Damon L. Woodard

Head pose estimation in the wild using approximate view manifolds

In this paper, we present a head pose estimation method for unconstrained images using feature-based manifold embedding. The main challenge of manifold embedding methods is to learn a similarity kernel that is reflective of variations only due to head pose and ignore other sources of variation. To address this challenge, we have used the feature correspondences of identity-invariant Geometric Blur features to learn a similarity kernel. To speed up the computation of the similarity kernel, we have used spatial pyramidal matching to approximate feature correspondences and random subsampling of training samples to approximate graph neighborhood. In addition to these approximations, we have used the Nyström approximation to embed out-of-sample test images in an efficient manner. Using these approximations, an approximate view manifold was learned for 14000 images in the Annotated Facial Landmarks in the Wild (AFLW) dataset. With the learned manifold, head pose estimation was performed on four in-the-wild face datasets - AFLW (remaining 7000 images), AFW, McGill and YouTube Faces. The Approximate View Manifold training achieves a 7X speedup compared to the non-approximated Learning-manifold-in-the-wild approach [15]. Further, pose estimation using the proposed approach shows significant improvement in accuracy and reduced Mean Angular Error(MAE) compared to other methods [36, 1, 29] on the challenging AFLW (7041 images), McGill (6833 images) and YouTube Faces (22534 images) datasets.

Surveying Stylometry Techniques and Applications

The analysis of authorial style, termed stylometry, assumes that style is quantifiably measurable for evaluation of distinctive qualities. Stylometry research has yielded several methods and tools over the past 200 years to handle a variety of challenging cases. This survey reviews several articles within five prominent subtasks: authorship attribution, authorship verification, authorship profiling, stylochronometry, and adversarial stylometry. Discussions on datasets, features, experimental techniques, and recent approaches are provided. Further, a current research challenge lies in the inability of authorship analysis techniques to scale to a large number of authors with few text samples. Here, we perform an extensive performance analysis on a corpus of 1,000 authors to investigate authorship attribution, verification, and clustering using 14 algorithms from the literature. Finally, several remaining research challenges are discussed, along with descriptions of various open-source and commercial software that may be useful for stylometry subtasks.

Mobile device application, Bluetooth, and Wi-Fi usage data as behavioral biometric traits

Patterns in the use of mobile devices have the potential to be used as a behavioral biometric for identification of the device user. We explore the distinctiveness and permanence of application, Bluetooth, and Wi-Fi mobile device usage data. Our database consists of data from two hundred mobile phone users collected over a 19-month span. To our knowledge, this is one of the largest databases of its kind. Results of over 500 experiments indicate that user identification rates averaging 80%, 77%, 93%, and 85% are achievable when using application, Bluetooth, Wi-Fi, and the combination of these three types of behavioral features, respectively.

Uncovering Susceptibility Risk to Online Deception in Aging

Objectives Fraud in the aged is an emerging public health problem. An increasingly common form of deception is conducted online. However, identification of cognitive and socioemotional risk factors has not been undertaken yet. In this endeavor, this study extended previous work suggesting age effects on susceptibility to online deception. Methods Susceptibility was operationalized as clicking on the link in simulated spear-phishing emails that young (18-37 years), young-old (62-74 years), and middle-old (75-89 years) Internet users received, without knowing that the emails were part of the study. Participants also indicated for a set of spear-phishing emails how likely they would click on the embedded link (susceptibility awareness) and completed cognitive and socioemotional measures to determine susceptibility risk profiles. Results Higher susceptibility was associated with lower short-term episodic memory in middle-old users and with lower positive affect in young-old and middle-old users. Greater susceptibility awareness was associated with better verbal fluency in middle-old users and with greater positive affect in young and middle-old users. Discussion Short-term memory, verbal fluency, and positive affect in middle-old age may contribute to resilience against online spear-phishing attacks. These results inform mechanisms of online fraud susceptibility and real-life decision-supportive interventions towards fraud risk reduction in aging.

Deep Learning for Biometrics: A Survey

In the recent past, deep learning methods have demonstrated remarkable success for supervised learning tasks in multiple domains including computer vision, natural language processing, and speech processing. In this article, we investigate the impact of deep learning in the field of biometrics, given its success in other domains. Since biometrics deals with identifying people by using their characteristics, it primarily involves supervised learning and can leverage the success of deep learning in other related domains. In this article, we survey 100 different approaches that explore deep learning for recognizing individuals using various biometric modalities. We find that most deep learning research in biometrics has been focused on face and speaker recognition. Based on inferences from these approaches, we discuss how deep learning methods can benefit the field of biometrics and the potential gaps that deep learning approaches need to address for real-world biometric applications.