Accurate extraction and measurement of fine cracks from concrete block surface image

Measurement and analysis of cracks on the surface of reinforced concrete can be an effective key for diagnosing quake-proofness of a construction or measuring material fatigue. The conventional method of diagnosis is to analyze cracks using a sketch manually produced by inspection engineers, however it takes a fairly long time and lacks quantitative objectivity. This paper proposes an automatic detection and analysis system for concrete block inspection. By employing a high-resolution camera, the cracks and displacement features are automatically extracted using an integrated image processing technique. Utilizing the proposed method, the crack scale can be measured with sub-pixel order accuracy. Automatic feature extraction and quantitative analysis of cracks are implemented to make the system efficient tool for assisting specialists in inspection procedures.