Fast crack detection method for large-size concrete surface images using percolation-based image processing

Tomoyuki Yamaguchi, Shuji Hashimoto

    Research output: Contribution to journalArticle

    178 Citations (Scopus)

    Abstract

    The detection of cracks on concrete surfaces is the most important step during the inspection of concrete structures. Conventional crack detection methods are performed by experienced human inspectors who sketch crack patterns manually; however, such detection methods are expensive and subjective. Therefore, automated crack detection techniques that utilize image processing have been proposed. Although most the image-based approaches focus on the accuracy of crack detection, the computation time is also important for practical applications because the size of digital images has increased up to 10 megapixels. We introduce an efficient and high-speed crack detection method that employs percolation-based image processing. We propose termination-and skip-added procedures to reduce the computation time. The percolation process is terminated by calculating the circularity during the processing. Moreover, percolation processing can be skipped in subsequent pixels according to the circularity of neighboring pixels. The experimental result shows that the proposed approach efficiently reduces the computation cost.

    Original languageEnglish
    Pages (from-to)797-809
    Number of pages13
    JournalMachine Vision and Applications
    Volume21
    Issue number5
    DOIs
    Publication statusPublished - 2010 Aug

    Fingerprint

    Crack detection
    Image processing
    Concretes
    Pixels
    Cracks
    Processing
    Concrete construction
    Inspection
    Costs

    Keywords

    • Concrete surface
    • Crack detection
    • Large-size image
    • Percolation

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Computer Vision and Pattern Recognition
    • Software
    • Computer Science Applications

    Cite this

    Fast crack detection method for large-size concrete surface images using percolation-based image processing. / Yamaguchi, Tomoyuki; Hashimoto, Shuji.

    In: Machine Vision and Applications, Vol. 21, No. 5, 08.2010, p. 797-809.

    Research output: Contribution to journalArticle

    @article{3cc3d78fd1ee4f42810680eef55fda55,
    title = "Fast crack detection method for large-size concrete surface images using percolation-based image processing",
    abstract = "The detection of cracks on concrete surfaces is the most important step during the inspection of concrete structures. Conventional crack detection methods are performed by experienced human inspectors who sketch crack patterns manually; however, such detection methods are expensive and subjective. Therefore, automated crack detection techniques that utilize image processing have been proposed. Although most the image-based approaches focus on the accuracy of crack detection, the computation time is also important for practical applications because the size of digital images has increased up to 10 megapixels. We introduce an efficient and high-speed crack detection method that employs percolation-based image processing. We propose termination-and skip-added procedures to reduce the computation time. The percolation process is terminated by calculating the circularity during the processing. Moreover, percolation processing can be skipped in subsequent pixels according to the circularity of neighboring pixels. The experimental result shows that the proposed approach efficiently reduces the computation cost.",
    keywords = "Concrete surface, Crack detection, Large-size image, Percolation",
    author = "Tomoyuki Yamaguchi and Shuji Hashimoto",
    year = "2010",
    month = "8",
    doi = "10.1007/s00138-009-0189-8",
    language = "English",
    volume = "21",
    pages = "797--809",
    journal = "Machine Vision and Applications",
    issn = "0932-8092",
    publisher = "Springer Verlag",
    number = "5",

    }

    TY - JOUR

    T1 - Fast crack detection method for large-size concrete surface images using percolation-based image processing

    AU - Yamaguchi, Tomoyuki

    AU - Hashimoto, Shuji

    PY - 2010/8

    Y1 - 2010/8

    N2 - The detection of cracks on concrete surfaces is the most important step during the inspection of concrete structures. Conventional crack detection methods are performed by experienced human inspectors who sketch crack patterns manually; however, such detection methods are expensive and subjective. Therefore, automated crack detection techniques that utilize image processing have been proposed. Although most the image-based approaches focus on the accuracy of crack detection, the computation time is also important for practical applications because the size of digital images has increased up to 10 megapixels. We introduce an efficient and high-speed crack detection method that employs percolation-based image processing. We propose termination-and skip-added procedures to reduce the computation time. The percolation process is terminated by calculating the circularity during the processing. Moreover, percolation processing can be skipped in subsequent pixels according to the circularity of neighboring pixels. The experimental result shows that the proposed approach efficiently reduces the computation cost.

    AB - The detection of cracks on concrete surfaces is the most important step during the inspection of concrete structures. Conventional crack detection methods are performed by experienced human inspectors who sketch crack patterns manually; however, such detection methods are expensive and subjective. Therefore, automated crack detection techniques that utilize image processing have been proposed. Although most the image-based approaches focus on the accuracy of crack detection, the computation time is also important for practical applications because the size of digital images has increased up to 10 megapixels. We introduce an efficient and high-speed crack detection method that employs percolation-based image processing. We propose termination-and skip-added procedures to reduce the computation time. The percolation process is terminated by calculating the circularity during the processing. Moreover, percolation processing can be skipped in subsequent pixels according to the circularity of neighboring pixels. The experimental result shows that the proposed approach efficiently reduces the computation cost.

    KW - Concrete surface

    KW - Crack detection

    KW - Large-size image

    KW - Percolation

    UR - http://www.scopus.com/inward/record.url?scp=77956619263&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77956619263&partnerID=8YFLogxK

    U2 - 10.1007/s00138-009-0189-8

    DO - 10.1007/s00138-009-0189-8

    M3 - Article

    AN - SCOPUS:77956619263

    VL - 21

    SP - 797

    EP - 809

    JO - Machine Vision and Applications

    JF - Machine Vision and Applications

    SN - 0932-8092

    IS - 5

    ER -