The identification of living persons on images: A literature review

Pattern analysis using lower body human walking data to identify the gaitprint

All people have a fingerprint that is unique to them and persistent throughout life. Similarly, we propose that people have a gaitprint, a persistent walking pattern that contains unique information about an individual. To provide evidence of a unique gaitprint, we aimed to identify individuals based on basic spatiotemporal variables. 81 adults were recruited to walk overground on an indoor track at their own pace for four minutes wearing inertial measurement units. A total of 18 trials per participant were completed between two days, one week apart. Four methods of pattern analysis, a) Euclidean distance, b) cosine similarity, c) random forest, and d) support vector machine, were applied to our basic spatiotemporal variables such as step and stride lengths to accurately identify people. Our best accuracy (98.63%) was achieved by random forest, followed by support vector machine (98.40%), and the top 10 most similar trials from cosine similarity (98.40%). Our results clearly demonstrate a persistent walking pattern with sufficient information about the individual to make them identifiable, suggesting the existence of a gaitprint.

Accuracy of geometric morphometrics for age estimation using frontal face photographs of children and adolescents: A promising method for forensic practice

Age estimation is crucial in legal and humanitarian contexts. Forensic professionals may use various procedures to estimate age, including dental analysis, bone density tests, evaluation of physical characteristics including facial bone structure and development, and image-based methods. Although images are often the only material available, visual observation of photographic material is an imprecise method in age estimation, which can compromise judicial decision-making. Analyzing 4000 photographs from the Brazilian Federal Police database, representing four age groups (6, 10, 14, and 18 years), the study employed automated analysis by marking 28 photogrammetric points. Data were used to establish facial patterns by age and sex using the facial geometric morphometrics method. Performance was assessed through a Multinomial Logistic Regression model, evaluating accuracy, sensitivity, and specificity across the categorical age groups. Analyses were conducted using R software, with a 5 % significance level. The study found that facial geometric morphometrics achieved an overall accuracy of 69.3 % in age discrimination, with higher accuracy in males (74.7 %) compared to females (65.8 %) (p < 0.001). The method excelled at predicting the age of 6-year-olds with 87.3 % sensitivity and 95.6 % specificity but had lower performance at 14 years. It showed greater accuracy in distinguishing age groups with larger age gaps, achieving up to 99.5 % accuracy between certain groups, and was particularly effective in differentiating ages of 6 and 10 years in females and 10, 14, and 18 years in males. The facial geometric morphometrics emerges as a promising approach for age estimation among children and adolescents in forensic settings.

Head poses and grimaces: Challenges for automated face identification algorithms?

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.

Reconsideration of Bertillonage in the age of digitalisation: Digital anthropometric patterns as a promising method for establishing identity

The idea of using measurements of the human body for identity matching is deeply associated with Bertillonage, a historic biometric system that was briefly applied until it was superseded by fingerprinting in the early 20th century. The apparent failure then commonly causes doubt with regard to the suitability of a set of measurements as a biometric identifier in the present. Hence, the aim of this paper is to explore the potentials of using an anthropometric pattern, comprising of a set of body measurements, for identity matching. For this purpose, it will begin with a thorough examination of Bertillon's system and move on to conduct a comprehensive inquiry of the current possibilities of using digital anthropometric patterns in image or video-based evidence.

Two heads are better than one: Dual systems obtain better performance in facial comparison

Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems model (including SeetaFace and FaceNet) for facial comparison was constructed, and Bayesian networks were utilized as the basic frame. In order to prove its superiority, a large-scale experiment (on the dataset CelebA) has been carried on to evaluate the score-based likelihood ratio. We used three likelihood ratio evaluation tools (Empirical Cross-Entropy, Cost Likelihood Ratio, Limit Tippett Plots) to assess the performance of the model. The Wasserstein distance was also used to evaluate the detailed likelihood ratio performance. The experimental results show that the likelihood ratio performance of our dual-systems model is better than single system. Besides, our method of model building and evaluation can also be used in the condition of triple or more systems.

