Leila Mirmohamadsadeghi

Palm vein recognition with Local Binary Patterns and Local Derivative Patterns

Palm vein feature extraction from near infrared images is a challenging problem in hand pattern recognition. In this paper, a promising new approach based on local texture patterns is proposed. First, operators and histograms of multi-scale Local Binary Patterns (LBPs) are investigated in order to identify new efficient descriptors for palm vein patterns. Novel higher-order local pattern descriptors based on Local Derivative Pattern (LDP) histograms are then investigated for palm vein description. Both feature extraction methods are compared and evaluated in the framework of verification and identification tasks. Extensive experiments on CASIA Multi-Spectral Palmprint Image Database V1.0 (CASIA database) identify the LBP and LDP descriptors which are better adapted to palm vein texture. Tests on the CASIA datasets also show that the best adapted LDP descriptors consistently outperform their LBP counterparts in both palm vein verification and identification.

Respiratory rate estimation from the ECG using an instantaneous frequency tracking algorithm

Monitoring the respiratory rate (RR) is important in many clinical and non-clinical situations but it is difficult in practice, for existing devices are obtrusive, bulky and expensive. The extraction of the RR from the routinely acquired electrocardiogram (ECG) has been proposed lately. Two approaches exist, one exploiting the modulation of the heart rate by the respiration, known as the respiratory sinus arrhythmia (RSA) and the other using the modulation by the respiration of the R-peak amplitudes (RPA). In this study, the weighted multi-signal oscillator based band pass filtering (W-OSC) algorithm is applied to track the common frequency in the RSA and RPA waveforms simultaneously, as an estimate of the instantaneous RR. On the public PhysioNet Fantasia data set, it is shown that the presented method is automatic, instantaneous and comparable in accuracy to the state-of-the-art

Palm vein recognition with local texture patterns

Biometric recognition using the palm vein characteristics is emerging as a touchless and spoof-resistant hand-based means to identify individuals or to verify their identity. One of the open challenges in this field is the creation of fast and modality-dependent feature extractors for recognition. This article investigates features using local texture description methods. The local binary pattern (LBP) operator as well as the local derivative pattern (LDP) operator and the fusion of the two are studied in order to create efficient descriptors for palm vein recognition by systematically adapting their parameters to fit palm vein structures. Results of experiments are reported on the CASIA multi-spectral palm print image database V1.0 (CASIA database). It is found that the local texture patterns proposed in this study can be adapted to the vein description task for biometric recognition and that the LDP operator consistently outperforms the LBP operator in palm vein recognition.

Introduction of cylinder quality measure into Minutia Cylinder-Code based fingerprint matching

Poor data quality is responsible for many or even most matching errors in fingerprint recognition systems. It became obvious that particular effort is needed in adaptation of the state-of-the-art minutiae-based fingerprint matching techniques to real-world conditions using quality measures. In this paper, we address a challenging problem of how to associate local quality measures to local minutiae descriptors, in particular Minutia Cylinder-Code (MCC), in order to obtain better recognition rates. Firstly, we introduce a new local quality measure, called Cylinder Quality Measure (CQM), corresponding to each MCC descriptor by combining the qualities of individual minutiae involved. Then, we propose a method for incorporating such quality measures into fingerprint matching through a quality-based relaxation procedure. Our experiments on the FVC2002 (DB1 and DB3) and FVC2004 (DB3) databases demonstrate that integrating the cylinder quality measure through the proposed procedure improves the overall matching performance comparing to the state-of-the-art MCC based fingerprint matching algorithms.

