A Multilevel Image Processing Approach for Minangkabau Ornament Detection Using CLAHE, Multi Threshold Otsu, and CNN

Suci Wahyuni; Yogi  Wiyandra; Firna Yenila

doi:10.59395/ijadis.v7i1.1520

Authors

Suci Wahyuni Universitas Putra Indonesia YPTK, Padang, Indonesia
Yogi Wiyandra Universitas Putra Indonesia YPTK, Padang, Indonesia
Firna Yenila Universitas Putra Indonesia YPTK, Padang, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i1.1520

Keywords:

Minangkabau Ornaments, Image Processing, CLAHE, Multi-Threshold Otsu, Convolutional neural network

Abstract

Traditional Minangkabau ornaments such as pucuak rabuang, itiak pulang patang, kaluak paku, and rabuang sanjo represent a form of visual cultural heritage with high aesthetic and philosophical value. However, the digital documentation and preservation of these ornaments still face significant challenges, particularly due to variations in media, fine surface textures, uneven illumination, and complex image backgrounds. These conditions complicate the separation of ornament motifs from the background and consequently affect the accuracy of identification and classification processes. This study aims to develop an image processing approach for the detection and identification of Minangkabau ornaments through image quality enhancement and multi-level segmentation. The proposed method begins with a preprocessing stage that includes motif area cropping, image size normalization, noise reduction through filtering, contrast stretching, and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance local contrast. Subsequently, segmentation is performed using the Multi-Threshold Otsu method to divide the image into multiple intensity classes, enabling a more detailed separation of ornament structures. The segmentation results are evaluated using morphological analysis and further tested using a Convolutional Neural Network (CNN) to assess classification performance. Experiments were conducted on a dataset of 1,024 images, with a training–testing split of 70% and 30%, respectively. The experimental results demonstrate that the proposed approach produces representative motif segmentation and achieves a classification accuracy of 99.67%. These findings indicate that the integration of systematic preprocessing, multi-threshold segmentation, and CNN-based classification is effective in supporting the digital preservation of Minangkabau ornaments.

1206 313

Downloads

Download data is not yet available.

References

[1] Nofrial, P. Prihatin, and M. A. Laksono, “Ukiran Ornamen Tradisional Minangkabau pada Dekorasi Pelaminan,” Naskah Diterima Naskah Final Naskah Publish Corak: Jurnal Seni Kriya, vol. 10, no. 2, pp. 153–168, Nov. 2021, doi: 10.24821/corak.v10i2.4581. DOI: https://doi.org/10.24821/corak.v10i2.4581

[2] T. Akbar, I. Desra, N. Rahmanita, D. Yanuarmi, and I. Qomarats, “Representasi Nilai Multikultural dalam Desain Ornamen Songket ‘Kambang Cino’ Koto Gadang,” ANDHARUPA:Jurnal Desain Komunikasi Visual & Multimedia, vol. 9, no. 3, pp. 326–342, Sep. 2023, doi: 10.33633/andharupa.v9i03.6996. DOI: https://doi.org/10.33633/andharupa.v9i03.6996

[3] A. Bentkowska-Kafel and L. MacDonald, Digital techniques For Documenting and preseving Cultural Heritage. Arc Humanities Press, 2017. DOI: https://doi.org/10.5040/9781641899444

[4] P. S. Krishnapriya, G. Nikitha, K. V. U. Kiran, K. Aparna, and S. C. Priya, “A Deep Learning-based Smart System for Ornaments and Devices Detection during Check-In of Entrance Exams,” in Procedia Computer Science, 2024, vol. 233, pp. 464–473. doi: 10.1016/j.procs.2024.03.236. DOI: https://doi.org/10.1016/j.procs.2024.03.236

[5] I. G. A. G. A. Kadyanan, N. Gunantara, I. B. G. Manuaba, K. O. Saputra, and W. F. Mahmudy, “Classification of Ornament or Pepatran in Balinese Traditional Architecture Pattern Using Learning Vector Quantization Algorithm,” in ACM International Conference Proceeding Series, Apr. 2024, pp. 90–96. doi: 10.1145/3669754.3669768. DOI: https://doi.org/10.1145/3669754.3669768

