Regression-Based Automated Facial Image Quality Model

Regression-Based Automated Facial Image Quality Model

Fatema Tuz Zohra (University of Calgary, Calgary, Canada), Andrei D. Gavrilov (University of British Columbia, Calgary, Canada), Omar A. Zatarain (International Institute of Cognitive Informatics and Cognitive Computing (ICIC), Laboratory for Computational Intelligence, Cognitive Systems, Software Science and Denotational Mathematics, Department of Electrical and Computer Engineering, Schulich School of Engineering and Hotchkiss Brain Institute, University of Calgary, Calgary, Canada) and Marina L. Gavrilova (Department of Computer Science, University of Calgary, Calgary, Canada)
DOI: 10.4018/IJCINI.2017100102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Nowadays, biometric technologies became reliable and widespread means of unobtrusive user authentication in a variety of real-world applications. The performance of an automated face recognition system has a strong relationship with the quality of the biometric samples. The facial samples can be affected by various quality factors, such as uneven illumination, low or high contrast, excessive brightness, blurriness, etc. In this article, the authors propose a quality estimation method based on linear regression analysis to characterize the relationship between different quality factors and the performance of a face recognition system. The regression model can predict the overall quality of a facial sample which reflects the effects of various quality factors on that sample. The weights assigned to the different quality factors by the linear regression model reflect the impact of those quality factors on the performance of the recognition system. Therefore, the prediction scores generated from the model is a strong indicator of the overall quality of the facial images. The authors evaluated the quality estimation model on the Extended Yale Database B. They also performed a study to understand which quality factors affect the face recognition the most.
Article Preview

Introduction

Despite the widespread use of automatic facial recognition systems, their consistent performance is affected when presented with uncooperative users and uncontrolled environments. Image quality has a very strong connection with the recognition performance and identification errors of a biometric system (Grother & Tabassi, 2007; Alonso-Fernandez et al., 2012; Bharadwaj et al., 2014). The quality of facial images during enrollment and verification stages significantly affects the performance of an automated face recognition system. Poor quality of data, due to changes in lighting conditions, facial expressions, pose, occlusion, and poor sensor quality, may cause efficiency loss. Recent studies show that variations in lighting conditions, resolution, camera movement, occlusion, expressions and other quality factors have a major impact on the recognition rate of a face biometric system (Sellahewa & Jassim, 2010; Abaza et al., 2012; Abaza et al., 2014; Punnappurath et al., 2015). Researchers have attempted to categorize the face-based quality factors based on digital formatting of facial images, scenes and photographics. Several techniques have been proposed in the literature to effectively compute different quality factors (Wang & Bovik, 2002; Abaza et al. 2012; Abaza et al., 2014; Sang et al. 2009). However, few attempts have been made to jointly consider various quality factors under one framework (Abaza et al., 2012; Abaza et al., 2014). Though researchers have considered a partial subset of these quality factors, there is yet no effective analysis of the impact of different quality factors on the performance of a face recognition system. Therefore, an effective quality estimation model is needed, which can characterize the quality of the facial image by integrating different quality measures into a single quality score which is an indicator of the overall quality of the facial image. The model should also reflect the impact of different quality factors on the face recognition performance.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2017)
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing