Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems.

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.

The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth.

Several studies have examined the accuracy of the Kinect V2 sensor during gait analysis. Usually the data retrieved by the Kinect V2 sensor are compared with the ground truth of certified systems using a Euclidean comparison. Due to the Kinect V2 sensor latency, the application of a uniform temporal alignment is not adequate to compare the signals. On that basis, the purpose of this study was to explore the abilities of the dynamic time warping (DTW) algorithm to compensate for sensor latency (3 samples or 90 ms) and develop a proper accuracy estimation. During the experimental stage, six iterations were performed using the a dual Kinect V2 system. The walking tests were developed at a self-selected speed. The sensor accuracy for Euclidean matching was consistent with that reported in previous studies. After latency compensation, the sensor accuracy demonstrated considerably lower error rates for all joints. This demonstrated that the accuracy was underestimated due to the use of inappropriate comparison techniques. On the contrary, DTW is a potential method that compensates for the sensor latency, and works sufficiently in comparison with certified systems.

Bio-Inspired Presentation Attack Detection for Face Biometrics.

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.

Efectos del síndrome de fricción de la banda iliotibial sobre la cinemática de carrera en corredoras populares / Effects of iliotibial band syndrome on running kinematics in female amateur runners / Efeitos da Síndrome de Atrito da banda do Trato Iliotibial na cinemática na carreira em corredores de rua

Objetivo: Examinar diferencias sobre los ángulos articulares de la cadera, rodilla, tobillo y retropie en corredoras con el síndrome de fricción de la banda iliotibial en el momento de la investigación, en comparación con corredoras sin historial de lesión en la rodilla ocasionada por la carrera. Método: Teniendo en cuenta los criterios de inclusión, en este estudio retrospectivo se estudiaron a un total de 30 corredoras amateurs, 15 sanas y 15 con el síndrome de fricción de la banda iliotibial. Mediante un análisis cinemático tridimensional, se registraron los ángulos 3D de las articulaciones del miembro inferior durante la carrera en suelo. Resultados: El grupo con síndrome de fricción de la banda iliotibial mostró menor flexión de la rodilla en el inicio del contacto (13.48º versus 17.17º P = 0.02) y mayor aducción de la cadera durante el despegue (-5.65 versus -2.68 P = 0.03) en comparación al grupo de corredoras sanas. No se observaron diferencias significativas en el ángulo máximo de aducción de la cadera (P = 0.95), ángulo máximo de rotación interna de la rodilla (P = 0.80) y ángulo máximo de eversión del retropié (P = 0.16) entre los grupos. Conclusiones: Las corredoras con síndrome de fricción de la banda iliotibial actual muestran un perfil cinemático asociado a su lesión, se sugiere una falta de movilidad en varios planos de movimiento

Objective: The purpose of this retrospective study was to determine how iliotibial band syndrome influences hip, knee, ankle and rear foot joint angle in female runners with iliotibial band syndrome and female runners with no history of knee injury at the moment of study. Method: In this retrospective study, the sample was composed of 30 recreational female runners (15 healthy runners and 15 with iliotibial band syndrome). A 3-D kinematic analysis was performed to measure 3D joint angles of the lower limb. Results: The iliotibial band syndrome group exhibited a reduced knee flexion angle at heel strike (13.48º vs. 17.17º p = 0.02) and greater hip adduction at toe-off (-5.65 vs. -2.68 p = 0.03) as compared to controls. In contrast, no significant differences were observed in peak hip adduction (p = 0.95), maximum knee internal rotation (p = 0.80) and maximum rearfoot eversion (p = 0.16) between the two groups. Conclusion: Female recreational runners with ITBS exhibit a specific kinematic profile suggestive of restricted movement at several planes

Objetivo: Examinar as diferenças nos ângulos articulares do quadril, joelho, tornozelo e dorso em corredores com a Síndrome de Atrito da Banda Iliotibial no momento da investigação, em comparação com corredores sem histórico de lesão no joelho causada pela corrida. Método: Considerando os critérios de inclusão, neste estudo retrospectivo foram estudados 30 corredores amadores, sendo 15 saudáveis e 15 com síndrome de Atrito da Banda Iliotibial. Por meio de uma análise cinemática tridimensional, os ângulos 3D das articulações do membro inferior foram registrados durante a corrida no solo. Resultados: O grupo com síndrome de atrito da banda iliotibial apresentou menor flexão de joelho no início do contato (13.48º versus 17.17º p = 0.02) e maior adução do quadril durante a decolagem (-5.65 versus -2.68 p = 0.03) em comparação com o grupo de corredores saudáveis. Não foram observadas diferenças significativas no ângulo máximo de adução do quadril (p = 0.95), ângulo máximo de rotação interna do joelho (p = 0.80) e ângulo máximo de eversão do retropé (p = 0.16) entre os grupos. Conclusões: Corredores com síndrome de fricção da banda iliotibial apresentam um perfil cinemático associado à sua lesão, sugerindo uma falta de mobilidade em vários planos de movimento

Videosensor for the detection of unsafe driving behavior in the proximity of black spots.

This paper discusses the overall design and implementation of a video sensor for the detection of risky behaviors of car drivers near previously identified and georeferenced black spots. The main goal is to provide the driver with a visual audio alert that informs of the proximity of an area of high incidence of highway accidents only if their driving behavior could result in a risky situation. It proposes a video sensor for detecting and supervising driver behavior, its main objective being manual distractions, so hand driver supervision is performed. A GPS signal is also considered, the GPS information is compared with a database of global positioning Black Spots to determine the relative proximity of a risky area. The outputs of the video sensor and GPS sensor are combined to evaluate a possible risky behavior. The results are promising in terms of risk analysis in order to be validated for use in the context of the automotive industry as future work.

Combination and selection of traffic safety expert judgments for the prevention of driving risks.

In this paper, we describe a new framework to combine experts’ judgments for the prevention of driving risks in a cabin truck. In addition, the methodology shows how to choose among the experts the one whose predictions fit best the environmental conditions. The methodology is applied over data sets obtained from a high immersive cabin truck simulator in natural driving conditions. A nonparametric model, based in Nearest Neighbors combined with Restricted Least Squared methods is developed. Three experts were asked to evaluate the driving risk using a Visual Analog Scale (VAS), in order to measure the driving risk in a truck simulator where the vehicle dynamics factors were stored. Numerical results show that the methodology is suitable for embedding in real time systems.