Click here to skip to this page's main content.

New Feature: You can now embed Open Library books on your website!   Learn More
Last edited by WorkBot
January 24, 2010 | History

A biologically inspired gait recognition system using the Hough transform 1 edition

A biologically inspired gait recognition system using the Hough transf ...
Kevin Cannons

No ebook available.

Prefer the physical book? Check nearby libraries powered by WorldCat

Buy this book

Zut alors! There's no description for this book yet. Can you help?
There is only 1 edition record, so we'll show it here...  •  Add edition?

A biologically inspired gait recognition system using the Hough transform.

Published 2005 .
Written in English.

About the Book

Humans are remarkably efficient at identifying motion of a biological origin. Computers have thus far been unable to emulate this ability. A gait recognition system which combines knowledge of the human visual architecture with computer vision techniques is proposed. The basic premise of the system is to model the human body as an articulated structure composed of straight line segments. The limbs of a walking individual are detected using the Hough transform, a technique which shares similarities with the primary visual cortex. The angles of the detected limbs are used as features to train and test a hidden Markov model (HMM) classifier. The system obtains a correct classification rate of 65% with a standard motion database. This performance is comparable to other leading systems.

Edition Notes

Source: Masters Abstracts International, Volume: 44-02, page: 0928.

Thesis (M.A.Sc.)--University of Toronto, 2005.

Electronic version licensed for access by U. of T. users.

GERSTEIN MICROTEXT copy on microfiche (2 microfiches).

The Physical Object

92 leaves.
Number of pages

ID Numbers

Open Library

History Created December 11, 2009 · 2 revisions Download catalog record: RDF / JSON

January 24, 2010 Edited by WorkBot add more information to works
December 11, 2009 Created by WorkBot add works page