Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal KOMPUTA : Jurnal Ilmiah Komputer dan Informatika
Mongkol, Nick Engelbert
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Perbandingan Algoritma Sobel, Kirsch, Laplacian Of Gaussian dan Canny Untuk Deteksi pada Citra Keretakan Dinding Verado, Kyan Dillan; Riti, Yosefina Finsensia; Mongkol, Nick Engelbert
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.15919

Abstract

The durability and structural soundness of building walls are matters of concern. The process of identifying cracks in building structures takes a lot of time and effort, and is also inefficient in terms of cost and accuracy because it relies on the subjective judgment of the supervisor. The use of edge detection in detecting cracks can improve the efficiency of the process. The four algorithms selected for this research are Sobel, Kirsch, LoG, and Canny algorithms. This study aims to analyze the best algorithm in detecting cracks in the walls of building structures, using the parameters of Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR) values. The results of this study show that the Canny algorithm is the best algorithm of the four algorithms used to detect cracks and also avoid graffiti, with an MSE measurement value of 112.08 and a PSNR value of 27.66 on images that have cracks on the wall, and also has an MSE measurement value of 113.94 and a PSNR value of 27.61 on images that do not have cracks.
Co-Authors Riti, Yosefina Finsensia Verado, Kyan Dillan