The juvenile face as a suitable age indicator in child pornography cases: a pilot study on the reliability of automated and visual estimation approaches

Abstract

The visual analysis of the face produces reasonably accurate age estimates up to the age of 18 years, which is the legally relevant age threshold for victims in cases of pedo-pornography. This approach can be applied in conjunction with the conventional methods for a preliminary age estimation of juveniles depicted on images.

Accuracy of a cut-off value based on the third molar index: Validation in an Australian population

“…In the latter situation, judicial laws generally mandate presentation of evidence that the person(s), charged with a criminal act, have met an age of legal responsibility [6,7].…”

Improving Borderline Adulthood Facial Age Estimation through Ensemble Learning

“…Furthermore, the 12,792 images used for training and testing (80% and 20% respectively) came from sources described in Section 4. Each input image was resized to a dimension of 224 x 224 pixels and the output had a size of 5 (Multi-class classifier) and were mapped to a value pertaining to the following age range classes: [0-5], [6][7][8][9][10], [11][12][13][14][15], [16][17] and [18][19][20][21][22][23][24][25]. The ranges were adapted from the "Criminal networks involved in the trafficking and exploitation of underage victims in the European Union" 2018 report 14 , which indicates that the classification of subjects into one of these age ranges is sufficient, and that precise age estimation is not crucial for investigators.…”

Juvenile age estimation from facial images

“…A more precise age is often required to determine the severity of offender sentencing and may be used in the identification of the victim (4,5). Age evaluations could aid the sequencing of images, when there are several images present which have been taken over a period of time (6).…”

“…The use of anthropometrics to estimate the age of a child from facial photographs has been tested by a group of European researchers (6,13). These studies have been carried out with the aim of being able to define an age, or age range from the faces of individuals present in images of alleged child pornography.…”

“…A recent study demonstrated the ability of an automated system to estimate age with a mean absolute error of 1.47 years. Visual assessment of age was also made by experts and lay-persons with mean absolute errors of 1.63 and 1.84 years respectively, however, only female children aged between 10 -19 years old were considered in this study (6).…”