Search Results

Your search on keyword:face recognition found these results. 1 to 10 of 551 records in 3.12s



save citation
full views 9
citation viewed 0

Robust Face Recognition Technique for a Real-Time Embedded Face Recognition System

Author/Creator: Shan, Ting, Bigdeli, Abbas, Lovell, Brian C., Chen, Shaokang
Resource type:
Date: 2008
Subject: face recognition, pattern recognition
Record contributed by: The University of Queensland

Full Record and related resources:
http://espace.library.uq.edu.au/view/UQ:151909
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
isMemberOf Excellence in Research Australia (ERA) - Collection http://espace.library.uq.edu.au/list/UQ:152266
less
http://espace.library.uq.edu.au/view/UQ:151909
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
more

Description
In Chapter 8, Shan, Bigdeli, Lovell and Chen propose a pose variability compensation technique which synthesizes realistic frontal face images from non-frontal views. It is based on modeling the face via active appearance models and estimating the pose through a correlation model. The proposed technique is coupled with adaptive principal component analysis (APCA) which was previously shown to perform well in the presence of both lighting and expression variations. The proposed recognition techniques, though advanced, are not computationally intensive. So they are quite well-suited to the embedded system environment. Indeed, the authors have implemented an early prototype of a face recognition module on a mobile camera phone so that the camera could be used to identify the person holding the phone.

Publisher: Information Science Reference
Contributor: Brijesh Verma; Michael Blumenstein

Coverage: 2008-01-01T00:00:00Z
less
In Chapter 8, Shan, Bigdeli, Lovell and Chen propose a pose variability compensation technique which synthesizes realistic frontal face images from non-frontal views. It is based on modeling the face via active appearance models and estimating the pose through ...
more
save citation
full views 1
citation viewed 0

Representative feature chain for single gallery image face recognition

Author/Creator: Chen, Shaokang, Sanderson, Conrad, Sun, Sai, Lovell, Brian
Resource type:
Date: 2009
Subject: D face recognition (2)
Record contributed by: The University of Queensland

Full Record and related resources:
http://espace.library.uq.edu.au/view/UQ:175102
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Excellence in Research Australia (ERA) - Collection http://espace.library.uq.edu.au/list/UQ:152266
less
http://espace.library.uq.edu.au/view/UQ:175102
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Excellence in Research Australia (ERA) - Collection http://espace.library.uq.edu.au/list/UQ:152266

Description
Under the constraint of using only a single gallery image per person, this paper proposes a fast multi-class pattern classification approach to 2D face recognition robust to changes in pose, illumination, and expression (PIE). This work has three main contributions: (1) we propose a representative face space method to extract robust features, (2) we apply a learning method to weight features in pairs, (3) we combine the feature pairs into a feature chain in order to find the weights for all features. The approach is evaluated for face recognition under PIE changes on three public databases. Results show that the method performs considerably better than several other appearance-based methods and can reliably recognise faces at large pose angles without the need for fragile pose estimation pre-processing. Moreover,computational load is low (comparable to standard eigenface methods), which is a critical factor in wide-area surveillance applications.

Publisher: Institute of Electrical and Electronics Engineers

Coverage: 2009-01-01T00:00:00Z
less
Under the constraint of using only a single gallery image per person, this paper proposes a fast multi-class pattern classification approach to 2D face recognition robust to changes in pose, illumination, and expression (PIE). This work has three main contributions: ...
more
save citation
full views 1
citation viewed 0

Face recognition using a time-of-flight camera

Author/Creator: Meers, S., Ward, K.
Resource type: presentation
Date: 2009
Subject: Face recognition, time-of-flight, SwissRanger
Record contributed by: University of Wollongong

Full Record and related resources:
http://ro.uow.edu.au/infopapers/745
less
http://ro.uow.edu.au/infopapers/745

Description
This paper presents a novel three-dimensional (3D) method for detecting, tracking and recognising human faces using a time-of-flight camera. The system works by detecting a single central feature point, typically the nose tip, and by intersecting the 3D point data with spheres centred at the central feature point. The resulting spherical intersection profiles are used to perform face recognition and to track the position and orientation of the face. The main benefit of this method is that it is fast and efficient in terms or memory and computational expense. Furthermore, as the system utilises a time-of-flight camera and topographical information, it is not affected by variations in illumination, face orientation or partial occlusion of facial features. Experimental results are provided which show the potential of this method to exceed the real-time performance of existing head-pose tracking and face recognition systems.

Publisher: Research Online

Format: application/pdf
Source: Faculty of Informatics - Papers
less
This paper presents a novel three-dimensional (3D) method for detecting, tracking and recognising human faces using a time-of-flight camera. The system works by detecting a single central feature point, typically the nose tip, and by intersecting the 3D point ...
more
save citation
full views 0
citation viewed 0

Selection and Fusion of Facial Features for Face Recognition

Author/Creator: Fan, Xiaolong, Faculty of Arts, Business, Informatics and Education, Verma, Brijesh, Faculty of Arts, Business, Informatics and Education
Resource type: journal article
Date: 2009
Subject: Face recognition, Neural networks, Evolutionary algorithms
Record contributed by: Central Queensland University

Full Record and related resources:
http://hdl.cqu.edu.au/10018/45491
less
http://hdl.cqu.edu.au/10018/45491

Description
This paper proposes and investigates a facial feature selection and fusion technique for improving the classification accuracy of face recognition systems. The proposed technique is novel in terms of feature selection and fusion processes. It incorporates neural networks and genetic algorithms for the selection and classification of facial features. The proposed technique is evaluated by using the separate facial region features and the combined features. The combined features outperform the separate facial region features in the experimental investigation. A comprehensive comparison with other existing face recognition techniques on FERET benchmark database is included in this paper. The proposed technique has produced 94% classification accuracy, which is a significant improvement and best classification accuracy among the published results in the literature.


Other identifier: acquire3-20100227-08434; cqu:5853
less
This paper proposes and investigates a facial feature selection and fusion technique for improving the classification accuracy of face recognition systems. The proposed technique is novel in terms of feature selection and fusion processes. It incorporates neural ...
more
save citation
full views 1
citation viewed 0

Representative Feature Chain for Single Gallery Image Face Recognition

Author/Creator: Chen, S., Sanderson, C., Sun S., Lovell, B. C.
Resource type:
Date: 2009
Subject: face recognition, data mining, pattern recognition
Record contributed by: The University of Queensland

Full Record and related resources:
http://espace.library.uq.edu.au/view/UQ:177329
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
less
http://espace.library.uq.edu.au/view/UQ:177329
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801

Description
Under the constraint of using only a single gallery image per person, this paper proposes a fast multi-class pattern classification approach to 2D face recognition robust to changes in pose, illumination, and expression (PIE). This work has three main contributions: (1) we propose a representative face space method to extract robust features, (2) we apply a learning method to weight features in pairs, (3) we combine the feature pairs into a feature chain in order to find the weights for all features. The approach is evaluated for face recognition under PIE changes on three public databases. Results show that the method performs considerably better than several other appearance-based methods and can reliably recognise faces at large pose angles without the need for fragile pose estimation pre-processing. Moreover,computational load is low (comparable to standard eigenface methods), which is a critical factor in wide-area surveillance applications.

Publisher: IEEE Computer Society

Coverage: 2009-01-01T00:00:00Z
less
Under the constraint of using only a single gallery image per person, this paper proposes a fast multi-class pattern classification approach to 2D face recognition robust to changes in pose, illumination, and expression (PIE). This work has three main contributions: ...
more
save citation
full views 4
citation viewed 0

A study of the illumination cones method for face recognition under variable illumination

Author/Creator: Chin, Tat-Jun, Suter, David
Resource type: report
Date: 2004, 2010
Subject: Face recognition; lighting variation; Illumination Cones method
Record contributed by: The University of Adelaide

Full Record and related resources:
http://hdl.handle.net/2440/55705
http://link.library.adelaide.edu.au/?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=report&rft.date=2004&rft.place=Melbourne&rft.issue=7&rft.series=Technical+Report+MECSE-7-2004&rft.pub=Monash+University&rft.aulast=Chin&rft.title=A+study+of+the+illumination+cones+method+for+face+recognition+under+variable+illumination
http://www.ds.eng.monash.edu.au/suter_publications/
less
http://hdl.handle.net/2440/55705
http://link.library.adelaide.edu.au/?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=report&rft.date=2004&rft.place=Melbourne&rft.issue=7&rft.series=Technical+Report+MECSE-7-2004&rft.pub=Monash+University&rft.aulast=Chin&rft.title=A+study+of+the+illumination+cones+method+for+face+recognition+under+variable+illumination
http://www.ds.eng.monash.edu.au/suter_publications/

Description
Earlier face recognition algorithms have performed sufficiently well under tight environment constraints. However, simplistic and crude algorithms such as the geometric feature-based matching method and the template matching method fail catastrophically under slight environment changes, such as illumination variations. More sophisticated approaches like the Eigenface method or other Appearance-Based Methods, which had worked extremely well for face images with considerable changes in facial expression and occlusions, failed to tackle the issue of lighting changes. More recently, developments of methods that involve creating generative models of face images and extracting three-dimensional shape of faces have shown promising results. This report shall attempt to provide a detailed account of the Illumination Cones method that has shown a vast accuracy improvement compared to earlier methods in terms of robustness against illumination variation

Tat-Jun Chin and D. Suter

Publisher: Monash University
Contributor: School of Computer Science
Relation: Technical Report; MECSE-7-2004

Other identifier: 0020094178
Language: en
less
Earlier face recognition algorithms have performed sufficiently well under tight environment constraints. However, simplistic and crude algorithms such as the geometric feature-based matching method and the template matching method fail catastrophically under ...
more
save citation
full views 2
citation viewed 0

A study of the eigenface approach for face recognition

Author/Creator: Chin, Tat-Jun, Suter, David
Resource type: report
Date: 2004, 2010
Subject: Face recognition; Appearance-based holistic methods; Eigenface Approach Illumination effects
Record contributed by: The University of Adelaide

Full Record and related resources:
http://hdl.handle.net/2440/55709
http://www.ds.eng.monash.edu.au/techrep/reports/
less
http://hdl.handle.net/2440/55709
http://www.ds.eng.monash.edu.au/techrep/reports/

Description
Appearance-based approaches in face recognition, specifically the Eigenface approach, were one of first successful demonstrations of machine recognition of faces [1]. These methods, such as those proposed in [2, 3], proved to be effective in experiments with large databases. Further development of holistic methods of face recognition and their theoretical background, such as those proposed in [4-9], were focused towards recognizing faces from images with changes caused by illumination effects and pose variations. Although much effort has been made towards this goal, current algorithms are still far away from the capability of the human perception system [1]. This report shall give a detailed description of the fundamentals of appearance-based holistic methods for face recognition, specifically the Eigenface approach [3], as well as our experimental results on the Yale Face Database.

Publisher: Monash University
Contributor: School of Computer Science
Relation: Technical Report; MECSE-6-2004

Other identifier: 0020094179
Language: en
less
Appearance-based approaches in face recognition, specifically the Eigenface approach, were one of first successful demonstrations of machine recognition of faces [1]. These methods, such as those proposed in [2, 3], proved to be effective in experiments with ...
more
save citation
full views 14
citation viewed 0

Robust Face recognition for Data Mining

Author/Creator: Lovell, B. C., Chen, S.
Resource type:
Date: 2008
Subject: face recognition, data mining
Record contributed by: The University of Queensland

Full Record and related resources:
http://espace.library.uq.edu.au/view/UQ:151908
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
less
http://espace.library.uq.edu.au/view/UQ:151908
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266

Description
While the technology for mining text documents in large databases could be said to be relatively mature, the same cannot be said for mining other important data types such as speech, music, images and video. Yet these forms of multimedia data are becoming increasingly prevalent on the Internet and intranets as bandwidth rapidly increases due to continuing advances in computing hardware and consumer demand. An emerging major problem is the lack of accurate and efficient tools to query these multimedia data directly, so we are usually forced to rely on available metadata, such as manual labeling. Currently the most effective way to label data to allow for searching of multimedia archives is for humans to physically review the material. This is already uneconomic or, in an increasing number of application areas, quite impossible because these data are being collected much faster than any group of humans could meaningfully label them — and the pace is accelerating, forming a veritable explosion of non-text data. Some driver applications are emerging from heightened security demands in the 21st century, post-production of digital interactive television, and the recent deployment of a planetary sensor network overlaid on the Internet backbone.

