Automated crack detection for concrete surface image using percolation model and edge information

Tomoyuki Yamaguchi, Shuji Hashimoto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    29 Citations (Scopus)

    Abstract

    A crack Is an important indicator in concrete structure diagnosis. Although cracks tend to display linear characteristics, it is not easy to detect them by conventional methods. There are a variety of difficult sources of noise: concrete bleb, stain noise, insufficient contrast, and shadings. In this paper, we introduce a novel crack detection method for a concrete surface image based on a percolation model. Our method evaluates the central pixel in a local window according to a cluster formed using percolation processing. In addition, we describe reducing the computational burden while still preserving the precision of the crack detection. To achieve this, our method utilizes edge information to reduce the number of starting points for percolation processing. The validity of the proposed technique is investigated through experiments with images of real concrete surfaces and it is shown that robust and reliable crack detection without oversight is achieved.

    Original languageEnglish
    Title of host publicationIECON Proceedings (Industrial Electronics Conference)
    Pages3355-3360
    Number of pages6
    DOIs
    Publication statusPublished - 2006
    EventIECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics - Paris
    Duration: 2006 Nov 62006 Nov 10

    Other

    OtherIECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics
    CityParis
    Period06/11/606/11/10

    Fingerprint

    Crack detection
    Concretes
    Cracks
    Processing
    Concrete construction
    Pixels
    Experiments

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering

    Cite this

    Yamaguchi, T., & Hashimoto, S. (2006). Automated crack detection for concrete surface image using percolation model and edge information. In IECON Proceedings (Industrial Electronics Conference) (pp. 3355-3360). [4153629] https://doi.org/10.1109/IECON.2006.348070

    Automated crack detection for concrete surface image using percolation model and edge information. / Yamaguchi, Tomoyuki; Hashimoto, Shuji.

    IECON Proceedings (Industrial Electronics Conference). 2006. p. 3355-3360 4153629.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Yamaguchi, T & Hashimoto, S 2006, Automated crack detection for concrete surface image using percolation model and edge information. in IECON Proceedings (Industrial Electronics Conference)., 4153629, pp. 3355-3360, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, Paris, 06/11/6. https://doi.org/10.1109/IECON.2006.348070
    Yamaguchi T, Hashimoto S. Automated crack detection for concrete surface image using percolation model and edge information. In IECON Proceedings (Industrial Electronics Conference). 2006. p. 3355-3360. 4153629 https://doi.org/10.1109/IECON.2006.348070
    Yamaguchi, Tomoyuki ; Hashimoto, Shuji. / Automated crack detection for concrete surface image using percolation model and edge information. IECON Proceedings (Industrial Electronics Conference). 2006. pp. 3355-3360
    @inproceedings{282e0743e9d34ac88edfb07f87e5283f,
    title = "Automated crack detection for concrete surface image using percolation model and edge information",
    abstract = "A crack Is an important indicator in concrete structure diagnosis. Although cracks tend to display linear characteristics, it is not easy to detect them by conventional methods. There are a variety of difficult sources of noise: concrete bleb, stain noise, insufficient contrast, and shadings. In this paper, we introduce a novel crack detection method for a concrete surface image based on a percolation model. Our method evaluates the central pixel in a local window according to a cluster formed using percolation processing. In addition, we describe reducing the computational burden while still preserving the precision of the crack detection. To achieve this, our method utilizes edge information to reduce the number of starting points for percolation processing. The validity of the proposed technique is investigated through experiments with images of real concrete surfaces and it is shown that robust and reliable crack detection without oversight is achieved.",
    author = "Tomoyuki Yamaguchi and Shuji Hashimoto",
    year = "2006",
    doi = "10.1109/IECON.2006.348070",
    language = "English",
    isbn = "1424401364",
    pages = "3355--3360",
    booktitle = "IECON Proceedings (Industrial Electronics Conference)",

    }

    TY - GEN

    T1 - Automated crack detection for concrete surface image using percolation model and edge information

    AU - Yamaguchi, Tomoyuki

    AU - Hashimoto, Shuji

    PY - 2006

    Y1 - 2006

    N2 - A crack Is an important indicator in concrete structure diagnosis. Although cracks tend to display linear characteristics, it is not easy to detect them by conventional methods. There are a variety of difficult sources of noise: concrete bleb, stain noise, insufficient contrast, and shadings. In this paper, we introduce a novel crack detection method for a concrete surface image based on a percolation model. Our method evaluates the central pixel in a local window according to a cluster formed using percolation processing. In addition, we describe reducing the computational burden while still preserving the precision of the crack detection. To achieve this, our method utilizes edge information to reduce the number of starting points for percolation processing. The validity of the proposed technique is investigated through experiments with images of real concrete surfaces and it is shown that robust and reliable crack detection without oversight is achieved.

    AB - A crack Is an important indicator in concrete structure diagnosis. Although cracks tend to display linear characteristics, it is not easy to detect them by conventional methods. There are a variety of difficult sources of noise: concrete bleb, stain noise, insufficient contrast, and shadings. In this paper, we introduce a novel crack detection method for a concrete surface image based on a percolation model. Our method evaluates the central pixel in a local window according to a cluster formed using percolation processing. In addition, we describe reducing the computational burden while still preserving the precision of the crack detection. To achieve this, our method utilizes edge information to reduce the number of starting points for percolation processing. The validity of the proposed technique is investigated through experiments with images of real concrete surfaces and it is shown that robust and reliable crack detection without oversight is achieved.

    UR - http://www.scopus.com/inward/record.url?scp=34047257501&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34047257501&partnerID=8YFLogxK

    U2 - 10.1109/IECON.2006.348070

    DO - 10.1109/IECON.2006.348070

    M3 - Conference contribution

    AN - SCOPUS:34047257501

    SN - 1424401364

    SN - 9781424401369

    SP - 3355

    EP - 3360

    BT - IECON Proceedings (Industrial Electronics Conference)

    ER -