Ekstraksi fitur tekstur kerusakan situs warisan budaya pascabencana menggunakan deep features efficientnet-B7

Muhammad Hatif; Sri Harini; Ririen Kusumawati; Zainal Abidin; Muhammad Ainul Yaqin; Agung Teguh Wibowo Almais

doi:10.33795/eltek.v24i2.9886

Authors

Muhammad Hatif Universitas Islam Negeri Maulana Malik Ibrahim
Sri Harini Universitas Islam Negeri Maulana Malik Ibrahim
Ririen Kusumawati Universitas Islam Negeri Maulana Malik Ibrahim
Zainal Abidin Universitas Islam Negeri Maulana Malik Ibrahim
Muhammad Ainul Yaqin Universitas Islam Negeri Maulana Malik Ibrahim
Agung Teguh Wibowo Almais Universitas Islam Negeri Maulana Malik Ibrahim

DOI:

https://doi.org/10.33795/eltek.v24i2.9886

Keywords:

Damage Detection, Cultural Heritage, EfficientNet-B7, Feature Extraction, Texture, Deep Learning, Post-Disaster

Abstract

Situs warisan budaya sangat rentan mengalami kerusakan akibat bencana alam, sehingga memerlukan metode inspeksi yang cepat, akurat, dan objektif untuk mendukung upaya konservasi. Penelitian ini mengusulkan pendekatan ekstraksi dan karakterisasi fitur tekstur otomatis melalui pemanfaatan fitur mendalam (deep feature extraction) menggunakan arsitektur EfficientNet-B7 sebagai landasan untuk deteksi kerusakan. Metode ini memanfaatkan model pre-trained untuk mengekstraksi peta fitur dari lapisan awal block2a_expand_activation, yang peka terhadap detail tekstural seperti tepi, retak, dan variasi permukaan. Dari 144 saluran fitur yang dihasilkan, dihitung tiga deskriptor statistik sederhana per saluran—Kontras (standar deviasi), Energi (rata-rata kuadrat aktivasi), dan Homogenitas (turunan kontras)—sebagai deskriptor tekstur kuantitatif (bukan fitur GLCM klasik). Sebagai studi awal (proof of concept), pendekatan ini diujicobakan pada satu citra kerusakan plafon masjid pascabencana dan berhasil mengkarakterisasi variasi tekstur antar-saluran, menghasilkan 432 fitur numerik (3 statistik × 144 saluran). Secara konseptual, dibandingkan metode tradisional seperti Gray Level Co-occurrence Matrix (GLCM), pendekatan ini berpotensi lebih unggul dalam hal otomasi, kedalaman fitur, dan skalabilitas karena tidak memerlukan parameterisasi manual, meskipun perbandingan empiris langsung masih perlu dilakukan. Meskipun membutuhkan sumber daya komputasi yang signifikan, metode yang diusulkan menawarkan solusi yang efisien dan andal untuk analisis kerusakan otomatis, yang dapat mendukung prioritisasi dan pemulihan situs warisan budaya pascabencana.

Abstract

Cultural heritage sites are highly vulnerable to damage from natural disasters, necessitating fast, accurate, and objective inspection methods to support conservation efforts. This study proposes an automated approach for texture feature extraction and characterization through deep feature extraction using the EfficientNet-B7 architecture, serving as a foundation for damage detection. This method utilizes a pre-trained model to extract feature maps from the initial block2a_expand_activation layer, which is sensitive to textural details such as edges, cracks, and surface variations. From the 144 feature channels generated, three simple per-channel statistical descriptors were computed—Contrast (standard deviation), Energy (mean squared activation), and Homogeneity (derived from contrast)—as quantitative texture descriptors. As a proof of concept, the approach was tested on a single mosque ceiling damage image and successfully characterized inter-channel texture variations, producing 432 numerical features (3 statistics × 144 channels). Conceptually, compared to traditional methods such as Gray Level Co-occurrence Matrix (GLCM), this approach is potentially superior in terms of automation, feature depth, and scalability, as it does not require manual parameterization, although a direct empirical comparison remains to be conducted. Although requiring significant computational resources, the proposed method offers an efficient and reliable solution for automated damage analysis, which can support the prioritization and restoration of cultural heritage sites after disasters.

