Analisis Performa dan Efisiensi VGG16, ResNet50, dan MobileNetV2 pada Klasifikasi Citra Jajanan Tradisional
-
Ni Luh Widi Rahayu
*
Universitas Bali Internasional Muhammadiyah, Denpasar,
Indonesia
- Ni Kadek Bumi Krismentari Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia
- I Kayan Herdiana Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia (*) Corresponding Author
Abstract
Previous research on traditional food image classification demonstrated that the VGG16 architecture could achieve good classification performance. However, the study focused on a single architecture and did not provide a comprehensive comparison between predictive performance and computational efficiency across multiple models. This limitation highlights the need to evaluate other architectures in order to identify a model that is not only accurate but also suitable for different deployment environments. This study aims to compare the performance and efficiency of three transfer learning architectures, namely VGG16, ResNet50, and MobileNetV2, for traditional food image classification. The dataset consisted of 2,445 images grouped into ten classes: batun bedil, bubur injin, jaje lukis, jaje piling, jaje wajik, kaliadrem, klepon, laklak, ongol-ongol, and pisang rai. The dataset was divided using a 70:15:15 ratio into 1,706 training images, 363 validation images, and 376 testing images. All models were trained under the same configuration, using an input size of 224 × 224 pixels, batch size of 64, Adam optimizer, learning rate of 0.0001, categorical crossentropy loss, data augmentation, and 10 epochs. Model evaluation was conducted using accuracy, precision, recall, F1-score, training time, model size, and inference time per image. The results showed that ResNet50 achieved the best classification performance, with an accuracy of 84.04%, precision of 85.15%, recall of 85.16%, and F1-score of 84.89%. MobileNetV2 achieved an accuracy of 82.45% with the smallest model size of 12.98 MB, while VGG16 obtained an accuracy of 73.67%. These findings indicate that ResNet50 is more suitable for systems that prioritize classification performance, whereas MobileNetV2 is more appropriate for applications requiring a lightweight model. The contribution of this study lies in the comparative evaluation of performance and efficiency across three architectures under the same experimental setting, resulting in practical model recommendations based on deployment requirements.
Downloads
References
Akmal, L., Yadi, I. Z., Kunang, Y. N., & Sari, F. (2026). Pengembangan Aplikasi Presensi Berbasis Deep Learning. Jurnal Ilmu Komputer Dan Sistem Informasi (JIRSI), 5(2), 219–233. https://doi.org/10.70340/jirsi.v5i2.354
Alfan, D. S., & Kumalasari, I. (2026). Implementasi Model Deep Learning MobileNetV2 untuk Klasifikasi Citra Melanoma Berbasis Web. Journal of Information System Research (JOSH), 7(3), 670–680. https://doi.org/10.47065/josh.v7i3.8848
Amini, A., Nurul, F., & Zalmi, H. (2025). Strategi Preservasi Pengetahuan Tradisional Minangkabau Melalui Digitalisasi Tradisi Lisan Di Perpustakaan Perguruan Tinggi. Jurnal Ilmu Perpustakaan Dan Informasi Islam, 5(1), 76–86. https://doi.org/10.37108/almaarif.v5i1.2316
Arumsari, D., Kharisma, & Ulfi Saidata Aesyi. (2024). Sistem Chatbot Layanan Informasi Mahasiswa Menggunakan Algoritma Long Short-Term Memory. Indonesian Journal on Data Science, 2(2), 77–86. https://doi.org/10.30989/ijds.v2i2.1489
Bagaskara, M., Putra, D., Bratayadnya, P. A., & Raharjo, A. (2025). Jajanan Khas Bali Dalam Fotografi Komersial. Retina Jurnal Fotografi, 5(1), 118–127. https://doi.org/10.59997/rjf.v5i1.5270
