Klasifikasi Motif Kain Batik Nitik Menggunakan Support Vector Machine dengan Ekstraksi Fitur EfficientNet-B0
Abstract
Nitik Batik is an Indonesian cultural heritage with complex geometric dot patterns, yet its digitalization and preservation efforts remain limited. This study aims to develop an automatic classification system for 60 Nitik Batik motifs using a combination of EfficientNet-B0 as a feature extractor and Support Vector Machine (SVM) as a classifier. The Batik Nitik 960 Dataset was expanded from 960 to 1,920 images with rotation augmentation. Experiments were conducted with 10-fold cross-validation and evaluation on separate test data. Results show that the model without augmentation achieved 55.71% accuracy, 90.06% macro precision, 55.71% recall, and 65.29% F1-score. Blur augmentation with 30% probability reduced accuracy to 49.29% although it decreased overfitting by 6.63%. SVM parameters were set to C=0.3 and gamma=0.01 to improve regularization. This study concludes that the combination of EfficientNet-B0 and SVM is effective for multi-class batik classification, but blur augmentation is unsuitable for detail-rich textile data. Future research recommendations include exploring geometric augmentation and more advanced feature extractor architectures.
Kata kunci: Nitik Batik; Image classification; EfficientNet-B0; Support Vector Machine; augmentation.
Abstrak
Batik Nitik merupakan warisan budaya Indonesia dengan motif geometris berbentuk titik yang kompleks, namun upaya digitalisasi dan pelestariannya masih terbatas. Penelitian ini bertujuan mengembangkan sistem klasifikasi otomatis untuk 60 motif Batik Nitik menggunakan kombinasi EfficientNet-B0 sebagai ekstraktor fitur dan Support Vector Machine (SVM) sebagai klasifikator. Dataset Batik Nitik 960 Dataset diperluas dari 960 menjadi 1.920 citra dengan augmentasi rotasi. Eksperimen dilakukan dengan skema 10-fold cross-validation dan evaluasi pada data uji terpisah. Hasil menunjukkan bahwa model tanpa augmentasi mencapai akurasi 55,71%, precision macro 90,06%, recall 55,71%, dan F1-score 65,29%. Augmentasi blur 30% justru menurunkan akurasi menjadi 49,29% meskipun mengurangi overfitting sebesar 6,63%. Parameter SVM diatur C=0,3 dan gamma=0,01 untuk meningkatkan regularisasi. Penelitian ini menyimpulkan bahwa kombinasi EfficientNet-B0 dan SVM efektif untuk klasifikasi batik multikelas, namun augmentasi blur tidak sesuai untuk data tekstur kaya detail. Rekomendasi penelitian selanjutnya adalah eksplorasi augmentasi geometris dan arsitektur feature extractor yang lebih advance.
Kata kunci: Batik Nitik; Klasifikasi citra; EfficientNet-B0; Support Vector Machine; Augmentasi.
References
UNESCO, "Indonesian Batik," 2009.
A. A. Kasim, M. F. Rizal, dan D. A. Saputra, "Digital preservation of batik heritage: A review," Journal of Cultural Heritage, vol. 54, pp. 12–22, 2022.
N. Wirasanti dan Mahirta, "Menelisik tanda nitik pada batik," Jurnal Heritage Management, vol. 8, no. 2, pp. 112–125, 2022.
A. E. Minarno, Y. Munarko, F. D. W. Azizah, H. Wibawanto, dan E. R. Widasari, "Batik Nitik 960 Dataset: A collection of Nitik batik motifs for pattern recognition research," Data in Brief, vol. 47, pp. 108987, 2023.
A. A. Kasim, M. F. Rizal, dan D. A. Saputra, "Spatial and topology feature extraction on batik pattern recognition: A review," Journal of Informatics, vol. 16, no. 1, pp. 1–7, 2022.
P. N. Andono dan E. H. Rachmawanto, "Evaluasi ekstraksi fitur GLCM dan LBP menggunakan multikernel SVM untuk klasifikasi batik," Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 4, pp. 512–520, 2022.
D. Sinaga, A. F. Rochim, dan S. Wibirama, "Multi-layer convolutional neural networks for batik image classification," Scientific Journal of Informatics, vol. 8, no. 1, pp. 45–55, 2024.
N. N. Arif, R. R. Dewi, dan S. Hadi, "Analisis dan perbandingan metode CNN dan SVM dalam mendeteksi batik Nusantara," dalam Prosiding SENASTIKA 2024, pp. 112–119, 2024.
