Characterization Of Structural Building Damage In Post-Disaster Using GLCM-PCA Analysis Integration (sertifikat hak cipta)

Paper (2024) Characterization Of Structural Building Damage In Post-Disaster Using GLCM-PCA Analysis Integration (sertifikat hak cipta). EC002024223084.

Text sertifikat_EC002024223084.pdf Restricted to Repository staff only Download (2MB)

Abstract

Understanding the characteristics of a building after a natural disaster can be achieved using
image analysis techniques. Among these techniques are the Gray-Level Co-occurrence Matrix
(GLCM) and Principal Component Analysis (PCA). In the GLCM process, the input image is converted into
numerical values using eight different angles and varying pixel distances (1 and 0.5 pixels). The resulting
numerical values from GLCM are then fed into the PCA process to reveal information stored within post-
disaster building images. Interestingly, the PCA results differ between images processed with GLCM at a 1-
pixel distance versus a 0.5-pixel distance. After validation based on surveyor assessments, it was found that
the valid and accurate representation of real-world image information corresponds to the GLCM results
obtained with a 0.5-pixel distance, indicating severe damage. This conclusion is supported by the fact that
PCA results using a GLCM distance of 0.5 produce 2D and 3D visualizations predominantly clustered around
severely damaged coordinates, with a range of values (n) where n ≥ 2. Therefore, integrating image analysis
techniques such as GLCM and PCA can be used to determine the level of post-disaster building damage.

Item Type:	Hak Cipta
Keywords:	Characteristics, Building, Post-Natural Disaster, GLCM, PCA.
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080104 Computer Vision 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Agung teguh Wibowo Almais
Date Deposited:	05 Dec 2025 10:14

Downloads

Origin of downloads

Actions (login required)

View Item