Filters








1,169 Hits in 4.8 sec

The CMU pose, illumination, and expression database

Terence Sim, S. Baker, M. Bsat
2003 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We call this the CMU Pose, Illumination, and Expression (PIE) database.  ...  Using the CMU 3D Room we imaged each person across 13 different poses, under 43 different illumination conditions, and with 4 different expressions.  ...  Sundar Vedula and German Cheung gave us great help using the CMU 3D Room. We would also like to thank Henry Schneiderman and Jeff Cohn for discussions on what  ... 
doi:10.1109/tpami.2003.1251154 fatcat:lqd4nmklwvcsnh22z3deyfvgje

The CMU Pose, Illumination, and Expression (PIE) database

T. Sim, S. Baker, M. Bsat
Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition  
We call this database the CMU Pose, Illumination, and Expression (PIE) database.  ...  Using the CMU 3D Room we imaged each person across 13 different poses, under 43 different illumination conditions, and with 4 different expressions.  ...  Financial support for the collection of the PIE database was provided by the U.S. Office of Naval Research (ONR) under contract N00014-00-1-0915.  ... 
doi:10.1109/afgr.2002.1004130 dblp:conf/fgr/SimBB02 fatcat:hne4qj54xndmxkjkibpubbdpau

Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron

José Hiroki Saito, Thiago Vieira de Carvalho, Marcelo Hirakuri, André Saunite, Alessandro Noriaki Ide, Sandra Abib
2005 The European Symposium on Artificial Neural Networks  
Using a large-scale human face database (CMU PIE), the optimal thresholds of the Neocognitron to human face recognition are verified.  ...  As a result it is verified that a number of 25 training images per subjects is enough to obtain very high recognition rate (98%) to the frontal pose images from the database. 350 validation images, non-overlapping  ...  Acknowledgements The authors would like to thank Prof. Simon Baker from Carneggie Mellon University for the kindness of sending the PIE database, used in this work.  ... 
dblp:conf/esann/SaitoCHSIA05 fatcat:kc2lwyk3ybb3paondlspb5jb7y

Multi-PIE

Ralph Gross, Iain Matthews, Jeffrey Cohn, Takeo Kanade, Simon Baker
2010 Image and Vision Computing  
Collection of the Multi-PIE database was supported by United States Government's Technology Support Working Group (TSWG) through award N41756-03-C-402 and by Sandia National Laboratories.  ...  Acknowledgment We would like to thank Jonathon Phillips, James Wayman, and David Herrington for discussions and support and the anonymous reviewers for comments.  ...  To support research for face recognition across pose and illumination the Pose, Illumination, and Expression (PIE) database was collected at CMU in the fall of 2000 [7] .  ... 
doi:10.1016/j.imavis.2009.08.002 pmid:20490373 pmcid:PMC2873597 fatcat:iopmps4dbfgyvdolgtjsmiuqe4

Multi-PIE

Ralph Gross, Iain Matthews, Jeffrey Cohn, Takeo Kanade, Simon Baker
2008 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition  
Collection of the Multi-PIE database was supported by United States Government's Technology Support Working Group (TSWG) through award N41756-03-C-402 and by Sandia National Laboratories.  ...  Acknowledgment We would like to thank Jonathon Phillips, James Wayman, and David Herrington for discussions and support and the anonymous reviewers for comments.  ...  To support research for face recognition across pose and illumination the Pose, Illumination, and Expression (PIE) database was collected at CMU in the fall of 2000 [7] .  ... 
doi:10.1109/afgr.2008.4813399 dblp:conf/fgr/GrossMCKB08 fatcat:lnzflyaguzhpbkgedlnesweyg4

PERFORMANCE ANALYSIS OF FACE RECOGNITION ALGORITHMS ON KOREAN FACE DATABASE

MYUNG-CHEOL ROH, SEONG-WHAN LEE
2007 International journal of pattern recognition and artificial intelligence  
Acknowledgments This research was supported by the 2005 Seoul R&BD Program and the Korea Information Security Agency.  ...  This database includes 13 poses, 43 illuminations and 4 expressions images.  ...  In particular, the experiments of pose variation on both the databases and illumination 2 variation on the CMU-PIE showed drastic changes of recognition rate.  ... 
doi:10.1142/s0218001407005818 fatcat:6hxrflygbjdunkq333w7kqrbjq

Face Databases for 2D and 3D Facial Recognition: A Survey

R. Senthilkumar
2013 IOSR Journal of Engineering  
The cmu pie and multi-pie databases were developed for testing the performance of different video and still face recognition algorithms.  ...  The simple face database developed at AT & T lab contains 40 subjects each with 10 images. The database was collected by AT & T lab and it has the subjects of different pose and facial expressions.  ...  CMU PIE (POSE, ILLUMINATION AND EXPRESSION) DATABASE It consists of a face database of 41,368 images of 68 people [10] .  ... 
doi:10.9790/3021-03414348 fatcat:5waja3k5w5d5xissw6ageygw6u

The CMU Face In Action (FIA) Database [chapter]

Rodney Goh, Lihao Liu, Xiaoming Liu, Tsuhan Chen
2005 Lecture Notes in Computer Science  
Our team has collected a face video database named the CMU Face In Action (FIA) database.  ...  We expect the database to be useful for analysis and modeling of faces and gestures.  ...  Possible Usage The CMU FIA database, with different kinds of variations such as pose, illumination, expression, aging, and etc. is beneficial to the task of recognizing human faces.  ... 
doi:10.1007/11564386_20 fatcat:akiwzel5crcgdem7m4je3ct6zu