[6] Y. Li, M. Zhao, J. Mao, Y. Chen, L. Zheng, and L. Yan, “Detection and recognition of Chinese porcelain inlay images of traditional Lingnan architectural decoration based on YOLOv4 technology,” Herit Sci, vol. 12, no. 1, pp. 1–41, Dec. 2024, doi: 10.1186/s40494-024-01227-z. DOI: https://doi.org/10.1186/s40494-024-01227-z

[7] M. D. Nayeem, S. Z. Sraboni, S. S. Biswas, and M. M. Islam, “OrnAsia: A dataset of asian ornaments for image classification and cultural identification,” Data Brief, vol. 63, pp. 1–6, Dec. 2025, doi: 10.1016/j.dib.2025.112195. DOI: https://doi.org/10.1016/j.dib.2025.112195

[8] Y. Xian, Y. Lee, T. Shen, P. Lan, Q. Zhao, and L. Yan, “Enhanced Object Detection in Thangka Images Using Gabor, Wavelet, and Color Feature Fusion,” Sensors, vol. 25, no. 11, pp. 1–22, Jun. 2025, doi: 10.3390/s25113565. DOI: https://doi.org/10.3390/s25113565

[9] A. L. Sari and A. A. Yusuf, “Cultural Navigation and Multiple Roles: Study of Adaptation of Minangkabau People in Overseas Land in the Perspective of the Proverb ‘Nan Sakuduang Jadi Saruik, Nan Salapeh Jadi Kambang,’” INFLUENCE: International Journal of Science Review, vol. 5, no. 2, pp. 419–425, 2023, doi: 10.54783/influencejournal.v5i2.170. DOI: https://doi.org/10.54783/influencejournal.v5i2.170

[10] C. C. Andrianos et al., “Development of a Fully Optimized Convolutional Neural Network for Astrocytoma Classification in MRI Using Explainable Artificial Intelligence,” J Imaging, vol. 11, no. 10, pp. 1–22, Oct. 2025, doi: 10.3390/jimaging11100343. DOI: https://doi.org/10.3390/jimaging11100343

[11] D. I. Mulyana and M. A. A. Abyan, “Image Quality Improvement for Sign Language Gestures Through Gaussian Filter and Contrast Stretching Techniques,” International Journal Software Engineering and Computer Science (IJSECS), vol. 5, no. 3, pp. 1029–1044, Dec. 2025, doi: 10.35870/ijsecs.v5i3.5254. DOI: https://doi.org/10.35870/ijsecs.v5i3.5254

[12] F. Noor, Muhathir, Fadliansyah, and D. Syahputra, “Analysis of Combined Contrast Limited Adaptive Histogram Equalization (CLAHE) and Median Filter Methods for Enhancement of CCTV Screenshot Image Quality,” JITE (Journal of Informatics and Telecommunication Engineering), vol. 8, no. 2, pp. 335–345, Jan. 2025, doi: 10.31289/jite.v8i2.14016.

[13] Y. Guo, Y. Wang, K. Meng, and Z. Zhu, “Otsu Multi-Threshold Image Segmentation Based on Adaptive Double-Mutation Differential Evolution,” Biomimetics, vol. 8, no. 5, pp. 1–22, Sep. 2023, doi: 10.3390/biomimetics8050418. DOI: https://doi.org/10.3390/biomimetics8050418

[14] R. Lu et al., “Strategic sampling for training a semantic segmentation model in operational mapping: Case studies on cropland parcel extraction,” Remote Sens Environ, vol. 331, pp. 1–17, Dec. 2025, doi: 10.1016/j.rse.2025.115034. DOI: https://doi.org/10.1016/j.rse.2025.115034

