Beom-Seok Oh

Combining sclera and periocular features for multi-modal identity verification

In this paper, we propose to combine sclera and periocular features for identity verification. The proposal is particularly useful in applications related to face recognition when the face is partially occluded with only periocular region revealed. Due to its relatively new exposition in the literature of biometrics, particular attention will be paid to sclera feature extraction in this work. For periocular feature extraction, structured random projections were adopted to extract compressed vertical and horizontal components of image features. The binary sclera features are eventually fused with the periocular features at a score level. Extensive experiments have been performed on UBIRIS v1 session1 and session2 databases to assess the verification performance before and after fusion. Around 5% of equal error rate performance was observed to be enhanced by fusing sclera with periocular features comparing with that before fusion.

Extraction and fusion of partial face features for cancelable identity verification

In this paper, we propose to extract localized random features directly from partial face image matrix for cancelable identity verification. Essentially, the extracted random features consist of compressed horizontal and vertical facial information obtained from a structured projection of the raw face images. For template security reason, the face appearance information is concealed via averaging several templates over different transformations. The match score outputs of these cancelable templates are then fused through a total error rate minimization. Extensive experiments were carried out to evaluate and benchmark the performance of the proposed method based on the AR, FERET, ORL, Sheffield and BERC databases. Our empirical results show encouraging performances in terms of verification accuracy as well as satisfying four cancelable biometric properties.

Combining local face image features for identity verification

With an aim of extracting robust facial features under pose variations, this paper presents two directional projections corresponding to extraction of vertical and horizontal local face image features. The matching scores computed from both horizontal and vertical features are subsequently fused at score level via an extreme learning machine that optimizes the total error rate for performance enhancement. In order to benchmark the performance, both the feature extraction and fusion results are compared with that of popular face recognition methods such as principal components analysis and linear discriminant analysis in terms of equal error rate and CPU time. Our empirical experiments using four data sets show encouraging results under considerable horizontal pose variations.

On projection-based methods for periocular identity verification

The periocular biometric comes into the spotlight recently due to several advantageous characteristics such as easily available and provision of crucial face information. However, many existing works are dedicated to extracting image features using texture based techniques such as local binary pattern (LBP). In view of the simplicity and effectiveness offered, this paper proposes to investigate into projection-based methods for periocular identity verification. Several well established projection-based methods such as principal component analysis, its variants and linear discriminant analysis will be adopted in our performance evaluation based on a subset of FERET face database. Our empirical results show that supervised learning methods significantly outperform those unsupervised learning methods and LBP in terms of equal error rate performance.

An image edge mask for face identity verification

In this paper, we propose an image edge mask method for face identity verification. The method uses a mask matrix arising from edge detection to extract essential facial information via a Hadamard-Schur product to form a feature template. Several edge detectors have been experimented and our empirical observations show encouraging results. Apart from using an edge mask, the proposed method is generic in the sense that it can be easily extended using different image masks for direct and fast feature extraction.

Manifold ranking based scoring system with its application to cardiac arrest prediction

BACKGROUND The recently developed geometric distance scoring system has shown the effectiveness of scoring systems in predicting cardiac arrest within 72h and the potential to predict other clinical outcomes. However, the geometric distance scoring system predicts scores based on only local structure embedded by the data, thus leaving much room for improvement in terms of prediction accuracy. METHODS We developed a novel scoring system for predicting cardiac arrest within 72h. The scoring system was developed based on a semi-supervised learning algorithm, manifold ranking, which explores both the local and global consistency of the data. System evaluation was conducted on emergency department patients׳ data, including both vital signs and heart rate variability (HRV) parameters. Comparison of the proposed scoring system with previous work was given in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV). RESULTS Out of 1025 patients, 52 (5.1%) met the primary outcome. Experimental results show that the proposed scoring system was able to achieve higher area under the curve (AUC) on both the balanced dataset (0.907 vs. 0.824) and the imbalanced dataset (0.774 vs. 0.734) compared to the geometric distance scoring system. CONCLUSIONS The proposed scoring system improved the prediction accuracy by utilizing the global consistency of the training data. We foresee the potential of extending this scoring system, as well as manifold ranking algorithm, to other medical decision making problems. Furthermore, we will investigate the parameter selection process and other techniques to improve performance on the imbalanced dataset.

Effects of noisy sounds on human stress using ECG signals: An empirical study

In this paper, we explore the effects of noisy sounds (i.e. auditory stressor) on human stress using electrocardiogram (ECG) signals. The noisy sounds utilized in this study include: sound of car horn, children crying, siren, drilling and from a construction site. Essentially, the ECG signals are represented by eight heart rate variability features which are commonly utilized in human stress related literature. A statistical significance test is then performed per feature per sound so that those effective features for detecting human stress caused by the noisy sounds can be localized. Our empirical results performed using an in-house database (ten minutes of ECG signals from seventeen healthy subjects), showed that some of the noisy sounds cause human stress. The results also reveal that frequency-domain features contain more stress related information caused by the noisy sounds than that of time-domain and geometric features.

Visual tracking with online discriminative learning

We treat tracking as a binary classification task in order to distinguish between an object to be tracked and the background. We propose to integrate an online learning based total-error-rate minimization method (OTER) with an observation model of particle filter for visual tracking. The particle filter is modeled using an affine dynamic model and an observation model. The observation model is constructed using the OTER classifier for binary pattern classification. The proposed method is empirically evaluated both qualitatively and quantitatively using several publicly available video sequences.

Extreme learning machine based mutual information estimation with application to time-series change-points detection

Abstract In this paper, we propose an efficient parameter tuning-free squared-loss mutual information (SMI) estimator in a form of a radial basis function (RBF) network. The input layer of the proposed network propagates a sample pair of two random variables to the hidden layer. The propagated samples are then transformed by a set of Gaussian RBF kernels with randomly determined kernel centers and widths similar to that in an extreme learning machine. The output layer adopts a linear weighting scheme which can be analytically estimated. Our empirical results show that the proposed estimator outperforms the competing state-of-the-art SMI estimators in terms of computational efficiency while showing the comparable estimation accuracy performance. Moreover, the proposed model achieves promising results in an application study of time-series change-points detection and driving stress.

A single layer feedforward fusion network for face verification

In this paper, a single hidden-layer feedforward fusion network is proposed for face identity verification. Essentially, the feature extraction, matching score calculation and fusion algorithm design steps are integrated and absorbed into a hidden layer of the model. Each hidden node works on the raw face image directly and produces an Euclidean distance based match score within the network. These scores are then incorporated with output weights to produce a fused score at the final stage. Our experimental study conducted using three face databases shows that the proposed model consistently outperforms competing methods.