A robust algorithm for text extraction in color video

Edward Wong, M. Chen

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

    Abstract

    We report on the development and implementation of a new algorithm for extracting text in digitized color video. The algorithm operates by locating potential text line segments from horizontal scan lines. Detected text line segments are expanded or combined with text line segments from adjacent scan lines to form larger text blocks, which are then subject to filtering and refinement. Text pixels within text blocks are then found by using bi-color clustering and connected-component analysis. A morphological contour smoothing, and a morphological resolution enhancement algorithms are then applied to the detected binary texts to enhance their visual quality. The implemented algorithm has fast execution time and is effective in detecting text in difficult cases, such as scenes with highly textured background, and scenes with small text. A variety of color images digitized from broadcast television are used to test the algorithm and excellent performance result was obtained.

    Original languageEnglish (US)
    Title of host publicationIEEE International Conference on Multi-Media and Expo
    Pages797-800
    Number of pages4
    EditionII/TUESDAY
    StatePublished - 2000
    Event2000 IEEE International Conference on Multimedia and Expo (ICME 2000) - New York, NY, United States
    Duration: Jul 30 2000Aug 2 2000

    Other

    Other2000 IEEE International Conference on Multimedia and Expo (ICME 2000)
    CountryUnited States
    CityNew York, NY
    Period7/30/008/2/00

    Fingerprint

    Color
    Television
    Pixels

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Wong, E., & Chen, M. (2000). A robust algorithm for text extraction in color video. In IEEE International Conference on Multi-Media and Expo (II/TUESDAY ed., pp. 797-800)

    A robust algorithm for text extraction in color video. / Wong, Edward; Chen, M.

    IEEE International Conference on Multi-Media and Expo. II/TUESDAY. ed. 2000. p. 797-800.

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

    Wong, E & Chen, M 2000, A robust algorithm for text extraction in color video. in IEEE International Conference on Multi-Media and Expo. II/TUESDAY edn, pp. 797-800, 2000 IEEE International Conference on Multimedia and Expo (ICME 2000), New York, NY, United States, 7/30/00.
    Wong E, Chen M. A robust algorithm for text extraction in color video. In IEEE International Conference on Multi-Media and Expo. II/TUESDAY ed. 2000. p. 797-800
    Wong, Edward ; Chen, M. / A robust algorithm for text extraction in color video. IEEE International Conference on Multi-Media and Expo. II/TUESDAY. ed. 2000. pp. 797-800
    @inproceedings{04307d90f42044c692cadbca7efdc07c,
    title = "A robust algorithm for text extraction in color video",
    abstract = "We report on the development and implementation of a new algorithm for extracting text in digitized color video. The algorithm operates by locating potential text line segments from horizontal scan lines. Detected text line segments are expanded or combined with text line segments from adjacent scan lines to form larger text blocks, which are then subject to filtering and refinement. Text pixels within text blocks are then found by using bi-color clustering and connected-component analysis. A morphological contour smoothing, and a morphological resolution enhancement algorithms are then applied to the detected binary texts to enhance their visual quality. The implemented algorithm has fast execution time and is effective in detecting text in difficult cases, such as scenes with highly textured background, and scenes with small text. A variety of color images digitized from broadcast television are used to test the algorithm and excellent performance result was obtained.",
    author = "Edward Wong and M. Chen",
    year = "2000",
    language = "English (US)",
    pages = "797--800",
    booktitle = "IEEE International Conference on Multi-Media and Expo",
    edition = "II/TUESDAY",

    }

    TY - GEN

    T1 - A robust algorithm for text extraction in color video

    AU - Wong, Edward

    AU - Chen, M.

    PY - 2000

    Y1 - 2000

    N2 - We report on the development and implementation of a new algorithm for extracting text in digitized color video. The algorithm operates by locating potential text line segments from horizontal scan lines. Detected text line segments are expanded or combined with text line segments from adjacent scan lines to form larger text blocks, which are then subject to filtering and refinement. Text pixels within text blocks are then found by using bi-color clustering and connected-component analysis. A morphological contour smoothing, and a morphological resolution enhancement algorithms are then applied to the detected binary texts to enhance their visual quality. The implemented algorithm has fast execution time and is effective in detecting text in difficult cases, such as scenes with highly textured background, and scenes with small text. A variety of color images digitized from broadcast television are used to test the algorithm and excellent performance result was obtained.

    AB - We report on the development and implementation of a new algorithm for extracting text in digitized color video. The algorithm operates by locating potential text line segments from horizontal scan lines. Detected text line segments are expanded or combined with text line segments from adjacent scan lines to form larger text blocks, which are then subject to filtering and refinement. Text pixels within text blocks are then found by using bi-color clustering and connected-component analysis. A morphological contour smoothing, and a morphological resolution enhancement algorithms are then applied to the detected binary texts to enhance their visual quality. The implemented algorithm has fast execution time and is effective in detecting text in difficult cases, such as scenes with highly textured background, and scenes with small text. A variety of color images digitized from broadcast television are used to test the algorithm and excellent performance result was obtained.

    UR - http://www.scopus.com/inward/record.url?scp=0034516968&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0034516968&partnerID=8YFLogxK

    M3 - Conference contribution

    SP - 797

    EP - 800

    BT - IEEE International Conference on Multi-Media and Expo

    ER -