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.
The utilisation of biometrics in mobile scenarios is increasing remarkably. At the same time, handwritten signature recognition is one of the modalities with highest potential of use for those applications where customers are used to sign in those traditional processes. However, several improvements have to be made in order to reach acceptable levels of performance, reliability and interoperability. The evaluation carried out in this study contributes with multiple results obtained from 43 users signing 60 times, divided in three sessions, in eight different capture devices, being six of them mobile devices and the other two digitisers specially made for signing and used as a baseline. At each session, a total of 20 signatures per user are captured by each device, so that the evaluation here reported a total of 20 640 signatures, stored in ISO/IEC 19794-7 format. The algorithm applied is a DTW-based one, particularly modified for mobile environments. The results analysed include interoperability, visual feedback and modality tests. One of the big challenges of this research was to discover if the handwritten signature modality in mobile devices should be split into two different modalities, one for those cases when the signature is performed with a stylus, and another when the fingertip is used for signing. Many relevant conclusions have been collected and, over all, multiple improvements have been reached contributing to future deployments of biometrics in mobile environments.
Biometrics has burst into mobile technology. Fingerprint scanners are being embedded in smartphones and tablets supplying these devices with the security and usability provided by biometric authentication mechanisms. However, performance results obtained by biometric systems cannot be extrapolated to mobile devices. The conditions change, especially at capture process, due to the reduced sensing area of the scanners used. The impact of small fingerprint scanners on the quality and biometric performance of the system is studied. A database using three different fingerprint scanners has been collected and reduced-size images (i.e. 12 × 12 mm 2 , 10 × 10 mm 2 and 8 × 8 mm 2) have been modelled by cropping the original ones. Performance testing has been conducted using one public and one commercial algorithm, and considering two application scenarios. One scenario in which enrolment and authentication are executed using the same small sensor included in the mobile device (i.e. cropped image against cropped image) and a second scenario in which enrolment is executed using an external larger sensor and authentication is done using the mobile device sensor (i.e. full image against cropped image). Results show the gradual worsening of quality and error rates as the size of the fingerprint scanner is reduced revealing a significant difference between the application scenarios analysed.
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.
In the last few decades, we have witnessed a large-scale deployment of biometric systems in different life applications replacing the traditional recognition methods such as passwords and tokens. We approached a time where we use biometric systems in our daily life. On a personal scale, the authentication to our electronic devices (smartphones, tablets, laptops, etc.) utilizes biometric characteristics to provide access permission. Moreover, we access our bank accounts, perform various types of payments and transactions using the biometric sensors integrated into our devices. On the other hand, different organizations, companies, and institutions use biometric-based solutions for access control. On the national scale, police authorities and border control measures use biometric recognition devices for individual identification and verification purposes.
Fingerprint recognition systems have proven significant performance in many services such as forensics, border control, and mobile applications. Even though fingerprint systems have shown high accuracy and user acceptance, concerns have raised questions about the possibility of having our fingerprint pattern stolen and presented to the system by an imposter. In this paper, we propose a dynamic presentation attack detection mechanism that seeks to mitigate presentation attacks. The adopted mechanism extracts the variation of global fingerprint features in video acquisition scenario and uses it to distinguish bona fide from attack presentations. For that purpose, a dynamic dataset has been collected from 11 independent subjects, 6 fingerprints per user, using thermal and optical sensors. A total of 792 bona fide presentations and 2772 attack presentations are collected. The final PAD subsystem is evaluated based on the standard ISO/IEC 30107-3. Considering SVM classification and 3 folds cross validation, the obtained error rates at 5% APCER are 18.1% BPCER for the thermal subset and 19.5% BPCER for the optical subset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.