Recognizing Faces -- An Approach Based on Gabor Wavelets
As a hot research topic over the last 25 years, face recognition still seems to be a difficult and largely problem. Distortions caused by variations in illumination, expression and pose are the main challenges to be dealt with by researchers in this field. Efficient recognition algorithms, robust ag...
| Main Author: | |
|---|---|
| Format: | Thesis (University of Nottingham only) |
| Language: | English |
| Published: |
2005
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/10177/ |
| _version_ | 1848791043904897024 |
|---|---|
| author | Shen, Linlin |
| author_facet | Shen, Linlin |
| author_sort | Shen, Linlin |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | As a hot research topic over the last 25 years, face recognition still seems to be a difficult and largely problem. Distortions caused by variations in illumination, expression and pose are the main challenges to be dealt with by researchers in this field. Efficient recognition algorithms, robust against such distortions, are the main motivations of this research.
Based on a detailed review on the background and wide applications of Gabor wavelet, this powerful and biologically driven mathematical tool is adopted to extract features for face recognition. The features contain important local frequency information and have been proven to be robust against commonly encountered distortions. To reduce the computation and memory cost caused by the large feature dimension, a novel boosting based algorithm is proposed and successfully applied to eliminate redundant features. The selected features are further enhanced by kernel subspace methods to handle the nonlinear face variations. The efficiency and robustness of the proposed algorithm is extensively tested using the ORL, FERET and BANCA databases.
To normalize the scale and orientation of face images, a generalized symmetry measure based algorithm is proposed for automatic eye location. Without the requirement of a training process, the method is simple, fast and fully tested using thousands of images from the BioID and BANCA databases.
An automatic user identification system, consisting of detection, recognition and user management modules, has been developed. The system can effectively detect faces from real video streams, identify them and retrieve corresponding user information from the application database. Different detection and recognition algorithms can also be easily integrated into the framework. |
| first_indexed | 2025-11-14T18:22:14Z |
| format | Thesis (University of Nottingham only) |
| id | nottingham-10177 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T18:22:14Z |
| publishDate | 2005 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-101772025-02-28T11:07:23Z https://eprints.nottingham.ac.uk/10177/ Recognizing Faces -- An Approach Based on Gabor Wavelets Shen, Linlin As a hot research topic over the last 25 years, face recognition still seems to be a difficult and largely problem. Distortions caused by variations in illumination, expression and pose are the main challenges to be dealt with by researchers in this field. Efficient recognition algorithms, robust against such distortions, are the main motivations of this research. Based on a detailed review on the background and wide applications of Gabor wavelet, this powerful and biologically driven mathematical tool is adopted to extract features for face recognition. The features contain important local frequency information and have been proven to be robust against commonly encountered distortions. To reduce the computation and memory cost caused by the large feature dimension, a novel boosting based algorithm is proposed and successfully applied to eliminate redundant features. The selected features are further enhanced by kernel subspace methods to handle the nonlinear face variations. The efficiency and robustness of the proposed algorithm is extensively tested using the ORL, FERET and BANCA databases. To normalize the scale and orientation of face images, a generalized symmetry measure based algorithm is proposed for automatic eye location. Without the requirement of a training process, the method is simple, fast and fully tested using thousands of images from the BioID and BANCA databases. An automatic user identification system, consisting of detection, recognition and user management modules, has been developed. The system can effectively detect faces from real video streams, identify them and retrieve corresponding user information from the application database. Different detection and recognition algorithms can also be easily integrated into the framework. 2005 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en arr https://eprints.nottingham.ac.uk/10177/1/Recognizing_Faces_--_An_Approach_Based_on_Gabor_Wavelet.pdf Shen, Linlin (2005) Recognizing Faces -- An Approach Based on Gabor Wavelets. PhD thesis, University of Nottingham. Face Recognition Gabor Wavelets Linear Subspace Methods Kernel Subspace Methods Boosting Algorithm Eye Location |
| spellingShingle | Face Recognition Gabor Wavelets Linear Subspace Methods Kernel Subspace Methods Boosting Algorithm Eye Location Shen, Linlin Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title | Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title_full | Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title_fullStr | Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title_full_unstemmed | Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title_short | Recognizing Faces -- An Approach Based on Gabor Wavelets |
| title_sort | recognizing faces -- an approach based on gabor wavelets |
| topic | Face Recognition Gabor Wavelets Linear Subspace Methods Kernel Subspace Methods Boosting Algorithm Eye Location |
| url | https://eprints.nottingham.ac.uk/10177/ |