Improved image decoding over noisy channels using minimum mean-squared estimation and a Markov mesh

Moon Seo Park, David Jonathan Miller

    Research output: Contribution to journalArticle

    15 Citations (Scopus)

    Abstract

    Joint source-channel (JSC) decoding based on residual source redundancy is a technique for providing channel robustness to quantized data. Previous work assumed a model equivalent to viewing the encoder/noisy channel tandem as a discrete hidden Markov model (HMM) with transmitted indices the hidden states. Here, we generalize this HMM-based (1-D) approach for images, using the more powerful hidden Markov mesh random field (HMMRF) model. While previous state estimation methods for HMMRF's base estimates on only a causal subset of the observed data, our new method uses both causal and anticausal subsets. For JSC-based image decoding, the new method provides significant benefits over several competing techniques.

    Original languageEnglish (US)
    Pages (from-to)863-867
    Number of pages5
    JournalIEEE Transactions on Image Processing
    Volume8
    Issue number6
    DOIs
    StatePublished - Jan 1 1999

    Fingerprint

    Hidden Markov models
    Decoding
    State estimation
    Redundancy

    All Science Journal Classification (ASJC) codes

    • Software
    • Computer Graphics and Computer-Aided Design

    Cite this

    @article{18994451ee8846e4941dad575f926d53,
    title = "Improved image decoding over noisy channels using minimum mean-squared estimation and a Markov mesh",
    abstract = "Joint source-channel (JSC) decoding based on residual source redundancy is a technique for providing channel robustness to quantized data. Previous work assumed a model equivalent to viewing the encoder/noisy channel tandem as a discrete hidden Markov model (HMM) with transmitted indices the hidden states. Here, we generalize this HMM-based (1-D) approach for images, using the more powerful hidden Markov mesh random field (HMMRF) model. While previous state estimation methods for HMMRF's base estimates on only a causal subset of the observed data, our new method uses both causal and anticausal subsets. For JSC-based image decoding, the new method provides significant benefits over several competing techniques.",
    author = "Park, {Moon Seo} and Miller, {David Jonathan}",
    year = "1999",
    month = "1",
    day = "1",
    doi = "10.1109/83.766862",
    language = "English (US)",
    volume = "8",
    pages = "863--867",
    journal = "IEEE Transactions on Image Processing",
    issn = "1057-7149",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "6",

    }

    Improved image decoding over noisy channels using minimum mean-squared estimation and a Markov mesh. / Park, Moon Seo; Miller, David Jonathan.

    In: IEEE Transactions on Image Processing, Vol. 8, No. 6, 01.01.1999, p. 863-867.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Improved image decoding over noisy channels using minimum mean-squared estimation and a Markov mesh

    AU - Park, Moon Seo

    AU - Miller, David Jonathan

    PY - 1999/1/1

    Y1 - 1999/1/1

    N2 - Joint source-channel (JSC) decoding based on residual source redundancy is a technique for providing channel robustness to quantized data. Previous work assumed a model equivalent to viewing the encoder/noisy channel tandem as a discrete hidden Markov model (HMM) with transmitted indices the hidden states. Here, we generalize this HMM-based (1-D) approach for images, using the more powerful hidden Markov mesh random field (HMMRF) model. While previous state estimation methods for HMMRF's base estimates on only a causal subset of the observed data, our new method uses both causal and anticausal subsets. For JSC-based image decoding, the new method provides significant benefits over several competing techniques.

    AB - Joint source-channel (JSC) decoding based on residual source redundancy is a technique for providing channel robustness to quantized data. Previous work assumed a model equivalent to viewing the encoder/noisy channel tandem as a discrete hidden Markov model (HMM) with transmitted indices the hidden states. Here, we generalize this HMM-based (1-D) approach for images, using the more powerful hidden Markov mesh random field (HMMRF) model. While previous state estimation methods for HMMRF's base estimates on only a causal subset of the observed data, our new method uses both causal and anticausal subsets. For JSC-based image decoding, the new method provides significant benefits over several competing techniques.

    UR - http://www.scopus.com/inward/record.url?scp=0032639843&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0032639843&partnerID=8YFLogxK

    U2 - 10.1109/83.766862

    DO - 10.1109/83.766862

    M3 - Article

    C2 - 18267498

    AN - SCOPUS:0032639843

    VL - 8

    SP - 863

    EP - 867

    JO - IEEE Transactions on Image Processing

    JF - IEEE Transactions on Image Processing

    SN - 1057-7149

    IS - 6

    ER -