Document image compression using straight line extraction and block context model

Hwayong Joung, Edward Wong, Yu Chen, Seung P. Kim

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

    Abstract

    We present a new lossy technique for document image compression by using straight line extraction and a block context model. Straight line segments are extracted from a binary document image and subtracted from the original image. Their endpoint coordinates and width can then be efficiently coded. The remaining part of the image, which mainly contains text and other symbols, is coded using a high-order block context model (HOBCM) based on vector quantization (VQ). The proposed method is particularly effective for document images containing a large number of straight line segments, such as engineering or architectural drawings. It achieves much higher compression than conventional lossless techniques, such as the JBIG and CCITT G3 and G4 standards, with little loss of visual quality. In the experiments we performed on a group of engineering drawings digitized at 200 dpi, compression ratios ranging from 30 to 70 were obtained.

    Original languageEnglish (US)
    Title of host publicationIEEE International Conference on Image Processing
    PublisherIEEE Comp Soc
    Pages530-534
    Number of pages5
    Volume1
    StatePublished - 1998
    EventProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) - Chicago, IL, USA
    Duration: Oct 4 1998Oct 7 1998

    Other

    OtherProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3)
    CityChicago, IL, USA
    Period10/4/9810/7/98

    Fingerprint

    Drawing (graphics)
    Image compression
    Vector quantization
    Experiments

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition
    • Hardware and Architecture
    • Electrical and Electronic Engineering

    Cite this

    Joung, H., Wong, E., Chen, Y., & Kim, S. P. (1998). Document image compression using straight line extraction and block context model. In IEEE International Conference on Image Processing (Vol. 1, pp. 530-534). IEEE Comp Soc.

    Document image compression using straight line extraction and block context model. / Joung, Hwayong; Wong, Edward; Chen, Yu; Kim, Seung P.

    IEEE International Conference on Image Processing. Vol. 1 IEEE Comp Soc, 1998. p. 530-534.

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

    Joung, H, Wong, E, Chen, Y & Kim, SP 1998, Document image compression using straight line extraction and block context model. in IEEE International Conference on Image Processing. vol. 1, IEEE Comp Soc, pp. 530-534, Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, 10/4/98.
    Joung H, Wong E, Chen Y, Kim SP. Document image compression using straight line extraction and block context model. In IEEE International Conference on Image Processing. Vol. 1. IEEE Comp Soc. 1998. p. 530-534
    Joung, Hwayong ; Wong, Edward ; Chen, Yu ; Kim, Seung P. / Document image compression using straight line extraction and block context model. IEEE International Conference on Image Processing. Vol. 1 IEEE Comp Soc, 1998. pp. 530-534
    @inproceedings{f9b0f94e63084826872018c14109332f,
    title = "Document image compression using straight line extraction and block context model",
    abstract = "We present a new lossy technique for document image compression by using straight line extraction and a block context model. Straight line segments are extracted from a binary document image and subtracted from the original image. Their endpoint coordinates and width can then be efficiently coded. The remaining part of the image, which mainly contains text and other symbols, is coded using a high-order block context model (HOBCM) based on vector quantization (VQ). The proposed method is particularly effective for document images containing a large number of straight line segments, such as engineering or architectural drawings. It achieves much higher compression than conventional lossless techniques, such as the JBIG and CCITT G3 and G4 standards, with little loss of visual quality. In the experiments we performed on a group of engineering drawings digitized at 200 dpi, compression ratios ranging from 30 to 70 were obtained.",
    author = "Hwayong Joung and Edward Wong and Yu Chen and Kim, {Seung P.}",
    year = "1998",
    language = "English (US)",
    volume = "1",
    pages = "530--534",
    booktitle = "IEEE International Conference on Image Processing",
    publisher = "IEEE Comp Soc",

    }

    TY - GEN

    T1 - Document image compression using straight line extraction and block context model

    AU - Joung, Hwayong

    AU - Wong, Edward

    AU - Chen, Yu

    AU - Kim, Seung P.

    PY - 1998

    Y1 - 1998

    N2 - We present a new lossy technique for document image compression by using straight line extraction and a block context model. Straight line segments are extracted from a binary document image and subtracted from the original image. Their endpoint coordinates and width can then be efficiently coded. The remaining part of the image, which mainly contains text and other symbols, is coded using a high-order block context model (HOBCM) based on vector quantization (VQ). The proposed method is particularly effective for document images containing a large number of straight line segments, such as engineering or architectural drawings. It achieves much higher compression than conventional lossless techniques, such as the JBIG and CCITT G3 and G4 standards, with little loss of visual quality. In the experiments we performed on a group of engineering drawings digitized at 200 dpi, compression ratios ranging from 30 to 70 were obtained.

    AB - We present a new lossy technique for document image compression by using straight line extraction and a block context model. Straight line segments are extracted from a binary document image and subtracted from the original image. Their endpoint coordinates and width can then be efficiently coded. The remaining part of the image, which mainly contains text and other symbols, is coded using a high-order block context model (HOBCM) based on vector quantization (VQ). The proposed method is particularly effective for document images containing a large number of straight line segments, such as engineering or architectural drawings. It achieves much higher compression than conventional lossless techniques, such as the JBIG and CCITT G3 and G4 standards, with little loss of visual quality. In the experiments we performed on a group of engineering drawings digitized at 200 dpi, compression ratios ranging from 30 to 70 were obtained.

    UR - http://www.scopus.com/inward/record.url?scp=0032315781&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0032315781&partnerID=8YFLogxK

    M3 - Conference contribution

    VL - 1

    SP - 530

    EP - 534

    BT - IEEE International Conference on Image Processing

    PB - IEEE Comp Soc

    ER -