A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automatic Annotation of Web Images for Domain-Specific Crack Classification
Abstract Manual visual crack detection and classification for inspection of civil infrastructure is time-consuming and labor-intensive. Many automatic crack detection and classification algorithms have, thus, been developed in the past decade, several of which achieved acceptable performance results for specific applications and using large datasets for training. However, developing training data for automatic crack classification is not an easy task. It requires a large dataset in terms of quantity and variability, as well as well-trained professionals to label the dataset. Hence, there is a need for efficient ways to develop well-labeled datasets that could not only reduce human effort, but also adapt to diverse inspection contexts for improved classification performance. To address this need, this paper proposes a data retrieval and annotation method to automatically retrieve and label crack images from the Web. The dataset can be used as pseudo training data for supervised machine learning-based crack classification algorithms. The proposed method incrementally retrieves and labels crack images. A weak Convolutional Neural Network classifier first learns from a limited set of Web images, and then acts as a machine annotator and further labels a larger size of data. The proposed method was able to retrieve and label a set of images with 95% labeling recall, which shows that the proposed approach is promising.
Automatic Annotation of Web Images for Domain-Specific Crack Classification
Abstract Manual visual crack detection and classification for inspection of civil infrastructure is time-consuming and labor-intensive. Many automatic crack detection and classification algorithms have, thus, been developed in the past decade, several of which achieved acceptable performance results for specific applications and using large datasets for training. However, developing training data for automatic crack classification is not an easy task. It requires a large dataset in terms of quantity and variability, as well as well-trained professionals to label the dataset. Hence, there is a need for efficient ways to develop well-labeled datasets that could not only reduce human effort, but also adapt to diverse inspection contexts for improved classification performance. To address this need, this paper proposes a data retrieval and annotation method to automatically retrieve and label crack images from the Web. The dataset can be used as pseudo training data for supervised machine learning-based crack classification algorithms. The proposed method incrementally retrieves and labels crack images. A weak Convolutional Neural Network classifier first learns from a limited set of Web images, and then acts as a machine annotator and further labels a larger size of data. The proposed method was able to retrieve and label a set of images with 95% labeling recall, which shows that the proposed approach is promising.
Automatic Annotation of Web Images for Domain-Specific Crack Classification
Liu, Peter Cheng-Yang (author) / El-Gohary, Nora (author)
2018-10-04
8 pages
Article/Chapter (Book)
Electronic Resource
English
Crack classification , Machine learning , Convolutional neural networks , Automatic training data generation , Image retrieval , Image annotation Engineering , Building Construction and Design , Data Mining and Knowledge Discovery , Building Repair and Maintenance , Computer-Aided Engineering (CAD, CAE) and Design , Light Construction, Steel Construction, Timber Construction , Construction Management
Progressive Automatic Method for Annotation of Concrete Crack Images
| Springer Verlag | 2025
Automatic road crack detection from pavement images
| DataCite | 2024
Challenges in Road Crack Segmentation Due to Coarse Annotation
| Springer Verlag | 2023
British Library Conference Proceedings | 2015