Chen, L., Li, S., Bai, Q., Yang, J., Jiang, S., & Miao, Y. (2021). Review of Image Classification Algorithms Based on Convolutional Neural Networks. Remote Sensing, 13(22). https://doi.org/10.3390/rs13224712
Erlanda, E., & Krisnadi, A. R. (2025). Pengaruh Perubahan Prefrensi Makanan Dan Dampak Tren Kuliner Terhadap Minat Beli Makanan Tradisional Generasi Z Di Jakarta. Pendas : Jurnal Ilmiah Pendidikan Dasar, 10(September), 230–244. https://doi.org/10.23969/jp.v10i03.30741
Felicia Lie, A., Susanto, J. E., Sutarman, M. O., Simon, S., & Tiatri, S. (2026). Peran Makanan Tradisional Dalam Pembentukan Identitas Budaya: Suatu Tinjauan Sistematis. CENDEKIA: Jurnal Ilmu Pengetahuan, 6(1), 80–89. https://doi.org/10.51878/cendekia.v6i1.8195
Fransiska, M., Wiradnyani, N. K., & Suryanto, I. W. (2026). Analisis Popularitas dan Profitabilitas Jajanan Khas Bali pada Toko JASTIP di Wilayah Badung dengan Pendekatan Menu Engineering. Jurnal Ekonomi, Manajemen, Akuntansi Dan Keuangan, 7(1), 1–14. https://doi.org/10.53697/emak.v7i1.3479
Harsana, M., Rinawati, W., & Fauziah, A. (2023). Inventarisasi makanan tradisional dalam menunjang pengembangan wisata kuliner. JPPI (Jurnal Penelitian Pendidikan Indonesia), 9(1), 81–86. https://doi.org/10.29210/ 020221974 Contents
Kertopati, B. W., Yuspi, L., & Fajar, W. N. (2025). JURNAL LOCUS : Penelitian & Pengabdian Nilai-Nilai Kearifan Lokal Kuliner ( Studi Fenomenologi Transformasi Makanan Tradisional Gembus , Makna , serta Eksistensinya sebagai Sumber Ekonomi Masyarakat ). JURNAL LOCUS: Penelitian & Pengabdian, 4(8), 7723–7738. https://doi.org/10.58344/locus.v4i8.4142
Kolanowski, W., Nair, S. S., Varghese, A., & Trz, M. (2025). Post-Certification Quality Analysis of Traditional Indian Fried Snacks. Apllied Sciences, 1–16. https://doi.org/10.3390/app15137404
Kumar, R. (2023). Transfer Learning in Computer Vision: Technique and applications. Tuijin Jishu/Journal of Propulsion Technology, 44, 81–83. https://doi.org/10.52783/tjjpt.v44.i1.2210
Linkon, A. H. M., Labib, M. M., Hasan, T., Hossain, M., & Jannat, M.-E.-. (2021). Deep learning in prostate cancer diagnosis and Gleason grading in histopathology images: An extensive study. Informatics in Medicine Unlocked, 24, 100582. https://doi.org/10.1016/j.imu.2021.100582
Liu, D., Zuo, E., Wang, D., He, L., Dong, L., & Lu, X. (2025). Deep Learning in Food Image Recognition : A Comprehensive Review. Applied Sciences, 1–18. https://doi.org/ 10.3390/app15147626
Liu, L., & Xiao, Z. (2025). Feature-Enhanced TResNet for Fine-Grained Food Image Classification. ArXiv. https://doi.org/10.48550/arXiv.2507.12828
Mufidatuzzainiya, A., & Faisal, M. (2025). Penggunaan Teknik Transfer Learning pada Metode CNN untuk Pengenalan Tanaman Bunga. JISKA (Jurnal Informatika Sunan Kalijaga), 10(2), 195–206. https://doi.org/10.14421/jiska.2025.10.2.195-206
Muriagista, A., & Kurniadi, D. (2025). Implementasi Arsitektur Resnet50 Pada Klasifikasi Motif Batik Indonesia Menggunakan Metode Convolutional Neural Network (CNN). Jurnal Rekayasa Sistem Informasi Dan Teknologi, 2(4). https://doi.org/10.70248/jrsit.v2i4.2375
Najla, A., Adibah, N., Fitria, R., Yan, A., Husna, N., Salsabila, Z. N., & Aulia, S. (2025). Nasionalisme Melalui Pelestarian Makanan Tradisional Indonesia. Jurnal Pendidikan Non Formal, 3(2), 1–8. https://doi.org/10.47134/jpn.v3i2.2287
Nurhidayat, R., & Kania Evita Dewi. (2023). Penerapan Algoritma K-Nearest Neighbor Dan Fitur Ekstraksi N-Gram Dalam Analisis Sentimen Berbasis Aspek. KOMPUTA : Jurnal Ilmiah Komputer Dan Informatika, 12(1), 91–100. https://doi.org/10.34010/komputa.v12i1.9458
