Pendekatan Machine Learning Untuk Prediksi Motif Batik Indonesia

Wahyu Marzian Putra; Erliyan Redy Susanto; Neneng Neneng

doi:10.58602/jaiti.v4i3.270

Wahyu Marzian Putra ^{(Corresponding Author)} Universitas Teknokrat Indonesia
Erliyan Redy Susanto Universitas Teknokrat Indonesia
Neneng Neneng Universitas Teknokrat Indonesia

DOI: https://doi.org/10.58602/jaiti.v4i3.270

Keywords: klasifikasi gambar, YOLOv11, SMOTE, cross-validation, deep learning

Abstract

Batik merupakan warisan budaya tak benda Indonesia yang diakui UNESCO sejak tahun 2009. Perkembangan teknologi kecerdasan buatan, khususnya deep learning, membuka peluang otomatisasi klasifikasi visual batik. Namun, klasifikasi otomatis batik Indonesia masih menghadapi tantangan utama, yaitu ketidakseimbangan kelas pada dataset (imbalanced dataset) dan kemiripan visual antarkelas yang tinggi . Penelitian ini mengembangkan sistem klasifikasi 20 jenis batik Indonesia menggunakan model YOLOv11 yang diintegrasikan dengan teknik Synthetic Minority Over-sampling Technique (SMOTE) serta skema 5-Fold Stratified Cross-Validation guna memperoleh evaluasi yang objektif. Dataset terdiri atas 983 gambar yang diakuisisi dari repositori Kaggle. SMOTE diterapkan pada representasi fitur piksel berdimensi tinggi (d = 12.288) untuk menyeimbangkan distribusi antarkelas tanpa mengorbankan informasi kelas mayoritas. Model YOLOv11 dilatih pada setiap lipatan dengan konfigurasi hyperparameter terkontrol menggunakan pengoptimasian AdamW. Hasil penelitian menunjukkan nilai mean Average Precision (mAP) keseluruhan sebesar 0,8251 dan rata-rata mAP per lipatan sebesar 0,8788 ± 0,0264, dengan konsistensi metrik yang tinggi di seluruh lipatan validasi. Analisis matriks kebingungan mengindikasikan bahwa misclassification cenderung terjadi antara kelas batik yang memiliki kemiripan visual tinggi. Kerangka kerja yang diusulkan berpotensi diimplementasikan sebagai sistem identifikasi batik otomatis untuk mendukung pelestarian warisan budaya, autentifikasi produk pada platform e-commerce, serta dokumentasi koleksi museum di era digital.

Downloads

Download data is not yet available.

References

UNESCO, “Decision of the Intergovernmental Committee: 4.COM 13.44 — Batik. Representative List of the Intangible Cultural Heritage of Humanity,” 2009.

Y. Lecun, L. Eon Bottou, Y. Bengio, and P. H. Abstract|, “Gradient-Based Learning Applied to Document Recognition.” DOI: 10.1109/5.726791

K. G. Kim, “Book Review: Deep Learning,” Healthc. Inform. Res., vol. 22, no. 4, p. 351, 2016, doi: 10.4258/hir.2016.22.4.351.

M. Kaur, E. Vikas Kumar, and M. Tech Scholar, “A COMPREHENSIVE STUDY ON CLASSIFICATION OF IMAGES BASED ON DEEP LEARNING APPROACH,” 2020. [Online]. Available: www.ijtre.com

N. Japkowicz dan S. Stephen, “‘The class imbalance problem: A systematic study,’” Intell. Data Anal. (Intelligent Data Analysis), pp. 429–449, Oct. 2002.

M. A. Rasyidi and T. Bariyah, “Batik pattern recognition using convolutional neural network,” Bulletin of Electrical Engineering and Informatics, vol. 9, no. 4, pp. 1430–1437, Aug. 2020, doi: 10.11591/eei.v9i4.2385.

A. Rocha, H. Adeli, G. Dzemyda, F. Moreira, and V. Colla, “Lecture Notes in Networks and Systems 799.”

N. V Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” 2002.

M. Tan and Q. V Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.”

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2323, 1998, doi: 10.1109/5.726791.

D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Jan. 2017, [Online]. Available: http://arxiv.org/abs/1412.6980

I. Loshchilov and F. Hutter, “Decoupled Weight Decay Regularization,” Jan. 2019, [Online]. Available: http://arxiv.org/abs/1711.05101

R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” 1995. [Online]. Available: http://robotics.stanford.edu/~ronnyk

N. Srivastava, G. Hinton, A. Krizhevsky, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” 2014.

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.

J. Davis and M. Goadrich, “The Relationship Between Precision-Recall and ROC Curves.”

S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.”

S. Elbagir and J. Yang, “Sentiment analysis of twitter data using machine learning techniques and scikit-learn,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Dec. 2018. doi: 10.1145/3302425.3302492.

M. A. Rasyidi and T. Bariyah, “Batik pattern recognition using convolutional neural network,” Bulletin of Electrical Engineering and Informatics, vol. 9, no. 4, pp. 1430–1437, Aug. 2020, doi: 10.11591/eei.v9i4.2385.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition.” [Online]. Available: http://image-net.org/challenges/LSVRC/2015/

A. Wijaya and D. Suharjito, “‘Batik motif classification using VGG-16 deep convolutional neural network with 10-fold cross-validation,’” J. Comput. Sci. (Singkatan dari Journal of Computer Science), vol. 17, no. 3, pp. 256–268, 2021.

M. F. and B. S. D. Saputra, “‘Automated batik motif identification using MobileNetV2 and transfer learning approach,’” in Proc. Int. Conf. Inf. Technol. Comput. Electr. Eng. (ICITACEE), Semarang, Indonesia., 2023, pp. 123–129.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks.” [Online]. Available: https://github.com/liuzhuang13/DenseNet.

A. Vaswani et al., “Attention Is All You Need.”

I. J. Goodfellow et al., “Generative Adversarial Nets.” [Online]. Available: http://www.github.com/goodfeli/adversarial

J. Ho, A. Jain, and P. Abbeel, “Denoising Diffusion Probabilistic Models.” [Online]. Available: https://github.com/hojonathanho/diffusion.

A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” Jun. 2021, [Online]. Available: http://arxiv.org/abs/2010.11929

R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.” [Online]. Available: http://gradcam.cloudcv.org

A. Howard et al., “Searching for MobileNetV3.”

T. Sugihartono, D. Soetarno, R. Sulaiman, and A. Name, “Ensemble Learning for Pediatric Stunting Detection: A Comparative Study of XGBoost, Random Forest, and LightGBM with Oversampling Techniques,” vol. 8, no. 2, 2026, doi: 10.63158/journalisi.v8i2.1568.