LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE

A NEW APPROACH FOR OBJECT-RECOGNITION.

Guido Gerig

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

    Abstract

    Images of bad quality require robust, global techniques for object recognition. The Hough technique for detection on curve-like image characteristics is well known. Parallel hardware, alternative data structures and projection techniques increase the efficiency of such methods, but the problem of interpreting the resulting accumulator remains. A backmapping technique is discussed which reduces the complexity of evidence information in accumulator space, and uniquely links specific points in image space to most-evident locations in accumulator space. The interpretation is substantially simplified and the accuracy of recognition increased. The global grouping of image points through common relations to evident accumulator cells offers the possibility of applying much more complex interpretation strategies. The advantage of the technique is illustrated by applying the method to three completely different recognition tasks in biomedical and medical imagery, where the link between points in image space and accumulated evidences is used in different ways.

    Original languageEnglish (US)
    Title of host publicationUnknown Host Publication Title
    PublisherIEEE
    Pages112-117
    Number of pages6
    ISBN (Print)081860777X
    StatePublished - 1987

    Fingerprint

    Object recognition
    Data structures
    Hardware

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Gerig, G. (1987). LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE: A NEW APPROACH FOR OBJECT-RECOGNITION. In Unknown Host Publication Title (pp. 112-117). IEEE.

    LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE : A NEW APPROACH FOR OBJECT-RECOGNITION. / Gerig, Guido.

    Unknown Host Publication Title. IEEE, 1987. p. 112-117.

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

    Gerig, G 1987, LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE: A NEW APPROACH FOR OBJECT-RECOGNITION. in Unknown Host Publication Title. IEEE, pp. 112-117.
    Gerig G. LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE: A NEW APPROACH FOR OBJECT-RECOGNITION. In Unknown Host Publication Title. IEEE. 1987. p. 112-117
    Gerig, Guido. / LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE : A NEW APPROACH FOR OBJECT-RECOGNITION. Unknown Host Publication Title. IEEE, 1987. pp. 112-117
    @inproceedings{c9992053d68941579ae77a76651079c0,
    title = "LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE: A NEW APPROACH FOR OBJECT-RECOGNITION.",
    abstract = "Images of bad quality require robust, global techniques for object recognition. The Hough technique for detection on curve-like image characteristics is well known. Parallel hardware, alternative data structures and projection techniques increase the efficiency of such methods, but the problem of interpreting the resulting accumulator remains. A backmapping technique is discussed which reduces the complexity of evidence information in accumulator space, and uniquely links specific points in image space to most-evident locations in accumulator space. The interpretation is substantially simplified and the accuracy of recognition increased. The global grouping of image points through common relations to evident accumulator cells offers the possibility of applying much more complex interpretation strategies. The advantage of the technique is illustrated by applying the method to three completely different recognition tasks in biomedical and medical imagery, where the link between points in image space and accumulated evidences is used in different ways.",
    author = "Guido Gerig",
    year = "1987",
    language = "English (US)",
    isbn = "081860777X",
    pages = "112--117",
    booktitle = "Unknown Host Publication Title",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE

    T2 - A NEW APPROACH FOR OBJECT-RECOGNITION.

    AU - Gerig, Guido

    PY - 1987

    Y1 - 1987

    N2 - Images of bad quality require robust, global techniques for object recognition. The Hough technique for detection on curve-like image characteristics is well known. Parallel hardware, alternative data structures and projection techniques increase the efficiency of such methods, but the problem of interpreting the resulting accumulator remains. A backmapping technique is discussed which reduces the complexity of evidence information in accumulator space, and uniquely links specific points in image space to most-evident locations in accumulator space. The interpretation is substantially simplified and the accuracy of recognition increased. The global grouping of image points through common relations to evident accumulator cells offers the possibility of applying much more complex interpretation strategies. The advantage of the technique is illustrated by applying the method to three completely different recognition tasks in biomedical and medical imagery, where the link between points in image space and accumulated evidences is used in different ways.

    AB - Images of bad quality require robust, global techniques for object recognition. The Hough technique for detection on curve-like image characteristics is well known. Parallel hardware, alternative data structures and projection techniques increase the efficiency of such methods, but the problem of interpreting the resulting accumulator remains. A backmapping technique is discussed which reduces the complexity of evidence information in accumulator space, and uniquely links specific points in image space to most-evident locations in accumulator space. The interpretation is substantially simplified and the accuracy of recognition increased. The global grouping of image points through common relations to evident accumulator cells offers the possibility of applying much more complex interpretation strategies. The advantage of the technique is illustrated by applying the method to three completely different recognition tasks in biomedical and medical imagery, where the link between points in image space and accumulated evidences is used in different ways.

    UR - http://www.scopus.com/inward/record.url?scp=0023209958&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0023209958&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 081860777X

    SP - 112

    EP - 117

    BT - Unknown Host Publication Title

    PB - IEEE

    ER -