Comparative Study of Baseline and CBAM-Enhanced ResNet50 and MobileNetV2 for Indonesian Rupiah Banknote Classification
DOI:
10.33395/sinkron.v10i1.15558Keywords:
CNN; CBAM; ResNet50; MobileNetV2; Banknote Classification; Attention MechanismAbstract
This study investigates the performance of Convolutional Neural Network (CNN) architectures enhanced with Convolutional Block Attention Module (CBAM) for Indonesian banknote classification. Although attention mechanisms have shown strong potential in improving fine-grained visual recognition, their effectiveness for the classification of banknotes with fine textures and similar color patterns remains underexplored, forming a key research gap addressed in this work. Four architectures, ResNet50, ResNet50+CBAM, MobileNetV2, and MobileNetV2+CBAM, were evaluated using K-Fold cross-validation on a dataset of 1,281 images representing seven banknote denominations. Experimental results show that ResNet50 achieves strong baseline performance with a weighted Train accuracy of 99.14% and a Val accuracy of 96.72%, while the integration of CBAM further improves feature discrimination, with ResNet50+CBAM obtaining the highest average accuracy across all folds with a weighted Train accuracy of 100% and a Val accuracy of 99.45%. MobileNetV2 showed lower performance due to its lightweight capacity with a Train accuracy of 91.88% and a decrease in Val accuracy of 85.71%. However, the addition of CBAM provided measurable improvements and greater stability with a Train accuracy of 99.61% and Val accuracy of 92.82%. Overall, CBAM improved CNN’s ability to focus on spatial information and salient channels, resulting in more reliable classification. ResNet50+CBAM emerged as the best-performing model, offering the best balance between accuracy and consistency. These findings support the development of reliable computer vision systems for financial technology applications, including automatic banknote recognition, counterfeit detection, and secure transaction verification.
Downloads
References
Amaludin, F., Zulfa, M. I., & Siswantoro, H. (2025). Pengaruh Hyperparameter Tuning Pada Kinerja MobileNetV2 Dengan Transfer Learning Untuk Deteksi Penyakit Kulit. Jurnal SINTA: Sistem Informasi Dan Teknologi Komputasi, 2(2). https://doi.org/10.61124/SINTA.V2I2.43
Aprillia, D., Rohana, T., Mudzakir, T. Al, & Wahiddin, D. (2024). Deteksi Nominal Mata Uang Rupiah Menggunakan Metode Convolutional Neural Network dan Feedforward Neural Network. KLIK: Kajian Ilmiah Informatika Dan Komputer, 4(4), 2068–2077. https://doi.org/10.30865/KLIK.V4I4.1711
Hanif, M. Z., Saputra, W. A., Choo, Y. H., & Yunus, A. P. (2024). Rupiah Banknotes Detection Comparison of The Faster R-CNN Algorithm and YOLOv5. JURNAL INFOTEL, 16(3), 502–517. https://doi.org/10.20895/INFOTEL.V16I3.1189
Hermanto, A. R., Aziz, A., & Sudianto, S. (2024). Perbandingan Arsitektur MobileNetV2 dan RestNet50 untuk Klasifikasi Jenis Buah Kurma. JUSTIN (Jurnal Sistem Dan Teknologi Informasi), 12(4), 630–637. https://doi.org/10.26418/JUSTIN.V12I4.80358
Ibrahim, M. M., Rahmadewi, R., & Nurpulaela, L. (2023). Pendeteksian Nominal Uang Pada Gambar Menggunakan Convolutional Neural Network: Integrasi Metode Pra-Pemrosesan Citra Dan Klasifikasi Berbasis Cnn. JATI (Jurnal Mahasiswa Teknik Informatika), 7(2), 1394–1400. https://doi.org/10.36040/JATI.V7I2.6863
Ismail, J., Tanti, L., & Wanayumini, W. (2025). Development Of Skin Cancer Pigment Image Classification Using a Combination of Mobilenetv2 and CBAM. JITK (Jurnal Ilmu Pengetahuan Dan Teknologi Komputer), 10(4), 770–780. https://doi.org/10.33480/JITK.V10I4.6541
Kohsasih, K. L., Zarlis, M., & Hayadi, B. H. (2022). Comparison of CNN Architecture for White Blood Cells Image Classification. ICOSNIKOM 2022 - 2022 IEEE International Conference of Computer Science and Information Technology: Boundary Free: Preparing Indonesia for Metaverse Society. https://doi.org/10.1109/ICOSNIKOM56551.2022.10034875
Maulana Azhar, K., Santoso, I., Yosua, D., & Soetrisno, A. A. (2021). Implementasi Deep Learning Menggunakan Metode Convolutional Neural Network Dan Algoritma Yolo Dalam Sistem Pendeteksi Uang Kertas Rupiah Bagi Penyandang Low Vision. Transient: Jurnal Ilmiah Teknik Elektro, 10(3), 502–509. https://doi.org/10.14710/TRANSIENT.V10I3.502-509
Nugroho, F. A., Wiliani, N., & Direvisi, D. (2025). Perbandingan Kinerja ANN dan CNN dalam Tugas Klasifikasi Citra Berbasis Pembelajaran Mesin. Teknomatika: Jurnal Informatika Dan Komputer, 18(1), 22–27. https://doi.org/10.30989/TEKNOMATIKA.V18I1.1561
Nur Hidayat, A. M., Antamil, A., & Zakiyah M, I. (2023). Identifikasi Nominal Mata Uang Rupiah Bagi Penyandang Tunanetra Dengan Algoritma Convolutional Neural Network Berbasis Android. Journal Software, Hardware and Information Technology, 3(2), 60–65. https://doi.org/10.24252/SHIFT.V3I2.102
Pratap, A., & Sardana, N. (2022). Machine learning-based image processing in materials science and engineering: A review. Materials Today: Proceedings, 62(P14), 7341–7347. https://doi.org/10.1016/J.MATPR.2022.01.200
Raja, V. R., Simla, J. A., L B, S. J., & Jemina, L. S. (2024). Enhanced Brain Tumor Analysis: Integrating ResNet50 with Convolutional Block Attention Modules for Advanced Insights. Journal of Electrical Systems, 20(6s), 2601–2612. https://doi.org/10.52783/JES.3272
Rakha, M., Sulistiyo, M. D., Nasien, D., & Ridha, M. (2024). A Combined MobileNetV2 and CBAM Model to Improve Classifying the Breast Cancer Ultrasound Images. Journal of Applied Engineering and Technological Science (JAETS), 6(1), 561–578. https://doi.org/10.37385/JAETS.V6I1.4836
Ratnasri, N., & Sharmilan, T. (2021). Vending Machine Technologies: A Review Article. International Journal of Sciences: Basic and Applied Research (IJSBAR), 58(2), 160–166. https://www.gssrr.org/JournalOfBasicAndApplied/article/view/12579
Rewina, A. E., Sulistyowati, S., Kurniawan, M., N, M. D., & Yunanda, S. F. (2024). Penerapan Metode CNN (Convolutional Neural Network) dalam Mengklasifikasi Uang Kertas dan Uang Logam. TIN: Terapan Informatika Nusantara, 4(12), 778–785. https://doi.org/10.47065/TIN.V4I12.5128
Riski Rahmadan, Nurliani, Efendi Rahayu, Saudah, Ayu Puspita Sari Sinaga, & Enda Ribka Meganta P. (2025). Evaluasi Penerapan Convolutional Neural Network (CNN) untuk Klasifikasi Penyakit Daun Jagung Menggunakan Pendekatan Systematic Literature Review. RJOCS (Riau Journal of Computer Science), 11(1), 19–27. https://doi.org/10.30606/RJOCS.V11I1.3068
Rissa Ilmia Agustin, Jamaludin Indra, Sutan Faisal, Ahmad Fauzi, & Rija Nur Hijriyya. (2024). Klasifikasi Pecahan Uang Kertas Rupiah Menggunakan Transfer Learning Dengan Model MobileNetV2. Jurnal INSTEK (Informatika Sains Dan Teknologi), 9(2), 242–250. https://doi.org/10.24252/INSTEK.V9I2.49123
Robet, R., Angin, J. T. K. P., & Siregar, T. H. (2025). Attention Augmented Deep Learning Model for Enhanced Feature Extraction in Cacao Disease Recognition. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(4), 1965–1977. https://doi.org/10.33395/SINKRON.V9I4.15249
Turahman, T., Hasmin, E., & Aryasa, K. (2024). Analisis Perbandingan Metode Convolutional Neural Network (CNN) dan MobileNet dalam Klasifikasi Penyakit Daun Padi. Jurnal JTIK (Jurnal Teknologi Informasi Dan Komunikasi), 9(1), 368–377. https://doi.org/10.35870/JTIK.V9I1.3218
Zhang, Y., Feng, W., Wu, Z., Li, W., Tao, L., Liu, X., Zhang, F., Gao, Y., Huang, J., & Guo, X. (2023). Deep-Learning Model of ResNet Combined with CBAM for Malignant–Benign Pulmonary Nodules Classification on Computed Tomography Images. Medicina (Lithuania), 59(6). https://doi.org/10.3390/MEDICINA59061088
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2026 Alvin, Robet, Feriani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
Muhammad Khoiruddin harahap
