1
|
Urbanova P, Goldmann T, Cerny D, Drahansky M. Head poses and grimaces: Challenges for automated face identification algorithms? Sci Justice 2024; 64:421-442. [PMID: 39025567 DOI: 10.1016/j.scijus.2024.06.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/23/2024] [Revised: 06/04/2024] [Accepted: 06/15/2024] [Indexed: 07/20/2024]
Abstract
In today's biometric and commercial settings, state-of-the-art image processing relies solely on artificial intelligence and machine learning which provides a high level of accuracy. However, these principles are deeply rooted in abstract, complex "black-box systems". When applied to forensic image identification, concerns about transparency and accountability emerge. This study explores the impact of two challenging factors in automated facial identification: facial expressions and head poses. The sample comprised 3D faces with nine prototype expressions, collected from 41 participants (13 males, 28 females) of European descent aged 19.96 to 50.89 years. Pre-processing involved converting 3D models to 2D color images (256 × 256 px). Probes included a set of 9 images per individual with head poses varying by 5° in both left-to-right (yaw) and up-and-down (pitch) directions for neutral expressions. A second set of 3,610 images per individual covered viewpoints in 5° increments from -45° to 45° for head movements and different facial expressions, forming the targets. Pair-wise comparisons using ArcFace, a state-of-the-art face identification algorithm yielded 54,615,690 dissimilarity scores. Results indicate that minor head deviations in probes have minimal impact. However, the performance diminished as targets deviated from the frontal position. Right-to-left movements were less influential than up and down, with downward pitch showing less impact than upward movements. The lowest accuracy was for upward pitch at 45°. Dissimilarity scores were consistently higher for males than for females across all studied factors. The performance particularly diverged in upward movements, starting at 15°. Among tested facial expressions, happiness and contempt performed best, while disgust exhibited the lowest AUC values.
Collapse
Affiliation(s)
- Petra Urbanova
- Department of Anthropology, Faculty of Science, Masaryk University, Czech Republic.
| | - Tomas Goldmann
- Department of Intelligent Systems, Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic
| | - Dominik Cerny
- Department of Anthropology, Faculty of Science, Masaryk University, Czech Republic
| | - Martin Drahansky
- Department of Anthropology, Faculty of Science, Masaryk University, Czech Republic
| |
Collapse
|
2
|
Cai J, Deng Y, Min Z, Zhang Y, Zhao Z, Jing D. Revealing the representative facial traits of different sagittal skeletal types: decipher what artificial intelligence can see by Grad-CAM. J Dent 2023; 138:104701. [PMID: 37717687 DOI: 10.1016/j.jdent.2023.104701] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2023] [Revised: 09/10/2023] [Accepted: 09/12/2023] [Indexed: 09/19/2023] Open
Abstract
OBJECTIVES Aesthetic improvement is a significant concern in dental therapy. While orthodontic treatment primarily targets hard tissue, the impact on soft tissue and the extent of these changes remains empirical. This study aims to unveil the intricate relationship between facial soft tissue and skeletal types using artificial intelligence (AI) analysis. METHODS First, we collected a dataset of 1044 3-side-photographs and categorized them based on cephalometric measurements. After pre-processing and data augmentation, samples were fed to two independent models (Sfa, Res model) for training and testing. After validating that the Sfa model could accurately recognize the skeletal types based merely on photographs, Grad-CAM algorithm was utilized for model decipherment. Verification of the vital traits were carried out by facial adjustment simulation. RESULTS The Sfa model demonstrated superior accuracy (0.9293) in identifying skeletal types based solely on soft tissue, compared to the Res model (0.8395) and even trained orthodontists (0.764), testifying our hypothesis that AI could be more capable of processing imperceptible cues compared to mankind. Intriguingly, Grad-CAM revealed that cheek volume, forehead, chin and nasolabial traits could be representative features of each type, exceeding the traditional knowledge which merely concerns mandible and chin. CONCLUSION By constructing a deep learning model as a classifier and then decipher it with Grad-CAM, we revealed the subtle and unnoticed cues associating skeletal and soft tissue, as well as provided a novel approach that could aid practitioners in devising tailored treatment plans for enhanced esthetic outcomes. CLINICAL SIGNIFICANCE The proposed AI methods offer valuable assistance to practitioners in identifying uncoordinated facial traits that may detract from a patient's attractiveness. By incorporating these insights into customized treatment plans, dental therapy can maximize esthetic benefits for individual patient.
Collapse
Affiliation(s)
- Jingyi Cai
- State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, No.14, 3rd Section, South Renmin Road, Chengdu, Sichuan 610041 China
| | - Yudi Deng
- State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, No.14, 3rd Section, South Renmin Road, Chengdu, Sichuan 610041 China
| | - Ziyang Min
- State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, No.14, 3rd Section, South Renmin Road, Chengdu, Sichuan 610041 China
| | - Yiyi Zhang
- State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, No.14, 3rd Section, South Renmin Road, Chengdu, Sichuan 610041 China
| | - Zhihe Zhao
- State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, No.14, 3rd Section, South Renmin Road, Chengdu, Sichuan 610041 China.