[15] M. Abu Talib, I. Ibrahim, and M. Anwer Abusirdaneh, “Reusability and benchmarking potential of architectural cultural heritage datasets for generative AI: An analytical study,” Expert Syst Appl, vol. 309, pp. 1–21, May 2026, doi: 10.1016/j.eswa.2025.130916. DOI: https://doi.org/10.1016/j.eswa.2025.130916

[16] H. Yenni, R. Muzawi, M. Khairul Anam, M. Kasaf, T. Rizqi Maysyarah Hadi, and D. Sari Wahyuni, “MYCD: Integration of YOLO-CNN and DenseNet for Real-Time Road Damage Detection Based on Field Images,” Journal of Applied Data Sciences, vol. 7, no. 1, pp. 384–395, 2026, doi: 10.47738/jads.v7i1.1040. DOI: https://doi.org/10.47738/jads.v7i1.1040

[17] H. G. Jeon and K. H. Lee, “Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System,” Applied Sciences (Switzerland), vol. 15, no. 10, pp. 1–18, May 2025, doi: 10.3390/app15105328. DOI: https://doi.org/10.3390/app15105328

[18] D. Li, J. Zhang, and K. Huang, “Learning to Learn Cropping Models for Different Aspect Ratio Requirements,” in Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12685–12694. doi: 10.1109/CVPR42600.2020.01270. DOI: https://doi.org/10.1109/CVPR42600.2020.01270

[19] M. Tsaqofah, L. S. Harahap, and D. S. Hasibuan, “Optimization of Digital Image Processing Through Gaussian Filtering for Noise Reduction,” Journal of Artificial Intelligence and Engineering Applications, vol. 4, no. 3, pp. 2808–4519, 2025, doi: 10.59934/jaiea.v4i3.1120. DOI: https://doi.org/10.59934/jaiea.v4i3.1120

[20] B. A. Rivera-Aguilar, E. Cuevas, A. Luque-Chang, J. López, and M. Pérez-Cisneros, “Pixel Interaction Model for Contrast Enhancement: Bridging Social Science and Image Processing,” Applied Sciences (Switzerland), vol. 14, no. 23, pp. 1–20, Dec. 2024, doi: 10.3390/app142310887. DOI: https://doi.org/10.3390/app142310887

[21] M. S. Z. Ahmad, N. A. A. Aziz, H. S. Lim, A. K. Ghazali, and ‘Afif Abdul Latiff, “Impact of Image Enhancement Using Contrast-Limited Adaptive Histogram Equalization (CLAHE), Anisotropic Diffusion, and Histogram Equalization on Spine X-Ray Segmentation with U-Net, Mask R-CNN, and Transfer Learning,” Algorithms, vol. 18, no. 12, pp. 1–22, Dec. 2025, doi: 10.3390/a18120796. DOI: https://doi.org/10.3390/a18120796

[22] J. Zheng, Y. Gao, H. Zhang, Y. Lei, and J. Zhang, “OTSU Multi-Threshold Image Segmentation Based on Improved Particle Swarm Algorithm,” Applied Sciences (Switzerland), vol. 12, no. 1, pp. 1–22, Nov. 2022, doi: 10.3390/app122211514. DOI: https://doi.org/10.3390/app122211514

[23] D. Yokokawa, K. Shikino, Y. Nishizaki, S. Fukui, and Y. Tokuda, “Evaluation of a Computer-Based Morphological Analysis Method for Free-Text Responses in the General Medicine In-Training Examination: Algorithm Validation Study,” JMIR Med Educ, vol. 10, no. 1, pp. 1–11, 2024, doi: 10.2196/52068. DOI: https://doi.org/10.2196/52068

[24] M. K. Anam, S. Sumijan, K. Karfindo, and M. B. Firdaus, “Comparison Analysis of HSV Method, CNN Algorithm, and SVM Algorithm in Detecting the Ripeness of Mangosteen Fruit Images,” Indonesian Journal of Artificial Intelligence and Data Mining, vol. 7, no. 2, pp. 348–356, May 2024, doi: 10.24014/ijaidm.v7i2.29739. DOI: https://doi.org/10.24014/ijaidm.v7i2.29739