1,721,332 research outputs found
Biometric walk recognizer: Gait recognition by a single smartphone accelerometer
No full textThis paper presents an approach to gait recognition based on a single consumer accelerometer, built in most present mobile devices. It does not propose a completely novel
algorithm, but rather investigates better ways to exploit the Dynamic TimeWarping (DTW), which is still one of the most used at present in literature. To this aim, the paper presents both a new segmentation algorithm to split the gait signal into cycles/steps, and investigates the best way to use the possibly segmented signal for recognition. Summarizing, the first contribution of the present work is the proposal of a new segmentation algorithm for the gait signal, which does not require any pre-processing, either interpolation or noise reduction, to enhance the original signal, and its comparison with two other state-of-the-art step segmentation algorithms. The second contribution is related to the extensive tests performed with the five different investigated matching methods. The tests are carried out exploiting all compared segmentation algorithms and three different datasets, collected using different sensors: the originally exploited BWR dataset, that includes walk templates from 30
volunteers, and two huge datasets used for this kind of testing, namely the ZJU-gaitacc and the OU-ISIR Inertial Sensor Database. Tests have been performed in both verification
mode, either single-template or multiple-template, and identification mode, both closed and open set. The latter is rarely found in literature though representing the most frequently predictable applicative setting. It is worth underlining that the final goal is to allow using low-cost, built-in sensors that nowadays equip most smartphones. The best result in closed set identification, which is the identification mode usually reported in literature, is achieved using the most constrained method, i.e., limiting the walks in the gallery and in the probe to have a similar number of steps. It reaches ≈ 93 % of Recognition Rate (RR) on ZJUgaitacc dataset. The best result obtained with methods exploiting segmentation to overcome the mentioned limitation reaches ≈ 83 % of Recognition Rate (RR) on the same dataset, using our proposed algorithm. The best results in verification is achieved using multiple templates per user, again without segmentation, with an Equal Error Rate (EER) of 0.09, while the best results with segmentation is achieved again with our algorithm and is and EER of 0.10. This is a very good result for a soft biometrics as gait if often considered. As expected, open set identification achieves lower performance
A new data normalization function for multibiometric contexts: A case study
No full textIt has been not possible yet to identify a physical or behavioural feature able by itself to identify a person in a way satisfying the acceptability and reliability constraints imposed by real applications. As a consequence the present trend is towards multimodal systems. Data normalization problem is crucial when fusing results from different subsystems. We introduce a new normalization function, the mapping function, able to overcome the limitations of commonly used techniques. In this work we also test it on a real hierarchical system obtained by the novel combination schema of the three different biometries face, ear and fingerprint. Experimental results in the final part of our work provide a positive feedback about assertions within the body of the paper
International Conference on Pattern Recognition: Applications and Methods - 2013
No full textThe International Conference on Pattern Recognition Applications and Methods would like to become a major point of contact between researchers, engineers and practitioners on the areas of Pattern Recognition, both from theoretical and application perspectives.
Contributions describing applications of Pattern Recognition techniques to real-world problems, interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance Pattern Recognition methods are especially encouraged.
Conference Areas
Each of these topic areas is expanded below but the sub-topics list is not exhaustive. Papers may address one or more of the listed sub-topics, although authors should not feel limited by them. Unlisted but related sub-topics are also acceptable, provided they fit in one of the following main topic areas:
1. THEORY AND METHODS
2. APPLICATION
From career education to vocational education and training in digital era: exploiting Communities of Practice
No full textThe aim of this contribution is to sketch the
possible role of the Communities of Practice (CoPs) in
projecting in the digital dimension both the activities aimed at
orienting towards a future professional life, and those aimed
at Vocational Education and Training (VET). While the
former are especially targeted at students just exiting from
high school, the latter rather span an overall lifetime,
including life-long learning, continuous in-service training
and professional outplacement. Though the stakeholders
participating the two processes might be different, the core
underlying processes have much in common
Biometrics Compendium
No full textThe IEEE Biometrics Compendium is the first IEEE virtual journal, which is a collection of previously published IEEE papers in specific scientific and technical disciplines, paired with value-added commentary from technology experts.
The IEEE Biometrics Compendium addresses the theory, design, and application of biometric characterization of human beings, based on physiological and/or behavioral features and traits, in particular for identification, identity verification, authentication, cancelable/revocable biometrics, and recognition and privacy considerations and social impact and medical diagnosis
Editorial - Introduction to the special issue on multimodal interaction through haptic feedback
No full textMultimodal interfacesarecharacterizedbythe(possi-
bly simultaneous)useofmultiplehumansensorymod-
alities andcansupportcombinedinput/outputmodes.
Modern multimodalinterfacesaimatemulatingthe
naturalmulti-sensorialformsofhuman–humandialogue,
relyingontheintegrationofadvancedinteractionmodes,
rangingfrompen-basedinput,tohandgestures,toeye
gaze, tohead/bodymovements,tohapticinput/output.
Multimodal interactionenhancedbyhapticfeedbackis
increasinglybeingexperiencedinsuchdomainsas
industry,medicine,andbiotechnology,wherenewpoten-
tialities canbeachieved.Thankstotheuseofhaptic
devices. Multimodalhapticinterfaceshavealsobeen
conceivedtoaddressmajorsocietalneeds,e.g.,byvisually
impairedpeopleorwheelchairusers.Therefore,agreat
deal ofattentionisbeingdevotedtoresearchesaimingto
investigatethepotentialofmultimodaldialoguesallowed
by advancedinteractiondevices,andinparticularto
evaluatethepossibleenhancementachievedbytradi-
tional visualinteractionsystemsthroughtheuseofsuch
additional communicationmodalities.Followingthis
trend, thefocusofthisspecialissueisonhaptic-enhanced
multimodal interactionandonresearchchallenges,and
innovativeideasandapproachesthathavebeenexperi-
mentedandvalidatedinthisspecificresearchfield
Workshop on Multimodal Interaction Through Haptic Feedback - MITH 2008
No full textThe workshop is meant to promote further investigation on the theoretical and practical valence of haptic-enhanced multimodal interaction, by stimulating discussion among researchers, possibly operating in different scientific fields. The final goal of this one-day meeting will be to encourage research cooperation among participants on multidisciplinary projects built upon individual past experiences with multimodal haptic interfaces. To that aim, workshop participants will be invited to take part in electronic forums, to be held prior and after the workshop, meant to discuss possible project joint proposals. An example of such proposals might be in response to the open call for Future and Emerging Technologies (FET), which is part of the Information Society Technologies (IST) area, under the Seventh Framework Programme (FP7)
- …
