Estimating sex and age from a face: a forensic approach using machine learning based on photo-anthropometric indexes of the Brazilian population.

The facial analysis permits many investigations, some of the most important of which are craniofacial identification, facial recognition, and age and sex estimation. In forensics, photo-anthropometry describes the study of facial growth and allows the identification of patterns in facial skull development, for example, by using a group of cephalometric landmarks to estimate anthropological information. Previous works presented, as indirect applications, the use of photo-anthropometric measurements to estimate anthropological information such as age and sex. In several areas, automation of manual procedures has achieved advantages over and similar measurement confidence as a forensic expert. This manuscript presents an approach using photo-anthropometric indexes, generated from frontal faces cephalometric landmarks of the Brazilian population, to create an artificial neural network classifier that allows the estimation of anthropological information, in this specific case age and sex. This work is focused on four tasks: (i) sex estimation on ages from 5 to 22 years old, evaluating the interference of age on sex estimation; (ii) age estimation from photo-anthropometric indexes for four age intervals (1 year, 2 years, 4 years, and 5 years); (iii) age group estimation for thresholds of over 14 and over 18 years old; and; (iv) the provision of a new data set, available for academic purposes only, with a large and complete set of facial photo-anthropometric points marked and checked by forensic experts, measured from over 18,000 faces of individuals from Brazil over the last 4 years. The proposed binary classifier obtained significant results, using this new data set, for the sex estimation of individuals over 14 years old, achieving accuracy values higher than 0.85 by the F1 measure. For age estimation, the accuracy results are 0.72 for the F1 measure with an age interval of 5 years. For the age group estimation, the F1 measures of accuracy are higher than 0.93 and 0.83 for thresholds of 14 and 18 years, respectively.

Applicability of a pre-established set of facial proportions from frontal photographs in forensic age estimation of a Brazilian population.

Child pornography on the internet is one of the crimes with highest increasing incidence worldwide. In this specific type of crime, the victim's age has important legal implications. To overcome the lack of scientifically established protocols, European researchers explored and proposed a set of facial proportions obtained from images to estimate age. Within a validation scope, the present study aimed to test the applicability of morphological proportions from frontal photographs of the face to estimate age in a Brazilian population. Standardized frontal view photographs from 800 Brazilians (400 females and 400 males) homogeneously distributed in 4 age groups (6, 10, 14 and 18 years ± 30 days) were randomly selected from a Civilian Database of the Brazilian Federal Police. The selected images were analyzed with the aid of cephalometric landmarks. After landmarking the photographs, eighteen metric relations pre-established by Cattaneo et al. (C. Cattaneo, Z. Obertová, M. Ratnayake, L. Marasciuolo, J. Tutkuviene, P. Poppa, D. Gibelli, P. Gabriel, S. Ritz-Timme, Can facial proportions taken from images be of use for ageing in cases of suspected child pornography? A pilot study, Int. J. Leg. Med. 126 2012 139-144) were assessed and analyzed through parametric statistical tests and discriminant analysis. Two indexes had a moderate correlation with age, while ten had a weak correlation and six were not correlated with age. Eleven indexes were statistically different between sexes (p < 0.05). The discriminant analysis showed that 49.6% of the pooled sample was correctly classified into the respective age group. This percentage increased when each sex was analyzed separately: 50.2% for females and 53.5% for males. The set of facial proportions from frontal images proposed by Cattaneo et al. (2012) is related to facial development. As expected, the discriminant power of this approach did not reach optimal effectiveness in the Brazilian sample. In practice, this age estimation method must be adapted for more reliable application in Brazilians.