Blind Image Quality Assessment for Face Pose Problem

Authors

Cerine Tafran, PhD Student, Faculty of Science, Beirut Arab University, Beirut, LebanonFollow
Mohamad El-Abed, Associate Professor, Computer & Information Systems Department, Rafik Hariri University, Beirut, LebanonFollow
Ziad Osman, Professor, Faculty of Engineering, Beirut Arab University, Beirut, LebanonFollow
Islam Elkabani, Assistant Professor, Faculty of Science, Beirut Arab University, Beirut, LebanonFollow

Keywords

Biometrics, No-reference Image Quality Assessment, SIFT, BLIINDS, Pose, Features extraction and classification

Disciplines

Architecture | Business | Engineering | Physical Sciences and Mathematics

Abstract

No-Reference image quality assessment for face images is of high interest since it can be required for biometric systems such as biometric passport applications to increase system performance. This can be achieved by controlling the quality of biometric sample images during enrollment. This paper proposes a novel no-reference image quality assessment method that extracts several image features and uses data mining techniques for detecting the pose variation problem in facial images. Using subsets from three public 2D face databases PUT, ENSIB, and AR, the experimental results recorded a promising accuracy of 97.06% when using the RandomForest Classifier, which outperforms other classifiers

Recommended Citation

Tafran, Cerine; El-Abed, Mohamad; Osman, Ziad; and Elkabani, Islam (2020) "Blind Image Quality Assessment for Face Pose Problem," BAU Journal - Science and Technology: Vol. 1: Iss. 2, Article 11.
DOI: https://doi.org/10.54729/2959-331X.1025

ISSN

2959-331X