Wael Louis

Co-Occurrence of Local Binary Patterns Features for Frontal Face Detection in Surveillance Applications

Face detection in video sequence is becoming popular in surveillance applications. The tradeoff between obtaining discriminative features to achieve accurate detection versus computational overhead of extracting these features, which affects the classification speed, is a persistent problem. This paper proposes to use multiple instances of rotational Local Binary Patterns (LBP) of pixels as features instead of using the histogram bins of the LBP of pixels. The multiple features are selected using the sequential forward selection algorithm we called Co-occurrence of LBP (CoLBP). CoLBP feature extraction is computationally efficient and produces a high-performance rate. CoLBP features are used to implement a frontal face detector applied on a 2D low-resolution surveillance sequence. Experiments show that the CoLBP face features outperform state-of-the-art Haar-like features and various other LBP features extensions. Also, the CoLBP features can tolerate a wide range of illumination and blurring changes.

Frontal face detection for surveillance purposes using dual Local Binary Patterns features

Face detection in video sequence is becoming popular in surveillance applications, but the usage of large number of features and the long training time are persistent problems. This paper integrates two types of Local Binary Patterns (LBP) features in order to achieve a high detection rate with a high discriminative power face detector. First LBP feature is a novel way of using the Circular LBP, in which the pixels of the image are targeted; it is a non-computationally expensive feature extraction. The second LBP feature is the LBP Histogram, in which regions in the image are targeted; it is more computationally expensive than Circular LBP features but has higher discriminative power. The proposed detector is examined on real-life low-resolution surveillance sequence. Conducted experiments show that the proposed detector achieves 98% detection rate in comparison to 91% for the Lienhart detector. The proposed detector tolerates wide range of illumination changes.

One dimensional multi-resolution Local Binary Patterns features (1DMRLBP) for regular electrocardiogram (ECG) waveform detection.

Feeding a noisy signal to a biometric system degrades its performance. Hence, signal quality measure is used to avoid passing irregular signals to subsequent systems such as bio-metric systems. To tackle this issue, 1DMRLBP features, which are 1 dimensional signal feature extraction (inspired by the 2 dimensional image Local Binary Patterns) is proposed. 1DMRLBP with its multi-resolution capability captures local and global signal characteristics; and with its histogram extraction avoids segments misalignment and reduces the number of features. Also with some modifications, 1DMRLBP accommodates the problem of unknown amplitude of a signal. 1DMRLBP achieves 91% performance rate in distinguishing between regular and irregular ECG waveforms. MATLAB code and more information are available at www.comm.utoronto.ca/~wlouis/1DMRLBP.

Enhanced weakly trained frontal face detector for surveillance purposes

Face detection is becoming popular in surveillance applications; however, the need of enormous size face/non-face dataset, large number of features, and long training time are persistent problems. This paper claims that only a subset of the total number of features conserves the major power to detect faces; hence, this subset is capable to detect faces with high detection rate. The proposed detector fuses the results of two classifiers where one is trained with only 40 Haar-like features and the other is trained with only 50 LBP Histogram features. A pre-processing stage of skin-tone detection is applied to reduce the false positive rate. The detector is examined on real-life low-resolution surveillance sequence. Conducted experiments show that the proposed detector can achieve a high detection rate and a low false positive rate. Also, it outperforms Lienhart detector and tolerates wide range of illumination and blurring changes.

On biometric systems: electrocardiogram Gaussianity and data synthesis

Electrocardiogram is a slow signal to acquire, and it is prone to noise. It can be inconvenient to collect large number of ECG heartbeats in order to train a reliable biometric system; hence, this issue might result in a small sample size phenomenon which occurs when the number of samples is much smaller than the number of observations to model. In this paper, we study ECG heartbeat Gaussianity and we generate synthesized data to increase the number of observations. Data synthesis, in this paper, is based on our hypothesis, which we support, that ECG heartbeats exhibit a multivariate normal distribution; therefore, one can generate ECG heartbeats from such distribution. This distribution is deviated from Gaussianity due to internal and external factors that change ECG morphology such as noise, diet, physical and psychological changes, and other factors, but we attempt to capture the underlying Gaussianity of the heartbeats. When this method was implemented for a biometric system and was examined on the University of Toronto database of 1012 subjects, an equal error rate (EER) of 6.71% was achieved in comparison to 9.35% to the same system but without data synthesis. Dimensionality reduction is widely examined in the problem of small sample size; however, our results suggest that using the proposed data synthesis outperformed several dimensionality reduction techniques by at least 3.21% in EER. With small sample size, classifier instability becomes a bigger issue and we used a parallel classifier scheme to reduce it. Each classifier in the parallel classifier is trained with the same genuine dataset but different imposter datasets. The parallel classifier has reduced predictors’ true acceptance rate instability from 6.52% standard deviation to 1.94% standard deviation.

