Deep Learning-Based Classification of Cikadu Batik Motifs Using ResNet50 and MobileNetV2
DOI:
10.33395/sinkron.v10i3.16368Keywords:
Batik Motif Classification, Cikadu Batik, Convolutional Neural Network, Deep Learning, MobileNetV2, ResNet50, Transfer LearningAbstract
Batik motif recognition is essential for cultural heritage preservation and the digitization of traditional Indonesian textile knowledge. This study proposes a deep learning-based framework for the automatic classification of Cikadu Batik motifs from Tanjung Lesung, Banten — a regionally distinct batik pattern that has not been systematically studied in prior computational literature. Two convolutional neural network (CNN) architectures were implemented and comparatively evaluated under identical experimental conditions: ResNet50, a high-capacity model employing residual skip connections, and MobileNetV2, a lightweight model utilizing depthwise separable convolutions and inverted residual blocks. A curated dataset of 2,500 images spanning five motif classes was constructed through collaboration with local batik artisans, preprocessed via resizing (224×224), pixel normalization, and augmentation (rotation, zoom, horizontal flip, brightness adjustment), and partitioned using a stratified 70:15:15 split. Both models were trained with transfer learning from ImageNet weights, using the Adam optimizer (lr=0.0001), categorical cross-entropy loss, batch size of 32, and early stopping over 30 epochs. Model evaluation employed accuracy, precision, recall, F1-score, AUC-ROC, inference time, and parameter count. ResNet50 achieved 95.51% accuracy, 95.67% precision, 95.34% recall, 95.50% F1-score, and 99.56% AUC-ROC, with an inference time of 18.2 ms and 25.64 million parameters. MobileNetV2 achieved 92.13% accuracy, 92.28% precision, 91.98% recall, 92.13% F1-score, and 98.89% AUC-ROC, with an inference time of 8.7 ms and only 3.54 million parameters — approximately 7× lighter and 2× faster. These results empirically establish a clear accuracy-efficiency trade-off, with ResNet50 favored for accuracy-critical server-based systems and MobileNetV2 better suited for real-time mobile deployment. This study constitutes the first published benchmark for deep learning-based Cikadu Batik classification and provides a principled basis for architecture selection in regional batik recognition applications
Downloads
References
Central Java using Transfer Learning Method. Ojs.Uajy.Ac.Id. Retrieved May 3, 2026, from https://ojs.uajy.ac.id/index.php/jbi/article/view/6977
Agista, R., & Kurniadi, B. (2024). Indonesian batik classification using ResNet50 deep learning model. Journal of Robotics and Intelligent Technology, 5(2), 89–97.
Alya, N., & others. (2023). Hybrid deep learning for batik recognition. Journal of Applied Computing, 11(2), 90–98.
Alya, R., Wibowo, M., (Jutif, P. P.-J. T. I., & 2023, undefined. (2023). Arsitektur Convolutional Neural Network untuk Model Klasifikasi Citra Batik Yogyakarta. Journal.Isas.or.Id, 4(1), 161–170. https://doi.org/10.20884/1.jutif.2023.4.1.564
Anastasya, D., Fahri, S., Situmorang, S., Ramadhani, F., & Komputer, J. I. (n.d.). Implementasi Metode Convolutional Neural Network (CNN) Dalam Klasifikasi Motif Batik. Journal.Fkom.Uniku.Ac.Id, 18(1), 2614–5405. Retrieved December 27, 2025, from https://journal.fkom.uniku.ac.id/ilkom/article/view/21
Aras, S., on, A. S.-2022 4th I. C., & 2022, undefined. (n.d.). Classification of papuan batik motifs using deep learning and data augmentation. Ieeexplore.Ieee.Org. Retrieved May 3, 2026, from https://ieeexplore.ieee.org/abstract/document/10031320/
Chandra, A., … P. S.-2025 2nd I., & 2025, undefined. (n.d.). Batik GAN for Generating Motif Synthesis using Multi-Discriminator and Self-Attention. Ieeexplore.Ieee.Org. Retrieved May 3, 2026, from https://ieeexplore.ieee.org/abstract/document/11082971/
Idris, M., Ahmad, A., … D. A. G.-J. (Jurnal, & 2026, undefined. (n.d.). KLASIFIKASI MOTIF BATIK INDONESIA MENGGUNAKAN DEEP LEARNING BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN). Ejournal.Itn.Ac.Id. Retrieved May 3, 2026, from https://www.ejournal.itn.ac.id/jati/article/view/16917
Intelligence, N. G.-B. R. of A., & 2021, undefined. (2021). Literature study of convolutional neural network algorithm for batik classification. Itscience-Indexing.Com, 1(1). https://doi.org/10.47709/briliance.v1i1.1069
Li, H., & others. (2024). Improved ResNet for Miao batik pattern classification. Pattern Recognition Letters, 178, 120–128.