R. Wiryadinata, T. H. Supriana, dan D. S. Maylawati, "Klasifikasi 12 motif batik Banten menggunakan Support Vector Machine," Jurnal EECCIS, vol. 10, no. 2, pp. 34–40, 2019.
S. Aras dan A. Setyanto, "Deep learning untuk klasifikasi motif batik Papua menggunakan EfficientNet dan transfer learning," Jurnal Informatika dan Security, vol. 7, no. 1, pp. 34–42, 2022.
D. Anastasya, E. R. Sembiring, dan F. F. Hasibuan, "Implementasi metode CNN dalam klasifikasi motif batik (EfficientNet-B0)," Nuansa Informatika, vol. 12, no. 1, pp. 67–75, 2024.
M. S. A. Karim, A. A. Hakim, C. S. Rafika, dan E. Y. Puspaningrum, "Klasifikasi motif batik Yogyakarta dan Pekalongan menggunakan metode GLCM dan CNN berbasis arsitektur EfficientNetB0," dalam Prosiding Seminar Nasional Informatika Bela Negara (SANTIKA), vol. 3, pp. 145–154, 2023.
I. P. Sari dan L. Elvitaria, "Data-driven approach for batik pattern classification using convolutional neural network (CNN)," Jurnal Mandiri IT, vol. 8, no. 2, pp. 112–120, 2023.
R. A. Hapsari dan I. Yuadi, "Batik pattern classification using logistic regression, SVM, and deep learning features," Preservation, Digital Technology & Culture, vol. 54, no. 1, pp. 45–56, 2025.
M. Tan dan Q. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," dalam Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 6105–6114, 2020.
M. Khomidov dan J. H. Lee, "The novel EfficientNet architecture-based system and algorithm to predict complex human emotions," Algorithms, vol. 17, no. 7, pp. 285, 2024.
S. J. Pan dan Q. Yang, "A survey on transfer learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2010.
C. Cortes dan V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
S. Ahlawat, A. Choudhary, A. Nayyar, S. Singh, dan B. Yoon, "Improved handwritten digit recognition using convolutional neural networks (CNN)," Sensors, vol. 20, no. 12, pp. 3344, 2020.
R. Ali, S. M. Khan, dan A. R. Javed, "EfficientNet-B0 for medical image classification: A lightweight deep learning approach," IEEE Access, vol. 13, pp. 45012–45022, 2025.
H. Basly, W. Ouarda, F. E. Sayadi, B. Ouni, dan A. M. Alimi, "CNN-SVM learning approach based human activity recognition," Lecture Notes in Computer Science, vol. 12119, pp. 271–281, 2020.
A. Yasar, "Analysis of selected deep features with CNN-SVM-based for bread wheat seed classification," European Food Research and Technology, vol. 250, no. 6, pp. 1551–1561, 2024.
L. Nanni, S. Ghidoni, dan S. Brahnam, "Deep features for training support vector machines," Journal of Imaging, vol. 7, no. 9, pp. 177, 2021.
M. Rodriguez, C. Estevez, dan J. Perez, "Multiclass classification: A review of methods and applications," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, pp. 3456–3472, 2022.
C. Shorten dan T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019.
L. Taylor dan G. Nitschke, "Improving deep learning with generic data augmentation," dalam IEEE Symposium Series on Computational Intelligence, pp. 1542–1547, 2018.
T. Hastie, R. Tibshirani, dan J. Friedman, The Elements of Statistical Learning, 2nd ed. New York: Springer, 2009.
J. Witjaksono, M. Y. Pusadan, Y. Anshori, R. Ardiansyah, dan R. Azhar, "Klasifikasi jenis batik Bomba menggunakan CNN dengan arsitektur EfficientNet-B2," JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 9, no. 3, pp. 78–92, 2024.
S. Aisyah, R. Astuti, F. M. Basysyar, O. Nurdiawan, dan I. Ali, "Convolutional neural networks for classification motives and the effect of image dimensions," Jurnal RESTI, vol. 8, no. 2, pp. 89–101, 2024.
H. Zhang, M. Cisse, Y. N. Dauphin, dan D. Lopez-Paz, "mixup: Beyond empirical risk minimization," dalam International Conference on Learning Representations (ICLR), 2018.
J. Deng, J. Guo, N. Xue, dan S. Zafeiriou, "ArcFace: Additive angular margin loss for deep face recognition," dalam IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4685–4694, 2019.
How To Cite This :
Refbacks
- There are currently no refbacks.
