MPBS 2015 Abstracts


Short Papers
Paper Nr: 7
Title:

A Preliminary Review of Behavioural Biometrics for Health Monitoring in the Elderly

Authors:

Jordi Solé-Casals, Mihaela Vancea and Jaume Miquel March

Abstract: This article explores the potential of ICT-based biometrics for monitoring the health status of the elderly people. It departs from specific ageing and biometric traits to then focus on behavioural biometric traits like handwriting, speech and gait to finally explore their practical application in health monitoring of elderly.

Paper Nr: 8
Title:

Automatic Detection of High-voltage Spindles for Parkinson’s Disease

Authors:

V. Vigneron, T. Syed and Hsin Chen

Abstract: Parkinson’s disease is a progressive neurodegenerative disorder which can be characterized by several symptoms such as tremor, slowness of movements, bradykinesia/akinesia and absence of postural reflexes . . . and affects 10 million people worldwide. This paper develops a novel strategy for treating patients with PD: silence High-Voltage-Spindle that resemble the pathophysiological b-waves and contribute to the development of b-waves. Silencing HVSs is expected to delay or even prevent the development of b-waves and thus the progression of PD motor symptoms. High-voltage spindles (HVSs) are observed during waking immobility of patients. In this study, the local field potentials collected from the lesioned and control rats on multiple channels were analyzed with an online detection algorithm to identify the characteristic scillations of HVSs from the second-order statistical properties of the signals and the detection performance is investigated to obtain the optimal choices. These results provide further motivation for the real-time implementation of the automatic HVS detection systems with improved performance for pathophysiological and therapeutic applications to the thalamocortical network dysfunctions.

Paper Nr: 9
Title:

Multi-camera Video Object Recognition Using Active Contours

Authors:

Joanna Isabelle Olszewska

Abstract: In this paper, we propose to tackle with multiple video-object detection and recognition in a multi-camera environment using active contours. Indeed, with the growth of multi-camera systems, many computer vision frameworks have been developed, but none taking advantage of the well-established active contour method. Hence, active contours allow precise and automatic delineation of entire object's boundaries in frames, leading to an accurate segmentation and tracking of video objects displayed into the multi-view system, while our late fusion approach allows robust recognition of the detected objects in the synchronized sequences. Our active-contour-based system has been successfully tested on video-surveillance standard datasets and shows excellent performance in terms of computational efficiency and robustness compared to state-of-art ones.

Paper Nr: 10
Title:

Face Recognition by Fast and Stable Bi-dimensional Empirical Mode Decomposition

Authors:

Esteve Gallego-Jutglà, Saad Al-Baddai, Karema Al-Subari, Ana Maria Tomé, Elmar W. Lang and Jordi Solé-Casals

Abstract: In this study the use of a new fast and stable decomposition technique, bi-dimensional empirical mode decomposition, is used for face recognition tasks. Images are decomposed individually, and then the distance with reference images is computed. Three different types of distances are tested. Then class association is based on minimum distance and by using a classifier. Preliminary results (90.0% of classification rate) are satisfactory and will justify a deep investigation on how to apply this bi- dimensional decomposition technique for face recognition.