StructDamage:A Large Scale Unified Crack and Surface Defect Dataset for Robust Structural Damage Detection

TL;DR

StructDamage is a large, diverse dataset of nearly 78,000 images across nine surface types, designed to improve the training and evaluation of deep learning models for crack and surface defect detection in civil engineering.

Contribution

The paper introduces StructDamage, a comprehensive, harmonized dataset of crack and surface defect images from multiple sources, enabling better generalization and benchmarking of detection algorithms.

Findings

High classification accuracy with macro F1-scores over 0.96.

DenseNet201 achieves 98.62% accuracy on the dataset.

Dataset supports robust training and evaluation of CNNs and Vision Transformers.

Abstract

Automated detection and classification of structural cracks and surface defects is a critical challenge in civil engineering, infrastructure maintenance, and heritage preservation. Recent advances in Computer Vision (CV) and Deep Learning (DL) have significantly improved automatic crack detection. However, these methods rely heavily on large, diverse, and carefully curated datasets that include various crack types across different surface materials. Many existing public crack datasets lack geographic diversity, surface types, scale, and labeling consistency, making it challenging for trained algorithms to generalize effectively in real world conditions. We provide a novel dataset, StructDamage, a curated collection of approximately 78,093 images spanning nine surface types: walls, tile, stone, road, pavement, deck, concrete, and brick. The dataset was constructed by systematically aggregating, harmonizing, and reannotating images from 32 publicly available datasets covering concrete structures, asphalt pavements, masonry walls, bridges, and historic buildings. All images are organized in a folder level classification hierarchy suitable for training Convolutional Neural Networks (CNNs) and Vision Transformers. To highlight the practical value of the dataset, we present baseline classification results using fifteen DL architectures from six model families, with twelve achieving macro F1-scores over 0.96. The best performing model DenseNet201 achieves 98.62% accuracy. The proposed dataset provides a comprehensive and versatile resource suitable for classification tasks. With thorough documentation and a standard structure, it is designed to promote reproducible research and support the development and fair evaluation of robust crack damage detection approaches.