Plested, J., Phiri, M., & Gedeon, T. (2025). Deep transfer learning for image classification : a survey. ArXiv. https://doi.org/10.48550/arXiv.2205.09904
Pratama, A. Y., & Ghozi, W. (2025). Prediksi Potensi Kinerja Calon Karyawan Customer Service Call Center Menggunakan Model Machine Learning Berbasis Data Rekrutmen. Building of Informatics, Technology and Science (BITS), 7(1), 201–212. https://doi.org/10.47065/bits.v7i1.7285
Pratama, R. A., Octariadi, B. C., & Alkadri, S. P. A. (2025). Penerapan Learning Vector Quantization Dalam Pengolahan Citra Digital Untuk Deteksi Penyakit Kulit. Jurnal Computer Science and Information Technology (CoSciTech), 6(2), 148–157. https://doi.org/10.37859/coscitech.v6i2.9270
Puspitasari, A., Sava, D., & Roliawati, D. (2025). Indonesian Journal on Data Science Penerapan ResNet-50 CNN untuk Optimalisasi Klasifikasi pada Data Fashion. Indonesian Journal on Data Science, 3(1), 1–12. https://doi.org/10.55382/jurnalpustakadata.v5i2.1117
Rahayu, N. L. W., Gunantara, N., & Sudarma, M. (2024). Klasifikasi Jajanan Khas Bali Untuk Preservasi Pengetahuan Kuliner Lokal. SINTECH JOURNAL, 7(1), 1–14. https://doi.org/10.31598
Reza, H., Biswas, N., Shaikh, S., Rabbani, G., & Chowdhury, M. E. H. (2026). A comprehensive review of convolutional neural networks : foundations , enhancements and applications. Neural Computing and Applications. https://doi.org/Neural Comhttps://doi.org/10.1007/s00521-025-11827-w
Romdona, H., Fitri, A., Qolyubi, A. H., & Azmul, M. (2026). Analisis Adaptasi Pedagang Kue Tradisional Terhadap Produk Makanan Modern Di Pasar Mingguan Manglayang. 1837–1845. https://doi.org/10.61104/alz.v4i3.5531
Satato, Y. R., Prabowo, B. A., & Pramudya, A. L. (2025). Pola Konsumsi dan Persepsi Generasi Z terhadap Ketahanan Pangan : Pengembangan Consumer-Centric Framework. 6(3), 997–1004. https://doi.org/10.47065/jbe.v6i3.8352
Tahir, G. A., & Loo, C. K. (2021). A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment. Healthcare (Basel, Switzerland), 9(12). https://doi.org/10.3390/healthcare9121676
Thiodorus, G., Prasetia, A., Afrizal, L., & Yudistira, N. (2021). Klasifikasi citra makanan / nonmakanan menggunakan metode Transfer Learning dengan model Residual Network Classification of food / non-food images using Transfer Learning method with Residual Network model. Teknologi: Jurnal Ilmiah Sistem Informasi, 11(2), 74–83. http://doi.org/10.26594/teknologi.v11i2.2402
Widjanarko, W., Lusiana, Y., Marhaeni, D. P., & Widodo, B. (2023). The Utilization of Social Media as Traditional Culinary Documentation in Strengthening Local Tourism : A Study on an Instagram Account of @ Dinporabudpar _ banyumas. Atlantis Press SARL. https://doi.org/10.2991/978-2-38476-028-2
Wijaya, N. P., & Christioko, B. V. (2025). Implementasi Arsitektur MobileNetV2 dengan Metode Transfer Learning untuk Identifikasi Objek Wisata Religi. Building of Informatics, Technology and Science (BITS), 7(3). https://doi.org/10.47065/bits.v7i3.8447
Witjaksono, J., Pusadan, M. Y., Anshori, Y., & Ardiansyah, R. (2025). Klasifikasi jenis batik bomba menggunakan convolutional neural network dengan arsitektur efficient-net b2 (batik bomba sulawesi tengah ). JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika), 10(3), 2134–2147. https://doi.org/10.29100/jipi.v10i3.6191
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Performa dan Efisiensi VGG16, ResNet50, dan MobileNetV2 pada Klasifikasi Citra Jajanan Tradisional
Pages: 1018-1031
Copyright (c) 2026 Ni Luh Widi Rahayu, Ni Kadek Bumi Krismentari, I Kayan Herdiana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
