A new robust algorithm for video text extraction

Edward Wong, Minya Chen

    Research output: Contribution to journalArticle

    Abstract

    We report on the development and implementation of a robust algorithm for extracting text in digitized color video. The algorithm first computes maximum gradient difference to detect potential text line segments from horizontal scan lines of the video. Potential text line segments are then expanded or combined with potential text line segments from adjacent scan lines to form text blocks, which are then subject to filtering and refinement. Color information is then used to more precisely locate text pixels within the detected text blocks. The robustness of the algorithm is demonstrated by using a variety of color images digitized from broadcast television for testing. The algorithm also performs well on images after JPEG compression and decompression, and on images corrupted with different types of noise.

    Original languageEnglish (US)
    Pages (from-to)1397-1406
    Number of pages10
    JournalPattern Recognition
    Volume36
    Issue number6
    DOIs
    StatePublished - Jun 2003

    Fingerprint

    Color
    Television
    Pixels
    Testing

    Keywords

    • Color segmentation
    • Scan line processing
    • Text detection
    • Video processing
    • Video text filtering

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition
    • Signal Processing
    • Electrical and Electronic Engineering

    Cite this

    A new robust algorithm for video text extraction. / Wong, Edward; Chen, Minya.

    In: Pattern Recognition, Vol. 36, No. 6, 06.2003, p. 1397-1406.

    Research output: Contribution to journalArticle

    Wong, Edward ; Chen, Minya. / A new robust algorithm for video text extraction. In: Pattern Recognition. 2003 ; Vol. 36, No. 6. pp. 1397-1406.
    @article{10b48c2c08104e33a3abd40323baa2e9,
    title = "A new robust algorithm for video text extraction",
    abstract = "We report on the development and implementation of a robust algorithm for extracting text in digitized color video. The algorithm first computes maximum gradient difference to detect potential text line segments from horizontal scan lines of the video. Potential text line segments are then expanded or combined with potential text line segments from adjacent scan lines to form text blocks, which are then subject to filtering and refinement. Color information is then used to more precisely locate text pixels within the detected text blocks. The robustness of the algorithm is demonstrated by using a variety of color images digitized from broadcast television for testing. The algorithm also performs well on images after JPEG compression and decompression, and on images corrupted with different types of noise.",
    keywords = "Color segmentation, Scan line processing, Text detection, Video processing, Video text filtering",
    author = "Edward Wong and Minya Chen",
    year = "2003",
    month = "6",
    doi = "10.1016/S0031-3203(02)00230-3",
    language = "English (US)",
    volume = "36",
    pages = "1397--1406",
    journal = "Pattern Recognition",
    issn = "0031-3203",
    publisher = "Elsevier Limited",
    number = "6",

    }

    TY - JOUR

    T1 - A new robust algorithm for video text extraction

    AU - Wong, Edward

    AU - Chen, Minya

    PY - 2003/6

    Y1 - 2003/6

    N2 - We report on the development and implementation of a robust algorithm for extracting text in digitized color video. The algorithm first computes maximum gradient difference to detect potential text line segments from horizontal scan lines of the video. Potential text line segments are then expanded or combined with potential text line segments from adjacent scan lines to form text blocks, which are then subject to filtering and refinement. Color information is then used to more precisely locate text pixels within the detected text blocks. The robustness of the algorithm is demonstrated by using a variety of color images digitized from broadcast television for testing. The algorithm also performs well on images after JPEG compression and decompression, and on images corrupted with different types of noise.

    AB - We report on the development and implementation of a robust algorithm for extracting text in digitized color video. The algorithm first computes maximum gradient difference to detect potential text line segments from horizontal scan lines of the video. Potential text line segments are then expanded or combined with potential text line segments from adjacent scan lines to form text blocks, which are then subject to filtering and refinement. Color information is then used to more precisely locate text pixels within the detected text blocks. The robustness of the algorithm is demonstrated by using a variety of color images digitized from broadcast television for testing. The algorithm also performs well on images after JPEG compression and decompression, and on images corrupted with different types of noise.

    KW - Color segmentation

    KW - Scan line processing

    KW - Text detection

    KW - Video processing

    KW - Video text filtering

    UR - http://www.scopus.com/inward/record.url?scp=0037410629&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0037410629&partnerID=8YFLogxK

    U2 - 10.1016/S0031-3203(02)00230-3

    DO - 10.1016/S0031-3203(02)00230-3

    M3 - Article

    AN - SCOPUS:0037410629

    VL - 36

    SP - 1397

    EP - 1406

    JO - Pattern Recognition

    JF - Pattern Recognition

    SN - 0031-3203

    IS - 6

    ER -