SPECIAL ISSUE: Getting Across the Border Between the Natural and the Artificial Worlds; Edited by G. Sanniti di BajaNo Access

POSE-EXPRESSION NORMALIZATION FOR FACE RECOGNITION USING CONNECTED COMPONENTS ANALYSIS

JAE-YOUNG CHOI

Department of Computer Science, UCLA, Los Angeles, CA 90024, USA

Search for more papers by this author

TAEG-KEUN WHANGBO

Department of Computer Science, Kyungwon University, Seongnam-si, Gyeonggi-do 461-701, Korea

Search for more papers by this author

YOUNG-GYU YANG

Department of Computer Science, Kyungwon University, Seongnam-si, Gyeonggi-do 461-701, Korea

Search for more papers by this author

MURLIKRISHNA VISWANATHAN

Department of Computer Science, Kyungwon University, Seongnam-si, Gyeonggi-do 461-701, Korea

Search for more papers by this author

, and

NAK-BIN KIM

Department of Computer Science, Kyungwon University, Seongnam-si, Gyeonggi-do 461-701, Korea

Search for more papers by this author

https://doi.org/10.1142/S0218001406005010Cited by:0 (Source: Crossref)

Abstract

Accurate measurement of poses and expressions can increase the efficiency of recognition systems by avoiding the recognition of spurious faces. This paper presents a novel and robust pose-expression invariant face recognition method in order to improve the existing face recognition techniques. First, we apply the TSL color model for detecting facial region and estimate the vector X-Y-Z of face using connected components analysis. Second, the input face is mapped by a deformable 3D facial model. Third, the mapped face is transformed to the frontal face which appropriates for face recognition by the estimated pose vector and action unit of expression. Finally, the damaged regions which occur during the process of normalization are reconstructed using PCA. Several empirical tests are used to validate the application of face detection model and the method for estimating facial poses and expression. In addition, the tests suggest that recognition rate is greatly boosted through the normalization of the poses and expression.

Keywords:

References

J. Ahlberg, Model-based Coding: Extraction, Coding, and Evaluation of Face Model Parameters, Dissertations, Department of Electrical Engineering, Linköping University, Sweden (2002) . Google Scholar
J. Ahlberg and H. Li, IEEE Trans. Circuits Syst. Vid. Technol. 93(3), 405 (1999), DOI: 10.1109/76.754768. Google Scholar
V. I. Belhumeur, J. P. Hespanha and D. J. Kriegman, IEEE Trans. Patt. Anal. Mach. Intell. 19(7), 711 (1997), DOI: 10.1109/34.598228. Crossref, Web of Science, Google Scholar
D. J. Beymer, Pose-invariant face recognition using real and virtual views, Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA (1995) . Google Scholar
V. Blanzet al., Face recognition based on frontal views generated from non-frontal images, IEEE Conf. Comput. Vis. Patt. Recogn.2 (2005) pp. 454–461, DOI: 10.1109/CVPR.2005.150. Google Scholar
R. Brunelli and T. Poggio, IEEE Trans. Patt. Anal. Mach. Intell. 15(10), 1042 (1993), DOI: 10.1109/34.254061. Crossref, Web of Science, Google Scholar
G. J. Edwards, T. F. Cootes and C. J. Taylor, Face recognition using active appearance models, Proc. Eur. Conf. Comput. Vis.2 (1998) pp. 581–695. Google Scholar
P. Ekman and W. Friesen , Facial Action Coding System: A Technique for the Measurement of Facial Movement ( Consulting Psychologists Press , 1978 ) . Google Scholar
E. Hjelmas and B. K. Low, Comput. Vis. Imag. Underst. 3(3), 236 (2001), DOI: 10.1006/cviu.2001.0921. Google Scholar
A. M. Martinez and A. C. Kak, IEEE Trans. Patt. Anal. Mach. Intell. 23(2), 228 (2001), DOI: 10.1109/34.908974. Crossref, Web of Science, Google Scholar
K. K. Sung and T. Poggio, IEEE Trans. Patt. Recogn. Mach. Intell. 20, 39 (1998), DOI: 10.1109/34.655648. Crossref, Web of Science, Google Scholar
J. C. Terrillon and S. Akamatsu, Comparative performance of different chrominance spaces for color segmentation and detection of human faces in complex scene images, IEEE Int. Conf. Automatic Face and Gesture Recognition (ICAFGR) (2000) pp. 54–60, DOI: 10.1109/AFGR.2000.840612. Google Scholar
M. Turk and A. Pentland, J. Cogn. Neurosci. 3(1), 71 (1991). Crossref, Web of Science, Google Scholar
V. Vezhnevets , V. Sazonov and A. Andreeva , A survey on pixel-based skin color detection techniques , Proc. Graphicon-2003 . Google Scholar
T.-K. Whangboet al., Pose-invariant face recognition using deformation analysis, Int. Symp. Brain Vision and Artificial Intelligence (BV&AI'05), Lecture Notes in Computer Science (2005) pp. 545–554. Google Scholar
H. Yao and W. Gao, Face locating and tracking method based on chroma transform in color images, Int. Conf. Signal Processing (ICSP) (2000) pp. 1367–1371, DOI: 10.1109/ICOSP.2000.891799. Google Scholar
G. Yongsheng, IEEE Trans. Patt. Anal. Mach. Intell. 24(6), 764 (2002), DOI: 10.1109/TPAMI.2002.1008383. Crossref, Web of Science, Google Scholar

Vol. 20, No. 06

Metrics

Downloaded 35 times

History

Keywords

PDF download

System Upgrade on Tue, May 28th, 2024 at 2am (EDT)

POSE-EXPRESSION NORMALIZATION FOR FACE RECOGNITION USING CONNECTED COMPONENTS ANALYSIS

Abstract

Recommended