Supersolution techniques for face recognition from video /

Warning The system is temporarily closed to updates for reporting purpose.

Sezer, Osman Gökhan (2005) Supersolution techniques for face recognition from video /. [Thesis]

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://risc01.sabanciuniv.edu/record=b1143166 (Table of Contents)


Performance of current face recognition algorithms reduces significantly when they are applied to low-resolution face images. To handle this problem, superresolution techniques can be applied either in the pixel domain or in the face subspace. Since face images are high dimensional data which are mostly redundant for the face recognition task, feature extraction methods that reduce the dimension of the data are becoming standard for face analysis. Hence, applying super-resolution in this feature domain, in other words in face subspace, rather than in pixel domain, brings many advantages in computation together with robustness against noise and motion estimation errors. Therefore, we propose new super-resolution algorithms using Bayesian estimation and projection onto convex sets methods in feature domain and present a comparative analysis of the proposed algorithms and those already in the literature.

Item Type:Thesis
Uncontrolled Keywords:Independent component analysis -- Principal components analysis -- Video -- Face recognition
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:8279
Deposited By:IC-Cataloging
Deposited On:15 Apr 2008 13:52
Last Modified:25 Mar 2019 16:53

Repository Staff Only: item control page