Context-based compression of binary images in parallel

Eugene Ageenko (Corresponding Author), Martti Forsell, Pasi Fränti

    Research output: Contribution to journalArticleScientificpeer-review

    1 Citation (Scopus)

    Abstract

    Binary images can be compressed efficiently using context-based statistical modeling and arithmetic coding. However, this approach is fully sequential and therefore additional computing power from parallel computers cannot be utilized. We attack this problem and show how to implement the context-based compression in parallel. Our approach is to segment the image into non-overlapping blocks, which are compressed independently by the processors. We give two alternative solutions about how to construct, distribute and utilize the model in parallel, and study the effect on the compression performance and execution time. We show by experiments that the proposed approach achieves speedup that is proportional to the number of processors. The work efficiency exceeds 50% with any reasonable number of processors.
    Original languageEnglish
    Pages (from-to)1223-1237
    JournalSoftware: Practice and Experience
    Volume32
    Issue number13
    DOIs
    Publication statusPublished - 2002
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Binary images
    Experiments

    Keywords

    • Image compression
    • context modeling
    • JBIG, parallel algorithms
    • EREW
    • PRAM

    Cite this

    Ageenko, Eugene ; Forsell, Martti ; Fränti, Pasi. / Context-based compression of binary images in parallel. In: Software: Practice and Experience. 2002 ; Vol. 32, No. 13. pp. 1223-1237.
    @article{112cbada3e0745dc89696590ebe48497,
    title = "Context-based compression of binary images in parallel",
    abstract = "Binary images can be compressed efficiently using context-based statistical modeling and arithmetic coding. However, this approach is fully sequential and therefore additional computing power from parallel computers cannot be utilized. We attack this problem and show how to implement the context-based compression in parallel. Our approach is to segment the image into non-overlapping blocks, which are compressed independently by the processors. We give two alternative solutions about how to construct, distribute and utilize the model in parallel, and study the effect on the compression performance and execution time. We show by experiments that the proposed approach achieves speedup that is proportional to the number of processors. The work efficiency exceeds 50{\%} with any reasonable number of processors.",
    keywords = "Image compression, context modeling, JBIG, parallel algorithms, EREW, PRAM",
    author = "Eugene Ageenko and Martti Forsell and Pasi Fr{\"a}nti",
    year = "2002",
    doi = "10.1002/spe.480",
    language = "English",
    volume = "32",
    pages = "1223--1237",
    journal = "Software: Practice and Experience",
    issn = "0038-0644",
    publisher = "Wiley",
    number = "13",

    }

    Context-based compression of binary images in parallel. / Ageenko, Eugene (Corresponding Author); Forsell, Martti; Fränti, Pasi.

    In: Software: Practice and Experience, Vol. 32, No. 13, 2002, p. 1223-1237.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Context-based compression of binary images in parallel

    AU - Ageenko, Eugene

    AU - Forsell, Martti

    AU - Fränti, Pasi

    PY - 2002

    Y1 - 2002

    N2 - Binary images can be compressed efficiently using context-based statistical modeling and arithmetic coding. However, this approach is fully sequential and therefore additional computing power from parallel computers cannot be utilized. We attack this problem and show how to implement the context-based compression in parallel. Our approach is to segment the image into non-overlapping blocks, which are compressed independently by the processors. We give two alternative solutions about how to construct, distribute and utilize the model in parallel, and study the effect on the compression performance and execution time. We show by experiments that the proposed approach achieves speedup that is proportional to the number of processors. The work efficiency exceeds 50% with any reasonable number of processors.

    AB - Binary images can be compressed efficiently using context-based statistical modeling and arithmetic coding. However, this approach is fully sequential and therefore additional computing power from parallel computers cannot be utilized. We attack this problem and show how to implement the context-based compression in parallel. Our approach is to segment the image into non-overlapping blocks, which are compressed independently by the processors. We give two alternative solutions about how to construct, distribute and utilize the model in parallel, and study the effect on the compression performance and execution time. We show by experiments that the proposed approach achieves speedup that is proportional to the number of processors. The work efficiency exceeds 50% with any reasonable number of processors.

    KW - Image compression

    KW - context modeling

    KW - JBIG, parallel algorithms

    KW - EREW

    KW - PRAM

    U2 - 10.1002/spe.480

    DO - 10.1002/spe.480

    M3 - Article

    VL - 32

    SP - 1223

    EP - 1237

    JO - Software: Practice and Experience

    JF - Software: Practice and Experience

    SN - 0038-0644

    IS - 13

    ER -