Alberto de Santos Sierra

Silhouette-based hand recognition on mobile devices

Hand Biometric Recognition not only gathers a good performance in identifying individuals but also it is known to be a non-invasive biometric technique. Furthermore, there exist new trends towards mobile implementation developments, focusing on embedding current biometric systems in mobile devices. This paper aims to implement hand biometric recognition with mobile devices.

Two Stress Detection Schemes Based on Physiological Signals for Real-Time Applications

This document presents two possible schemes suitable for stress detection. Considering only two physiological signals, namely Galvanic Skin Response and Heart Rate, both stress detection systems are able to detect in less than 10 seconds to what extend an individual is under stressing situations. Furthermore, their accuracy (around 95 %) and the time required to elucidate the stress level, yield to the conclusion that these approaches are two very suitable solutions for real-time security systems. Security systems could use these system to both detect stress level on individuals and, therefore, to make suppositions on the individual intentions and future actions in relation to the system.

Hand Biometric Segmentation by Means of Fuzzy Multiscale Aggregation for Mobile Devices

Biometrics applied to mobile devices is one of the most recent topic of interest in biometrics. Due to the limitations of these devices, in terms of computational cost, biometric techniques must be carefully adapted to this architectures. This paper proposes a quasi-linear approach for hand biometric segmentation based on fuzzy multiscale aggregation. The algorithm yields promising results in terms of segmentation accuracy, being tested with hand images acquired with a mobile device in a non-controlled and non-invasive environment. Finally, this approach is compared to the performance of the well-known Normalized Cuts algorithm, with positive results.

Speed-independent gait identification for mobile devices

Due to the intensive use of mobile phones for different purposes, these devices usually contain confidential information which must not be accessed by another person apart from the owner of the device. Furthermore, the new generation phones commonly incorporate an accelerometer which may be used to capture the acceleration signals produced as a result of owners gait. Nowadays, gait identification in basis of acceleration signals is being considered as a new biometric technique which allows blocking the device when another person is carrying it. Although distance based approaches as Euclidean distance or dynamic time warping have been applied to solve this identification problem, they show difficulties when dealing with gaits at different speeds. For this reason, in this paper, a method to extract an average template from instances of the gait at different velocities is presented. This method has been tested with the gait signals of 34 subjects while walking at different motion speeds (slow, normal and fast) and it has shown to improve the performance of Euclidean distance and classical dynamic time warping.

Iris segmentation based on Fuzzy Mathematical Morphology, Neural Networks and ontologies

Segmentation is one of the most time-consuming steps within the whole process of Iris Recognition. By means of Fuzzy Mathematical Morphology and Neural Networks, this new algorithm can fulfill the task of isolating the Iris, not only with an acceptable accuracy, but also with a very high improvement in terms of time. Furthermore, this innovative scheme presents an ontology able to decide whether the features can be extracted, based on previous segmentation. This paper provides a detailed explanation of both the problem to be solved and how this new approach meets the required goals. Current Iris Recognition algorithms may benefit from this new approach, and what is more, the essence of the algorithm can be extended to other biometric segmentation procedures.

A Comparative Study on Unconstrained Hand Biometrics

Biometrics applied to mobile devices are of great interest for security applications. Daily scenarios can benefit of a combination of both the most secure systems and most simple and extended devices. This document presents a hand biometric system oriented to mobile devices, proposing a non-intrusive, contact-less acquisition process where final users should take a picture of their hand in free-space with a mobile device without removals of rings, bracelets or watches. The main contribution of this paper is threefold: firstly, a feature extraction method is proposed, providing invariant hand measurements to previous changes; second contribution consists of providing a template creation based on hand geometric distances, requiring information from only one individual, without considering data from the rest of individuals within the database; finally, a proposal for template matching is proposed, minimizing the intra-class similarity and maximizing the inter-class likeliness. The proposed method is evaluated using three publicly available contact-less, platform-free databases. In addition, the results obtained with these databases will be compared to the results provided by two competitive pattern recognition techniques, namely Support Vector Machines (SVM) and

Gaussian multiscale aggregation applied to segmentation in hand biometrics.

k

Towards hand biometrics in mobile devices

-Nearest Neighbour, often employed within the literature. Therefore, this approach provides an appropriate solution to adapt hand biometrics to mobile devices, with an accurate results and a non-intrusive acquisition procedure which increases the overall acceptance from the final user.

A Comparative Evaluation of Gaussian Multiscale Aggregation for Hand Biometrics.

This paper presents an image segmentation algorithm based on Gaussian multiscale aggregation oriented to hand biometric applications. The method is able to isolate the hand from a wide variety of background textures such as carpets, fabric, glass, grass, soil or stones. The evaluation was carried out by using a publicly available synthetic database with 408,000 hand images in different backgrounds, comparing the performance in terms of accuracy and computational cost to two competitive segmentation methods existing in literature, namely Lossy Data Compression (LDC) and Normalized Cuts (NCuts). The results highlight that the proposed method outperforms current competitive segmentation methods with regard to computational cost, time performance, accuracy and memory usage.