Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Edition

This paper describes the results of the 2023 edition of the ''LivDet'' series of iris presentation attack detection (PAD) competitions. New elements in this fifth competition include (1) GAN-generated iris images as a category of presentation attack instruments (PAI), and (2) an evaluation of human accuracy at detecting PAI as a reference benchmark. Clarkson University and the University of Notre Dame contributed image datasets for the competition, composed of samples representing seven different PAI categories, as well as baseline PAD algorithms. Fraunhofer IGD, Beijing University of Civil Engineering and Architecture, and Hochschule Darmstadt contributed results for a total of eight PAD algorithms to the competition. Accuracy results are analyzed by different PAI types, and compared to human accuracy. Overall, the Fraunhofer IGD algorithm, using an attention-based pixel-wise binary supervision network, showed the best-weighted accuracy results (average classification error rate of 37.31%), while the Beijing University of Civil Engineering and Architecture's algorithm won when equal weights for each PAI were given (average classification rate of 22.15%). These results suggest that iris PAD is still a challenging problem.

Promoting Generalization in Cross-Dataset Remote Photoplethysmography

Remote Photoplethysmography (rPPG), or the remote monitoring of a subject's heart rate using a camera, has seen a shift from handcrafted techniques to deep learning models. While current solutions offer substantial performance gains, we show that these models tend to learn a bias to pulse wave features inherent to the training dataset. We develop augmentations to mitigate this learned bias by expanding both the range and variability of heart rates that the model sees while training, resulting in improved model convergence when training and cross-dataset generalization at test time. Through a 3-way cross dataset analysis we demonstrate a reduction in mean absolute error from over 13 beats per minute to below 3 beats per minute. We compare our method with other recent rPPG systems, finding similar performance under a variety of evaluation parameters.

Full-Body Cardiovascular Sensing with Remote Photoplethysmography

Remote photoplethysmography (rPPG) allows for noncontact monitoring of blood volume changes from a camera by detecting minor fluctuations in reflected light. Prior applications of rPPG focused on face videos. In this paper we explored the feasibility of rPPG from non-face body regions such as the arms, legs, and hands. We collected a new dataset titled Multi-Site Physiological Monitoring (MSPM), which will be released with this paper. The dataset consists of 90 frames per second video of exposed arms, legs, and face, along with 10 synchronized PPG recordings. We performed baseline heart rate estimation experiments from non-face regions with several state-of-the-art rPPG approaches, including chrominance-based (CHROM), plane-orthogonal-to-skin (POS) and RemotePulseNet (RPNet). To our knowledge, this is the first evaluation of the fidelity of rPPG signals simultaneously obtained from multiple regions of a human body. Our experiments showed that skin pixels from arms, legs, and hands are all potential sources of the blood volume pulse. The best-performing approach, POS, achieved a mean absolute error peaking at 7.11 beats per minute from non-facial body parts compared to 1.38 beats per minute from the face. Additionally, we performed experiments on pulse transit time (PTT) from both the contact PPG and rPPG signals. We found that remote PTT is possible with moderately high frame rate video when distal locations on the body are visible. These findings and the supporting dataset should facilitate new research on non-face rPPG and monitoring blood flow dynamics over the whole body with a camera.

Non-Contrastive Unsupervised Learning of Physiological Signals from Video

Subtle periodic signals such as blood volume pulse and respiration can be extracted from RGB video, enabling remote health monitoring at low cost. Advancements in remote pulse estimation -- or remote photoplethysmography (rPPG) -- are currently driven by deep learning solutions. However, modern approaches are trained and evaluated on benchmark datasets with associated ground truth from contact-PPG sensors. We present the first non-contrastive unsupervised learning framework for signal regression to break free from the constraints of labelled video data. With minimal assumptions of periodicity and finite bandwidth, our approach is capable of discovering the blood volume pulse directly from unlabelled videos. We find that encouraging sparse power spectra within normal physiological bandlimits and variance over batches of power spectra is sufficient for learning visual features of periodic signals. We perform the first experiments utilizing unlabelled video data not specifically created for rPPG to train robust pulse rate estimators. Given the limited inductive biases and impressive empirical results, the approach is theoretically capable of discovering other periodic signals from video, enabling multiple physiological measurements without the need for ground truth signals. Codes to fully reproduce the experiments are made available along with the paper.

Hallucinated Heartbeats: Anomaly-Aware Remote Pulse Estimation

Camera-based physiological monitoring, especially remote photoplethysmography (rPPG), is a promising tool for health diagnostics, and state-of-the-art pulse estimators have shown impressive performance on benchmark datasets. We argue that evaluations of modern solutions may be incomplete, as we uncover failure cases for videos without a live person, or in the presence of severe noise. We demonstrate that spatiotemporal deep learning models trained only with live samples "hallucinate" a genuine-shaped pulse on anomalous and noisy videos, which may have negative consequences when rPPG models are used by medical personnel. To address this, we offer: (a) An anomaly detection model, built on top of the predicted waveforms. We compare models trained in open-set (unknown abnormal predictions) and closed-set (abnormal predictions known when training) settings; (b) An anomaly-aware training regime that penalizes the model for predicting periodic signals from anomalous videos. Extensive experimentation with eight research datasets (rPPG-specific: DDPM, CDDPM, PURE, UBFC, ARPM; deep fakes: DFDC; face presentation attack detection: HKBU-MARs; rPPG outlier: KITTI) show better accuracy of anomaly detection for deep learning models incorporating the proposed training (75.8%), compared to models trained regularly (73.7%) and to hand-crafted rPPG methods (52-62%).

Haven't I Seen You Before? Assessing Identity Leakage in Synthetic Irises

Generative Adversarial Networks (GANs) have proven to be a preferred method of synthesizing fake images of objects, such as faces, animals, and automobiles. It is not surprising these models can also generate ISO-compliant, yet synthetic iris images, which can be used to augment training data for iris matchers and liveness detectors. In this work, we trained one of the most recent GAN models (StyleGAN3) to generate fake iris images with two primary goals: (i) to understand the GAN's ability to produce "never-before-seen" irises, and (ii) to investigate the phenomenon of identity leakage as a function of the GAN's training time. Previous work has shown that personal biometric data can inadvertently flow from training data into synthetic samples, raising a privacy concern for subjects who accidentally appear in the training dataset. This paper presents analysis for three different iris matchers at varying points in the GAN training process to diagnose where and when authentic training samples are in jeopardy of leaking through the generative process. Our results show that while most synthetic samples do not show signs of identity leakage, a handful of generated samples match authentic (training) samples nearly perfectly, with consensus across all matchers. In order to prioritize privacy, security, and trust in the machine learning model development process, the research community must strike a delicate balance between the benefits of using synthetic data and the corresponding threats against privacy from potential identity leakage.

Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines

Programming Language Processing (PLP) using machine learning has made vast improvements in the past few years. Increasingly more people are interested in exploring this promising field. However, it is challenging for new researchers and developers to find the right components to construct their own machine learning pipelines, given the diverse PLP tasks to be solved, the large number of datasets and models being released, and the set of complex compilers or tools involved. To improve the findability, accessibility, interoperability and reusability (FAIRness) of machine learning components, we collect and analyze a set of representative papers in the domain of machine learning-based PLP. We then identify and characterize key concepts including PLP tasks, model architectures and supportive tools. Finally, we show some example use cases of leveraging the reusable components to construct machine learning pipelines to solve a set of PLP tasks.

Analyzing the Impact of Shape & Context on the Face Recognition Performance of Deep Networks

In this article, we analyze how changing the underlying 3D shape of the base identity in face images can distort their overall appearance, especially from the perspective of deep face recognition. As done in popular training data augmentation schemes, we graphically render real and synthetic face images with randomly chosen or best-fitting 3D face models to generate novel views of the base identity. We compare deep features generated from these images to assess the perturbation these renderings introduce into the original identity. We perform this analysis at various degrees of facial yaw with the base identities varying in gender and ethnicity. Additionally, we investigate if adding some form of context and background pixels in these rendered images, when used as training data, further improves the downstream performance of a face recognition model. Our experiments demonstrate the significance of facial shape in accurate face matching and underpin the importance of contextual data for network training.

Interpretable Deep Learning-Based Forensic Iris Segmentation and Recognition

Iris recognition of living individuals is a mature biometric modality that has been adopted globally from governmental ID programs, border crossing, voter registration and de-duplication, to unlocking mobile phones. On the other hand, the possibility of recognizing deceased subjects with their iris patterns has emerged recently. In this paper, we present an end-to-end deep learning-based method for postmortem iris segmentation and recognition with a special visualization technique intended to support forensic human examiners in their efforts. The proposed postmortem iris segmentation approach outperforms the state of the art and in addition to iris annulus, as in case of classical iris segmentation methods - detects abnormal regions caused by eye decomposition processes, such as furrows or irregular specular highlights present on the drying and wrinkling cornea. The method was trained and validated with data acquired from 171 cadavers, kept in mortuary conditions, and tested on subject-disjoint data acquired from 259 deceased subjects. To our knowledge, this is the largest corpus of data used in postmortem iris recognition research to date. The source code of the proposed method are offered with the paper. The test data will be available through the National Archive of Criminal Justice Data (NACJD) archives.