Stochastic sampling from image coder induced probability distributions

Onur G. Guleryuz, Viresh Ratnakar, Regunathan Radhakrishnan, Nasir Memon

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

    Abstract

    In this paper we use stochastic sampling to obtain images from the probability distributions induced by well-known image coders SPIHT, JPEG, JPEG2000, and JPEG-LS. Our aim is to obtain actual samples from the typical sets that these coders form in the space of images. We utilize mathematical measures that allow us to quantify the role edges play in representing the resulting sample images. We qualitatively and quantitatively compare these images with a basic form of natural image definition as well as with the standard test images Lenna and Barbara. Our results indicate that today's state-of-the-art image coders are applicable to a variety of localized image regions but they do not significantly model or take advantage of edges that mark the boundaries of different regions.

    Original languageEnglish (US)
    Title of host publicationConference Record of the Asilomar Conference on Signals, Systems and Computers
    EditorsM.B. Matthews
    Pages1562-1566
    Number of pages5
    Volume2
    StatePublished - 2003
    EventConference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
    Duration: Nov 9 2003Nov 12 2003

    Other

    OtherConference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers
    CountryUnited States
    CityPacific Grove, CA
    Period11/9/0311/12/03

    Fingerprint

    Probability distributions
    Sampling

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Signal Processing
    • Hardware and Architecture

    Cite this

    Guleryuz, O. G., Ratnakar, V., Radhakrishnan, R., & Memon, N. (2003). Stochastic sampling from image coder induced probability distributions. In M. B. Matthews (Ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers (Vol. 2, pp. 1562-1566)

    Stochastic sampling from image coder induced probability distributions. / Guleryuz, Onur G.; Ratnakar, Viresh; Radhakrishnan, Regunathan; Memon, Nasir.

    Conference Record of the Asilomar Conference on Signals, Systems and Computers. ed. / M.B. Matthews. Vol. 2 2003. p. 1562-1566.

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

    Guleryuz, OG, Ratnakar, V, Radhakrishnan, R & Memon, N 2003, Stochastic sampling from image coder induced probability distributions. in MB Matthews (ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers. vol. 2, pp. 1562-1566, Conference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/9/03.
    Guleryuz OG, Ratnakar V, Radhakrishnan R, Memon N. Stochastic sampling from image coder induced probability distributions. In Matthews MB, editor, Conference Record of the Asilomar Conference on Signals, Systems and Computers. Vol. 2. 2003. p. 1562-1566
    Guleryuz, Onur G. ; Ratnakar, Viresh ; Radhakrishnan, Regunathan ; Memon, Nasir. / Stochastic sampling from image coder induced probability distributions. Conference Record of the Asilomar Conference on Signals, Systems and Computers. editor / M.B. Matthews. Vol. 2 2003. pp. 1562-1566
    @inproceedings{1d5dc2333595463283f1804e7d2d3f02,
    title = "Stochastic sampling from image coder induced probability distributions",
    abstract = "In this paper we use stochastic sampling to obtain images from the probability distributions induced by well-known image coders SPIHT, JPEG, JPEG2000, and JPEG-LS. Our aim is to obtain actual samples from the typical sets that these coders form in the space of images. We utilize mathematical measures that allow us to quantify the role edges play in representing the resulting sample images. We qualitatively and quantitatively compare these images with a basic form of natural image definition as well as with the standard test images Lenna and Barbara. Our results indicate that today's state-of-the-art image coders are applicable to a variety of localized image regions but they do not significantly model or take advantage of edges that mark the boundaries of different regions.",
    author = "Guleryuz, {Onur G.} and Viresh Ratnakar and Regunathan Radhakrishnan and Nasir Memon",
    year = "2003",
    language = "English (US)",
    volume = "2",
    pages = "1562--1566",
    editor = "M.B. Matthews",
    booktitle = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

    }

    TY - GEN

    T1 - Stochastic sampling from image coder induced probability distributions

    AU - Guleryuz, Onur G.

    AU - Ratnakar, Viresh

    AU - Radhakrishnan, Regunathan

    AU - Memon, Nasir

    PY - 2003

    Y1 - 2003

    N2 - In this paper we use stochastic sampling to obtain images from the probability distributions induced by well-known image coders SPIHT, JPEG, JPEG2000, and JPEG-LS. Our aim is to obtain actual samples from the typical sets that these coders form in the space of images. We utilize mathematical measures that allow us to quantify the role edges play in representing the resulting sample images. We qualitatively and quantitatively compare these images with a basic form of natural image definition as well as with the standard test images Lenna and Barbara. Our results indicate that today's state-of-the-art image coders are applicable to a variety of localized image regions but they do not significantly model or take advantage of edges that mark the boundaries of different regions.

    AB - In this paper we use stochastic sampling to obtain images from the probability distributions induced by well-known image coders SPIHT, JPEG, JPEG2000, and JPEG-LS. Our aim is to obtain actual samples from the typical sets that these coders form in the space of images. We utilize mathematical measures that allow us to quantify the role edges play in representing the resulting sample images. We qualitatively and quantitatively compare these images with a basic form of natural image definition as well as with the standard test images Lenna and Barbara. Our results indicate that today's state-of-the-art image coders are applicable to a variety of localized image regions but they do not significantly model or take advantage of edges that mark the boundaries of different regions.

    UR - http://www.scopus.com/inward/record.url?scp=4143129109&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=4143129109&partnerID=8YFLogxK

    M3 - Conference contribution

    VL - 2

    SP - 1562

    EP - 1566

    BT - Conference Record of the Asilomar Conference on Signals, Systems and Computers

    A2 - Matthews, M.B.

    ER -