An adaptive multi-level wavelet denoising method for 40-Hz ASSR

This paper presents a novel method for extracting auditory steady state response (ASSR) signals from background electroencephalogram. 40-Hz ASSR signals are sensitive to subjects state of consciousness and can be used as a monitor for the depth of anaesthesia. The suggested method is a multilevel adaptive wavelet denoising scheme that extracts ASSR cycles faster than the currently used averaging schemes and can monitor depth of anesthesia with minimum delay. It estimates the variance of noise and adapts the threshold at each denoising level. The algorithm benefits from the fact that wavelet transform preserves temporality and takes into consideration the correlation of the neighbor wavelet coefficients. Our method extracts ASSR from small number of epochs in a short time moreover, it does not neglect the variations of the signal from one epoch to the other and outperforms averaging. The performance of the proposed scheme is evaluated on the synthetic and on real data recorded during induction of anaesthesia ASSR signals in the paper.

Enhanced binary patterns for electrocardiogram (ECG) biometrics

Most, if not all, binary patterns variants consider signals observations separately; hence, binary patterns variants ignore any relationship among observations. In this paper we proposed an algorithm that enhances binary patterns extraction to accommodate for temporal progression changes. The enhanced binary patterns feature extraction extracts a single feature vector that captures changes occurred to observations over time. This enhancement is crucial in cases where the examined signal is repetitive in nature, such as ECG signal. Enhanced binary patterns were examined for ECG biometric application on ECG database with 1,012 subjects. The enhanced binary patterns achieved an EER of 7.89% in comparison to 12.4% and 12.3% for non-enhanced binary patterns and a state of the art work. We also showed that enhanced binary patterns features are capable to extract discriminative ECG features that reduced EER by 15% when compared to time-domain raw samples.

Weakly trained dual features extraction based detector for frontal face detection

This paper investigates the inconvenience of using huge number of features, enormous training dataset and lengthy training session to achieve a good performance frontal face detector. The proposed face detector is based on a novel idea which proposes using joint decision from two parallel different features trained detectors, one detector is trained with Local Binary Patterns (LBP) features and the other with Haar-like features. Both detectors are trained with few features using not a huge face/non-face dataset and within relatively short period of time. Hence, both detectors agree on the face image but seldom agree on the non-face image. The result is significantly improved using a multi-detections merging algorithm using simple clustering method. The robustness of the detector is examined once using a face/non-face dataset and compared to Lienhart frontal face detector, and secondly using a real-life sequence.

Feature Selection for Nonstationary Data: Application to Human Recognition Using Medical Biometrics

Electrocardiogram (ECG) and transient evoked otoacoustic emission (TEOAE) are among the physiological signals that have attracted significant interest in biometric community due to their inherent robustness to replay and falsification attacks. However, they are time-dependent signals and this makes them hard to deal with in across-session human recognition scenario where only one session is available for enrollment. This paper presents a novel feature selection method to address this issue. It is based on an auxiliary dataset with multiple sessions where it selects a subset of features that are more persistent across different sessions. It uses local information in terms of sample margins while enforcing an across-session measure. This makes it a perfect fit for aforementioned biometric recognition problem. Comprehensive experiments on ECG and TEOAE variability due to time lapse and body posture are done. Performance of the proposed method is compared against seven state-of-the-art feature selection algorithms as well as another six approaches in the area of ECG and TEOAE biometric recognition. Experimental results demonstrate that the proposed method performs noticeably better than other algorithms.

Real-time heartbeat outlier removal in electrocardiogram (ECG) biometrie system

Electrocardiogram signal is prone to noise interference. Processing noisy signals in an automated system such as biometric systems negatively affects its performance. In this paper, we developed a real-time abnormal electrocardiogram heartbeat detection and removal. The proposed technique eliminates outliers in real-time while subjects data are being collected. We used Gaussian mixture model to model normal electrocardiogram heartbeat. A Gaussian mixture of 2 components achieved the least equal error rate of 12% in separating normal from abnormal heartbeats. We utilized this outlier removal method in a biometric system and examined it on a fingertip acquired ECG signals database. The designed biometric system had an equal error rate of 5.94% in comparison to 12.30% in a state of the art approach.