We are currently experiencing intermittent issues impacting performance. We apologize for the inconvenience.
By Topic

High performance algorithms for object recognition problem by multiresolution template matching

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Prasad, L. ; Theor. Phys. Div., Los Alamos Nat. Lab., NM, USA ; Iyengar, S.S.

Template matching is a fundamental method of detecting the presence or the absence of objects and identifying them in an image. A template is itself an image that contains a feature or an object or a part of a bigger image, and is used to search a given image for the presence or the absence of the contents of the template. This search is carried out by translating the template systematically pixel-by-pixel all over the image, and at each position of the template the closeness of the template to the area covered by it is measured. The location at which the maximum degree of closeness is achieved is declared to be the location of the object detected. The problem of object/shape recognition is addressed in this paper in a multiresolutional setting using pyramidal decomposition of images with respect to an orthonormal wavelet basis. A new approach to efficient template matching to detect objects using computational geometric methods is put forward. An efficient paradigm for object recognition is described in detail with a complexity analysis

Published in:

Tools with Artificial Intelligence, 1995. Proceedings., Seventh International Conference on

Date of Conference:

5-8 Nov 1995