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

Porto, Lucas Faria; Lima, Laíse Nascimento Correia; Franco, Ademir; Pianto, Donald M.; Machado, Carlos Eduardo Palhares; Vidal, Flávio de Barros

doi:10.1007/s00414-020-02346-5

Cited by 18 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although artificial intelligence and deep learning techniques have clinical applications in several medical specialties [ 2 , 4 , 6 , 7 ], forensic applications have been relatively scarce [ 3 , 8 – 11 ] and centered on subfields other than forensic pathology. To the best of our knowledge, this is the first study to address deep learning in gunshot wound interpretation.…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning is a subcategory under artificial intelligence, utilizing neural networks in a wide range of concepts such as image, text, and speech recognition [ 2 , 4 , 5 ]. While the applications of artificial intelligence and deep learning techniques are considered revolutionary within the healthcare sector and several medical specialties [ 2 , 4 , 6 , 7 ], forensic applications have been relatively scarce [ 3 , 8 – 11 ] and centered on subfields other than forensic pathology. This somewhat surprising, given the visual nature of forensic pathology at both microscopic and macroscopic levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning in forensic gunshot wound interpretation—a proof-of-concept study

Oura

Junno

2021

Int J Legal Med

View full text Add to dashboard Cite

While the applications of deep learning are considered revolutionary within several medical specialties, forensic applications have been scarce despite the visual nature of the field. For example, a forensic pathologist may benefit from deep learning-based tools in gunshot wound interpretation. This proof-of-concept study aimed to test the hypothesis that trained neural network architectures have potential to predict shooting distance class on the basis of a simple photograph of the gunshot wound. A dataset of 204 gunshot wound images (60 negative controls, 50 contact shots, 49 close-range shots, and 45 distant shots) was constructed on the basis of nineteen piglet carcasses fired with a .22 Long Rifle pistol. The dataset was used to train, validate, and test the ability of neural net architectures to correctly classify images on the basis of shooting distance. Deep learning was performed using the AIDeveloper open-source software. Of the explored neural network architectures, a trained multilayer perceptron based model (MLP_24_16_24) reached the highest testing accuracy of 98%. Of the testing set, the trained model was able to correctly classify all negative controls, contact shots, and close-range shots, whereas one distant shot was misclassified. Our study clearly demonstrated that in the future, forensic pathologists may benefit from deep learning-based tools in gunshot wound interpretation. With these data, we seek to provide an initial impetus for larger-scale research on deep learning approaches in forensic wound interpretation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning in forensic gunshot wound interpretation—a proof-of-concept study

Oura

Junno

2021

Int J Legal Med

View full text Add to dashboard Cite

show abstract

“…Prediction of soft tissues according to the hard tissues of the skull and vice versa can be significantly improved upon big-data training of 3D CNN with supplementary metadata about age, sex, BMI or ethnicity. New algorithms to perform facial reconstruction from a given skull has forensic application in helping the identification of skeletal remains when other information is unavailable [62,67,[69][70][71][72][73]75,76,89,90,92,93,96,145]. Implementation of 3D CNN can also unintentionally open pandora box of guided improving the morphology of the facial soft-tissues.…”

Section: Artificial Intelligence Implementation In Soft-tissue Face Prediction From Skull and Vice Versamentioning

confidence: 99%

“…Soft-tissue face prediction from skull and in reverse [62][63][64][65][66][67][68][69][70][71][72][73][74][75][76][77][78][79][80][81] 5. Facial growth vectors prediction [14,62,[82][83][84][85][86][87][88][89][90][91][92][93][94] The result of this paper is a detailed guide for forensic scientists to implement features of 3D CNN to forensic research and analyses of their own (in five themes described above). This resulting practical concept -possible workflow shall be useful for any forensic expert interested in implementing this advanced artificial intelligence feature.…”

Section: Introductionmentioning

confidence: 99%

Use of Advanced Artificial Intelligence in Forensic Medicine

Thurzo¹,

Kosnáčová²,

Kurilová³

et al. 2021

Preprint

View full text Add to dashboard Cite

Three-dimensional convolutional neural networks (3D CNN) as a type of artificial intelligence (AI) are powerful in image processing and recognition using deep learning to perform generative and descriptive tasks. The advantage of CNN compared to its predecessors is that it automatically detects the important features without any human supervision. 3D CNN are used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim of this article was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers. With emphasis activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance the forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore and present 3D CNN method for forensic research design concept in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.

show abstract

“…Currently, investigations may be performed using two-dimensional photographs, but methods to solve scale and calibration issues are required, as well as rigorous standardization of photographic procedure [ 23 ]. Optical image analysis systems working in three-dimensional (3D) space allow us to overcome that limitation; among them, stereophotogrammetry, laser scanning and structured light cameras are probably the most used worldwide, coupling minimal or null patient discomfort with a fast data collection [ 2 , 8 , 10 , 11 , 12 , 18 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ].…”

Section: Introductionmentioning

confidence: 99%

Age- and Sex-Related Changes in Labial Dimensions of Sudanese Youngs of Arab Descent: A Three-Dimensional Cross-Sectional Study

et al. 2021

View full text Add to dashboard Cite

Proper evaluation of facial features during growth and development requires the knowledge of anthropometric reference values validated for ethnicity, sex and age. In order to provide information concerning the normal sex-related size of the lips during childhood and young adulthood in Sudanese people of Arab descent, the three-dimensional coordinates of nine labial soft tissue landmarks were obtained by a laser scanner in 332 male and 386 female healthy Northern Sudanese subjects aged 3–30 years. Six labial linear distances, the vermilion height to mouth width ratio, vermilion areas and lip volumes were calculated and averaged for age and sex. Comparisons were performed by factorial analysis of variance (p < 0.01). All labial dimensions significantly increased with age. Significant effects of sex were found for four measurements only, with very small effect size; nonetheless, lips and their parts grew faster in females than in males at almost all ages. Philtrum width was the first linear distance that attained adult values. The vermilion height to mouth width ratio was nearly constant across the age groups. Data collected in this study contribute to information about ethnic-specific lip morphology during growth and development. As orolabial features change over time with their own pattern, the relevant age-related trends should be properly considered for clinical treatment planning.

show abstract

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

Cited by 18 publications

References 41 publications

Deep learning in forensic gunshot wound interpretation—a proof-of-concept study

Deep learning in forensic gunshot wound interpretation—a proof-of-concept study

Use of Advanced Artificial Intelligence in Forensic Medicine

Age- and Sex-Related Changes in Labial Dimensions of Sudanese Youngs of Arab Descent: A Three-Dimensional Cross-Sectional Study

Contact Info

Product

Resources

About