Top

Published in:

01-11-2020 | Original Article

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

Authors: Lucas Faria Porto, Laíse Nascimento Correia Lima, Ademir Franco, Donald Pianto, Carlos Eduardo Palhares Machado, Flavio de Barros Vidal

Published in: International Journal of Legal Medicine | Issue 6/2020

Abstract

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.

Available only for authorised users

When the term “avoiding” is used throughout the manuscript, it means information from a specific class was not used in the proposed tests.

The data set and the developed machine learning model will be available to download soon, after the review process is completed, in attendance of the journal’s submission criteria.

All boxplots are available in the specific Section of the Supplementary Material files (File PAIs_sex_age_boxplots_supplemental.pdf).

See Fig. 2, for example, where outliers can be identified as the points well above or well below the boxes in the boxplot.

Marquez-Grant N (2015) An overview of age estimation in forensic anthropology: perspectives and practical considerations. Annals of human biology 42(4):308–322PubMed

Silva RF, Franco A, Dias PEM, Gonçalves AS, Paranhos LR (2013) Interrelationship between forensic radiology and forensic odontology–a case report of identified skeletal remains. Journal of Forensic Radiology and Imaging 1(4):201–206

Adserias-Garriga J, Thomas C, Ubelaker DH, Zapico SC (2018) When forensic odontology met biochemistry: Multidisciplinary approach in forensic human identification. Archives of oral biology 87:7–14PubMed

INTERPOL (2018) INTERPOL disaster victim identification guide. https://www.interpol.int/INTERPOL-expertise/Forensics/DVI-Pages/DVI-guide, URL https://www.interpol.int/

Zaghetto C, Aguiar LHM, Zaghetto A, Ralha CG, de Barros Vidal F (2017) Agent-based framework to individual tracking in unconstrained environments. Expert Systems with Applications 87:118 – 128. https://doi.org/10.1016/j.eswa.2017.05.065. URL https://www.sciencedirect.com/science/article/pii/S0957417417303925CrossRef

Cattaneo C, Obertová Z, Ratnayake M, Marasciuolo L, Tutkuviene J, Poppa P, Gibelli D, Gabriel P, Ritz-Timme S (2012) Can facial proportions taken from images be of use for ageing in cases of suspected child pornography? A pilot study. International journal of legal medicine 126(1):139–144PubMed

Ratnayake M, Obertová Z, Dose M, Gabriel P, Bröker HM, Brauckmann M, Barkus A, Rizgeliene R, Tutkuviene J, Ritz-Timme S, et al. (2014) The juvenile face as a suitable age indicator in child pornography cases: a pilot study on the reliability of automated and visual estimation approaches. International journal of legal medicine 128(5):803–808PubMed

de Melo Nunes LF, Zaghetto C, de Barros Vidal F (2018) 3d face recognition on point cloud data - an approaching based on curvature map projection using low resolution devices. In: Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, INSTICC. SciTePress, pp 266–273, DOI https://doi.org/10.5220/0006843702660273, (to appear in print)

Borges DL, Vidal FB, Flores MRP, Melani RFH, Guimarães MA, Machado CEP (2018) Photoanthropometric face iridial proportions for age estimation: An investigation using features selected via a joint mutual information criterion. Forensic Science International 284:9 – 14PubMed

10.

Cattaneo C, Ritz-Timme S, Gabriel P, Gibelli D, Giudici E, Poppa P, Nohrden D, Assmann S, Schmitt R, Grandi M (2009) The difficult issue of age assessment on pedo-pornographic material. Forensic science international 183(1):e21–e24PubMed

11.

Machado CEP, Flores MRP, Lima LNC, Tinoco RLR, Franco A, Bezerra ACB, Evison MP, Guimarães MA (2017) A new approach for the analysis of facial growth and age estimation: Iris ratio. PLOS ONE 12(7):e0180330PubMedPubMedCentral

12.

