Crack Density and Length Detection using Machine Learning

Abstract

This study presents a comprehensive approach for detecting and analyzing microscopic cracks in rock samples using computer vision techniques and machine learning algorithms. The proposed methodology involves image segmentation, crack detection, length, and density prediction, utilizing a combination of image processing techniques and linear regression modeling. Microscopic rock images captured at various temperatures were analyzed to detect and measure cracks accurately. The developed system demonstrated effective crack detection and length measurement capabilities, aided by image segmentation, edge detection, and feature extraction methods. Moreover, the application of linear regression facilitated the prediction of crack parameters, exhibiting a clear relationship between crack characteristics and temperature variations. The findings contribute to a deeper understanding of crack formation mechanisms in rocks under different temperature conditions, offering valuable insights for geological studies and infrastructure integrity assessments. © 2024, Avestia Publishing. All rights reserved.