Use of log polar space for foveation and feature recognition

The finding and maintaining of high accuracy foveation points for several types of recognised feature in log polar space such as a line, circular or elliptical arc is considered. Log polar space is preferred over cartesian space as it provides a high resolution and a wide viewing angle; feature invariance in the fovea simplifies foveation; it allows multi-resolution analysis; and rotation and scale are linear translations in log polar space.

Human saccadic eye movements and tracking by active foveation in log polar space

One of the possible models of the human visual system (HVS) in the computer vision literature has a high resolution fovea and exponentially decreasing resolution periphery. The high resolution fovea is used to extract necessary information in order to solve a vision task and the periphery may be used to detect motion. To obtain the desired information, the fovea is guided by the contents of the scene and other knowledge to position the fovea over areas of interest. These eye movements are called saccades and corrective saccades. A two stage process has been implemented as a mechanism for changing foveation in log polar space. Initially, the open loop stage roughly foveates on the best interest feature and then the closed loop stage is invoked to accurately iteratively converge onto the foveation point. The open loop stage developed for the foveation algorithm is applied to saccadic eye movements and a tracking system. Log polar space is preferred over Cartesian space as: (1) it simultaneously provides high resolution and a wide viewing angle; and (2) feature invariance occurs in the fovea which simplifies the foveation process.

Resolution considerations in spatially variant sensors

Log polar transformations for space variant systems have been proposed and used in active vision research. The idea is to generate an image with a varying resolution over a wide angle field of view. The fovea is of high resolution and the periphery is of exponentially reduced resolution. The justifications for such a sensor are: (i) it provides high resolution and a wide viewing angle, (ii) feature invariance in the fovea simplifies foveation, and (iii) it allows multiresolution analysis. The receptor density of the human retina is very high, i.e. of the order of 106 receptors at the fovea. The question is, what resolution should space variant active vision systems have? Real visual sensors have been implemented but is the resolution produced high enough? This paper investigates the resolution requirements of a space variant sensor by simulation for a tracking system using raytracing

The personal wellbeing index : psychometric equivalance for adults and school children

Despite the wealth of accumulated research evaluating subjective wellbeing (SWB) in children and adults, the validity of scores from parallel forms of SWB measures for each age group has yet to be empirically tested. This study examines the psychometric equivalence of the child and adult forms of the personal wellbeing index (PWI) using multiple-group confirmatory factor analysis. The child sample comprised 1,029 Victorian high-school students (aged 11–20) sampled across three independent studies. The adult sample comprised 1,965 Australian adults drawn from the Australian Unity Wellbeing Index. The results demonstrated strict factorial invariance between both versions, suggesting that the PWI measures the same underlying construct in adolescent and adult populations. These findings provide support for quantitative comparisons between adult and adolescent SWB data as valid.

Measuring walking within and outside the neighborhood in Chinese elders : reliability and validity

Background : Walking is a preferred, prevalent and recommended activity for aging populations and is influenced by the neighborhood built environment. To study this influence it is necessary to differentiate whether walking occurs within or outside of the neighborhood. The Neighborhood Physical Activity Questionnaire (NPAQ) collects information on setting-specific physical activity, including walking, inside and outside one's neighborhood. While the NPAQ has shown to be a reliable measure in adults, its reliability in older adults is unknown. Additionally its validity and the influence of type of neighborhood on reliability and validity have yet to be explored. Methods : The NPAQ walking component was adapted for Chinese speaking elders (NWQ-CS). Ninety-six Chinese elders, stratified by social economic status and neighborhood walkability, wore an accelerometer and completed a log of walks for 7 days. Following the collection of valid data the NWQ-CS was interviewer-administered. Fourteen to 20 days (average of 17 days) later the NWQ-CS was re-administered. Test-retest reliability and validity of the NWQ-CS were assessed. Results : Reliability and validity estimates did not differ with type of neighborhood. NWQ-CS measures of walking showed moderate to excellent reliability. Reliability was generally higher for estimates of weekly frequency than minutes of walking. Total weekly minutes of walking were moderately related to all accelerometry measures. Moderate-to-strong associations were found between the NWQ-CS and log-of-walks variables. The NWQ-CS yielded statistically significantly lower mean values of total walking, weekly minutes of walking for transportation and weekly frequency of walking for transportation outside the neighborhood than the log-of-walks. Conclusions : The NWQ-CS showed measurement invariance across types of neighborhoods. It is a valid measure of walking for recreation and frequency of walking for transport. However, it may systematically underestimate the duration of walking for transport in samples that engage in high levels of this type of walking.

