Indian Journal of Innovations and Developments

Open Access Open Access  Restricted Access Subscription Access

Face Recognition - Multi Algorithm Approach using Average Half Face


Affiliations
1 Research Scholar, Department of ECE, Sathyabama University, Chennai-600 096, India
2 Professor & Head Department of ECE, St.Peter’s College of Engineering & Technology, Chennai-600 054, India
3 Department of ECE, Prathyusha Institute of Technology and Management, Chennai-600 096, India
 

Face recognition has received much attention in recent years due to its many applications such as human computer interface, video surveillance and face image database management. It is a challenging technique due to under different lighting conditions, facial expressions and changes in head pose. Single class of feature is not enough to capture all the available information in face. Multi algorithm approach of face recognition improves the accuracy using feature level fusion. This paper proposes an efficient technique for identification of an individual by using Average Half Face (AHF). We propose feature fusion technique using Principal component Analysis (PCA) and Discrete Wavelet Transform (DWT). For classification, distance classifier is used. The proposed method was tested using the cropped extended Yale B database, where the images vary in illumination and expression. High recognition performance has been obtained by fusion of PCA and Wavelet features at feature level for average half face compared to full face.

Keywords

Face Recognition, PCA, Wavelet, Multi Algorithm, Average Half Face.
User
Notifications

  • Soyuj Kumar Sahoo, Tarun Choubisa, SR Mahadeva Prasanna (2012). Multimodal Biometric Person Authentication: A Re view, IETE Technical Review vol 29 issue 1, pp.54-75.

  • Rao RM, and Bopardikar AS, (1998).Wavelet Transforms-Introduction to theory and Applications, Addison Wesley Longman.

  • Turk M, and Pentland A, (1991). Eigenfaces for recognition, J. Cognitive Neurosci., vol. 13, no. 1, pp. 71–86.

  • Penev PS and Atick JJ (1996). Local Feature Analysis: A General statistical theory for object representation, Computational Neuroscience laboratory, The Rockfeller University, USA.

  • Duda RO, Hart, PE, (1973). Pattern classification and scene analysis, Wiley, New York.

  • Ramesha K and Raja KB, (2011). Gram-Schmidt Orthogonalization Based Face Recognition Using Dwt, International Journal of Engineering Science and Technology, pp 494-503.

  • Ergun Gumus, Niyazi Kilic, Ahmet Sertbas, Osman N. Ucan, (2010).Evaluation of face recognition techniques using PCA, wavelets and SVM”, Expert Systems with Applications, pp 6404–6408.

  • Nandini C, and RaviKumar C, (2007). Multi- Biometrics Approach for Facial Recognition, IEEE International Conference on Computational Intelligence and Multimedia Applications, pp 417-422.

  • Sumatra Kar and Swati Hiremath, (2006). A Multi-Algorithmic Face Recognition System, IEEE International Conference on Advanced Computing and Communications, pp 321-326.

  • Marcialis GL, and Roli F, (2002). Fusion of LDA and PCA for Face Verification, Proceedings of the Workshop on Biometric Authentication, Springer LNCS 2359, Copenhagen Denmark.

  • Arun Ross and Rohin Govindarajan. Feature Level Fusion in Biometric Systems.

  • Josh Harguess and Shalini Gupta, (2008). 3D Face Recognition with the Average Half Face”, IEEE International Conference on Pattern Recognition, pp 1-4.

  • Wankou Yang and Changyin Sun, (2011). A multi-manifold discriminant analysis method for image feature extraction, Journal of Pattern Recognition, pp 1-9.

  • Josh Harguess and Aggarwal JK, (2009). A Case for the Average-Half-Face in 2D and 3D for Face Recognition, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp7-12.

  • Wei Chen and Tongfeng Sun, (2009). Face Detection Based on Half Face-template, IEEE 9th International Conference on Electronic Measurement & Instruments, pp 54-57.

  • Sumathi and Ranihemamalini R, (2011). “Efficient Identification System Using wavelet transform and Average Half-face”, CIIT International Journal of Digital Image Processing, Vol 3,No 20,.ISSN-0974-9691,pp 1259-1263.

  • Sumathi and Ranihemamalini R, (2012). “Multi-biometric Authentication using DWT and Score Level Fusion”, European Journal of Scientific Research, Vol.80 No.2 ISSN 1450-216X, pp.213-223.

  • Kittler J, Hatef M, Duin R, and Matas J, (1998). On combining classifiers, IEEE Transaction on Pattern Anal. Mach. Intell., vol. 20, no. 3, pp. 226–239.

  • Cover TM, and Hart PE, (1967). Nearest neighbor pattern Classifiers, IEEE Trans. Information Theory, Vol. 13,pp 21-27.

  • Lin SH, Kung SY and Lin LJ, (1997). Face Recognition / Detection by probabilistic decision based Neural Network, IEEE Trans.Neural Networks,vol 8,no 1,pp 114-132,Jan.1997.

  • Nefian AV and Hayes MH III, (1998). Hidden Markov Models for Face Recognition, Proc IEEE int’l Conf. Acoustic,Speech and Signal Processing,pp.2721-2724.

  • Xiaoyang Tan and Bill Triggs, (2010). Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions, IEEE Transactions on Image Processing, pp1635-1650.

  • Yale FaceDatabase: http://vision.ucsd.edu/~leekc/ExtYaleDatabase/ExtYaleB.html


Abstract Views: 344

PDF Views: 74




  • Face Recognition - Multi Algorithm Approach using Average Half Face

Abstract Views: 344  |  PDF Views: 74

Authors

S. Sumathi
Research Scholar, Department of ECE, Sathyabama University, Chennai-600 096, India
R. Ranihema
Professor & Head Department of ECE, St.Peter’s College of Engineering & Technology, Chennai-600 054, India
V. Thulasibai
Department of ECE, Prathyusha Institute of Technology and Management, Chennai-600 096, India

Abstract


Face recognition has received much attention in recent years due to its many applications such as human computer interface, video surveillance and face image database management. It is a challenging technique due to under different lighting conditions, facial expressions and changes in head pose. Single class of feature is not enough to capture all the available information in face. Multi algorithm approach of face recognition improves the accuracy using feature level fusion. This paper proposes an efficient technique for identification of an individual by using Average Half Face (AHF). We propose feature fusion technique using Principal component Analysis (PCA) and Discrete Wavelet Transform (DWT). For classification, distance classifier is used. The proposed method was tested using the cropped extended Yale B database, where the images vary in illumination and expression. High recognition performance has been obtained by fusion of PCA and Wavelet features at feature level for average half face compared to full face.

Keywords


Face Recognition, PCA, Wavelet, Multi Algorithm, Average Half Face.

References