Docstoc

Khan

Document Sample
Khan Powered By Docstoc
					Gait Recognition

      By Arshiya Khan
Biometrics
   Authentication based on the physiological
    or behavioral characteristics of people
   It is a pattern recognition system at
    establishes a person’s identity by
    comparison of data .
   It’s authentication is "automatic", "real-
    time", "non-forensic" subset of the broader
    field of human identification.
Classifications
   Biometric systems:
o    Verification
o   Identification
   Biometric devices:
o   Positive Identification
o   Negative Identification
Examples of Biometrics
   Fingerprint
   Handwritten signature
   Facial recognition
   Speech recognition
   Gait recognition
What is Gait recognition
   It aims to discriminate individuals by the
    way they walk
   It is unobtrusive.
    It depends on how the silhouette shape of
    an individual changes over time in an image
    sequence
Gait Recognition Algorithm
Human Detection and Tracking
FEATURE EXTRACTION
   Silhouette
    Representation
    2D silhouettes are
    changed into an
    associated sequence
    of 1D signals
   di=((xi-xc)2+(yi-yc)2)1/2
RECOGNITION
CONCLUSION
   Subject to the effects of different types
    of clothes.
   Lack of generality of viewing angles.
References
   “Silhouette Analysis-Based Gait Recognition
   for Human Identification”
http://www.sinobiometrics.com/publications/lwang/PAM
   I.pdf
 “Gait Recognition Using Static, Activity-
   Specific Parameters “
   http://www.cc.gatech.edu/cpl/amos/mypapers/cvpr2
   001_Gait.pdf
    “A Newly Emergent Study: Gait Recognition “
 http://www.sinobiometrics.com/gait.htm

				
DOCUMENT INFO
Shared By:
Categories:
Stats:
views:27
posted:4/28/2011
language:English
pages:11