Face is an important biometric trait that has been used for various application of today’s technology. Face recognition comprises recognition of an individual identity to others on the basis of facial features. Facial features provide low accuracy due to variation in illumination and resolution of the images. In this paper an approach has been proposed that overcomes the issue of low recognition accuracy under low resolution captured images. In this paper texture features based approach that has been developed from the local ternary pattern by using two different groups of neighbour pixel values. On the basis of these two different groups texture features have been computed by comparing these values with centre pixel value of particular regions. By using local codes developed from the particular region whole image features have been computed using different codes from different regions. In this paper an approach that is combination of filtering and feature extraction has been proposed so that better face recognition can be achieved. On the basis of parameters analysis proposed work outperforms as compare to exiting approaches.

Face recognition, DCT, DWT, LDA, LTP, LBP and PCA

[1] Georghiades, A.S. and Belhumeur, P.N. and Kriegman, D. J.“From Few too Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose” IEEE Trans. Pattern Anal. Mach. Intelligence, vol. 23, 6, pp. 643-660, 2001.
[2] Sena, Bima, Bayu D. and Miura, Jun“Fuzzy-Based Illumination Normalization for Face Recognition” IEEE Workshop on Advanced Robotics and its Social Impacts, Pp. 131-136, DOI 10.1109/ARSO.2013.6705518, 2013.
[3] W.Jin, Bin Li and Ming You“Feature Extraction Based on Equalized ULBP for Face Recognition” IEEE Trans. Pattern Anal. Mach. Intelligence, vol. 25, 6, pp. 643-660,2013.
[4] S. Nazari, M.ShahramMoin “Face Recognition Using Global and Local Gabor Features” International Journal of Security and Its Applications, pp-754-759,2013.
[5] B.Yuan, H.Cao, J.Chu “Combining Local Binary Pattern and Local Phase Quantization for Face Recognition” IEEE international conference on face reorganization, pp-764-770 ,2013.
[6] Rashid, R.D., Jassim, S.A. and Sellahewa, H.“LBP Based on Multi Wavelet Sub-Bands Feature Extraction Used for Face Recognition”, IEEE International Workshop on Machine Learning for Signal Processing, pp. 1-6, ISSN 1551-2541, 2013.
[7] Mohamed, Abdallah A. , Yampolskiy, Roman V. “Adaptive Extended Local Ternary Pattern (AELTP) for Recognizing Avatar Faces”, International Conference on Machine Learning and Applications, ISSN. 978-0-7695-4913-2/12 , 2012.
[8] J.Sun, C.Zhang and H.Yan “Low-Resolution Face Recognition with Variable Illumination Based on Differential Images” International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), pp. 146-149, ISBN 978-1-4673-1741-2 , 2012.
[9] Khoukhi, A. and Ahmed, S.F. “Fuzzy LDA for Face Recognition with GA Based Optimization” Fuzzy Information Processing Society (NAFIPS) Annual Meeting of the North American, pp. 1-6, ISBN 978-1-4244-7859-0, 2010.
[10] Prabhjot Singh and Anjana Sharma, "Face Recognition Using Principal Component Analysis in MATLAB", International Journal of Scientific Research in Computer Science and Engineering, Vol.3, Issue.1, pp.1-5, 2015
[11] Ratnesh Kumar Shukla, Ajay Agarwal, Anil Kumar Malviya, "An Introduction of Face Recognition and Face Detection for Blurred and Noisy Images", International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.3, pp.39-43, 2018