Sparse temporal representations for facial expression recognition

In automatic facial expression recognition, an increasing number of techniques had been proposed for in the literature that exploits the temporal nature of facial expressions. As all facial expressions are known to evolve over time, it is crucially important for a classifier to be capable of modelling their dynamics. We establish that the method of sparse representation (SR) classifiers proves to be a suitable candidate for this purpose, and subsequently propose a framework for expression dynamics to be efficiently incorporated into its current formulation. We additionally show that for the SR method to be applied effectively, then a certain threshold on image dimensionality must be enforced (unlike in facial recognition problems). Thirdly, we determined that recognition rates may be significantly influenced by the size of the projection matrix \Phi. To demonstrate these, a battery of experiments had been conducted on the CK+ dataset for the recognition of the seven prototypic expressions - anger, contempt, disgust, fear, happiness, sadness and surprise - and comparisons have been made between the proposed temporal-SR against the static-SR framework and state-of-the-art support vector machine.

The morphology of service bundling settings

The purpose of this paper is to advance our understanding of what contextual factors influence the service bundling process in an organizational setting. Although previous literature contains insights into the mechanisms underlying bundling and the artefacts for performing the bundling task itself, the body of knowledge seems to lack a comprehensive framework for analysing the actual scenario in which the bundling process is performed. This is required as the scenario will influence the bundling method and the IT support. We address this need by designing a morphological box for analysing bundling scenarios in different organizational settings. The factors featured in the box are systematised into a set of four categories of bundling layers which we identify from reviewing literature. The two core layers in the framework are the service bundling on a type level and on an instance level (i.e. configuration). To demonstrate the applicability and utility of the proposed morphological box, we apply it to assess the underlying differences and commonalities of two different bundling scenarios from the B2B and G2C sectors which stress the differences between bundling on a type and instance level. In addition, we identify several prospects for future research that can benefit from the proposed morphological box.

No evidence for subliminal affective priming with emotional facial expression primes

The present study investigated whether facial expressions of emotion presented outside consciousness awareness will elicit evaluative responses as assessed in affective priming. Participants were asked to evaluate pleasant and unpleasant target words that were preceded by masked or unmasked schematic (Experiment 1) or photographic faces (Experiments 1 and 2) with happy or angry expressions. They were either required to perform the target evaluation only or to perform the target evaluation and to name the emotion expressed by the face prime. Prime-target interval was 300 ms in Experiment 1 and 80 ms in Experiment 2. Naming performance confirmed the effectiveness of the masking procedure. Affective priming was evident after unmasked primes in tasks that required naming of the facial expressions for schematic and photographic faces and after unmasked primes in tasks that did not require naming for photographic faces. No affective priming was found after masked primes. The present study failed to provide evidence for affective priming with masked face primes, however, it indicates that voluntary attention to the primes enhances affective priming.

Discovering the best feature extraction and selection algorithms for spontaneous facial expression recognition

Feature extraction and selection are critical processes in developing facial expression recognition (FER) systems. While many algorithms have been proposed for these processes, direct comparison between texture, geometry and their fusion, as well as between multiple selection algorithms has not been found for spontaneous FER. This paper addresses this issue by proposing a unified framework for a comparative study on the widely used texture (LBP, Gabor and SIFT) and geometric (FAP) features, using Adaboost, mRMR and SVM feature selection algorithms. Our experiments on the Feedtum and NVIE databases demonstrate the benefits of fusing geometric and texture features, where SIFT+FAP shows the best performance, while mRMR outperforms Adaboost and SVM. In terms of computational time, LBP and Gabor perform better than SIFT. The optimal combination of SIFT+FAP+mRMR also exhibits a state-of-the-art performance.

