1,721,104 research outputs found
Towards the suitability of gait wearable signal processing for long term recognition
No full textOne of the present approaches to gait recognition exploits the signals captured by wearable sensors, especially the accelerometers embedded in modern smartphones. However, the different speed, the ground slope, or simply the time lapse between captures cause variations that negatively affect long term recognition in a dramatic way. The proposed procedure aims at extracting gait characteristics that are as invariant as possible, and therefore useful for accurate long term recognition. The experiments compare the performance of the proposal with others in state-of-the-art that use the same benchmark, namely the ZJU-gaitacc dataset. This dataset includes a high number of samples per subject, captured in two time-separated sessions. This allows to assess the performance of the proposed method also in the long term, i.e., when comparing templates captured in different times. Most works using the same benchmark so far have not exploited both sessions. They use samples captured in the same time, constraining the use of this trait to continuous recognition, e.g., of the smartphone owner. The obtained results testify that, in this condition, the proposed feature-based method outperforms competitors in the current literature. The experiments also compare the results from a session-based partition with those obtained from a training that mixes-up samples from different sessions. As expected, the latter strategy can dramatically improve the measured performance. The significantly different results seem to suggest that the session-based partition, when feasible, can provide more realistic results, closer to the real-world application context when behavioural traits are involved in the medium/long term. The same results seem also to testify that there is still need to improve the accuracy of gait recognition via wearable sensors. This calls for further investigation of the problems related to the variability over time in the pattern of individual gait signals
User gait biometrics in smart ambient applications through wearable accelerometer signals: an analysis of the influence of training setup on recognition accuracy
No full textGait recognition can exploit the signals from wearables, e.g., the accelerometers embedded in smart devices. At present, this kind of recognition mostly underlies subject verification: the incoming probe is compared only with the templates in the system gallery that belong to the claimed identity. For instance, several proposals tackle the continuous recognition of the device owner to detect possible theft or loss. In this case, assuming a short time between the gallery template acquisition and the probe is reasonable. This work rather investigates the viability of a wider range of applications including identification (comparison with a whole system gallery) in the medium-long term. The first contribution is a procedure for extraction and two-phase selection of the most relevant aggregate features from a gait signal. A model is trained for each identity using Logistic Regression. The second contribution is the experiments investigating the effect of the variability of the gait pattern in time. In particular, the recognition performance is influenced by the benchmark partition into training and testing sets when more acquisition sessions are available, like in the exploited ZJU-gaitacc dataset. When close-in-time acquisition data is only available, the results seem to suggest re-identification (short time among captures) as the most promising application for this kind of recognition. The exclusive use of different dataset sessions for training and testing can rather better highlight the dramatic effect of trait variability on the measured performance. This suggests acquiring enrollment data in more sessions when the intended use is in medium-long term applications of smart ambient intelligence
Comparison of two architectures for text-independent verification after character-unaware text segmentation
No full textThis paper compares the performance of two popular CNN architectures, ResNet-50 and MobileNetV2, fine-Tuned for text-independent writer verification. The used benchmark is IAM dataset. The further contributions are an easy and fast sub-region cropping for robust model training, and a biometrics-oriented performance evaluation. The preliminary results are encouraging
Walking in a smart city: Investigating the gait stabilization effect for biometric recognition via wearable sensors
No full textTechnology is expected to enhance life in a Smart City: everything is intelligent, digital, interconnected, and inclusive. In addition, all everyday activities are facilitated. This paper presents a biometric authentication strategy based on gait dynamics. The produced signals are acquired by the common mobile device accelerometers (especially those embedded in smartphones). The user has nothing to do but normally approach a controlled entry: authentication is automatically triggered by ambient elements (beacons). This transparent protocol entails user awareness of the authentication since the user has to install a suitable app, therefore it does not cause any covert privacy violation. In addition, it allows avoiding any explicit, possibly cumbersome authentication procedure. Last but not least, the use of a sensor directly embedded in everyday users’ equipment supports an efficient approach without the need for further hardware
Your face may say the truth when you lie
No full textThis work proposes the preliminary results of a system to recognize deception from facial micro-expressions. The adopted method starts from facial landmarks to analyze the micro-dynamics underlying the facial modifications. The procedure is repeated both while answering neutral questions (entailing no reason to lie) and when answering questions whose responses may cause harm or embarrassment, at least. The preliminary results invite us to continue the research of suitable features to tackle the problem of deception detection
Automatic Face Image Tagging in Large Collections
No full textIn this chapter, the authors present some issues related to automatic face image tagging techniques. Their main purpose in user applications is to support the organization (indexing) and retrieval (or easy browsing) of images or videos in large collections. Their core modules include algorithms and strategies for handling very large face databases, mostly acquired in real conditions. As a background for understanding how automatic face tagging works, an overview about face recognition techniques is given, including both traditional approaches and novel proposed techniques for face recognition in uncontrolled settings. Moreover, some applications and the way they work are summarized, in order to depict the state of the art in this area of face recognition research. Actually, many of them are used to tag faces and to organize photo albums with respect to the person(s) presented in annotated photos. This kind of activity has recently expanded from personal devices to social networks, and can also significantly support more demanding tasks, such as automatic handling of large editorial collections for magazine publishing and archiving. Finally, a number of approaches to large-scale face datasets as well as some automatic face image tagging techniques are presented and compared. The authors show that many approaches, both in commercial and research applications, still provide only a semi-automatic solution for this problem
VoiceWriting: A completely speech-based text editor
No full textAssistive technologies, mostly based on speech recognition and synthesis, help visually-impaired people writing text on digital devices. However, they do not fully support non-sequential text editing without the use of sight. This paper discusses the design of the interaction protocol underlying the first prototype of a text editor that is especially designed for people with very poor eyesight. It does not require the visual localization of text for non-sequential editing of multiple-paragraph documents and only exploits voice and "uninterpreted"keyboard input, namely the outmoded "press any key"for mode-switching. Preliminary tests complete the paper
- …