Iranian Face Database with age, pose and expression

Azam Bastanfard, Melika Abbasian Nik, Mohammad Mahdi Dehshibi
2007 2007 International Conference on Machine Vision  
Four different poses, two different expressions, and one image with glasses were taken if the subjects were interested.  ...  The background was a white frame and the only illumination was the daylight. We named this database the Iranian Face Database (IFDB).  ...  CMU-PIE (Pose, Illumination, and Expression) Database The CMU (Carnegie Mellon University) PIE database systematically samples a large number of pose and illumination conditions along with a variety of  ... 
doi:10.1109/icmv.2007.4469272 fatcat:gujihgzxpbflho7j7fvq6xsdiu

The Photoface database

Stefanos Zafeiriou, Mark Hansen, Gary Atkinson, Vasileios Argyriou, Maria Petrou, Melvyn Smith, Lyndon Smith
2011 CVPR 2011 WORKSHOPS  
Unlike other publicly available databases the level of cooperation between subjects and the capture mechanism was minimal. The proposed device may also be used, to capture 3D expressive faces.  ...  Apart from the description of the device and the Photoface database, we present experiments from baseline face recognition and verification algorithms using albedo, normals and the recovered depth maps  ...  Others on the other hand, for example the widely used CMU PIE database [19] or the Harvard RL database [11] , concentrate more on varying the capture conditions such as pose and illumination.  ... 
doi:10.1109/cvprw.2011.5981840 dblp:conf/cvpr/ZafeiriouHAAPSS11 fatcat:lvm5qokzvfbsrhr2miqt6fxwy4

Face Databases and Evaluation [chapter]

Leon Gu, Takeo Kanade, Dmitry O. Gorodnichy, Ming-Hsuan Yang, Massimo Tistarelli, Patrick Grother, Elham Tabassi, Shiguang Shan, Xilin Chen, Wen Gao, Ioannis Patras, Ioannis A. Kakadiaris (+75 others)
2009 Encyclopedia of Biometrics  
CMU PIE Database is one of the largest datasets developed to investigate the affect of Pose, Illumination and Expression.  ...  Similar to the CMU PIE database, this database has images with varying pose, illumination, and facial expressions. In total, 52 images were obtained per subject.  ... 
doi:10.1007/978-0-387-73003-5_192 fatcat:ibkbtt46dndjzffjyzjjloqcfa

Performance Evaluation of Face Recognition Algorithms on the Asian Face Database, KFDB [chapter]

Hwang Bon-Woo, Hyeran Byun, Roh Myoung-Cheol, Lee Seong-Whan
2003 Lecture Notes in Computer Science  
In general, however, many believe that the technology has yet to improve further, particularly to overcome the instability due to variable illuminations, expressions, poses and accessories.  ...  And a number of commercial products have reached the market already.  ...  But there are still many technical limitations coming from the variety of illumination, expression, pose and accessory.  ... 
doi:10.1007/3-540-44887-x_66 fatcat:irn4ep7dmneinkpqtmutvjvjve

UHDB11 Database for 3D-2D Face Recognition [chapter]

George Toderici, Georgios Evangelopoulos, Tianhong Fang, Theoharis Theoharis, Ioannis A. Kakadiaris
2014 Lecture Notes in Computer Science  
The database consists of samples from 23 individuals, in the form of 2D high-resolution images spanning six illumination conditions and 12 head-pose variations, and 3D facial mesh and texture.  ...  Performance boosts in face recognition have been facilitated by the formation of facial databases, with collection protocols customized to address challenges such as light variability, expressions, pose  ...  Controlled light conditions were also used in the CMU PIE database [15] , which in addition included viewpoint variations, resulting in different head poses, using a fixed camera grid and a still subject  ... 
doi:10.1007/978-3-642-53842-1_7 fatcat:ltcndrwhgvdlnlaesluitkp6ne

A Distributed Face Recognition Framework Based on Data Fusion

Zheng Zhang, Yan Guo, Guozhi Song
2014 International Journal of Database Theory and Application  
Firstly, four face regions are interactively marked and the Multi-scale Block Local Binary Patterns are extracted from these regions to achieve both locally and globally informative features.  ...  In experiment, the runtime and recognition performance of our system is compared with several other popular face recognition paradigms.  ...  Acknowledgements The authors would like to thank the Robotics Institute of Carnegie Mellon University for providing the CMU PIE database. The authors would also like to thank to Mr.  ... 
doi:10.14257/ijdta.2014.7.4.08 fatcat:qz6v6v24nrfvzc7fouwhqxf4h4

A Novel Landmarked Face Database for Arab Celebrities

R.M. Ghanem, M.L. Ramadan
2020 Benha Journal of Applied Sciences  
It is challenging to inpaint face images in the wild-life, due to the large variation of appearances, such as expressions, gender, different poses, and ethnicity.  ...  In this paper, we present a novel database of colored and gray, plausible face images.  ...  Database Resolution AR [3] 768 × 576 Banca [4] 720 × 576 CAS-PEAL [5] 360 × 480 CMU Hyperspectral [6] 640 × 480 CMU PIE [7] 640 × 486 Equinox IR [8] 240 × 320 FERET [9, 10] 256 × 384 JAFFE  ... 
doi:10.21608/bjas.2020.226893 fatcat:mm33suan6nbunkdqy6xyzc5gwm
« Previous Showing results 1 — 15 out of 1,169 results