Regaining the ability to walk after a stroke is a major rehabilitation goal. Rehabilitation strategies that are task oriented and intensive can drive cortical reorganization and increase activity levels in people after a stroke. This paper describes a novel, wearable device for use with such rehabilitation strategies. The device is based on the combination of a smartphone and in-shoe sensors, and is designed to operate in free living conditions. Data collected from the device can be used for automatic recognition of postures and activities, characterization of extremity use and to provide behavioral enhancing feedback to patients recovering from a stroke. The proposed wearable platform's operation was validated in a small scale study involving three healthy individuals. The average accuracy of classification of three postures and activities was over 99%. Based on the results of validation and previously reported results on recognition of postures and activities in stroke patients, it is anticipated that recognition of postures and activities may be performed with high accuracy in free living conditions.

In this work, we utilize progressive growth-based Generative Adversarial Networks (GANs) to develop the Clarkson Fingerprint Generator (CFG). We demonstrate that the CFG is capable of generating realistic, high fidelity, 512 × 512 pixels, full, plain impression fingerprints. Our results suggest that the fingerprints generated by the CFG are unique, diverse, and resemble the training dataset in terms of minutiae configuration and quality, while not revealing the underlying identities of the training data. We make the pre-trained CFG model and the synthetically generated dataset publicly available at https: //github.com/keivanB/Clarkson_Finger_Gen

Fingerprint capture systems can be fooled by widely accessible methods to spoof the system using fake fingers, known as presentation attacks. As biometric recognition systems become more extensively relied upon at international borders and in consumer electronics, presentation attacks are becoming an increasingly serious issue. A robust solution is needed that can handle the increased variability and complexity of spoofing techniques. This paper demonstrates the viability of utilizing a sensor with timeseries and color-sensing capabilities to improve the robustness of a traditional fingerprint sensor and introduces a comprehensive fingerprint dataset with over 36,000 image sequences and a state-of-the-art set of spoofing techniques. The specific sensor used in this research captures a traditional gray-scale static capture and a time-series color capture simultaneously. Two different methods for Presentation Attack Detection (PAD) are used to assess the benefit of a color dynamic capture. The first algorithm utilizes Static-Temporal Feature Engineering on the fingerprint capture to generate a classification decision. The second generates its classification decision using features extracted by way of the Inception V3 CNN trained on ImageNet. Classification performance is evaluated using features extracted exclusively from the static capture, exclusively from the dynamic capture, and on a fusion of the two feature sets. With both PAD approaches we find that the fusion of the dynamic and static feature-set is shown to improve performance to a level not individually achievable.

No abstract