Body image during pregnancy: an evaluation of the suitability of the body attitudes questionnaire

Background: 

Cross-cultural adaption of the Health Educaiton Impact Questionnaire: experimental study showed expert committee, not back-translation, added value

Objectives
To assess the contribution of back-translation and expert committee to the content and psychometric properties of a translated multidimensional questionnaire.

Study Design and Setting
Recommendations for questionnaire translation include back-translation and expert committee, but their contribution to measurement properties is unknown. Four English to French translations of the Health Education Impact Questionnaire were generated with and without committee or back-translation. Face validity, acceptability, and structural properties were compared after random assignment to people with rheumatoid arthritis (N = 1,168), chronic renal failure (N = 2,368), and diabetes (N = 538). For face validity, 15 bilingual people compared translations quality with the original. Psychometric properties were examined using confirmatory factor analysis (metric and scalar invariance) and item response theory.

Results
Qualitatively, there were five types of translation errors: style, intensity, frequency/time frame, breadth, and meaning. Bilingual assessors ranked best the translations with committee (P = 0.0026). All translations had good structural properties (root mean square error of approximation <0.05; comparative fit index [CFI], ≥0.899; and Tucker–Lewis index, ≥0.889). Full measurement invariance was observed between translations (ΔCFI ≤ 0.01) with metric invariance between translations and original (lowest ΔCFI = 0.022 between fully constrained models and models with free intercepts). Item characteristic curve analyses revealed no significant differences.

Conclusion
This is the first experimental evidence that back-translation has moderate impact, whereas expert committee helps to ensure accurate content.

Colour invariants for machine face recognition

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colour-based representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

Face Recognition from Video Using the Generic Shape-Illumination Manifold

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. In particular there are three areas of novelty: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation, learnt offline, to generalize in the presence of extreme illumination changes; (ii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve invariance to unseen head poses; and (iii) we introduce an accurate video sequence “reillumination” algorithm to achieve robustness to face motion patterns in video. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our system consistently demonstrated a nearly perfect recognition rate (over 99.7%), significantly outperforming state-of-the-art commercial software and methods from the literature

Face set classification using maximally probable mutual modes

In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of maximally probable mutual modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals

On Person Authentication by Fusing Visual and Thermal Face Biometrics

Recognition algorithms that use data obtained by imaging faces in the thermal spectrum are promising in achieving invariance to extreme illumination changes that are often present in practice. In this paper we analyze the performance of a recently proposed face recognition algorithm that combines visual and thermal modalities by decision level fusion. We examine (i) the effects of the proposed data preprocessing in each domain, (ii) the contribution to improved recognition of different types of features, (iii) the importance of prescription glasses detection, in the context of both 1-to-N and 1-to-1 matching (recognition vs. verification performance). Finally, we discuss the significance of our results and, in particular, identify a number of limitations of the current state-of-the-art and propose promising directions for future research.

A pose-wise linear illumination manifold model for face recognition using video

The objective of this work is to recognize faces using video sequences both for training and novel input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. There are three major areas of novelty: (i) illumination generalization is achieved by combining coarse histogram correction with fine illumination manifold-based normalization; (ii) pose robustness is achieved by decomposing each appearance manifold into semantic Gaussian pose clusters, comparing the corresponding clusters and fusing the results using an RBF network; (iii) a fully automatic recognition system based on the proposed method is described and extensively evaluated on 600 head motion video sequences with extreme illumination, pose and motion pattern variation. On this challenging data set our system consistently demonstrated a very high recognition rate (95% on average), significantly outperforming state-of-the-art methods from the literature.