3D‐3D facial registration method applied to personal identification: Does it work with limited portions of faces? An experiment in ideal conditions

Personal identification of faces represents a challenging issue, especially for what concerns the quantification of the comparison. The 3D‐3D superimposition approach proved to distinguish between matches and mismatches. However, the potential of this procedure applied to cases where only parts of faces are visible still has to be verified. This study aimed at verifying the applicability of a 3D‐3D procedure to faces divided into three thirds. 3D models of fifty male subjects acquired through stereophotogrammetry were used. The 3D facial models were divided into upper, middle, and lower thirds and registered onto other models belonging to the same and different individuals according to the least point‐to‐point distance. In total, 50 matches and 50 mismatches were analyzed. RMS value (root mean square) of point‐to‐point distance between the two facial surfaces was calculated through VAM® software. Statistically significant differences between matches and mismatches in each facial third were assessed through Mann–Whitney test (p < 0.05). On average, RMS value in matches was 0.32 ± 0.12 mm in upper third, 0.36 ± 0.15 mm in middle third, and 0.40 ± 0.20 mm in lower third, respectively; in mismatches, RMS value was 1.40 ± 0.32 mm in upper third, 1.96 ± 0.58 mm in middle third, and 2.39 ± 0.90 mm in lower third, respectively. Differences in RMS values between matches and mismatches were significantly different for all facial thirds, without superimpositions (p < 0.01). This study shows that the existing 3D‐3D superimposition methods may be useful also when only a limited portion of face is visible in ideal conditions. Their application to forensic cases of identification still needs to be verified.

Forensic Facial Comparison: Current Status, Limitations, and Future Directions

Global escalation of crime has necessitated the use of digital imagery to aid the identification of perpetrators. Forensic facial comparison (FFC) is increasingly employed, often relying on poor-quality images. In the absence of standardized criteria, especially in terms of video recordings, verification of the methodology is needed. This paper addresses aspects of FFC, discussing relevant terminology, investigating the validity and reliability of the FISWG morphological feature list using a new South African database, and advising on standards for CCTV equipment. Suboptimal conditions, including poor resolution, unfavorable angle of incidence, color, and lighting, affected the accuracy of FFC. Morphological analysis of photographs, standard CCTV, and eye-level CCTV showed improved performance in a strict iteration analysis, but not when using analogue CCTV images. Therefore, both strict and lenient iterations should be conducted, but FFC must be abandoned when a strict iteration performs worse than a lenient one. This threshold ought to be applied to the specific CCTV equipment to determine its utility. Chance-corrected accuracy was the most representative measure of accuracy, as opposed to the commonly used hit rate. While the use of automated systems is increasing, trained human observer-based morphological analysis, using the FISWG feature list and an Analysis, Comparison, Evaluation, and Verification (ACE-V) approach, should be the primary method of facial comparison.

Performance of forensic facial comparison by morphological analysis across optimal and suboptimal CCTV settings

Facial comparison is an important yet understudied discipline in forensics. The recommended method for facial comparison in a forensic setting involves morphological analysis (MA) with the use of a facial feature list. The performance of this approach has not been tested across various closed-circuit television (CCTV) conditions. This is of particular concern as video and image data available to law enforcement is often varied and of subpar conditions. The present study aimed at testing MA across two types of CCTV data, representing ideal and less than ideal settings, also assessing which particular shortcomings arose from less-than-ideal settings. The study was conducted on a subset of the Wits Face Database arranged in a total of 225 face pools. Each face pool consisted of a target image obtained from either a high-definition digital CCTV camera or a low-definition analogue CCTV camera in monochrome, contrasted to 10 possible matches. The face pools were analysed and scored using MA and confusion matrices were used to analyse the outcomes. A notably high chance corrected accuracy (CCA) (97.3%) and reliability (0.969) was identified across the digital CCTV sample, while in the analogue CCTV sample MA appeared to underperform both in accuracy (CCA: 33.1%) and reliability (0.529). The majority of the errors in scoring resulted in false negatives in the analogue sample (75.2%), while across both CCTV conditions false positives were low (digital: 0.3%; analogue: 1.2%). Even though hit rates appeared deceptively high in the analogue sample, the various measures of performance used and particularly the chance corrected accuracy highlighted its shortfalls. Overall, CCTV recording quality appears closely associated to MA performance, despite the favourable error rates when using the Facial Identification Scientific Working Group feature list.

Can a spontaneous smile invalidate facial identification by photo-anthropometry?

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.

Personal identification systems for persons with dementia: a systematic review

People with dementia can become missing and unable to be identified due to their cognitive decline and may not have belongings, including personally identifiable information. The aim of this systematic review was to summarise and discuss the current status of personal identification systems for missing and unidentified persons with dementia. An electronic systematic literature search was conducted by using PubMed, Web of Science, Cochrane Library, and CINAHL. By performing an electronic literature search, 128 texts were extracted. However, only three eligible texts were included in this review, and these were divided on the basis of the analysis target as follows: medical and human community support systems and digital systems. It is important to develop medical and social care systems and to construct and advance social personal identification systems, including medical and human community support systems and digital systems, for persons with dementia. However, this systematic review clarified that there have only been a few reports about the development and construction of social systems for missing and unidentified persons with dementia. People who interact with persons with dementia should consider this problem, which is increasing each year, and strive to build a social system that can be applied to personal identification as soon as possible.

Improving 3D-3D facial registration methods: potential role of three-dimensional models in personal identification of the living

Personal identification of the living from video surveillance systems usually involves 2D images. However, the potentiality of three-dimensional facial models in gaining personal identification through 3D-3D comparison still needs to be verified. This study aims at testing the reliability of a protocol for 3D-3D registration of facial models, potentially useful for personal identification. Fifty male subjects aged between 18 and 45 years were randomly chosen from a database of 3D facial models acquired through stereophotogrammetry. For each subject, two acquisitions were available; the 3D models of faces were then registered onto other models belonging to the same and different individuals according to the least point-to-point distance on the entire facial surface, for a total of 50 matches and 50 mismatches. RMS value (root mean square) of point-to-point distance between the two models was then calculated through the VAM® software. Intra- and inter-observer errors were assessed through calculation of relative technical error of measurement (rTEM). Possible statistically significant differences between matches and mismatches were assessed through Mann–Whitney test (p < 0.05). Both for intra- and inter-observer repeatability rTEM was between 2.2 and 5.2%. Average RMS point-to-point distance was 0.50 ± 0.28 mm in matches, 2.62 ± 0.56 mm in mismatches (p < 0.01). An RMS threshold of 1.50 mm could distinguish matches and mismatches in 100% of cases. This study provides an improvement to existing 3D-3D superimposition methods and confirms the great advantages which may derive to personal identification of the living from 3D facial analysis.

Computerized delineation of the teeth and comparison with a smiling photograph: identification of a body skeletonized by cadaverous ichthyofauna action

Amazonian's forensic experts usually experience considerable difficulties in the identification of drowned bodies rescued from the rivers of the Amazon basin, since they are frequently found skeletonized by the action of the cadaverous ichthyofauna. In these circumstances, especially when the soft tissues are completely absent, bones and teeth may represent the unique source of information for the identification of the body. This work reports a case of positive identification of a body skeletonized by scavenger ichthyofauna. The identification was performed by comparing computerized delineation of the dental characteristics of the cadaver with those observed in a smiling photograph of the victim. This report also highlights the ferocity of Cetopsis candiru (candiru cobra), Cetopsis coecutiens (candiru-açu) and Calophysus macropterus (piracatinga).

