Software-based evaluation of human age: a pilot study.

PURPOSE This pilot study was to assess a smartphone application regarding its use as an objective evaluation tool for subject age in comparison to human raters and to identify potential factors influencing the estimation of age. MATERIALS AND METHODS Ten Caucasian participants (six females, four males, mean age 42.1 ± 22.6 years) were randomly chosen, and frontal facial pictures of each participant were taken. The smartphone application PhotoAge (Version 1.5, ©2012, Percipo Inc., San Francisco, CA, USA) was used to evaluate the age of the participants. For comparison, 100 randomly selected raters (60 females, 40 males, mean age 29.3 ± 1.3 years) were asked to evaluate the age of the same participants. The influence of participants' facial expression, age, and sex as well as raters' age, sex, and profession was investigated as well. Statistical analyses (linear mixed models with random intercepts; least square means, confidence interval 95%; p < 0.05) were implemented. RESULTS PhotoAge resulted in a mean age of 43.1 ± 18.2 years, with a difference from the true mean age of 1.0 ± 8.2 years (p = 0.5996). The evaluation by the raters revealed a mean age of 41.5 ± 19.0 years, with a difference from the true mean age of -0.6 ± 8.5 years (p = 0.6078). There was no statistical significance between the two groups (p = 0.2783). CONCLUSION The evaluation of age with the software application PhotoAge seems to be a reliable procedure with comparable results to human raters. CLINICAL SIGNIFICANCE This study gives a better understanding about the reliability of a software-based evaluation tool for age and identifies factors (e.g., the visibility of the teeth) potentially affecting the estimation of age. Naturally looking teeth seem to have no influence on the evaluation of a person's age. Thus, the application of this specific application for dental purposes is questionable; however, in forensics, it might be a valuable tool for estimating a person's age.

[1]  Yun Fu,et al.  A study on automatic age estimation using a large database , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Haizhou Ai,et al.  Demographic Classification with Local Binary Patterns , 2007, ICB.

[3]  Hongyuan Zha,et al.  Learning distance metric for regression by semidefinite programming with application to human age estimation , 2009, ACM Multimedia.

[4]  Rama Chellappa,et al.  Computational methods for modeling facial aging: A survey , 2009, J. Vis. Lang. Comput..

[5]  Yu Zhang,et al.  Learning from facial aging patterns for automatic age estimation , 2006, MM '06.

[6]  Yun Fu,et al.  Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression , 2008, IEEE Transactions on Image Processing.

[7]  I. Trenholme,et al.  Perceived Age and Perceived Physical Attractiveness , 1982 .

[8]  S. Lennon.  Physical Attractiveness, Age, And Body Type , 1988 .

[9]  Karl Grammer,et al.  Visual attention to variation in female facial skin color distribution , 2008, Journal of cosmetic dermatology.

[10]  Pawan Sinha,et al.  Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About , 2006, Proceedings of the IEEE.

[11]  Matthew G. Rhodes,et al.  Age estimation of faces: a review† , 2009 .

[12]  Alice J. O'Toole,et al.  FRVT 2006 and ICE 2006 Large-Scale Experimental Results , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  C. Christodoulou,et al.  Comparing different classifiers for automatic age estimation , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  A. Gunay,et al.  Automatic age classification with LBP , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

[15]  John A. Robinson.  Regularized single-kernel conditional density estimation for face description , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[16]  M. Freyd,et al.  The Graphic Rating Scale. , 1923 .

[17]  R. Boyd,et al.  . Facial attractiveness: ranking of end-of-treatment facial photographs by pairs of Chinese and US orthodontists. , 2008, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[18]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  G. Hole,et al.  Factors Influencing the Accuracy of Age Estimates of Unfamiliar Faces , 1995, Perception.

[20]  Natalie C. Ebner,et al.  Let me guess how old you are: effects of age, gender, and facial expression on perceptions of age. , 2012, Psychology and aging.

[21]  Yun Fu,et al.  Human Age Estimation With Regression on Discriminative Aging Manifold , 2008, IEEE Transactions on Multimedia.

[22]  K. Grammer,et al.  Skin color distribution plays a role in the perception of age, attractiveness and health in female faces , 2006 .

[23]  D. Perrett,et al.  When Facial Attractiveness is Only Skin Deep , 2004, Perception.

[24]  K. Grammer,et al.  Human (Homo sapiens) facial attractiveness in relation to skin texture and color. , 2001, Journal of comparative psychology.

[25]  C. Borelli,et al.  "Beauty lies in the eye of the beholder"? Aspects of beauty and attractiveness. , 2009, Journal der Deutschen Dermatologischen Gesellschaft = Journal of the German Society of Dermatology : JDDG.

[26]  Zhi-Hua Zhou,et al.  Automatic Age Estimation Based on Facial Aging Patterns , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Niels da Vitoria Lobo,et al.  Age Classification from Facial Images , 1999, Comput. Vis. Image Underst..