Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Gait recognition for human identification based on ICA and fuzzy SVM through multiple views fusion
Lu J., Zhang E. Pattern Recognition Letters28 (16):2401-2411,2007.Type:Article
Date Reviewed: Jun 2 2008

Through biometrics, video cameras watch over us and computers can automatically identify us using metrics for human physiology--such as face, fingerprints, iris, and hand geometry--and also metrics for human behavior. Most biometrics require a close and detailed view of the person, and in some security applications this is not possible to obtain. Gait, a behavioral biometric based on a person’s way of walking, is an answer to the need for a biometric applicable from a distance. Most existing gait-recognition algorithms consider gait to be a sequence of body silhouettes. These algorithms basically differ on the features selected to represent each silhouette, and on the classifier used to recognize the unknown gait as being one of the gaits belonging to the training database.

This paper presents a gait-recognition algorithm that transforms the person’s silhouette into a one-dimensional signal, representing the signal by means of a Fourier descriptor, wavelet descriptor, and pseudo-Zernike moments. Different classifiers are tested, particularly the genetic fuzzy support vector machine (GFSVM). The authors show that the fusion of the classification results obtained with the different features improves the individual results. Furthermore, they also improve the simple view results by fusing the classification results of correspondent sequences from different views (lateral, oblique, and frontal).

Although the authors assume that further evaluation of their algorithm is needed to show robustness, the main contributions of this paper are the multiple-feature fusion for a one-view gait identification system and the different views fusion for multiple-views gait identification.

This is a very new research field, and there is still a lack of a general standard database that includes a large number of gait sequences of different persons, with different clothes, and from different views. This kind of resource is necessary to evaluate algorithms, and to allow a comparison among them.

Reviewer:  Marma Abasolo Review #: CR135662 (0904-0387)
Bookmark and Share
 
Object Recognition (I.4.8 ... )
 
 
Edge And Feature Detection (I.4.6 ... )
 
 
Feature Evaluation And Selection (I.5.2 ... )
 
 
Feature Representation (I.4.7 ... )
 
 
Fuzzy Set (I.5.1 ... )
 
 
Design Methodology (I.5.2 )
 
  more  
Would you recommend this review?
yes
no
Other reviews under "Object Recognition": Date
On view likelihood and stability
Weinshall D., Werman M. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(2): 97-108, 1997. Type: Article
Feb 1 1999
Junctions
Parida L., Geiger D., Hummel R. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(7): 687-698, 1998. Type: Article
Apr 1 1999
Topological recognition of polyhedral objects from multiple views
Laurentini A. Artificial Intelligence 127(1): 31-55, 2001. Type: Article
Apr 17 2002
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy