RESUMEN
This paper presents a novel mechanism for fingerprint dynamic presentation attack detection. We utilize five spatio-temporal feature extractors to efficiently eliminate and mitigate different presentation attack species. The feature extractors are selected such that the fingerprint ridge/valley pattern is consolidated with the temporal variations within the pattern in fingerprint videos. An SVM classification scheme, with a second degree polynomial kernel, is used in our presentation attack detection subsystem to classify bona fide and attack presentations. The experiment protocol and evaluation are conducted following the ISO/IEC 30107-3:2017 standard. Our proposed approach demonstrates efficient capability of detecting presentation attacks with significantly low BPCER where BPCER is 1.11% for an optical sensor and 3.89% for a thermal sensor at 5% APCER for both.
RESUMEN
Currently, there exist different technologies applied in the world of medicine dedicated to the detection of health problems such as cancer, heart diseases, etc. However, these technologies are not applied to the detection of lower body pathologies. In this article, a Neural Network (NN)-based system capable of classifying pathologies of the lower train by the way of walking in a non-controlled scenario, with the ability to add new users without retraining the system is presented. All the signals are filtered and processed in order to extract the Gait Cycles (GCs), and those cycles are used as input for the NN. To optimize the network a random search optimization process has been performed. To test the system a database with 51 users and 3 visits per user has been collected. After some improvements, the algorithm can correctly classify the 92% of the cases with 60% of training data. This algorithm is a first approach of creating a system to make a first stage pathology detection without the requirement to move to a specific place.
RESUMEN
In this article, a gait recognition algorithm is presented based on the information obtained from inertial sensors embedded in a smartphone, in particular, the accelerometers and gyroscopes typically embedded on them. The algorithm processes the signal by extracting gait cycles, which are then fed into a Recurrent Neural Network (RNN) to generate feature vectors. To optimize the accuracy of this algorithm, we apply a random grid hyperparameter selection process followed by a hand-tuning method to reach the final hyperparameter configuration. The different configurations are tested on a public database with 744 users and compared with other algorithms that were previously tested on the same database. After reaching the best-performing configuration for our algorithm, we obtain an equal error rate (EER) of 11.48% when training with only 20% of the users. Even better, when using 70% of the users for training, that value drops to 7.55%. The system manages to improve on state-of-the-art methods, but we believe the algorithm could reach a significantly better performance if it was trained with more visits per user. With a large enough database with several visits per user, the algorithm could improve substantially.