Li, X., & others. (2024). Deep learning for cultural heritage image classification. IEEE Access, 12, 88900–88910.
Mahardika, F., … E. S.-S. J. T., & 2019, undefined. (n.d.). Penerapan Segmentasi Warna pada Gambar di Media Sosial dengan Algoritma Fuzzy K-Means Cluster. Ojs3-Jurnal.Umk.Ac.Id. Retrieved December 19, 2025, from https://ojs3-jurnal.umk.ac.id/index.php/simet/article/view/3381
Mahardika, F., … L. S.-J. T. I., & 2026, undefined. (2026). IoT-Based Smart Detector with SVM and XGBoost for Real-Time Child Growth Monitoring and Stunting Risk Prediction. Jutif.If.Unsoed.Ac.IdF Mahardika, L Syafirullah, A NugrohoJurnal Teknik Informatika (Jutif), 2026•jutif.If.Unsoed.Ac.Id, 7(1), 2723–3863. https://doi.org/10.52436/1.jutif.2026.7.2.5394
Mahardika, F., Setiawan, E., Intan, D., & Saputra, S. (2019). PENERAPAN SEGMENTASI WARNA PADA GAMBAR DI MEDIA SOSIAL DENGAN ALGORITMA FUZZY K-MEANS CLUSTER. Simetris: Jurnal Teknik Mesin, Elektro Dan Ilmu Komputer, 10(2), 631–638. https://doi.org/10.24176/SIMET.V10I2.3381
Muri, A., & Nim, A. (2025). Implementasi Arsitektur Resnet50 Pada Klasifikasi Motif Batik Indonesia Menggunakan Metode Convolutional Neural Network (Cnn). https://repository.unissula.ac.id/40941/
Negara, B., Satria, E., … S. S.-… C. of A., & 2021, undefined. (n.d.). ResNet-50 for classifying Indonesian batik with data augmentation. Ieeexplore.Ieee.Org. Retrieved May 3, 2026, from https://ieeexplore.ieee.org/abstract/document/9493488/
Oktarino, A., Tasri, Y., Ocean, A. E.-J. of, and, M., & 2024, undefined. (2024). Identification of Batik Motif Based Deep Learning-Convolutional Neural Network Approach. Isomase.Org, (4), 23–30. https://doi.org/10.54554/jtec.2024.16.04.004
Pangestu, H. G., Yunus, A. P., & Khomsah, S. (2025). Comparative Evaluation of CNN Architectures for Neural Style Transfer in Indonesian Batik Motif Generation: A Comprehensive Study. https://arxiv.org/pdf/2601.00888
Pangestu, H., Yunus, A., arXiv:2601.00888, S. K. preprint, & 2025, undefined. (n.d.). Enhanced Semarang batik classification using deep learning: a comparative study of CNN architectures. Beei2.Org. Retrieved May 3, 2026, from http://beei2.org/index.php/EEI/article/view/9347
Pratama, D., & others. (2024). Mobile-based batik classification using EfficientNet-B1. IEEE Access, 12, 30021–30030.
Purwanto, R., Mahardika, F., Faiz, M. N., Purwanto, R., Mahardika, F., & Nur Faiz, M. (2025). A Comparative Analysis of KIP-K Acceptance Prediction Based on School Type Using XGBoost, Random Forest, and SVM-RBF: Evaluation Through Accuracy and. Ejournal.Pnc.Ac.Id, 7(2), 370–378. https://doi.org/10.35970/jinita.v7i2.2948
Puspaningrum, E., … E. M.-2025 I. 11th, & 2025, undefined. (n.d.). Deep Learning-Based Classification of Madura Batik Motifs Using Transfer Learning Approach. Ieeexplore.Ieee.OrgEY Puspaningrum, EP Mandyartha, FA Akbar, YN Kumala, A Rozi2025 IEEE 11th Information Technology International Seminar (ITIS), 2025•ieeexplore.Ieee.Org. Retrieved May 3, 2026, from https://ieeexplore.ieee.org/abstract/document/11309227/
Putra, R., & others. (2022). Performance analysis of transfer learning in batik recognition. Journal of Information Technology and Systems, 9(3), 140–148.
