Search

International audience; In this paper, we consider the problem of iris recognition in the context of video-based distant acquisition. We propose several systems aiming at improving the poor performance resulting from image degradations (low resolution, blur, lack of texture) obtained from such acquisitions. Our approach is based on simple super-resolution techniques applied at the pixel level on the different frames of a video, improved by taking into account some quality criteria. Our main novelty is the introduction of a local quality measure in the fusion scheme. This measure relies on a gaussian mixture model estimation of clean iris texture distribution. It can also be used to compute a global quality measure of the normalized iris image which can be used either for the selection of the best images in a sequence or in the fusion scheme. Extensive experiments on the QFIRE database at different acquisition distances (5, 7, and 11 feet) show the big improvement brought by the use of the global quality for both scenarios. Moreover, the local quality-based fusion scheme further increases the performance due to its ability to consider locally the different parts of the image and therefore to discard poorly segmented pixels in the fusion.

This paper presents an original hidden Markov model (HMM) approach for online beat segmentation and classification of electrocardiograms. The HMM framework has been visited because of its ability of beat detection, segmentation and classification, highly suitable to the electrocardiogram (ECG) problem. Our approach addresses a large panel of topics some of them never studied before in other HMM related works: waveforms modeling, multichannel beat segmentation and classification, and unsupervised adaptation to the patient's ECG. The performance was evaluated on the two-channel QT database in terms of waveform segmentation precision, beat detection and classification. Our waveform segmentation results compare favorably to other systems in the literature. We also obtained high beat detection performance with sensitivity of 99.79% and a positive predictivity of 99.96%, using a test set of 59 recordings. Moreover, premature ventricular contraction beats were detected using an original classification strategy. The results obtained validate our approach for real world application.

This letter describes an original CMOS imaging system dedicated to human face recognition. The main interest of this work is to provide ambient light invariant images and facilitate segmentation of the face from the background. This system has been implemented in a specially designed CMOS smart image sensor with only one analog memory per pixel. This simple pixel design gives the possibility to incorporate this functionality into classic low-cost CMOS image sensors. One of its possible applications is face recognition, since the human face appearance is dramatically dependent on illumination conditions. A first indoor experience with different illumination conditions shows that a simple correlation-based verification algorithm on face images of 25 people of the INT database gives promising results.

A new blind channel estimation algorithm is presented. This algorithm comes from the well-known maximum likelihood estimation approach. However, we intentionally "smooth" the joint probability density function (PDF) of a finite set of observations in order to reduce the computational burden. As a result, we obtain an online clustering algorithm whose main characteristic is the constraint of symmetry among cluster centers. Computational simulations are used to evaluate this algorithm.