Validation of forensic facial comparison by morphological analysis in photographic and CCTV samples

Between the ever-increasing availability of surveillance evidence and expert-based forensic facial comparison being considered admissible in court, confirming its validity is paramount. Facial comparison is most commonly conducted using morphological analysis (MA), a largely untested feature-based approach. This study aimed at validating the current recommended practice of MA in both standardised and suboptimal surveillance samples. Face pools of 175 South African males were compiled with a series of facial photographs, using images from the Wits Face Database. The first 75 face pools consisted of wildtype (unstandardised) high-quality target photographs, while the remaining 100 face pools consisted of suboptimal closed-circuit television (CCTV) target images. Target images were compared to high-quality standardised photographs. Face pools were analysed using the Facial Identification Scientific Working Group's guidelines and feature list. Confusion matrices were used to determine the performance of MA in each cohort. MA was found highly accurate (chance-corrected accuracy (CCA): 99.1%) and reliable (κ = 0.921) in the photographic sample and less accurate (CCA: 82.6%) and reliable (κ = 0.743), in the CCTV sample. Higher false-positive and false-negative rates were noted for the CCTV sample, with the majority of errors resulting in false-negative outcomes. The decreased performance in the CCTV sample was attributed to various factors including image quality, angle of recording and lighting. Other studies testing facial comparison identified lower accuracies and reliability across various conditions. Better performance was found here and in other studies that included some form of facial feature list, reinforcing the importance of using a systematic facial feature list.

Forensic anthropological video-based cases at the Department of Forensic Medicine, University of Copenhagen: a 10-year retrospective review

In criminal cases where there is a lack of evidence, the authorities sometimes ask our department to make a comparison of a criminal and suspect for possible identification or exclusion. This paper provides a comprehensive overview of 113 such cases analysed by the Department of Forensic Medicine, University of Copenhagen, Denmark in 2006–2016. The aims of the analyses were to assist the authorities in identifying individuals, predominantly due to a suspicion of involvement in criminal activity. The videos comprised surveillance footage showing a criminal committing a criminal act. Based on comparisons of specific parameters, such as face, gait and general body proportions, conclusions were drawn on the plausibly of a suspect being the perpetrator of the crime in the video footage. This paper describes the most typical case: a comparison of one suspect with one criminal committing a robbery. In the majority of cases, the suspect could not be excluded from being the criminal based on the analysis of the video footage.

The repeatability and reproducibility of the Sheffield Features of Gait Tool

Gait, the pattern or style in which locomotion is undertaken, has kinematic characteristics that may occur in varying proportions of a population and therefore have discriminatory potential. Forensic gait analysis is the analysis, comparison and evaluation of features of gait to assist the investigation of crime. While there have been recent developments in automated gait recognition systems, gait analysis presented in criminal court to assist in identification currently relies on observational analysis by expert witnesses. Observational gait analysis has been the focus of considerable research, and it has been shown that the adoption of a systematic approach to both the observation and recording of features of gait improves the reliability of the analysis. The Sheffield Features of Gait Tool was developed by forensic gait analysis practitioners based on their casework and trial experience, and consists of more than a hundred features of gait and variances. This paper reports the findings of a study undertaken to assess the repeatability and reproducibility of the Sheffield Features of Gait Tool. Fourteen participants, with experience in observational gait analysis, viewed footage of computer generated avatars walking, and completed the features of gait tool on multiple occasions. The repeatability scores varied between participants from a highest score of 42.59 out of a maximum possible score of 45 (94.65%), to a lowest score of 30.76 (68.35%), with a mean score of 35.79 (79.54%) and a standard deviation of 3.59 (7.98%). The reproducibility scores for the assessment of each avatar varied from a highest score of 137.73 out of the best possible score of 180 (76.52%), to a lowest score of 127.21 (70.67%), with a mean score of 132.21 (73.45) and a standard deviation of 3.82 (2.12%). The results demonstrated that the use of the Sheffield Features of Gait Tool by experienced analysists resulted in what could be considered to be good levels of both repeatability and reproducibility. Some variation was shown to occur both between the results produced by different analysts, and between those produced from the analysis of different avatars. An understanding of the probative value of gait analysis evidence is an important facet of its submission as evidence, and the design and testing of standardized methods of analysis and comparison are an essential element of developing that understanding. This study is the first to test a purpose designed features of gait tool for use in forensic gait analysis.

