Summary: This dataset contains 40,000 images of cracked and non-cracked concrete, designed for training and validating models for crack detection in concrete structures.
| Parameter | Value |
|---|---|
| Name | Concrete Crack Images for Classification |
| Labeled | Yes |
| Time Series | No |
| Simulation | No |
| Missing Values | No |
| Dataset Characteristics | Image |
| Feature Type | Image Data |
| Associated Tasks | Classification |
| Number of Instances | 40000 |
| Number of Features | INA |
| Date Donated | 15 January 2018 |
| Source | Mendeley Data |
The dataset contains concrete images having cracks. The data is collected from various METU Campus Buildings. The dataset is divided into two as negative and positive crack images for image classification. Each class has 20000 images with a total of 40000 images with 227 x 227 pixels with RGB channels. The dataset is generated from 458 high-resolution images (4032x3024 pixel) with the method proposed by Zhang et al (2016). High-resolution images have variance in terms of surface finish and illumination conditions. No data augmentation in terms of random rotation or flipping is applied.
Concrete, Crack detection, Image classification, Deep learning, Structural health monitoring