Academic Journals Database
Disseminating quality controlled scientific knowledge

An Efficient Gait Recognition System For Human Identification Using Modified ICA

Author(s): M.Pushpa Rani | G.Arumugam

Journal: International Journal of Computer Science & Information Technology
ISSN 0975-4660

Volume: 2;
Issue: 1;
Start page: 55;
Date: 2010;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Gait Recognition | Modified Independent Component Analysis (MICA) | Human detection and tracking | Skeletonization | Morphological operator

Biometric systems are becoming increasingly important, as they provide more reliable and efficientmeans of identity verification. Human identification at a distance has recently gained enormous interestamong computer vision researchers. Gait recognition aims essentially to address this problem byrecognising people based on the way they walk. In this paper, we propose an efficient self-similaritybased gait recognition system for human identification using modified Independent Component Analysis(MICA). Initially the background modelling is done from a video sequence. Subsequently, the movingforeground objects in the individual image frames are segmented using the background subtractionalgorithm. Then, the morphological skeleton operator is used to track the moving silhouettes of a walkingfigure. The MICA based on eigenspace transformation is then trained using the sequence of silhouetteimages. Finally, when a video sequence is fed, the proposed system recognizes the gait features andthereby humans, based on self-similarity measure. The proposed system is evaluated using gait databasesand the experimentation on outdoor video sequences demonstrates that the proposed algorithm achievesa pleasing recognition performance.
Save time & money - Smart Internet Solutions     

Tango Rapperswil
Tango Rapperswil