Ramadhan, D., Electrical, D. R.-J. of, Power, E. and, & 2024, undefined. (n.d.). Classification of Riau Batik motifs using the convolutional neural network (CNN) algorithm. Ijeepse.Id. Retrieved May 3, 2026, from https://www.ijeepse.id/journal/index.php/ijeepse/article/view/201
Ramadhan, F., & others. (2023). Batik motif classification using ResNet50 deep learning architecture. Journal of Informatics and Computing, 8(4), 201–209.
Ridwan Wibisono, M., Ma’ruf Nugroho, I., Defriani, M., Informatika, T., Tinggi, S., Wastukancana, T., Cikopak, J., 53, N., Babakancikao, K., Purwakarta, K., Barat, J., & Koresponden, P. (2025). Classification of Jombang Batik Motifs Using Ensemble Convolutional Neural Network. Jurnal.Kdi.or.Id, 6. https://jurnal.kdi.or.id/index.php/bt/article/view/3204
Santosa, S. B., Chrismanto, A. R., Susanto, B., & Artikel, R. (2026). TRANSFER LEARNING: COMPARISON OF RESNET50, MOBILENETV2, AND MOBILENETV3-LARGE IN CLASSIFICATION OF INDONESIAN BATIK MOTIFS …. Jurnal.Univrab.Ac.Id, 23(Maret), 46–60. https://doi.org/10.24246/aiti.v23i1.46-60
Saputra, A., Wahyuzi, Z., Bagus Pratama, Y., Belitung, B., Ahmad Dahlan KM, J. K., Keramat, K., & Bangka Belitung, K. (2026). Classification of Batik Cual Bangka Belitung Based on Deep Learning: YOLOv11 Approach. Journal.Uns.Ac.Id, 9(1), 26–37. https://journal.uns.ac.id/index.php/joive/article/view/3208
Sari, I., Elvitaria, L., IT, R. R.-J. M., & 2025, undefined. (2025). Enhancing Batik Classification Leveraging CNN Models and Transfer Learning. Joiv.Org, 13(3), 323–331. https://joiv.org/index.php/joiv/article/view/2535
Sari, R., & others. (2021). Traditional batik image classification using convolutional neural network. Journal of Computer Vision and Image Processing, 12(3), 45–52.
Sastypratiwi, H., Muhardi, H., on, Y. Y.-J. I. J., & 2024, undefined. (n.d.). Classification of Malaysian and Indonesian batik designs using deep learning models. Eprints.Leedsbeckett.Ac.Uk. Retrieved May 3, 2026, from https://eprints.leedsbeckett.ac.uk/id/eprint/11633/
Suyahman, S., Preservation, A. H.-, & D. T., & 2025, undefined. (2025). Batik Pattern Classification Using Logistic Regression, SVM, and Deep Learning Features. Jurnal.Bsi.Ac.Id, 54(3), 215–222. https://doi.org/10.1515/PDTC-2025-0009/HTML
Syafirullah, L., Mahardika, F., Purwanto, R., Prasetyanti, D. N., Rekayasa, T., Lunak, P., Cilacap, P. N., Informatika, T., & Cilacap, P. N. (2026). Performance Evaluation and Optimization of an IoT-Based Fish Smoking Monitoring System for Ensuring Product Quality. 10(1), 691–700.
Utami, M., … E. E.-2024 N. I., & 2024, undefined. (n.d.). Transfer Learning Implementation for Batik Besurek Motifs Classification: A Comparative Study. Ieeexplore.Ieee.Org. Retrieved May 3, 2026, from https://ieeexplore.ieee.org/abstract/document/10957440/
Whardana, T., & others. (2025). Improved batik image classification using CNN with preprocessing techniques. Sistem Komputer Dan Informatika Journal, 9(1), 33–41.
Zhang, Y., & others. (2024). Lightweight deep learning model using MobileNetV2 for real-time image classification. IEEE Transactions on Mobile Computing, 23(3), 1450–1459.
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2026 Rizki Ripai, Fajar Mahardika, Fazar Sidik, Nurul Badriah, Angga Maulana Purba
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Muhammad Khoiruddin harahap
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
