By Topic

Patterns in Motion

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

1 Author(s)
Allen, Allen D. ; Algorithms, Inc., Northridge, Calif. 91324.

The case is considered in which the shape of a moving object is observed from a fixed point of reference along the line of motion. Three distinct recognition algorithms are introduced: for recognizing patterns per se, for recognizing patterns in symbolic context and for recognizing patterns in the context of their motion. The second of these algorithms requires two observations of the moving object; that is, it must be observed from two distinct points along the line of motion. There are implications that the introduction of context into pattern recognition may depend upon a degradation of the recognition mechanism. If a moving object is to be recognized independent of the speed with which it moves past a point of reference, then the shape of the object must be generalized to a number of segments over which the derivatives of the variables defining its shape are continuously contained in one of the four classes: {the negative reals}, {zero}, {the positive reals}, and {infinity}.

Published in:

Systems, Man and Cybernetics, IEEE Transactions on  (Volume:SMC-2 ,  Issue: 1 )