Personal Identification of Deceased Persons: An Overview of the Current Methods Based on Physical Appearance

The use of the physical appearance of the deceased has become more important because the available antemortem information for comparisons may consist only of a physical description and photographs. Twenty-one articles dealing with the identification based on the physiognomic features of the human body were selected for review and were divided into four sections: (i) visual recognition, (ii) specific facial/body areas, (iii) biometrics, and (iv) dental superimposition. While opinions about the reliability of the visual recognition differ, the search showed that it has been used in mass disasters, even without testing its objectivity and reliability. Specific facial areas being explored for the identification of dead; however, their practical use is questioned, similarly to soft biometrics. The emerging dental superimposition seems to be the only standardized and successfully applied method for identification so far. More research is needed into a potential use of the individualizing features, considering that postmortem changes and technical difficulties may affect the identification.

Child trafficking and the European migration crisis: The role of forensic practitioners

Trafficking in children is one of the worst forms of human rights violation and is categorised as a serious crime. Children at high risk of becoming victims of trafficking are runaways, children with a history of abuse, and migrant children. Internationally, cases of child trafficking are increasing the most in Europe, which is likely the result of the current migration crisis. In crises, preventing and combating human trafficking needs to be prioritized, considering that the aims of humanitarian action include saving lives, easing suffering and preserving human dignity. The involvement of forensic practitioners in investigations of cases of child trafficking mainly concerning the identification of victims may save lives and certainly alleviate suffering of the child victims and their families searching for them. Moreover, by aiding the prosecution process through thorough documentation and expert reporting forensic practitioners may contribute to the protection, rehabilitation and possibly compensation of the child victims, and thus to the restoration of their rights and dignity. So far, forensic practitioners were rarely specifically mentioned as actors in the counter-trafficking efforts in the multitude of policies, regulations, guidelines and recommendations concerning different aspects of child trafficking. This seems surprising considering that the expertise and experience of practitioners from forensic sciences including cyber forensics, document analysis, forensic biology, anthropology, and medicine can be utilised for gathering intelligence in cases of suspected human trafficking, for identifying the victims as well as perpetrators, and for securing evidence for legal proceedings as this paper shows. While this article mainly discusses the role of forensic pathologists and anthropologists, with a specific focus on the identification of child victims of trafficking in the context of the European migration crisis, the notions regarding the contribution of forensic sciences to the counter-trafficking efforts can be adapted to other geographical and sociopolitical contexts.

Application of 3D models of palatal rugae to personal identification: hints at identification from 3D-3D superimposition techniques

Palatal rugae are known in literature as individualizing anatomical structures with a strong potential for personal identification. However, a 3D assessment of their uniqueness has not yet been performed. The present study aims at verifying the uniqueness of 3D models of the palate. Twenty-six subjects were recruited among the orthodontic patients of a private dental office; from every patient, at least two dental casts were taken in different time periods, for a total of 62 casts. Dental casts were digitized by a 3D laser scanner (iSeries, Dental Wings©, Montreal, Canada). The palatal area was identified, and a series of 250 superimpositions was then performed automatically through VAM©software in order to reach the minimum point-to point distance between two models. In 36 matches the models belonged to the same individual, whereas in 214 mismatches they came from different subjects. The RMS (root mean square) of point-to-point distances was then calculated by 3D software. Possible statistically significant differences were assessed through Mann-Whitney test (p < 0.05). Results showed a statistically significant difference in RMS mean point-to-point distance between matches (mean 0.26 mm; SD 0.12) and mismatches (mean 1.30; SD 0.44) (p < 0.0001).All matches reached an RMS value below 0.50 mm. This study first provided an assessment of uniqueness of palatal rugae, based on their anatomical 3D conformations, with consequent applications to personal identification.