• DocumentCode
    1776536
  • Title

    Retrieve the similar matching images using reduced SIFT with CED algorithm

  • Author

    Bandaru, Rajanna ; Naik, Dinesh

  • Author_Institution
    Dept. Of Inf. Technol., Nat. Inst. Of Technol. Karnataka, Mangalore, India
  • fYear
    2014
  • fDate
    10-11 July 2014
  • Firstpage
    1242
  • Lastpage
    1247
  • Abstract
    The local feature descriptor called SIFT, is one of the most widely used descriptors. The keypoints found with RSIFT and describe them in a standard way, which makes them invariant to the size changes, rotation, position, scale, and so on. These are quite powerful features and are used in a variety of tasks. This local feature SIFT descriptor gives potential key points, which are extracted from the image. If there are many such key points, a lot of computation time will be required for the matching key points, and some cases one key point matches more than once. For these reasons, here we have tried to reduce the key points in order to cluster the number of key points. The reduced SIFT with Canny Edge Detection (CED) algorithm can easily identify and trace the specified image from large the Database images as much fast as possible.
  • Keywords
    content-based retrieval; edge detection; image matching; image retrieval; transforms; CED algorithm; Canny edge detection algorithm; RSIFT; content based image retrieval; local feature SIFT descriptor; local feature descriptor; similar matching image retrieval; Databases; Feature extraction; Histograms; Image edge detection; Noise; Shape; Transforms; Color Histograms; Content based image retrieval (CBIR); RANSAC; RSIFT with CED; Retrieval; Scale invariant feature transform (SIFT); Shape;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control, Instrumentation, Communication and Computational Technologies (ICCICCT), 2014 International Conference on
  • Conference_Location
    Kanyakumari
  • Print_ISBN
    978-1-4799-4191-9
  • Type

    conf

  • DOI
    10.1109/ICCICCT.2014.6993151
  • Filename
    6993151