References

M. Li, “Disaster risk management of cultural heritage: A global scale analysis of characteristics, multiple hazards, lessons learned from historical disasters, and issues in current DRR measures in world heritage sites,” International Journal of Disaster Risk Reduction, vol. 110, hlm. 104633, Agu 2024, doi: 10.1016/j.ijdrr.2024.104633.

M. B. Ararat dan T. K. Yenice, “The use of artificial intelligence in damage assessment of historical buildings,” Frontiers of Architectural Research, vol. 15, no. 2, hlm. 554–565, Apr 2026, doi: 10.1016/j.foar.2025.06.008.

UNESCO, “Culture in city reconstruction and recovery position paper,” 2008.

J. Kallas dan R. Napolitano, “AUTOMATED LARGE-SCALE DAMAGE DETECTION on HISTORIC BUILDINGS in POST-DISASTER AREAS USING IMAGE SEGMENTATION,” dalam International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, International Society for Photogrammetry and Remote Sensing, Jun 2023, hlm. 797–804. doi: 10.5194/isprs-Archives-XLVIII-M-2-2023-797-2023.

M. Mishra dan P. B. Lourenço, “Artificial intelligence-assisted visual inspection for cultural heritage: State-of-the-art review,” 1 Maret 2024, Elsevier Masson s.r.l. doi: 10.1016/j.culher.2024.01.005.

X. Fu dan N. Angkawisittpan, “Detecting surface defects of heritage buildings based on deep learning,” Journal of Intelligent Systems, vol. 33, no. 1, Feb 2024, doi: 10.1515/jisys-2023-0048.

R. Zhang dkk., “Automatic detection of earthquake-damaged buildings by integrating UAV oblique photography and infrared thermal imaging,” Remote Sens. (Basel)., vol. 12, no. 16, Agu 2020, doi: 10.3390/RS12162621.

A. T. W. Almais dkk., “Characterization of Structural Building Damage in Post-Disaster Using GLCM-PCA Analysis Integration,” IEEE Access, vol. 12, hlm. 146190–146201, 2024, doi: 10.1109/ACCESS.2024.3469637.

S. Al Shafian dan D. Hu, “Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment,” Buildings, vol. 14, no. 8, hlm. 2344, Jul 2024, doi: 10.3390/buildings14082344.

A. Teguh Wibowo Almais, K. Fahmi Hayati Holle, K. Siwi Kinasih, D. Ayu Wiranti, dan S. Yustina Yasin, “Implementation Fuzzy Weighted Product Preparation Post Disaster Reconstruction And Rehabilitation Action Based Dynamics Decision Support System.”

A. Bachriwindi, E. K. Putra, U. M. Munawaroh, dan A. T. W. Almais, “Implementation of Web-Based Weighted Product Use Decision Support System to Determine the Post-Disaster Damage and Loss,” dalam Journal of Physics: Conference Series, Institute of Physics Publishing, Des 2019. doi: 10.1088/1742-6596/1413/1/012019.

A. Teguh, W. Almais, M. Sarosa, dan M. A. Muslim, “Implementation Of Multi Experts Multi Criteria Decision Making For Rehabilitation And Reconstruction Action After A Disaster.,” Matics, vol. 8, no. 1, hlm. 27–31, 2016.

Z. Zheng, Y. Zhong, J. Wang, A. Ma, dan L. Zhang, “Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: From natural disasters to man-made disasters,” Remote Sens. Environ., vol. 265, Nov 2021, doi: 10.1016/j.rse.2021.112636.

J. Tang, S. Yang, S. Huang, dan B. Xiao, “Remote Sensing Building Damage Assessment Based on Machine Learning,” International Journal of Advanced Network, Monitoring and Controls, vol. 9, no. 3, hlm. 1–12, Sep 2024, doi: 10.2478/ijanmc-2024-0021.

