A Novel Approach for Face Recognition under Varying Illumination Conditions

A Novel Approach for Face Recognition under Varying Illumination Conditions

V Mohanraj (Madras Institute of Technology, India), V. Vaidehi (VIT University, India), S Vasuhi (Anna University, India) and Ranajit Kumar (Department of Atomic Energy, India)
Copyright: © 2018 |Pages: 21
DOI: 10.4018/IJIIT.2018040102

Abstract

Face recognition systems are in great demand for domestic and commercial applications. A novel feature extraction approach is proposed based on TanTrigg Lower Edge Directional Patterns for robust face recognition. Histogram of Orientated Gradients is used to detect faces and the facial landmarks are localized using Ensemble of Regression Trees. The detected face is rotated based on facial landmarks using affine transformation followed by cropping and resizing. TanTrigg preprocessor is used to convert the aligned face region into an illumination invariant region for better feature extraction. Eight directional Kirsch compass masks are convolved with the preprocessed face image. Feature descriptor is extracted by dividing the TTLEDP image into several sub-regions and concatenating the histograms of all the sub-regions. Chi-square distance metric is used to match faces from the trained feature space. The experimental results prove that the proposed TTLEDP feature descriptor has better recognition rate than existing methods, overcoming the challenges like varying illumination and noise
Article Preview

The LBP, LTP, ELBP, SIFT, SURF, LDP, EnLDP, LDN methods produce illumination invariant feature representations. Timo Ahonen et al. (2006) proposed LBP algorithm for face recognition. LBP image is obtained by comparing its gray scale value with its neighbouring pixels. If the center pixel value is greater than the neighbouring pixel, then the binary value is set to 1 else 0. This binary pattern is converted to decimal value and it is assigned to LBP image. LBP image is divided into non-overlapped rectangular sub regions of size m × n, feature vectors are formed by concatenating the histograms of all sub regions. The feature vectors of LBP are reduced by considering only uniform patterns. Figure 1 shows the computation LBP for a single pixel and Figure 2 shows the taxonomy of face feature descriptor.

Figure 1.

Computation of LBP

Figure 2.

Taxonomy of face feature descriptor

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 15: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 14: 4 Issues (2018): 3 Released, 1 Forthcoming
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing