ABSTRACT
The performance of any face recognition system gets affected by the quality of the probe and the reference images. Rejecting or recapturing images with low-quality can improve the overall performance of the biometric system. There are many statistical as well as learning-based methods that provide quality scores given an image for the task of face recognition.
In this study, we take a different approach by asking 26 participants to provide subjective quality scores that represent the ease of recognizing the face on the images from a smartphone based face image dataset. These scores are then compared to measures implemented from ISO/IEC TR 29794-5. We observe that the subjective scores outperform the implemented objective scores while having a low correlation with them. Furthermore, we analyze the effect of pose, illumination, and distance on face recognition similarity scores as well as the generated mean opinion scores.
- A. Adler and T. Dembinsky. 2006. Human Vs. Automatic Measurement of Biometric Sample Quality. In 2006 Canadian Conference on Electrical and Computer Engineering. 2090--2093.Google Scholar
- L. Best-Rowden and A. K. Jain. 2018. Learning Face Image Quality From Human Assessments. IEEE Transactions on Information Forensics and Security 13, 12 (Dec 2018), 3064--3077. Google ScholarDigital Library
- Samarth Bharadwaj, Mayank Vatsa, and Richa Singh. 2014. Biometric quality: a review of fingerprint, iris, and face. EURASIP Journal on Image and Video Processing 2014, 1 (02 Jul 2014), 34.Google ScholarCross Ref
- Jiankang Deng, Jia Guo, and Stefanos Zafeiriou. 2018. Arcface: Additive angular margin loss for deep face recognition. arXiv preprint arXiv: 1801.07698 (2018).Google Scholar
- W. Funk, M. Arnold, C. Busch, and A. Munde. 2005. Evaluation of image compression algorithms for fingerprint and face recognition systems. In Proceedings from the Sixth Annual IEEE SMC Information Assurance Workshop. 72--78.Google Scholar
- P. Grother and E. Tabassi. 2007. Performance of Biometric Quality Measures. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 4 (April 2007), 531--543. Google ScholarDigital Library
- R. V. Hsu, J. Shah, and B. Martin. 2006. Quality Assessment of Facial Images. In 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference. 1--6.Google Scholar
- ISO/IEC. {n. d.}. ISO/IEC DIS 39794-5 Information technology -- Extensible biometric data interchange formats -- Part 5: Face image data. ISO/IEC.Google Scholar
- ISO/IEC. 2006. ISO/IEC 19795-1 Information technology -- Biometric performance testing and reporting -- Part 1: Principles and framework. ISO/IEC.Google Scholar
- ISO/IEC. 2010. ISO/IEC TR 29794-5 Information technology - Biometric sample quality - Part 5: Face image data. ISO/IEC.Google Scholar
- X. Liu, M. Pedersen, C. Charrier, and P. Bours. 2018. Can image quality enhancement methods improve the performance of biometric systems for degraded face images?. In 2018 Colour and Visual Computing Symposium (CVCS). 1--5.Google Scholar
- P. Marziliano, F. Dufaux, S. Winkler, and T. Ebrahimi. 2002. A no-reference perceptual blur metric. In Proceedings. International Conference on Image Processing, Vol. 3. III-III.Google Scholar
- Kresimir Matkovic, László Neumann, Attila Neumann, Thomas Psik, and Werner Purgathofer. 2005. Global Contrast Factor-a New Approach to Image Contrast. Computational Aesthetics 2005 (2005), 159--168. Google ScholarDigital Library
- Ajita Rattani and Reza Derakhshani. 2018. A Survey Of mobile face biometrics. Computers & Electrical Engineering 72 (2018), 39--52.Google ScholarCross Ref
- Carsten Schmitz et al. 2012. LimeSurvey: An open source survey tool. LimeSurvey Project Hamburg, Germany. URL http://www.limesurvey.org (2012).Google Scholar
- M. V. Shirvaikar. 2004. An optimal measure for camera focus and exposure. In Thirty-Sixth Southeastern Symposium on System Theory, 2004. Proceedings of the. 472--475.Google ScholarCross Ref
- T. Sim, S. Baker, and M. Bsat. 2002. The CMU Pose, Illumination, and Expression (PIE) database. In Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition. 53--58. Google ScholarDigital Library
- NEUROtechnology VeriLook. {n. d.}. 5.4,"VeriLook 5.4 Face SDK,".Google Scholar
- P. Wasnik, K. B. Raja, R. Ramachandra, and C. Busch. 2017. Assessing face image quality for smartphone based face recognition system. In 2017 5th International Workshop on Biometrics and Forensics (IWBF). 1--6.Google Scholar
- Pankaj Wasnik, Raghavendra Ramachandra, Kiran Raja, and Christoph Busch. 2018. An Empirical Evaluation of Deep Architectures on Generalization of Smartphone-based Face Image Quality Assessment. In IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS).Google Scholar
Index Terms
- Subjective Versus Objective Face Image Quality Evaluation For Face Recognition
Recommendations
Age-Invariant Face Recognition
One of the challenges in automatic face recognition is to achieve temporal invariance. In other words, the goal is to come up with a representation and matching scheme that is robust to changes due to facial aging. Facial aging is a complex process that ...
Face recognition under varying illumination using gradientfaces
In this correspondence, we propose a novel method to extract illumination insensitive features for face recognition under varying lighting called the Gradientfaces. Theoretical analysis shows Gradientfaces is an illumination insensitive measure, and ...
Automatic face analysis system based on face recognition and facial physiognomy
ICHIT'06: Proceedings of the 1st international conference on Advances in hybrid information technologyAn automatic face analysis system is proposed which uses face recognition and facial physiognomy. It first detects human's face, extracts its features, and classifies the shape of facial features. It will analyze the person's facial physiognomy and then ...
Comments