Flores MRP, Machado CEP, Gallidabino MD, de Arruda GHM, da Silva RHA, de Vidal FB, Melani RFH (2018) Comparative assessment of a novel photo-anthropometric landmark-positioning approach for the analysis of facial structures on two-dimensional images. Journal of forensic sciences

13.

Gonzales PS, Machado CEP, Michel-Crosato E (2018) Photoanthropometry of the face in the young white brazilian population. Brazilian dental journal 29(6):619–623PubMed

14.

Zhu G, van der Aa S (2017) Trends of age of consent legislation in europe: A comparative study of 59 jurisdictions on the european continent. New Journal of European Criminal Law 8(1):14–42

15.

Carpenter B, O’Brien E, Hayes S, Death J (2014) Harm, responsibility, age, and consent. New Criminal Law Review: In International and Interdisciplinary Journal 17(1):23–54

16.

Cericato GO, Franco A, Bittencourt MAV, Nunes MAP, Paranhos LR (2016) Correlating skeletal and dental developmental stages using radiographic parameters. Journal of forensic and legal medicine 42:13–18PubMed

17.

Machado MA, Júnior ED, Fernandes MM, Lima IFP, Cericato GO, Franco A, Paranhos LR (2018) Effectiveness of three age estimation methods based on dental and skeletal development in a sample of young brazilians. Archives of oral biology 85:166–171PubMed

18.

Lanitis A, Draganova C, Christodoulou C (2004) Comparing different classifiers for automatic age estimation. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 34(1):621–628. https://doi.org/10.1109/TSMCB.2003.817091CrossRef

19.

Fu Y, Huang TS (2008) Human age estimation with regression on discriminative aging manifold. IEEE Transactions on Multimedia 10(4):578–584. https://doi.org/10.1109/TMM.2008.921847CrossRef

20.

Guo G, Fu Y, Dyer CR, Huang TS (2008) Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Transactions on Image Processing 17(7):1178–1188. https://doi.org/10.1109/TIP.2008.924280CrossRefPubMed

21.

Xiao B, Yang X, Zha H, Xu Y, Huang TS (2009) Metric learning for regression problems and human age estimation. In: Muneesawang P, Wu F, Kumazawa I, Roeksabutr A, Liao M, Tang X (eds) Advances in Multimedia Information Processing - PCM 2009. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 88–99

22.

Chang K, Chen C, Hung Y (2010) A ranking approach for human ages estimation based on face images. In: 2010 20th International Conference on Pattern Recognition, pp 3396–3399, DOI https://doi.org/10.1109/ICPR.2010.829, (to appear in print)

23.

Chang K, Chen C (2015) A learning framework for age rank estimation based on face images with scattering transform. IEEE Transactions on Image Processing 24(3):785–798. https://doi.org/10.1109/TIP.2014.2387379CrossRefPubMed

24.

Chen S, Zhang C, Dong M, Le J, Rao M (2017) Using ranking-CNN for age estimation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 742–751, DOI https://doi.org/10.1109/CVPR.2017.86, (to appear in print)

25.

Zhang L, Shi Z, Cheng M-M, Liu Y, Bian J-W, Zhou JT, Zheng G, Zeng Z (2019) Robust regression via deep negative correlation learning. arXiv:1908.09066

26.

Taheri S, Toygar O (2019) On the use of dag-CNN architecture for age estimation with multi-stage features fusion. Neurocomputing 329:300–310

27.

Xie J-C, Pun C-M (2019) Chronological age estimation under the guidance of age-related facial attributes. IEEE Transactions on Information Forensics and Security

28.

International Organization for Standardization (2005) ISO/IEC 19794-5: Information technology – Biometric data interchange formats – Part 5: Face image data. Standard, International Organization for Standardization

29.

Pinheiro-Flores MR, Palhares-Machado CE (2017) Manual of facial photoanthropometry: landmarks in frontal view from visual references, 1st edn. https://facisgroup.org/facial_landmarks

30.

