Pupil size as a soft biometrics for age and gender classification

Abstract The pupil size is a soft biometric trait but in-depth study to analyze it for biometric purposes is lacking in the literature, as well as datasets focused on this field of research are missing. On the basis of these observations, we present an extensive study with the objective of demonstrating that pupil size and dilation over time can be potentially used to classify people by age and by gender. To do this, 14 supervised classifiers were applied on a dataset meant for gaze analysis. Measuring the right and left pupil individually and also simultaneously, the performances of the classifiers have been compared and the worst and best performing selected to support potential fusion strategies. If good results have been obtained for age classification, ranging in 79% - 82% of accuracy, it cannot be said the same for gender. This is due to the dual nature of this biometric trait. Pupil size can be considered as a physical trait for the age classification and behavioral trait for the gender. The results achieved in this study suggest the need for more balanced and reliable datasets.

[1]  Michele Nappi,et al.  F-FID: fast fuzzy-based iris de-noising for mobile security applications , 2019, Multimedia Tools and Applications.

[2]  Matthew J. Betts,et al.  Emotional arousal and recognition memory are differentially reflected in pupil diameter responses during emotional memory for negative events in younger and older adults , 2017, Neurobiology of Aging.

[3]  Qing-Xing Qu,et al.  Can eye movements be effectively measured to assess product design?: Gender differences should be considered , 2019, International Journal of Industrial Ergonomics.

[4]  Michele Nappi,et al.  Multibiometric score-level fusion through optimization and training , 2019, 2019 3rd International Conference on Bio-engineering for Smart Technologies (BioSMART).

[5]  Michele Nappi,et al.  Gait Analysis for Gender Classification in Forensics , 2019, DependSys.

[6]  Michele Nappi,et al.  Eye-Movement and Touch Dynamics: A Proposed Approach for Activity Recognition of a Web User , 2019, 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[7]  Andrea F. Abate,et al.  Clustering Facial Attributes: Narrowing the Path From Soft to Hard Biometrics , 2020, IEEE Access.

[8]  Buket D. Barkana,et al.  Utilizing CNNs and transfer learning of pre-trained models for age range classification from unconstrained face images , 2019, Image Vis. Comput..

[9]  Radu Danescu,et al.  In the Eye of the Deceiver: Analyzing Eye Movements as a Cue to Deception , 2018, J. Imaging.

[10]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[11]  Michele Nappi,et al.  Gender classification on 2D human skeleton , 2019, 2019 3rd International Conference on Bio-engineering for Smart Technologies (BioSMART).

[12]  M. Gobbe,et al.  The Effects of Age, Refractive Status, and Luminance on Pupil Size , 2016, Optometry and vision science : official publication of the American Academy of Optometry.

[13]  M. Lalumière,et al.  Sex Differences in Patterns of Genital Sexual Arousal: Measurement Artifacts or True Phenomena? , 2009, Archives of sexual behavior.

[14]  Veikko Surakka,et al.  Pupil size variation as an indication of affective processing , 2003, Int. J. Hum. Comput. Stud..

[15]  Michele Nappi,et al.  Demographic classification through pupil analysis , 2020, Image Vis. Comput..

[16]  Javier Lorenzo-Navarro,et al.  On using periocular biometric for gender classification in the wild , 2016, Pattern Recognit. Lett..

[17]  Adrian Glasser,et al.  Age related changes in the characteristics of the near pupil response , 2006, Vision Research.

[18]  Mohammed Abo-Zahhad,et al.  A Novel Biometric Approach for Human Identification and Verification Using Eye Blinking Signal , 2015, IEEE Signal Processing Letters.

[19]  Marco Porta,et al.  Pupil Size as a Biometric Trait , 2014, BIOMET.

[20]  Jue Qu,et al.  Study on the Identification of Irritability Emotion Based on the Percentage Change in Pupil Size , 2020, IVSP.

[21]  Kyong Jin Cho,et al.  Analysis of various factors affecting pupil size in patients with glaucoma , 2017, BMC Ophthalmology.

[22]  Patrick J. Flynn,et al.  A linear regression analysis of the effects of age related pupil dilation change in iris biometrics , 2013, 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS).