Special Feature

User Panel

My Panel

My Panel

Bookmark Science Articles

Recent News
Bookmark / Share This Science Site

Class-based feature matching across unrestricted transformations.

Class-based feature matching across unrestricted transformations. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

  • Abstract Text of This Paper
  • Journal Published
  • MeSH Keywords of This Abstract
  • Chemicals and Substances Used in this Paper
  • Grants and Granting Agency of this Research
  • Database Accession Numbers Used in this Paper
  • Related Papers
  • Related Research Tags
  • Rate this Research Paper
  • Class-based feature matching across unrestricted transformations. Abstract Text:

    We develop a novel method for class-based feature matching across large changes in viewing conditions. The method is based on the property that when objects share a similar part, the similarity is preserved across viewing conditions. Given a feature and a training set of object images, we first identify the subset of objects that share this feature. The transformation of the feature's appearance across viewing conditions is determined mainly by properties of the feature, rather than of the object in which it is embedded. Therefore, the transformed feature will be shared by approximately the same set of objects. Based on this consistency requirement, corresponding features can be reliably identified from a set of candidate matches. Unlike previous approaches, the proposed scheme compares feature appearances only in similar viewing conditions, rather than across different viewing conditions. As a result, the scheme is not restricted to locally planar objects or affine transformations. The approach also does not require examples of correct matches. We show that by using the proposed method, a dense set of accurate correspondences can be obtained. Experimental comparisons demonstrate that matching accuracy is significantly improved over previous schemes. Finally, we show that the scheme can be successfully used for invariant object recognition.

    Class-based feature matching across unrestricted transformations. Publishing Authors By Initials

    For similar abstracts research abstracts see: abstracts research

    PUBMED ID PMID:

    MEDLINE DATE:

    Class-based feature matching across unrestricted transformations. Journal Published:

    PUBLICATION TYPE: Research Support, Non-U.S. Gov

    Journal: IEEE transactions on pattern analysis and machine

    VOLUME: 30

    Page Numbers: 1618-31

    Journal Abbreviation:

    ISSN: 0162-8828

    DAY: 11

    MONTH: Sep

    YEAR: 2008

    Class-based feature matching across unrestricted transformations. Information

    Number of References:

    LANGUAGE: eng

    NlmUniqueID: 9885960

    Class-based feature matching across unrestricted transformations. Keywords Mesh Terms:

    KEYWORDS:

    MESH TERMS:

    Chemical & Substance for Abstract: Class-based feature matching across unrestricted transformations. Information

    Substance Name:

    Registry Number:

    Grant and Affiliation Information for Class-based feature matching across unrestricted transformations.

    AFFILIATION: California Institute of Technology, Pasadena, CA 91125, USA. eugenenbart@gmail.com

    Country: United States

    United States Research PublicationUnited States Research Publication

    AGENCY:

    GRANT:

    ACRONYM:

    MEDLINETA: IEEE Trans Pattern Anal Mach I

    REFSOURCE:

    DATABASENAME:

    ACCESSION NUMBER:

    Number Hits: 0

    Class-based feature matching across unrestricted transformations Related Publications

     

    Molecular Station USER Menu

    Welcome to Molecular Station!

    You have to register before you can post on our forums or use our advanced features. Register Now! Its Free and Fast!

    Already registered? Login now below.

    User Name:

    Password:

    Already registered and Forgot your password? Click below to recover it.

    Recover Lost Password

    Join now - it's fast and free!

    Molecular Station is THE largest network of researchers, scientists and science lovers anywhere!

    Research Terms of Usage and Disclaimer
    Home
    Features

    Protocols

    DNA Forum

    Science Forum

    DNA Forum
    Biology Forum

    Science News


    [CaRP] XML error: Invalid document end at line 2

    For more click here:Science News