Pinheiro-Flores MR (2014) Proposta de metodologia de análise fotoantropométrica para identificação humana em imagens faciais em norma frontal. Master’s Thesis, Faculdade de Odontologia de Ribeirão Preto, Universidade de São Paulo

31.

Porto LF, Lima LNC, Flores MRP, Valsecchi A, Ibanez O, Palhares CEM, de Barros Vidal F (2019) Automatic cephalometric landmarks detection on frontal faces: An approach based on supervised learning techniques. Digital Investigation 30:108 – 116. https://www.sciencedirect.com/science/article/pii/S1742287619301288, https://doi.org/10.1016/j.diin.2019.07.008

32.

Caple J, Stephan C (2016) A standardized nomenclature for craniofacial and facial anthropometry. International Journal of Legal Medicine 130(3):863–879PubMed

33.

Farkas LG (1994) Anthropometry of the head and face. Raven Pr ed 2. New York, Raven Press

34.

Brown RE, Kelliher TP, Tu PH, Turner WD, Taister MA, Miller KWP (2004) A survey of tissue-depth landmarks for facial approximation. Forensic Sci. Commun, 6(1)

35.

Phillips PJ, Moon H, Rizvi S, Rauss PJ, et al. (2000) The FERET evaluation methodology for face-recognition algorithms. Pattern Analysis and Machine Intelligence, IEEE Transactions on 22 (10):1090–1104

36.

Apeland S (2019) Intel AI devcloud. URL https://www.intel.ai/devcloud/ Accessed: 2019-01-22

37.

Chollet F, et al. (2015) Keras. https://keras.io

38.

Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: Large-scale machine learning on heterogeneous systems. https://www.tensorflow.org/, Software available from tensorflow.org

39.

Gardner MW, Dorling SR (1998) Artificial neural networks (the multilayer perceptron)–a review of applications in the atmospheric sciences. Atmospheric environment 32(14-15):2627–2636

40.

Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980

41.

Powers DMW (2011) Evaluation: From precision, recall and f-measure to roc., informedness, markedness & correlation. Journal of Machine Learning Technologies 2(1):37–63

42.

Provost F, Kohavi R (1998) On applied research in machine learning. In: Machine learning, pp 127–132

43.

Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction. Springer, 2nd edn Springer-Verlag New York. https://www-stat.stanford.edu/tibs/ElemStatLearn/

44.

Kohavi R, et al. (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, vol 14, Stanford, CA, pp 1137–1145

45.

Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in Neural Information Processing Systems 27. https://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf. Curran Associates, Inc., pp 2672–2680

46.

Wilk MB, Shapiro SS (1965) An analysis of variance test for normality (complete samples). Biometrika 52(3-4):591–611. https://doi.org/10.1093/biomet/52.3-4.591. https://oup.prod.sis.lan/biomet/article-pdf/52/3-4/591/962907/52-3-4-591.pdfCrossRef

47.

Kutner MH (2005) Applied linear statistical models. McGrwa-Hill international edition, McGraw-Hill Irwin. https://books.google.com.br/books?id=0xqCAAAACAAJ

48.

Schmeling A, Olze A, Reisinger W, Geserick G (2001) Age estimation of living people undergoing criminal proceedings. The Lancet 358(9276):89–90

49.

Schmeling A, Dettmeyer R, Rudolf E, Vieth V, Geserick G (2016) Forensic age estimation: methods, certainty, and the law. Deutsches Ärzteblatt International 113(4):44PubMedPubMedCentral

50.

Silva RF, Mendes SDSC, do Rosário Júnior AF, Dias PEM, Martorell LB (2013) Evidência documental X evidência biológica para estimativa da idade–relato de caso pericial. Revista Odontológica do Brasil Central 22(60):6–10

51.