N. Takhtkeshha, A. Mohammadzadeh, dan B. Salehi, “A Rapid Self-Supervised Deep-Learning-Based Method for Post-Earthquake Damage Detection Using UAV Data (Case Study: Sarpol-e Zahab, Iran),” Remote Sens. (Basel)., vol. 15, no. 1, hlm. 123, Des 2022, doi: 10.3390/rs15010123.

F. Kizilay, M. R. Narman, H. Song, H. S. Narman, C. Cosgun, dan A. Alzarrad, “Evaluating fine tuned deep learning models for real-time earthquake damage assessment with drone-based images,” AI in Civil Engineering, vol. 3, no. 1, hlm. 15, Des 2024, doi: 10.1007/s43503-024-00034-6.

H. Huang, Y. Cai, C. Zhang, Y. Lu, A. Hammad, dan L. Fan, “Crack detection of masonry structure based on thermal and visible image fusion and semantic segmentation,” Autom. Constr., vol. 158, hlm. 105213, Feb 2024, doi: 10.1016/j.autcon.2023.105213.

A. Fariza, N. P. Abhimata, dan J. A. Nur Hasim, “Earthquake disaster risk map in east Java, Indonesia, using analytical hierarchy process — Natural break classification,” dalam 2016 International Conference on Knowledge Creation and Intelligent Computing (KCIC), IEEE, Nov 2016, hlm. 141–147. doi: 10.1109/KCIC.2016.7883638.

K. Hacıefendioğlu, A. C. Altunışık, dan T. Abdioğlu, “Deep Learning-Based Automated Detection of Cracks in Historical Masonry Structures,” Buildings, vol. 13, no. 12, hlm. 3113, Des 2023, doi: 10.3390/buildings13123113.

N. Karimi, M. Mishra, dan P. B. Lourenço, “Automated Surface Crack Detection in Historical Constructions with Various Materials Using Deep Learning-Based YOLO Network,” International Journal of Architectural Heritage, vol. 19, no. 5, hlm. 581–597, Mei 2025, doi: 10.1080/15583058.2024.2376177.

M. Tan dan Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th International Conference on Machine Learning, ICML 2019, vol. 2019-June, hlm. 10691–10700, 2019.

A. Ghosh, B. Soni, dan U. Baruah, “Transfer Learning-Based Deep Feature Extraction Framework Using Fine-Tuned EfficientNet B7 for Multiclass Brain Tumor Classification,” Arab. J. Sci. Eng., vol. 49, no. 9, hlm. 12027–12048, Sep 2024, doi: 10.1007/s13369-023-08607-w.

N. Vaswani, Y. Chi, dan T. Bouwmans, “Rethinking PCA for Modern Data Sets: Theory, Algorithms, and Applications,” 1 Agustus 2018, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/JPROC.2018.2853498.

B. Duran, S. Eftekhar Azam, dan M. Sanayei, “Leveraging Deep Learning for Robust Structural Damage Detection and Classification: A Transfer Learning Approach via CNN,” Infrastructures (Basel)., vol. 9, no. 12, hlm. 229, Des 2024, doi: 10.3390/infrastructures9120229.

S. Yang, M. Hou, dan S. Li, “Three-Dimensional Point Cloud Semantic Segmentation for Cultural Heritage: A Comprehensive Review,” Remote Sens. (Basel)., vol. 15, no. 3, hlm. 548, Jan 2023, doi: 10.3390/rs15030548.

A. Fariza, N. P. Abhimata, J. Akhmad, dan N. Hasim, “Earthquake Disaster Risk Map in East Java, Indonesia, using Analytical Hierarchy Process-Natural Break Classification.”

M. Tan dan Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep 2020, [Daring]. Tersedia pada: http://arxiv.org/abs/1905.11946

R. K. Adhikari dkk., “GLOSI taxonomy: A tool for ‘seismic risk assessment’ oriented classification of school buildings,” International Journal of Disaster Risk Reduction, vol. 87, Mar 2023, doi: 10.1016/j.ijdrr.2023.103594.

H. Wei dkk., “A texture feature extraction method considering spatial continuity and gray diversity,” International Journal of Applied Earth Observation and Geoinformation, vol. 130, hlm. 103896, Jun 2024, doi: 10.1016/j.jag.2024.103896.