• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage StatisticsView Google Analytics Statistics

    Study of face recognition systems

    Thumbnail
    View/Open
    200411001.pdf (1.122Mb)
    Date
    2006
    Author
    Patel, Hima M.
    Metadata
    Show full item record
    Abstract
    Face Recognition comes under the general area of object recognition and has attracted researchers in the pattern recognition community for the past thirty years. The significance of this area has grown rapidly largely for surveillance purposes. This thesis is on a study of face recognition techniques. Three new algorithms have been proposed, implemented and tested using standard databases and encouraging results have been obtained for all of them. The first algorithm uses modular Principal Component Analysis (PCA) for feature extraction and a multi class SVM classifier for classification. The algorithm has been tested for frontal face images, face images with variations in expression, pose and illumination conditions. Experimental results denote a 100% classification accuracy on frontal faces, 95% accuracy on expression variation images, 78% for pose variation and 67% for illumination variation images. The next algorithm concentrates solely on the illumination variation problem. Edginess method based on one dimensional processing of signals is used to extract an edginess map. Application of PCA on the edginess images gives the weight vectors which are used as features to a multi class SVM classifier. An accuracy of 100% has been obtained, proving the method to be tolerant to illumination variations. The final part of the thesis proposes a bayesian framework for face recognition. The nodes of the bayesian classifier are modelled as a Gaussian Mixture Model (GMM) and the parameters of the nodes are learnt using Maximum Likelihood Estimation (MLE) algorithm. The inferencing is done using the junction tree inferencing algorithm. An accuracy of 93.75% has been achieved.
    URI
    http://drsr.daiict.ac.in/handle/123456789/102
    Collections
    • M Tech Dissertations [923]

    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     


    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV