Search

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.

Forensic iris recognition, as opposed to live iris recognition, is an emerging research area that leverages the discriminative power of iris biometrics to aid human examiners in their efforts to identify deceased persons. As a machine learning-based technique in a predominantly human-controlled task, forensic recognition serves as "back-up" to human expertise in the task of post-mortem identification. As such, the machine learning model must be (a) interpretable, and (b) post-mortem-specific, to account for changes in decaying eye tissue. In this work, we propose a method that satisfies both requirements, and that approaches the creation of a post-mortem-specific feature extractor in a novel way employing human perception. We first train a deep learning-based feature detector on post-mortem iris images, using annotations of image regions highlighted by humans as salient for their decision making. In effect, the method learns interpretable features directly from humans, rather than purely data-driven features. Second, regional iris codes (again, with human-driven filtering kernels) are used to pair detected iris patches, which are translated into pairwise, patch-based comparison scores. In this way, our method presents human examiners with human-understandable visual cues in order to justify the identification decision and corresponding confidence score. When tested on a dataset of post-mortem iris images collected from 259 deceased subjects, the proposed method places among the three best iris matchers, demonstrating better results than the commercial (non-human-interpretable) VeriEye approach. We propose a unique post-mortem iris recognition method trained with human saliency to give fully-interpretable comparison outcomes for use in the context of forensic examination, achieving state-of-the-art recognition performance.

It is broadly accepted that there is a "gender gap" in face recognition accuracy, with females having higher false match and false non-match rates. However, relatively little is known about the cause(s) of this gender gap. Even the recent NIST report on demographic effects lists "analyze cause and effect" under "what we did not do". We first demonstrate that female and male hairstyles have important differences that impact face recognition accuracy. In particular, compared to females, male facial hair contributes to creating a greater average difference in appearance between different male faces. We then demonstrate that when the data used to estimate recognition accuracy is balanced across gender for how hairstyles occlude the face, the initially observed gender gap in accuracy largely disappears. We show this result for two different matchers, and analyzing images of Caucasians and of African-Americans. These results suggest that future research on demographic variation in accuracy should include a check for balanced quality of the test data as part of the problem formulation. To promote reproducible research, matchers, attribute classifiers, and datasets used in this research are/will be publicly available.

We explore varying face recognition accuracy across demographic groups as a phenomenon partly caused by differences in face illumination. We observe that for a common operational scenario with controlled image acquisition, there is a large difference in face region brightness between African-American and Caucasian, and also a smaller difference between male and female. We show that impostor image pairs with both faces under-exposed, or both overexposed, have an increased false match rate (FMR). Conversely, image pairs with strongly different face brightness have a decreased similarity measure. We propose a brightness information metric to measure variation in brightness in the face and show that face brightness that is too low or too high has reduced information in the face region, providing a cause for the lower accuracy. Based on this, for operational scenarios with controlled image acquisition, illumination should be adjusted for each individual to obtain appropriate face image brightness. This is the first work that we are aware of to explore how the level of brightness of the skin region in a pair of face images (rather than a single image) impacts face recognition accuracy, and to evaluate this as a systematic factor causing unequal accuracy across demographics. The code is at https://github.com/HaiyuWu/FaceBrightness.

In our data-centric world, most services rely on collecting and using personal data. The EU's General Data Protection Regulation (GDPR) aims to enhance individuals' control over their data, but its practical impact is not well understood. We present a 10-participant study, where each participant filed 4-5 data access requests. Through interviews accompanying these requests and discussions scrutinising returned data, it appears that GDPR falls short of its goals due to non-compliance and low-quality responses. Participants found their hopes to understand providers' data practices or harness their own data unmet. This causes increased distrust without any subjective improvement in power, although more transparent providers do earn greater trust. We propose designing more effective, data-inclusive and open policies and data access systems to improve both customer relations and individual agency, and also that wider public use of GDPR rights could help with delivering accountability and motivating providers to improve data practices., Comment: 19 pages, to be published in CHI Conference on Human Factors in Computing Systems (CHI '22), April 29 - May 05, 2022, New Orleans, LA, USA

In robotic-assisted partial nephrectomy, surgeons remove a part of a kidney often due to the presence of a mass. A drop-in ultrasound probe paired to a surgical robot is deployed to execute multiple swipes over the kidney surface to localise the mass and define the margins of resection. This sub-task is challenging and must be performed by a highly skilled surgeon. Automating this sub-task may reduce cognitive load for the surgeon and improve patient outcomes. The overall goal of this work is to autonomously move the ultrasound probe on the surface of the kidney taking advantage of the use of the Pneumatically Attachable Flexible (PAF) rail system, a soft robotic device used for organ scanning and repositioning. First, we integrate a shape-sensing optical fibre into the PAF rail system to evaluate the curvature of target organs in robotic-assisted laparoscopic surgery. Then, we investigate the impact of the stiffness of the material of the PAF rail on the curvature sensing accuracy, considering that soft targets are present in the surgical field. Finally, we use shape sensing to plan the trajectory of the da Vinci surgical robot paired with a drop-in ultrasound probe and autonomously generate an Ultrasound scan of a kidney phantom., Comment: 9 pages, 11 figures

Media reports have accused face recognition of being ''biased'', ''sexist'' and ''racist''. There is consensus in the research literature that face recognition accuracy is lower for females, who often have both a higher false match rate and a higher false non-match rate. However, there is little published research aimed at identifying the cause of lower accuracy for females. For instance, the 2019 Face Recognition Vendor Test that documents lower female accuracy across a broad range of algorithms and datasets also lists ''Analyze cause and effect'' under the heading ''What we did not do''. We present the first experimental analysis to identify major causes of lower face recognition accuracy for females on datasets where previous research has observed this result. Controlling for equal amount of visible face in the test images mitigates the apparent higher false non-match rate for females. Additional analysis shows that makeup-balanced datasets further improves females to achieve lower false non-match rates. Finally, a clustering experiment suggests that images of two different females are inherently more similar than of two different males, potentially accounting for a difference in false match rates., Comment: arXiv admin note: substantial text overlap with arXiv:2008.06989

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.

Can deep learning models achieve greater generalization if their training is guided by reference to human perceptual abilities? And how can we implement this in a practical manner? This paper proposes a training strategy to ConveY Brain Oversight to Raise Generalization (CYBORG). This new approach incorporates human-annotated saliency maps into a loss function that guides the model's learning to focus on image regions that humans deem salient for the task. The Class Activation Mapping (CAM) mechanism is used to probe the model's current saliency in each training batch, juxtapose this model saliency with human saliency, and penalize large differences. Results on the task of synthetic face detection, selected to illustrate the effectiveness of the approach, show that CYBORG leads to significant improvement in accuracy on unseen samples consisting of face images generated from six Generative Adversarial Networks across multiple classification network architectures. We also show that scaling to even seven times the training data, or using non-human-saliency auxiliary information, such as segmentation masks, and standard loss cannot beat the performance of CYBORG-trained models. As a side effect of this work, we observe that the addition of explicit region annotation to the task of synthetic face detection increased human classification accuracy. This work opens a new area of research on how to incorporate human visual saliency into loss functions in practice. All data, code and pre-trained models used in this work are offered with this paper.

Advances in face synthesis have raised alarms about the deceptive use of synthetic faces. Can synthetic identities be effectively used to fool human observers? In this paper, we introduce a study of the human perception of synthetic faces generated using different strategies including a state-of-the-art deep learning-based GAN model. This is the first rigorous study of the effectiveness of synthetic face generation techniques grounded in experimental techniques from psychology. We answer important questions such as how often do GAN-based and more traditional image processing-based techniques confuse human observers, and are there subtle cues within a synthetic face image that cause humans to perceive it as a fake without having to search for obvious clues? To answer these questions, we conducted a series of large-scale crowdsourced behavioral experiments with different sources of face imagery. Results show that humans are unable to distinguish synthetic faces from real faces under several different circumstances. This finding has serious implications for many different applications where face images are presented to human users.

Remote photoplethysmography (rPPG) is a technique for estimating blood volume changes from reflected light without the need for a contact sensor. We present the first examples of presentation attacks in the digital and physical domains on rPPG from face video. Digital attacks are easily performed by adding imperceptible periodic noise to the input videos. Physical attacks are performed with illumination from visible spectrum LEDs placed in close proximity to the face, while still being difficult to perceive with the human eye. We also show that our attacks extend beyond medical applications, since the method can effectively generate a strong periodic pulse on 3D-printed face masks, which presents difficulties for pulse-based face presentation attack detection (PAD). The paper concludes with ideas for using this work to improve robustness of rPPG methods and pulse-based face PAD.

Large detectors employing xenon are a leading technology in existing and planned searches for new physics, including searches for neutrinoless double beta decay ($0\nu\beta\beta$) and dark matter. While upcoming detectors will employ target masses of a ton or more, further extending gas or liquid phase Xe detectors to the kton scale would enable extremely sensitive next-generation searches for rare phenomena. The key challenge to extending this technology to detectors well beyond the ton scale is the acquisition of the Xe itself. We describe the motivation for extending Xe time projection chambers (TPCs) to the kton scale and possible avenues for Xe acquisition that avoid existing supply chains. If acquisition of Xe in the required quantities is successful, kton-scale detectors of this type could enable a new generation of experiments, including searches for $0\nu\beta\beta$ at half-life sensitivities as long as $10^{30}$ yr., Comment: 19 pages, 10 figures; published version

POMDPs are useful models for systems where the true underlying state is not known completely to an outside observer; the outside observer incompletely knows the true state of the system, and observes a noisy version of the true system state. When the number of system states is large in a POMDP that often necessitates the use of approximation methods to obtain near optimal solutions for control. This survey is centered around the origins, theory, and approximations of finite-state POMDPs. In order to understand POMDPs, it is required to have an understanding of finite-state Markov Decision Processes (MDPs) in \autoref{mdp} and Hidden Markov Models (HMMs) in \autoref{hmm}. For this background theory, I provide only essential details on MDPs and HMMs and leave longer expositions to textbook treatments before diving into the main topics of POMDPs. Once the required background is covered, the POMDP is introduced in \autoref{pomdp}. The origins of the POMDP are explained in the classical papers section \autoref{classical}. Once the high computational requirements are understood from the exact methodological point of view, the main approximation methods are surveyed in \autoref{approximations}. Then, I end the survey with some new research directions in \autoref{conclusion}.

We present the Deception Detection and Physiological Monitoring (DDPM) dataset and initial baseline results on this dataset. Our application context is an interview scenario in which the interviewee attempts to deceive the interviewer on selected responses. The interviewee is recorded in RGB, near-infrared, and long-wave infrared, along with cardiac pulse, blood oxygenation, and audio. After collection, data were annotated for interviewer/interviewee, curated, ground-truthed, and organized into train / test parts for a set of canonical deception detection experiments. Baseline experiments found random accuracy for micro-expressions as an indicator of deception, but that saccades can give a statistically significant response. We also estimated subject heart rates from face videos (remotely) with a mean absolute error as low as 3.16 bpm. The database contains almost 13 hours of recordings of 70 subjects, and over 8 million visible-light, near-infrared, and thermal video frames, along with appropriate meta, audio and pulse oximeter data. To our knowledge, this is the only collection offering recordings of five modalities in an interview scenario that can be used in both deception detection and remote photoplethysmography research., Comment: The dataset will be available for download at https://cvrl.nd.edu/projects/data/#deception-detection-and-physiological-monitoringddpm

The reinforcement learning problem of finding a control policy that minimizes the minimum time objective for the Mountain Car environment is considered. Particularly, a class of parameterized nonlinear feedback policies is optimized over to reach the top of the highest mountain peak in minimum time. The optimization is carried out using quasi-Stochastic Gradient Descent (qSGD) methods. In attempting to find the optimal minimum time policy, a new parameterized policy approach is considered that seeks to learn an optimal policy parameter for different regions of the state space, rather than rely on a single macroscopic policy parameter for the entire state space. This partitioned parameterized policy approach is shown to outperform the uniform parameterized policy approach and lead to greater generalization than prior methods, where the Mountain Car became trapped in circular trajectories in the state space.

Deep learning has driven remarkable accuracy increases in many computer vision problems. One ongoing challenge is how to achieve the greatest accuracy in cases where training data is limited. A second ongoing challenge is that trained models oftentimes do not generalize well even to new data that is subjectively similar to the training set. We address these challenges in a novel way, with the first-ever (to our knowledge) exploration of encoding human judgement about salient regions of images into the training data. We compare the accuracy and generalization of a state-of-the-art deep learning algorithm for a difficult problem in biometric presentation attack detection when trained on (a) original images with typical data augmentations, and (b) the same original images transformed to encode human judgement about salient image regions. The latter approach results in models that achieve higher accuracy and better generalization, decreasing the error of the LivDet-Iris 2020 winner from 29.78% to 16.37%, and achieving impressive generalization in a leave-one-attack-type-out evaluation scenario. This work opens a new area of study for how to embed human intelligence into training strategies for deep learning to achieve high accuracy and generalization in cases of limited training data., Comment: To appear at WACV 2022

News reports have suggested that darker skin tone causes an increase in face recognition errors. The Fitzpatrick scale is widely used in dermatology to classify sensitivity to sun exposure and skin tone. In this paper, we analyze a set of manual Fitzpatrick skin type assignments and also employ the individual typology angle to automatically estimate the skin tone from face images. The set of manual skin tone rating experiments shows that there are inconsistencies between human raters that are difficult to eliminate. Efforts to automate skin tone rating suggest that it is particularly challenging on images collected without a calibration object in the scene. However, after the color-correction, the level of agreement between automated and manual approaches is found to be 96% or better for the MORPH images. To our knowledge, this is the first work to: (a) examine the consistency of manual skin tone ratings across observers, (b) document that there is substantial variation in the rating of the same image by different observers even when exemplar images are given for guidance and all images are color-corrected, and (c) compare manual versus automated skin tone ratings.