Bridging the gap: from biometrics to forensics

Post-mortem iris biometrics - Field, applications and methods

Post-mortem iris recognition (PMIR) is a recently developed area of expertise falling into the broader category of biometric methods utilizing human iris features for the purpose of automatic or semi-automatic establishing or confirming one's identity. Yet, contrary to traditional iris recognition applied to living individuals, post-mortem biometrics presents forensic experts and scientists with challenges that have previously been unknown and require novel approaches and development of new skills. This paper summarizes the current state of the art of research in this area, both with respect to studies exploring the feasibility of iris recognition in a forensic setting, as well as the challenges still pervasive in the scientific community and potential ways to overcome them. We argue that post-mortem iris biometrics can serve both as a way for improving iris recognition, as well as provide forensic examiners tools for extending knowledge and skills in their respective field.

Channel and Spatial Attention in Chest X-Ray Radiographs: Advancing Person Identification and Verification with Self-Residual Attention Network

BACKGROUND/OBJECTIVES

In contrast to traditional biometric modalities, such as facial recognition, fingerprints, and iris scans or even DNA, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual's skeletal structure, the ribcage of the chest, lungs, and heart, chest X-rays have emerged as a focal point for identification and verification, especially in the forensic field, even in scenarios where the human body damaged or disfigured. Discriminative feature embedding is essential for large-scale image verification, especially in applying chest X-ray radiographs for identity identification and verification. This study introduced a self-residual attention-based convolutional neural network (SRAN) aimed at effective feature embedding, capturing long-range dependencies and emphasizing critical spatial features in chest X-rays. This method offers a novel approach to person identification and verification through chest X-ray categorization, relevant for biometric applications and patient care, particularly when traditional biometric modalities are ineffective.

METHOD

The SRAN architecture integrated a self-channel and self-spatial attention module to minimize channel redundancy and enhance significant spatial elements. The attention modules worked by dynamically aggregating feature maps across channel and spatial dimensions to enhance feature differentiation. For the network backbone, a self-residual attention block (SRAB) was implemented within a ResNet50 framework, forming a Siamese network trained with triplet loss to improve feature embedding for identity identification and verification.

RESULTS

By leveraging the NIH ChestX-ray14 and CheXpert datasets, our method demonstrated notable improvements in accuracy for identity verification and identification based on chest X-ray images. This approach effectively captured the detailed anatomical characteristics of individuals, including skeletal structure, ribcage, lungs, and heart, highlighting chest X-rays as a viable biometric tool even in cases of body damage or disfigurement.

CONCLUSIONS

The proposed SRAN with self-residual attention provided a promising solution for biometric identification through chest X-ray imaging, showcasing its potential for accurate and reliable identity verification where traditional biometric approaches may fall short, especially in postmortem cases or forensic investigations. This methodology could play a transformative role in both biometric security and healthcare applications, offering a robust alternative modality for identity verification.

Artist profiling using micro-CT scanning of a Rijksmuseum terracotta sculpture

In the fine arts, impressions found on terracotta sculptures in museum collections are scarcely reported and not in a systematic manner. Here, we present a procedure for scanning fingermarks and toolmarks found on the visible surface and inner walls of a terracotta sculpture using 3D micro-computed tomography, as well as methods for quantitatively characterizing these impressions. We apply our pipeline on the terracotta sculpture Study for a Hovering Putto, attributed to Laurent Delvaux and housed in the Rijksmuseum collection. On the basis of combined archaeology and forensics research that assigns age groups to makers of European ancestry from ridge breadth values, we estimate that the fingermarks belong to an adult male. Given that each fingerprint is unique and the carving tools were exclusively made in the artist's workshop, we give incentive to aim for artist profiling using innovative computational approaches on preserved impressions from terracotta sculptures.

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

The fingerprint is a widely adopted biometric trait in forensic and civil applications. Fingerprint biometric systems have been investigated using contact prints and latent and contactless images which range from low to high resolution. While the imaging techniques are advancing with sensor variations, the input fingerprint images also vary. A general fingerprint recognition pipeline consists of a sensor module to acquire images, followed by feature representation, matching and decision modules. In the sensor module, the image quality of the biometric traits significantly affects the biometric system's accuracy and performance. Imaging modality, such as contact and contactless, plays a key role in poor image quality, and therefore, paying attention to imaging modality is important to obtain better performance. Further, underlying physical principles and the working of the sensor can lead to their own forms of distortions during acquisition. There are certain challenges in each module of the fingerprint recognition pipeline, particularly sensors, image acquisition and feature representation. Present reviews in fingerprint systems only analyze the imaging techniques in fingerprint sensing that have existed for a decade. However, the latest emerging trends and recent advances in fingerprint sensing, image acquisition and their challenges have been left behind. Since the present reviews are either obsolete or restricted to a particular subset of the fingerprint systems, this work comprehensively analyzes the state of the art in the field of contact-based, contactless 2D and 3D fingerprint systems and their challenges in the aspects of sensors, image acquisition and interoperability. It outlines the open issues and challenges encountered in fingerprint systems, such as fingerprint performance, environmental factors, acceptability and interoperability, and alternate directions are proposed for a better fingerprint system.

Ensemble of Heterogeneous Base Classifiers for Human Gait Recognition

Human gait recognition is one of the most interesting issues within the subject of behavioral biometrics. The most significant problems connected with the practical application of biometric systems include their accuracy as well as the speed at which they operate, understood both as the time needed to recognize a particular person as well as the time necessary to create and train a biometric system. The present study made use of an ensemble of heterogeneous base classifiers to address these issues. A Heterogeneous ensemble is a group of classification models trained using various algorithms and combined to output an effective recognition A group of parameters identified on the basis of ground reaction forces was accepted as input signals. The proposed solution was tested on a sample of 322 people (5980 gait cycles). Results concerning the accuracy of recognition (meaning the Correct Classification Rate quality at 99.65%), as well as operation time (meaning the time of model construction at <12.5 min and the time needed to recognize a person at <0.1 s), should be considered as very good and exceed in quality other methods so far described in the literature.

Bayesian evaluation of dynamic signatures in operational conditions

Forensic handwriting examiners (FHE) activities are focused on comparative analysis of handwritten objects such as signatures. Their role is to provide and evaluate evidence for and against the authenticity of a questioned signature. In recent years, cases involving handwritten signatures captured on electronic devices have become more commonplace. These so-called 'dynamic signatures' (also known as 'digitally captured signatures') are much different from paper-based signatures. Not only does the medium of recording differ, but also the type, volume of data and features are different from the pattern-based evidence that makes up paper-based signatures. Recent developments in forensic science - including signature examination - have led to the adoption of evaluative probabilistic methodologies in many disciplines [see, e.g. ENFSI 1915 Guidelines]. In the current paper, a probabilistic model to evaluate signature evidence in the form of multivariate data, as proposed and described in Wacom Europe GmbH (2019), is adopted. Topics like data sparsity, joint evaluation of multiple features and feature selection are investigated. Performed experimental studies showed an accuracy rate above 90% even when a limited number (5) of reference signatures was available. The performances of a multivariate approach are compared with those characterizing a so-called multiplicative approach where variables (features) are taken as independent and the Bayes' factor (BF) is obtained as the product of univariate BFs associated to each selected feature. The simplicity of this latter approach is, however, accompanied by severe issues about the reliability of results. The use of a multivariate approach is therefore highly recommended. Finally, the evidential values in correspondence of alternative feature sets are compared. Results suggest that discriminative features are writer-related and necessitate a case-specific selection.

MoLaBSS: Server-Specific Add-On Biometric Security Layer Model to Enhance the Usage of Biometrics

With high-paced growth in biometrics, and its easy availability to capture various biometric features, it is emerging as one of the most valuable technologies for multifactor authentication to verify a user’s identity, for data security. Organizations encourage their members to use biometrics, but they are hesitant to use them due to perceived security risks. Because of its low usage rate, many medium and small segment organizations find it unfeasible to deploy robust biometric systems. We propose a server-specific add-on biometric security layer model (MoLaBSS) to enhance confidence in the usage of biometrics. We tested this model via a biometric mobile app, and the survey showed a favorable response of 80%. The innovative mobile app was tested for its usability and got a score of more than 71%. For test tool reliability, we examined the equal error rate (EER) of the app and got a reasonably low score of 6%. The results show good potential of this framework to enhance users’ confidence level in the usage of biometrics. Higher usage rates may make deployment of biometrics more cost-effective for many organizations to decrease their information security risk.

Recognition of a Person Wearing Sport Shoes or High Heels through Gait Using Two Types of Sensors

Biometrics is currently an area that is both very interesting as well as rapidly growing. Among various types of biometrics the human gait recognition seems to be one of the most intriguing. However, one of the greatest problems within this field of biometrics is the change in gait caused by footwear. A change of shoes results in a significant lowering of accuracy in recognition of people. The following work presents a method which uses data gathered by two sensors: force plates and Microsoft Kinect v2 to reduce this problem. Microsoft Kinect is utilized to measure the body height of a person which allows the reduction of the set of recognized people only to those whose height is similar to that which has been measured. The entire process is preceded by identifying the type of footwear which the person is wearing. The research was conducted on data obtained from 99 people (more than 3400 strides) and the proposed method allowed us to reach a Correct Classification Rate (CCR) greater than 88% which, in comparison to earlier methods reaching CCR’s of <80%, is a significant improvement. The work presents advantages as well as limitations of the proposed method.

Fast Face Sketch–Photo Image Synthesis and Recognition

Face sketch recognition has great practical value in the criminal detection, security and other fields. Especially, it can help the police narrow down potential suspects in criminal detection effectively. Face sketch represents the original photos in a simple and recognizable form, so sketch and photo are images of two different modes. In order to identify the corresponding sketch face image in a lot of photo face images, this paper presents an improved sketch–photo transformation algorithm, and it uses the effective characteristics of the photo image more reasonably during transforming a photo image into sketch. In this way, it can reduce the difference between the sketch and photo image to improve the matching effect, and save the recognition time. Many experiments on CUHK Face Sketch database including 188 sketch–photos prove the effectiveness of the method in this paper.

Perceptual expertise in forensic facial image comparison

Forensic facial identification examiners are required to match the identity of faces in images that vary substantially, owing to changes in viewing conditions and in a person's appearance. These identifications affect the course and outcome of criminal investigations and convictions. Despite calls for research on sources of human error in forensic examination, existing scientific knowledge of face matching accuracy is based, almost exclusively, on people without formal training. Here, we administered three challenging face matching tests to a group of forensic examiners with many years' experience of comparing face images for law enforcement and government agencies. Examiners outperformed untrained participants and computer algorithms, thereby providing the first evidence that these examiners are experts at this task. Notably, computationally fusing responses of multiple experts produced near-perfect performance. Results also revealed qualitative differences between expert and non-expert performance. First, examiners' superiority was greatest at longer exposure durations, suggestive of more entailed comparison in forensic examiners. Second, experts were less impaired by image inversion than non-expert students, contrasting with face memory studies that show larger face inversion effects in high performers. We conclude that expertise in matching identity across unfamiliar face images is supported by processes that differ qualitatively from those supporting memory for individual faces.

Error Rates in Users of Automatic Face Recognition Software

In recent years, wide deployment of automatic face recognition systems has been accompanied by substantial gains in algorithm performance. However, benchmarking tests designed to evaluate these systems do not account for the errors of human operators, who are often an integral part of face recognition solutions in forensic and security settings. This causes a mismatch between evaluation tests and operational accuracy. We address this by measuring user performance in a face recognition system used to screen passport applications for identity fraud. Experiment 1 measured target detection accuracy in algorithm-generated 'candidate lists' selected from a large database of passport images. Accuracy was notably poorer than in previous studies of unfamiliar face matching: participants made over 50% errors for adult target faces, and over 60% when matching images of children. Experiment 2 then compared performance of student participants to trained passport officers-who use the system in their daily work-and found equivalent performance in these groups. Encouragingly, a group of highly trained and experienced "facial examiners" outperformed these groups by 20 percentage points. We conclude that human performance curtails accuracy of face recognition systems-potentially reducing benchmark estimates by 50% in operational settings. Mere practise does not attenuate these limits, but superior performance of trained examiners suggests that recruitment and selection of human operators, in combination with effective training and mentorship, can improve the operational accuracy of face recognition systems.

Error Rates in Users of Automatic Face Recognition Software

In recent years, wide deployment of automatic face recognition systems has been accompanied by substantial gains in algorithm performance. However, benchmarking tests designed to evaluate these systems do not account for the errors of human operators, who are often an integral part of face recognition solutions in forensic and security settings. This causes a mismatch between evaluation tests and operational accuracy. We address this by measuring user performance in a face recognition system used to screen passport applications for identity fraud. Experiment 1 measured target detection accuracy in algorithm-generated 'candidate lists' selected from a large database of passport images. Accuracy was notably poorer than in previous studies of unfamiliar face matching: participants made over 50% errors for adult target faces, and over 60% when matching images of children. Experiment 2 then compared performance of student participants to trained passport officers-who use the system in their daily work-and found equivalent performance in these groups. Encouragingly, a group of highly trained and experienced "facial examiners" outperformed these groups by 20 percentage points. We conclude that human performance curtails accuracy of face recognition systems-potentially reducing benchmark estimates by 50% in operational settings. Mere practise does not attenuate these limits, but superior performance of trained examiners suggests that recruitment and selection of human operators, in combination with effective training and mentorship, can improve the operational accuracy of face recognition systems.