CRACK DETECTION AND MEASUREMENT IN CONCRETE USING CONVOLUTION NEURAL NETWORK AND DBSCAN SEGMENTATION

Crack detection and measurement are essential for assessing the structural integrity of reinforced concrete (RC) structures, but challenges such as surface variability and class imbalance complicate accurate detection. This study introduces an approach integrating Convolutional Neural Networks (ConvNets), adaptive sliding windows, and DBSCAN-based semantic segmentation to address these challenges and enhance crack detection and quantification. The method was evaluated on various surface types, including painted masonry and concrete pavement, with a particular focus on overcoming class imbalance. To tackle this issue, the resampling (RS) technique was applied, achieving the best balance between precision and recall, with an F1 score of 0.836 during validation. The adaptive sliding window algorithm, optimized for lower magnification factors, further enhanced crack localization, improving IoU, recall, and precision. In semantic segmentation, the proposed method performed competitively on the DeepCrack dataset, achieving an IoU of 0.671, comparable to state-of-the-art models. Additionally, the measurement algorithm, which captures crack features such as length, width, and orientation, was tested on multiple surfaces. For painted masonry, it achieved a precision of 0.99, recall of 0.845, and IoU of 0.838, while for concrete pavement, it achieved a precision of 0.983, recall of 0.835, and IoU of 0.823. When applied to the DeepCrack dataset ground truth, it yielded a recall of 0.884, precision of 0.971, and IoU of 0.860. The results demonstrate the robustness and adaptability of this framework, offering an effective solution for automated crack detection and measurement across diverse surfaces.