Publisher: Information Science Reference
Contributor: John Wang

Coverage: 2008-01-01T00:00:00Z
less
While the technology for mining text documents in large databases could be said to be relatively mature, the same cannot be said for mining other important data types such as speech, music, images and video. Yet these forms of multimedia data are becoming increasingly ...
more
save citation
full views 9
citation viewed 0

Towards Robust Face Recognition for Intelligent-CCTV based Surveillance using One Gallery Image

Author/Creator: Shan, T., Chen, S., Sanderson, C., Lovell, B. C.
Resource type:
Date: 2007
Subject: closed circuit television, face recognition, video surveillance
Record contributed by: The University of Queensland

Full Record and related resources:
http://espace.library.uq.edu.au/view/UQ:151914
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
isMemberOf Excellence in Research Australia (ERA) - Collection http://espace.library.uq.edu.au/list/UQ:152266
less
http://espace.library.uq.edu.au/view/UQ:151914
isMemberOf School of Information Technology and Electrical Engineering Publications http://espace.library.uq.edu.au/list/UQ:3801
isMemberOf Security and Surveillance Collection http://espace.library.uq.edu.au/list/UQ:151266
more

Description
In recent years, the use of Intelligent Closed-Circuit Television (ICCTV) for crime prevention and detection has attracted significant attention. Existing face recognition systems require passport-quality photos to achieve good performance. However, use of CCTV images is much more problematic due to large variations in illumination, facial expressions and pose angle. In this paper we propose a pose variability compensation technique, which synthesizes realistic frontal face images from non-frontal views. It is based on modelling the face via Active Appearance Models and detecting the pose through a correlation model. The proposed technique is coupled with adaptive principal component analysis (APCA), which was previously shown to perform well in the presence of both lighting and expression variations. Experiments on the FERET dataset show up to 6 fold performance improvements. Finally, in addition to implementation and scalability challenges, we discuss issues related to on-going real life trials in public spaces using existing surveillance hardware.

Publisher: IEEE

Coverage: 2007-01-01T00:00:00Z
less
In recent years, the use of Intelligent Closed-Circuit Television (ICCTV) for crime prevention and detection has attracted significant attention. Existing face recognition systems require passport-quality photos to achieve good performance. However, use of ...
more
save citation
full views 0
citation viewed 0

Subspace-based face recognition: outlier detection and a new distance criterion

Author/Creator: Chen, Pei, Suter, David
Resource type: report
Date: 2003, 2010
Subject: Face recognition; Linear subspace;Principal component analysis; Illuminationeffect
Record contributed by: The University of Adelaide

Full Record and related resources:
http://hdl.handle.net/2440/56574
http://link.library.adelaide.edu.au/?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=report&rft.date=2003&rft.place=Melbourne&rft.issue=5&rft.series=Technical+Report+MECSE-5-2003&rft.pub=Monash+University&rft.aulast=Chen&rft.title=Subspace-based+face+recognition:+outlier+detection+and+a+new+distance+criterion.
less
http://hdl.handle.net/2440/56574
http://link.library.adelaide.edu.au/?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=report&rft.date=2003&rft.place=Melbourne&rft.issue=5&rft.series=Technical+Report+MECSE-5-2003&rft.pub=Monash+University&rft.aulast=Chen&rft.title=Subspace-based+face+recognition:+outlier+detection+and+a+new+distance+criterion.

Description
Illumination effects, including shadows and varying lighting, makes the problem of face recognition challenging. Experimental and theoretical results show that the face images under different illumination conditions lie in a low-dimensional subspace, hence principal component analysis (PCA) or low-dimensional subspace techniques have been used. Following this spirit, we propose new techniques for the face recognition problem, including an outlier detection strategy (mainly for those points not following the Lambertian reflectance model), and a new Bayesian-based error criterion for the recognition algorithm. Experiments using the Yale-B face database show the effectiveness of the new strategies

Pei Chen and David Suter

Publisher: Monash University
Contributor: School of Computer Science
Relation: Technical report ; MECSE-5-2003

Other identifier: 0020094196
Language: en
Source: http://www.ecse.monash.edu.au/techrep/reports/
less
Illumination effects, including shadows and varying lighting, makes the problem of face recognition challenging. Experimental and theoretical results show that the face images under different illumination conditions lie in a low-dimensional subspace, hence ...
more




Your search on keyword:face recognition found these results. 1 to 10 of 551 records in 3.12s

Narrow Search

Institutions

Subjects

Type

Decades

Creators