RESUMEN
Automated border control systems are the first critical infrastructure point when crossing a border country. Crossing border lines for unauthorized passengers is a high security risk to any country. This paper presents a multispectral analysis of presentation attack detection for facial biometrics using the learned features from a convolutional neural network. Three sensors are considered to design and develop a new database that is composed of visible (VIS), near-infrared (NIR), and thermal images. Most studies are based on laboratory or ideal conditions-controlled environments. However, in a real scenario, a subject's situation is completely modified due to diverse physiological conditions, such as stress, temperature changes, sweating, and increased blood pressure. For this reason, the added value of this study is that this database was acquired in situ. The attacks considered were printed, masked, and displayed images. In addition, five classifiers were used to detect the presentation attack. Note that thermal sensors provide better performance than other solutions. The results present better outputs when all sensors are used together, regardless of whether classifier or feature-level fusion is considered. Finally, classifiers such as KNN or SVM show high performance and low computational level.
RESUMEN
Today, face biometric systems are becoming widely accepted as a standard method for identity authentication in many security settings. For example, their deployment in automated border control gates plays a crucial role in accurate document authentication and reduced traveler flow rates in congested border zones. The proliferation of such systems is further spurred by the advent of portable devices. On the one hand, modern smartphone and tablet cameras have in-built user authentication applications while on the other hand, their displays are being consistently exploited for face spoofing. Similar to biometric systems of other physiological biometric identifiers, face biometric systems have their own unique set of potential vulnerabilities. In this work, these vulnerabilities (presentation attacks) are being explored via a biologically-inspired presentation attack detection model which is termed "BIOPAD." Our model employs Gabor features in a feedforward hierarchical structure of layers that progressively process and train from visual information of people's faces, along with their presentation attacks, in the visible and near-infrared spectral regions. BIOPAD's performance is directly compared with other popular biologically-inspired layered models such as the "Hierarchical Model And X" (HMAX) that applies similar handcrafted features, and Convolutional Neural Networks (CNN) that discover low-level features through stochastic descent training. BIOPAD shows superior performance to both HMAX and CNN in all of the three presentation attack databases examined and these results were consistent in two different classifiers (Support Vector Machine and k-nearest neighbor). In certain cases, our findings have shown that BIOPAD can produce authentication rates with 99% accuracy. Finally, we further introduce a new presentation attack database with visible and near-infrared information for direct comparisons. Overall, BIOPAD's operation, which is to fuse information from different spectral bands at both feature and score levels for the purpose of face presentation attack detection, has never been attempted before with a biologically-inspired algorithm. Obtained detection rates are promising and confirm that near-infrared visual information significantly assists in overcoming presentation attacks.
RESUMEN
OBJECTIVES: Epicrania fugax (EF) is a novel syndrome presenting with brief pain paroxysms that always start in a particular area of the head to spread immediately either forward or backward. Paroxysms stem from a focal area, in which a well-shaped continuous pain reminiscent of the symptomatic area described in nummular headache (NH) can be present. We aimed to analyze the association of these two epicranial headaches in eight patients. METHODS: We prospectively assessed all patients with EF attending an outpatient headache office from March 2008, when EF was first described, to June 2012. Among them, we selected those patients with a well-circumscribed continuous pain at the stemming point fulfilling the research diagnostic criteria for NH of the International Classification of Headache Disorders II Edition (ICHD-II) appendix. We considered the demographic and clinical features of the selected patients. RESULTS: Eight patients (five females, three males) were diagnosed with both EF and NH. Mean age of onset was 44.2 ± 12 (range: 23-60). Regarding NH, the diameter of the painful area was 4.4 ± 1 centimeters (range: 3-6) and pain intensity was 4.2 ± 0.7 (range: 3-5) on a 10-point verbal analogical scale (VAS). As for the EF, the radiating paroxysms always started in the NH painful area and lasted 6.6 ± 4.5 seconds (range: 2-15), with a pain intensity of 7.9 ± 1.6 (range 5-10) on the VAS. Five cases had forward radiation, while three cases had backward EF. Four cases had ipsilateral autonomic accompaniments. Six patients required a preventive, and lamotrigine achieved complete response in three of them. CONCLUSION: Although the etiology of NH and EF remains uncertain, both syndromes seem to share a peripheral source. Their association in a number of patients is probably reflecting a pathophysiological connection. Lamotrigine might be a good therapeutic option for those patients presenting with both disorders.