Machado ALR, Dezem TU, Bruni AT, da Silva RHA (2017) Age estimation by facial analysis based on applications available for smartphones. The Journal of forensic odonto-stomatology 35(2):55

52.

Deitos AR, Costa C, Michel-Crosato E, Galić I, Cameriere R, Biazevic MGH (2015) Age estimation among brazilians: younger or older than 18? Journal of forensic and legal medicine 33:111–115PubMed

53.

Santiago BM, Almeida L, Cavalcanti YW, Magno MB, Maia LC (2018) Accuracy of the third molar maturity index in assessing the legal age of 18 years: a systematic review and meta-analysis. International journal of legal medicine 132(4):1167– 1184PubMed

54.

Franco A, Thevissen P, Fieuws S, Souza PHC, Willems G (2013) Applicability of willems model for dental age estimations in brazilian children. Forensic science international 231(1-3):401–e1PubMed

55.

Graupner H (2000) Sexual consent: The criminal law in europe and overseas. Archives of Sexual Behavior 29(5):415–461PubMed

56.

Machado CEP, Santiago BM, Lima LNC, Gonzales PS, Franco A, de Barros Vidal F, Aguilera IA, Guimarães MA (2019) Applicability of a pre-established set of facial proportions from frontal photographs in forensic age estimation of a brazilian population. Forensic science international 301:e1–e7PubMed

57.

Baldasso RP, Damascena NP, Deitos AR, Palhares Machado CE, Franco A, de Oliveira RN (2019) Morphologic alterations ear, nose and lip detected with aging through facial photoanthropometric analysis. Journal of Forensic Odonto-Stomatology 37(2):25–34PubMed

58.

Balaji SM (2016) Facial feminization-surgical modification for indian, european and african faces. Annals of maxillofacial surgery 6(2):210PubMedPubMedCentral

59.

Kloess JA, Woodhams J, Whittle H, Grant T, Hamilton-Giachritsis CE (2017) The challenges of identifying and classifying child sexual abuse material. Sexual Abuse, p 1079063217724768

60.

Cummaudo M, Guerzoni M, Gibelli D, Cigada A, Obertovà Z, Ratnayake M, Poppa P, Gabriel P, Ritz-Timme S, Cattaneo C (2014) Towards a method for determining age ranges from faces of juveniles on photographs. Forensic science international 239:107–e1PubMed

61.

Tummon HM, Allen J, Bindemann M (2019) Facial identification at a virtual reality airport. i-Perception 10(4):2041669519863077PubMedPubMedCentral

Title: Estimating sex and age from a face: a forensic approach using machine learning based on photo-anthropometric indexes of the Brazilian population
Authors: Lucas Faria Porto
Laíse Nascimento Correia Lima
Ademir Franco
Donald Pianto
Carlos Eduardo Palhares Machado
Flavio de Barros Vidal
Publication date: 01-11-2020
Publisher: Springer Berlin Heidelberg
Published in: International Journal of Legal Medicine / Issue 6/2020
Print ISSN: 0937-9827
Electronic ISSN: 1437-1596
DOI: https://doi.org/10.1007/s00414-020-02346-5

At a glance: The STEP trials

Springer Medicine

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

Abstract

At a glance: The STEP trials

Springer Medicine

Abstract

Please log in to get access to this content

Other articles of this Issue 6/2020

Aspiration in lethal drug abuse—a consequence of opioid intoxication

Population genetic study of a Peruvian population using human identification STRs

Age estimation in the living: cervical ring apophysis development in a Turkish sample using CT

Technical note: age estimation by using pubic bone densitometry according to a twofold mode of CT measurement

Forensic sex estimation using the vertebrae: an evaluation on two European populations

Investigation of phase II metabolism of 11-hydroxy-Δ-9-tetrahydrocannabinol and metabolite verification by chemical synthesis of 11-hydroxy-Δ-9-tetrahydrocannabinol-glucuronide