抄録
In this paper, we introduce a novel image-based approach to detect cracks in concrete surfaces. Crack detection is important for the inspection, diagnosis, and maintenance of concrete structures. However, conventional image-based approaches cannot achieve precise detection since the image of the concrete surface contains various types of noise due to different causes such as concrete blebs, stain, insufficient contrast, and shading. In order to detect the cracks with high fidelity, we assume that they are composed of thin interconnected textures and propose an image-based percolation model that extracts a continuous texture by referring to the connectivity of brightness and the shape of the percolated region, depending on the length criterion of the scalable local image processing techniques. Additionally, noise reduction based on the percolation model is proposed. We evaluated the validity of the proposed technique by using precision recall and receiver operating characteristic (ROC) analysis by means of some experiments with actual concrete surface images.
| 元の言語 | English |
|---|---|
| ページ（範囲） | 128-135 |
| ページ数 | 8 |
| ジャーナル | IEEJ Transactions on Electrical and Electronic Engineering |
| 巻 | 3 |
| 発行部数 | 1 |
| DOI | |
| 出版物ステータス | Published - 2008 1 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
これを引用
Image-based crack detection for real concrete surfaces. / Yamaguchi, Tomoyuki; Nakamura, Shingo; Saegusa, Ryo; Hashimoto, Shuji.
：: IEEJ Transactions on Electrical and Electronic Engineering, 巻 3, 番号 1, 01.2008, p. 128-135.研究成果: Article
}
TY - JOUR
T1 - Image-based crack detection for real concrete surfaces
AU - Yamaguchi, Tomoyuki
AU - Nakamura, Shingo
AU - Saegusa, Ryo
AU - Hashimoto, Shuji
PY - 2008/1
Y1 - 2008/1
N2 - In this paper, we introduce a novel image-based approach to detect cracks in concrete surfaces. Crack detection is important for the inspection, diagnosis, and maintenance of concrete structures. However, conventional image-based approaches cannot achieve precise detection since the image of the concrete surface contains various types of noise due to different causes such as concrete blebs, stain, insufficient contrast, and shading. In order to detect the cracks with high fidelity, we assume that they are composed of thin interconnected textures and propose an image-based percolation model that extracts a continuous texture by referring to the connectivity of brightness and the shape of the percolated region, depending on the length criterion of the scalable local image processing techniques. Additionally, noise reduction based on the percolation model is proposed. We evaluated the validity of the proposed technique by using precision recall and receiver operating characteristic (ROC) analysis by means of some experiments with actual concrete surface images.
AB - In this paper, we introduce a novel image-based approach to detect cracks in concrete surfaces. Crack detection is important for the inspection, diagnosis, and maintenance of concrete structures. However, conventional image-based approaches cannot achieve precise detection since the image of the concrete surface contains various types of noise due to different causes such as concrete blebs, stain, insufficient contrast, and shading. In order to detect the cracks with high fidelity, we assume that they are composed of thin interconnected textures and propose an image-based percolation model that extracts a continuous texture by referring to the connectivity of brightness and the shape of the percolated region, depending on the length criterion of the scalable local image processing techniques. Additionally, noise reduction based on the percolation model is proposed. We evaluated the validity of the proposed technique by using precision recall and receiver operating characteristic (ROC) analysis by means of some experiments with actual concrete surface images.
KW - Crack detection
KW - Noise reduction
KW - Percolation
KW - Real concrete surface
UR - http://www.scopus.com/inward/record.url?scp=38049173628&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=38049173628&partnerID=8YFLogxK
U2 - 10.1002/tee.20244
DO - 10.1002/tee.20244
M3 - Article
AN - SCOPUS:38049173628
VL - 3
SP - 128
EP - 135
JO - IEEJ Transactions on Electrical and Electronic Engineering
JF - IEEJ Transactions on Electrical and Electronic Engineering
SN - 1931-4973
IS - 1
ER -