Vehicle

Abstract

Advances in transportation technology have driven the need for vehicle identification systems capable of operating automatically, quickly, and accurately, particularly to support the implementation of automated parking systems and smart transportation systems. This study aims to compare the performance of Transfer Learning-based Convolutional Neural Network (CNN) architectures namely MobileNetV2 and ResNet50 in classifying images of cars and motorcycles. The dataset used was sourced from Kaggle and consists of a total of 1,590 images, comprising 790 car images and 800 motorcycle images. The dataset was divided into training data (80%), validation data (10%), and test data (10%). The preprocessing stage included resizing the images to 224 × 224 pixels, normalization, and data augmentation. Both models were trained for 20 epochs using the Adam optimizer with a Transfer Learning approach. Model evaluation was performed using the metrics accuracy, precision, recall, F1-score, and confusion matrix. The test results showed that the MobileNetV2 model achieved an accuracy of 98.74%, a precision of 0.99, a recall of 0.99, and an F1-score of 0.99. Meanwhile, the ResNet50 model achieved an accuracy of 79.87%, a precision of 0.80, a recall of 0.80, and an F1-score of 0.80. These results indicate that MobileNetV2 outperforms ResNet50 in classifying vehicle images. Thus, MobileNetV2 has been shown to deliver better performance and has the potential to be applied as a vehicle classification model in automated parking systems and various AI-based smart transportation applications.

References

Anggay Luri Pramana. (2024). Analisis Perbandingan Evaluasi Metode Deep Learning pada Klasifikasi Jenis Kendaraan. Journal of Computer Science and Visual Communication Design, 9(1), 451–465. https://doi.org/10.55732/jikdiskomvis.v9i1.1252

Armando, M., & Sutresna Wati. (2024). Klasifikasi Kendaraan Militer (Pesawat F16, Kapal Fregat, Tank Leopard) Di Indonesia Menggunakan Convolutional Neural Network (Cnn). Jurnal Elektrosista, 12(1), 64–74. https://doi.org/10.63824/jtep.v12i1.245

Epiphany Shavna Gracia, & Nurul Anisa Sri Winarsih. (2025). Comparison of VGG16 , MobileNetV2, InceptionV3, ResNet50, and Custom CNN Architectures for Furniture Image Classification. Infotekmesin, 16(1), 24–30. https://doi.org/10.35970/infotekmesin.v16i1.2500

Fauzi, D. R., & Haqdu D, G. A. (2025). Comparison of CNN Models Using EfficientNetB0, MobileNetV2, and ResNet50 for Traffic Density with Transfer Learning. Journal of Intelligent Systems Technology and Informatics, 1(1), 22–30. https://doi.org/10.64878/jistics.v1i1.6

Gupta, J., Pathak, S., & Kumar, G. (2022). Deep Learning (CNN) and Transfer Learning: A Review. Journal of Physics: Conference Series, 2273(1). https://doi.org/10.1088/1742-6596/2273/1/012029

Herlawati, H., Hendharsetiawan, A. A., Priatna, W., Dzulqiyana, A. P., & Rahmadant, R. A. (2026). Komparasi Kinerja ResNet50 dan MobileNetV2 pada Klasifikasi Citra Multi-Domain. 10(1), 46–61.

Husnurrizqi, H. A., Kurnia, D. A., Wijaya, Y. A., Dikananda, F., Studi, P., Informatika, T., Studi, P., Informatika, M., Studi, P., & Informasi, S. (2026). KLASIFIKASI CITRA MENGGUNAKAN ARSITEKTUR MOBILENETV2 DENGAN PENDEKATAN TRANSFER LEARNING. 3(03), 1–5.

Nur Ridho, A., Mellyka, G., Saputra, F., & Padmo Azam Masa, A. (2024). Implementasi Metode Convolutional Neural Network (CNN) Untuk Klasifikasi Gambar Mobil dan Motor Menggunakan Keras. Jurnal Jambo Digitech, 1(1), 54–64. https://jurnal.lldikti13.id/index.php/jjd/article/view/24

Prasetyo, M. E., Faza, M. R., Pratama, R., Alhabsy, S. N. H., Purwanti, H., & Masa, A. P. A. (2023). Klasifikasi Ragam Kendaraan Menggunakan Metode Convolutional Neural Network (Cnn). Adopsi Teknologi Dan Sistem Informasi (ATASI), 2(2), 142–148. https://doi.org/10.30872/atasi.v2i2.1156

Radikto, Mulyana, D. I., Rofik, M. A., & Zakaria, M. O. Z. (2022). Klasifikasi kendaraan pada jalan raya menggunakan algoritma convolutional neural network (cnn). Jurnal Pendidikan Tambusai, 6(1), 1668–1679.

Wibowo, B. L., Caesarizky, O. Y., Hakim, M. I., & Munsarif, M. (2024). Penerapan algoritma Convolutional Neural Network (CNN) untuk mengklasifikasi jenis kendaraan. Jurnal Komputer Dan Teknologi Informasi, 2(2), 94–99. https://doi.org/10.26714/jkti.v2i2.13938

Downloads

Published

2026-11-16

How to Cite

Andina Humaedi, S. N., Rahmawati, A., Baharsyah, E. N., & Sinaga, H. Z. (2026). A COMPARATIVE ANALYSIS OF THE MOBILENETV2 AND RESNET50 MODELS FOR LIGHT VEHICLE IMAGE CLASSIFICATION. Journal of Computer Science and Technology (JCS-TECH), 6(2), 60–67. https://doi.org/10.54840/jcstech.v6i2.626

Issue

Section

Articles