Please use this identifier to cite or link to this item:
|Title:||Face recognition based on the combination of rectangle filters and unified subspace analysis approach||Authors:||Cai, Yichang||Keywords:||DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Biometrics||Issue Date:||2008||Abstract:||As one of the most successful applications of Image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second Is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face Images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system. The objective of my dissertation is to study some important and classical face recognition approaches include both the holistic approaches and the feature-based approaches for face recognition. I would also propose one method which is the combination of the two different approaches mentioned. The new method I proposed in this dissertation is the method called ‘face recognition based on the combination of the rectangle filters and unified subspace analysis approach’. This method is the combination of the UFS method and the rectangle filters. It combines the two method’s advantage together. This method can improve the face recognition performance as it extract lots of features inside one image use several rectangle filters and It combine the UFS method for the finally recognition process. We will see some experiment results later and can see its improvement compare to the traditional UFS method and rectangle filters method individually. Additionally, for this project I will do some face recognition experiments which are based on the approach called efficient rectangle feature extraction for face recognition. I write a MATLAB program to implement it. The code will be showed in the appendix part.||URI:||http://hdl.handle.net/10356/18849||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Theses|
Page view(s) 5261
checked on Oct 20, 2020
checked on Oct 20, 2020
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.