Automatic face recognition for film character retrieval in feature-length films

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Automatic cast listing in feature-length films with Anisotropic Manifold Space

Our goal is to automatically determine the cast of a feature-length film. This is challenging because the cast size is not known, with appearance changes of faces caused by extrinsic imaging factors (illumination, pose, expression) often greater than due to differing identities. The main contribution of this paper is an algorithm for clustering over face appearance manifolds. Specifically: (i) we develop a novel algorithm for exploiting coherence of dissimilarities between manifolds, (ii) we show how to estimate the optimal dataset-specific discriminant manifold starting from a generic one, and (iii) we describe a fully automatic, practical system based on the proposed algorithm. The performance of the system is evaluated on well-known featurelength films and situation comedies on which it is shown to produce good results.

Red-green-blue electrogenerated chemiluminescence utilizing a digital camera as detector

Exploiting the distinct excitation and emission properties of concomitant electrochemiluminophores in conjunction with the inherent color selectivity of a conventional digital camera, we create a new strategy for multiplexed electrogenerated chemiluminescence detection, suitable for the development of low-cost, portable clinical diagnostic devices. Red, green and blue emitters can be efficiently resolved over the three-dimensional space of ECL intensity versus applied potential and emission wavelength. As the relative contribution ratio of each emitter to the photographic RGB channels is constant, the RGB ECL intensity versus applied-potential curves could be effectively isolated to a single emitter at each potential.

Degree of contribution (DoC) feature selection algorithm for structural brain MRI volumetric features in depression detection

Accurate detection of depression at an individual level using structural magnetic resonance imaging (sMRI) remains a challenge. Brain volumetric changes at a structural level appear to have importance in depression biomarkers studies. An automated algorithm is developed to select brain sMRI volumetric features for the detection of depression.

Motor imagery data classification for BCI application using wavelet packet feature extraction

The noninvasive brain imaging modalities have provided us an extraordinary means for monitoring the working brain. Among these modalities, Electroencephalography (EEG) is the most widely used technique for measuring the brain signals under different tasks, due to its mobility, low cost, and high temporal resolution. In this paper we investigate the use of EEG signals in brain-computer interface (BCI) systems.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

Representing images using curvilinear feature driven subdivision surfaces.

This paper presents a subdivision-based vector graphics for image representation and creation. The graphics representation is a subdivision surface defined by a triangular mesh augmented with color attribute at vertices and feature attribute at edges. Special cubic B-splines are proposed to describe curvilinear features of an image. New subdivision rules are then designed accordingly, which are applied to the mesh and the color attribute to define the spatial distribution and piecewise-smoothly varying colors of the image. A sharpness factor is introduced to control the color transition across the curvilinear edges. In addition, an automatic algorithm is developed to convert a raster image into such a vector graphics representation. The algorithm first detects the curvilinear features of the image, then constructs a triangulation based on the curvilinear edges and feature attributes, and finally iteratively optimizes the vertex color attributes and updates the triangulation. Compared with existing vector-based image representations, the proposed representation and algorithm have the following advantages in addition to the common merits (such as editability and scalability): 1) they allow flexible mesh topology and handle images or objects with complicated boundaries or features effectively; 2) they are able to faithfully reconstruct curvilinear features, especially in modeling subtle shading effects around feature curves; and 3) they offer a simple way for the user to create images in a freehand style. The effectiveness of the proposed method has been demonstrated in experiments.

Oxidant/antioxidant imbalance is an inherent feature of depression

BACKGROUND: 50% to 60% of the people who have recovered from the first episode of depression experience a relapse. The immune system of the people suffering from depression is in a permanent state of pathological pro-inflammatory readiness. There are some reports that depressive episodes cause sensitization of immune-inflammatory pathways and that staing of depression (e.g. number of depressive episodes) is correlated with immune-inflammatory markers. The main objective of the study was to delineate whether recurrent major depression (rDD) is characterized by alterations in selected immune-inflammatory biomarkers as compared with first episode of depression (ED-I), i.e. expression of mRNA and enzymatic activity of manganese superoxide dismutase (MnSOD, SOD-2), myeloperoxidase (MPO), inducible nitric oxide synthase (iNOS, NOS-2), and cyclooxygenase-2 (COX-2). METHODS: The study was carried out in a group of 131 patients: ED-I group - 42 patients, rDD group - 89 patients. Depression severity was assessed with the 17-item Hamilton Depression Rating Scale (HDRS). The number of depression episodes and the disease duration periods were recorded in each patient. For the patients, HDRS was administered at admission during the symptomatic phase, which would generally be either before or shortly after modification of the previous antidepressant drug regimen. Reassessment of the mental condition was conducted after 8 weeks of the pharmacological treatment also with the use of the HDRS scale. RESULTS: No significant statistical differences were found between the analysed groups as regards the intensity of depressive disorders. No differences in the expression of MnSOD, MPO, COX-2 and i-NOS genes on the level of both mRNA and protein were observed between both groups. No significant interrelation was noticed between the number of depression episodes experienced and the expression of selected genes on the mRNA level and protein level. CONCLUSIONS: There is no significant difference in MnSOD, MPO, COX-2 and i-NOS between patients with recurrent depressive disorders and those in a first episode of depression. These findings suggest that these enzymes are trait markers of depression and are not related to staging of depression.