| | - Dian Jing
- Department of Orthodontics, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, College of Stomatology, National Center for Stomatology, National Clinical Research Center for Oral Diseases, Shanghai Key Laboratory of Stomatology, Shanghai Jiao Tong University, No.639, Zhizaoju Road, Huangpu District, Shanghai 200011, China.
| |
Collapse
|
3
|
Urbanová P, Eliášová H, Dostálová T. How accurate is forensic facial identification of surgically altered faces? AUST J FORENSIC SCI 2022. [DOI: 10.1080/00450618.2022.2032341] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- Petra Urbanová
- Department of Anthropology, Faculty of Science, Masaryk University, Brno, Czech Republic
| | - Hana Eliášová
- Police of the Czech Republic, Institute of Criminalistics, Prague, Czech Republic
| | - Taťjana Dostálová
- Department of Stomatology, 2nd Medical Faculty and Motol University Hospital, Charles University, Prague, Czech Republic
| |
Collapse
|
4
|
Pinto PHV, Rodrigues CHP, Rozatto JR, da Silva AMBR, Bruni AT, da Silva MAMR, da Silva RHA. Can a spontaneous smile invalidate facial identification by photo-anthropometry? Imaging Sci Dent 2021; 51:279-290. [PMID: 34621655 PMCID: PMC8479441 DOI: 10.5624/isd.20210002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2021] [Revised: 04/18/2021] [Accepted: 04/21/2021] [Indexed: 11/18/2022] Open
Abstract
Purpose Using images in the facial image comparison process poses a challenge for forensic experts due to limitations such as the presence of facial expressions. The aims of this study were to analyze how morphometric changes in the face during a spontaneous smile influence the facial image comparison process and to evaluate the reproducibility of measurements obtained by digital stereophotogrammetry in these situations. Materials and Methods Three examiners used digital stereophotogrammetry to obtain 3-dimensional images of the faces of 10 female participants (aged between 23 and 45 years). Photographs of the participants' faces were captured with their faces at rest (group 1) and with a spontaneous smile (group 2), resulting in a total of 60 3-dimensional images. The digital stereophotogrammetry device obtained the images with a 3.5-ms capture time, which prevented undesirable movements of the participants. Linear measurements between facial landmarks were made, in units of millimeters, and the data were subjected to multivariate and univariate statistical analyses using Pirouette® version 4.5 (InfoMetrix Inc., Woodinville, WA, USA) and Microsoft Excel® (Microsoft Corp., Redmond, WA, USA), respectively. Results The measurements that most strongly influenced the separation of the groups were related to the labial/buccal region. In general, the data showed low standard deviations, which differed by less than 10% from the measured mean values, demonstrating that the digital stereophotogrammetry technique was reproducible. Conclusion The impact of spontaneous smiles on the facial image comparison process should be considered, and digital stereophotogrammetry provided good reproducibility.
Collapse
Affiliation(s)
- Paulo Henrique Viana Pinto
- Department of Pathology and Forensic Medicine, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, SP, Brazil
| | - Caio Henrique Pinke Rodrigues
- Department of Chemistry, School of Philosophy, Sciences and Letters of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
| | - Juliana Rodrigues Rozatto
- Department of Oral Surgery and Periodontics, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
| | | | - Aline Thais Bruni
- Department of Chemistry, School of Philosophy, Sciences and Letters of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
| | | | - Ricardo Henrique Alves da Silva
- Department of Stomatology, Public Health and Forensic Odontology, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
| |
Collapse
|
5
|
Silva R, Pinto P, Jacometti V, Pereira J, Silva M. Comparative Analysis between Linear Measures from Bidimensional and Three-dimensional Images of the Face for Human Identification Purpose: A Pilot Study. JOURNAL OF OROFACIAL SCIENCES 2021. [DOI: 10.4103/jofs.jofs_289_20] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
|
6
|
Ubelaker DH, Wu Y, Cordero QR. Craniofacial photographic superimposition: New developments. Forensic Sci Int Synerg 2019; 1:271-274. [PMID: 32411979 PMCID: PMC7219178 DOI: 10.1016/j.fsisyn.2019.10.002] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2019] [Revised: 10/02/2019] [Accepted: 10/03/2019] [Indexed: 12/04/2022]
Abstract
Craniofacial superimposition is a technique used in the field of forensic anthropology to assist in the analysis of an unknown skull. The process involves superimposing an image of the recovered skull over an ante mortem image of the suspected individual. In the past two decades, there has been a decline in the application due to the development of molecular analysis as a more precise and accurate identification technique. Despite its decrease in use, there has been significant development in superimposition techniques in the past five years, specifically to standardize procedures. One project, MEPROCS (The New Methodologies and Protocols of Forensic Identification by Craniofacial Superimposition), has attempted to establish a framework for solving the problems of past superimposition techniques. Future researchers should consider integrating information gleaned from clinical practices with the statistical and technical advances of craniofacial superimposition for better facilitating its use in forensic anthropology.
Collapse
Affiliation(s)
- Douglas H Ubelaker
- Department of Anthropology, NMNH, Smithsonian Institution Washington, D.C., 20560, USA
| | - Yaohan Wu
- Department of Anthropology, NMNH, Smithsonian Institution Washington, D.C., 20560, USA
| | - Quinnlan R Cordero
- Department of Anthropology, NMNH, Smithsonian Institution Washington, D.C., 20560, USA
| |
Collapse
|