Related Experiment Video
Updated: Feb 26, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
Crack Detection in Concrete Tunnels Using a Gabor Filter Invariant to Rotation
Roberto Medina1, José Llamas2, Jaime Gómez-García-Bermejo3
1CARTIF Foundation, Parque Tecnológico de Boecillo, 47151 Valladolid, Spain. robmed@cartif.es.
This study introduces an automated system for detecting concrete tunnel cracks using image sensors and a novel Gabor filter method. The system achieves 95.27% accuracy, significantly improving upon existing crack detection techniques.
Area of Science:
- Civil Engineering
- Computer Vision
- Materials Science
Background:
- Concrete tunnels are critical infrastructure requiring regular structural integrity assessments.
- Manual crack detection is labor-intensive, subjective, and prone to errors.
- Automated methods are needed for efficient and reliable inspection of tunnel surfaces.
Purpose of the Study:
- To develop and evaluate an automated system for detecting cracks in concrete tunnel surfaces.
- To investigate optimal image acquisition parameters for crack detection.
- To introduce a rotation-invariant Gabor filter method for enhanced crack detection accuracy.
Main Methods:
- Data acquisition using linear cameras and controlled lighting.
- Analysis of camera resolution and quantity based on crack size and tunnel type.
- Application of a rotation-invariant Gabor filter optimized by a modified genetic algorithm (Differential Evolution).
Main Results:
- A balanced accuracy of 95.27% was achieved in detecting crack pixels.
- The proposed Gabor filter method effectively detects cracks in all directions.
- The system demonstrates superior performance compared to previous crack detection approaches.
Conclusions:
- The developed image-based system offers a highly accurate and efficient solution for concrete tunnel crack detection.
- The novel Gabor filter and genetic algorithm optimization provide a robust method for structural health monitoring.
- This technology has the potential to enhance tunnel safety and reduce maintenance costs.
Related Concept Videos
Types of Non-structural Cracks in Concrete
Plastic shrinkage cracks typically form within hours after the concrete is poured. The concrete's surface dries faster than the bottom, creating tensile stress that the still-plastic concrete cannot withstand, leading to diagonal or randomly patterned cracks on the concrete surface.
Microcracking in Concrete
Detection of Black Holes
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
Non-destructive Tests for Concrete Strength
Vibrating Concrete
Segregation in Fresh Concrete