3D motion matching algorithm using signature feature descriptor

This paper introduces a basic frame for rehabilitation motion practice system which detects 3D motion trajectory with the Microsoft Kinect (MSK) sensor system and proposes a cost-effective 3D motion matching algorithm. The rehabilitation motion practice system displays a reference 3D motion in the database system that the player (patient) tries to follow. The player’s motion is traced by the MSK sensor system and then compared with the reference motion to evaluate how well the player follows the reference motion. In this system, 3D motion matching algorithm is a key feature for accurate evaluation for player’s performance. Even though similarity measurement of 3D trajectories is one of the most important tasks in 3D motion analysis, existing methods are still limited. Recent researches focus on the full length 3D trajectory data set. However, it is not true that every point on the trajectory plays the same role and has the same meaning. In this situation, we developed a new cost-effective method that only uses the less number of features called ‘signature’ which is a flexible descriptor computed from the region of ‘elbow points’. Therefore, our proposed method runs faster than other methods which use the full length trajectory information. The similarity of trajectories is measured based on the signature using an alignment method such as dynamic time warping (DTW), continuous dynamic time warping (CDTW) or longest common sub-sequence (LCSS) method. In the experimental studies, we applied the MSK sensor system to detect, trace and match the 3D motion of human body. This application was assumed as a system for guiding a rehabilitation practice which can evaluate how well the motion practice was performed based on comparison of the patient’s practice motion traced by the MSK system with the pre-defined reference motion in a database. In order to evaluate the accuracy of our 3D motion matching algorithm, we compared our method with two other methods using Australian sign word dataset. As a result, our matching algorithm outperforms in matching 3D motion, and it can be exploited for a base framework for various 3D motion-based applications at low cost with high accuracy.

Stable feature selection with support vector machines

The support vector machine (SVM) is a popular method for classification, well known for finding the maximum-margin hyperplane. Combining SVM with l1-norm penalty further enables it to simultaneously perform feature selection and margin maximization within a single framework. However, l1-norm SVM shows instability in selecting features in presence of correlated features. We propose a new method to increase the stability of l1-norm SVM by encouraging similarities between feature weights based on feature correlations, which is captured via a feature covariance matrix. Our proposed method can capture both positive and negative correlations between features. We formulate the model as a convex optimization problem and propose a solution based on alternating minimization. Using both synthetic and real-world datasets, we show that our model achieves better stability and classification accuracy compared to several state-of-the-art regularized classification methods.

Stabilizing high-dimensional prediction models using feature graphs

We investigate feature stability in the context of clinical prognosis derived from high-dimensional electronic medical records. To reduce variance in the selected features that are predictive, we introduce Laplacian-based regularization into a regression model. The Laplacian is derived on a feature graph that captures both the temporal and hierarchic relations between hospital events, diseases, and interventions. Using a cohort of patients with heart failure, we demonstrate better feature stability and goodness-of-fit through feature graph stabilization.

Exploiting feature relationships towards stable feature selection

Feature selection is an important step in building predictive models for most real-world problems. One of the popular methods in feature selection is Lasso. However, it shows instability in selecting features when dealing with correlated features. In this work, we propose a new method that aims to increase the stability of Lasso by encouraging similarities between features based on their relatedness, which is captured via a feature covariance matrix. Besides modeling positive feature correlations, our method can also identify negative correlations between features. We propose a convex formulation for our model along with an alternating optimization algorithm that can learn the weights of the features as well as the relationship between them. Using both synthetic and real-world data, we show that the proposed method is more stable than Lasso and many state-of-the-art shrinkage and feature selection methods. Also, its predictive performance is comparable to other methods.

Stabilizing l1-norm prediction models by supervised feature grouping

Emerging Electronic Medical Records (EMRs) have reformed the modern healthcare. These records have great potential to be used for building clinical prediction models. However, a problem in using them is their high dimensionality. Since a lot of information may not be relevant for prediction, the underlying complexity of the prediction models may not be high. A popular way to deal with this problem is to employ feature selection. Lasso and l1-norm based feature selection methods have shown promising results. But, in presence of correlated features, these methods select features that change considerably with small changes in data. This prevents clinicians to obtain a stable feature set, which is crucial for clinical decision making. Grouping correlated variables together can improve the stability of feature selection, however, such grouping is usually not known and needs to be estimated for optimal performance. Addressing this problem, we propose a new model that can simultaneously learn the grouping of correlated features and perform stable feature selection. We formulate the model as a constrained optimization problem and provide an efficient solution with guaranteed convergence. Our experiments with both synthetic and real-world datasets show that the proposed model is significantly more stable than Lasso and many existing state-of-the-art shrinkage and classification methods. We further show that in terms of prediction performance, the proposed method consistently outperforms Lasso and other baselines. Our model can be used for selecting stable risk factors for a variety of healthcare problems, so it can assist clinicians toward accurate decision making.