Real-time multi-signal frequency tracking with a bank of notch filters to estimate the respiratory rate from the ECG

Measuring the instantaneous frequency of a signal rapidly and accurately is essential in many applications. However, the instantaneous frequency by definition is a parameter difficult to determine. Fourier-based methods introduce estimation delays as computations are performed in a time-window. Instantaneous methods based on the Hilbert transform lack robustness. State-of-the-art adaptive filters yield accurate estimates, however, with an adaptation delay. In this study we propose an algorithm based on short length-3 FIR notch filters to estimate the instantaneous frequency of a signal at each sample, in a real-time manner and with very low delay. The output powers of a bank of the above-mentioned filters are used in a recursive weighting scheme to estimate the dominant frequency of the input. This scheme has been extended to process multiple inputs containing a common frequency by introducing an additional weighting scheme upon the inputs. The algorithm was tested on synthetic data and then evaluated on real biomedical data, i.e. the estimation of the respiratory rate from the electrocardiogram. It was shown that the proposed method provided more accurate estimates with less delay than those of state-of-the-art methods. By virtue of its simplicity and good performance, the proposed method is a worthy candidate to be used in biomedical applications, for example in health monitoring developments based on portable and automatic devices.

Sleep Apnea Detection using Features from the Respiration and the ECG recorded with Smart-Shirts

The automatic detection of sleep apnea episodes, without the need of polysomnography and outside a clinical facility, could help facilitate the diagnosis of this disorder. In this work, features to detect sleep apnea events were computed from respiration and electrocardiogram recordings acquired with a wearable smart-shirt. First, a classical scheme exploiting the amplitude decrease of the respiration during apnea episodes was presented. Second, a novel measure of the phase coupling between the respiration and the respiratory sinus arrhythmia from the ECG was introduced. It was shown that these features were significantly different during sleep apnea episodes than for normal breathing.

Estimating the real-time respiratory rate from the ECG with a bank of notch filters

The respiratory rate is an important vital sign that needs to be monitored continuously in clinical and non-clinical health monitoring applications. It is commonly estimated from electrocardiogram (ECG)-derived respiratory waveforms such as the respiratory sinus arrhythmia (RSA) and the ECG R peak amplitudes (RPA). Current methods combine respiratory information from these two waveforms but produce large delays in estimating the respiratory rate. In this work, the powers of the outputs of a bank of order-3 FIR notch filters were used in a recursive scheme to estimate in real-time, and with a small delay, the respiratory rate from the RSA and the RPA waveforms simultaneously. The algorithm was tested on the public Physionet Fantasia data set and compared to the state-of-the-art in terms of estimation accuracy and delay. It was shown that the proposed method provides more accurate estimates with smaller delays than those of the state-of-the-art.

Using cardio-respiratory signals to recognize emotions elicited by watching music video clips

The automatic recognition of human emotions from physiological signals is of increasing interest in many applications. Images with high emotional content have been shown to alter signals such as the electrocardiogram (ECG) and the respiration among many other physiological recordings. However, recognizing emotions from multimedia stimuli, such as music video clips, which are growing in numbers in the digital world and are the medium of many recommendation systems, has not been adequately investigated. This study aims to investigate the recognition of emotions elicited by watching music video clips, from features extracted from the ECG, the respiration and several synchronization aspects of the two. On a public dataset, we achieved higher classification rates than the state-of-the-art using either the ECG or the respiration signals alone. A feature related to the synchronization of the two signals achieved even better performance.

The Respiration Pattern as an Indicator of the Anaerobic Threshold

The anaerobic threshold (AT) is a good index of personal endurance but needs a laboratory setting to be determined. It is important to develop easy AT field measurements techniques in order to rapidly adapt training programs. In the present study, it is postulated that the variability of the respiratory parameters decreases with exercise intensity (especially at the AT level). The aim of this work was to assess, on healthy trained subjects, the putative relationships between the variability of some respiration parameters and the AT. The heart rate and respiratory variables (volume, rate) were measured during an incremental exercise performed on a treadmill by healthy moderately trained subjects. Results show a decrease in the variance of 1/tidal volume with the intensity of exercise. Consequently, the cumulated variance (sum of the variance measured at each level of the exercise) follows an exponential relationship with respect to the intensity to reach eventually a plateau. The amplitude of this plateau is closely related to the AT (r=-0.8). It is concluded that the AT is related to the variability of the respiration.