Improved facial expression recognition via uni-hyperplane classification

Large margin learning approaches, such as support vector machines (SVM), have been successfully applied to numerous classification tasks, especially for automatic facial expression recognition. The risk of such approaches however, is their sensitivity to large margin losses due to the influence from noisy training examples and outliers which is a common problem in the area of affective computing (i.e., manual coding at the frame level is tedious so coarse labels are normally assigned). In this paper, we leverage the relaxation of the parallel-hyperplanes constraint and propose the use of modified correlation filters (MCF). The MCF is similar in spirit to SVMs and correlation filters, but with the key difference of optimizing only a single hyperplane. We demonstrate the superiority of MCF over current techniques on a battery of experiments.

Molecules, morphology, and ecology indicate a recent, amphibious ancestry for echidnas

The semiaquatic platypus and terrestrial echidnas (spiny anteaters) are the only living egg-laying mammals (monotremes). The fossil record has provided few clues as to their origins and the evolution of their ecological specializations; however, recent reassignment of the Early Cretaceous Teinolophos and Steropodon to the platypus lineage implies that platypuses and echidnas diverged >112.5 million years ago, reinforcing the notion of monotremes as living fossils. This placement is based primarily on characters related to a single feature, the enlarged mandibular canal, which supplies blood vessels and dense electrosensory receptors to the platypus bill. Our reevaluation of the morphological data instead groups platypus and echidnas to the exclusion of Teinolophos and Steropodon and suggests that an enlarged mandibular canal is ancestral for monotremes (partly reversed in echidnas, in association with general mandibular reduction). A multigene evaluation of the echidna–platypus divergence using both a relaxed molecular clock and direct fossil calibrations reveals a recent split of 19–48 million years ago. Platypus-like monotremes (Monotrematum) predate this divergence, indicating that echidnas had aquatically foraging ancestors that reinvaded terrestrial ecosystems. This ecological shift and the associated radiation of echidnas represent a recent expansion of niche space despite potential competition from marsupials. Monotremes might have survived the invasion of marsupials into Australasia by exploiting ecological niches in which marsupials are restricted by their reproductive mode. Morphology, ecology, and molecular biology together indicate that Teinolophos and Steropodon are basal monotremes rather than platypus relatives, and that living monotremes are a relatively recent radiation.

Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Sections of the city : architecturalising the tools of urban morphology

The study of urban morphology has become an expanding field of research within the architectural discipline, providing theories to be used as tools in the understanding and design of urban landscapes from the past, the present and into the future. Drawing upon contemporary architectural design theory, this investigation reveals what a sectional analysis of an urban landscape can add to the existing research methods within this field. This paper conducts an enquiry into the use of the section as a tool for urban morphological analysis. Following the methodology of the British school of urban morphology, sections through the urban fabric of the case study city of Brisbane are compared. The results are categorised to depict changes in scale, components and utilisation throughout various timeframes. The key findings illustrate how the section, when read in conjunction with the plan can be used to interpret changes to urban form and the relationship that this has to the quality of the urban environment in the contemporary city.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

From slum to suburbia : examining a spectrum of planned and unplanned urban morphology in humid sub-tropical regions of the world

The current rapid urban growth throughout the world manifests in various ways and historically cities have grown, similarly, alternately or simultaneously between planned extensions and organic informal settlements (Mumford, 1989). Within cities different urban morphological regions can reveal different contexts of economic growth and/or periods of dramatic social/technological change (Whitehand, 2001, 105). Morpho-typological study of alternate contexts can present alternative models and contribute to the present discourse which questions traditional paradigms of urban planning and design (Todes et al, 2010). In this study a series of cities are examined as a preliminary exploration into the urban morphology of cities in ‘humid subtropical’ climates. From an initial set of twenty, six cities were selected: Sao Paulo, Brazil; Jacksonville, USA; Maputo, Mozambique; Kanpur, India; Hong Kong, China; and Brisbane, Australia. The urban form was analysed from satellite imagery at a constant scale. Urban morphological regions (types) were identified as those demonstrating particular consistant characteristics of form (density, typology and pattern) different to their surroundings when examined at a constant scale. This analysis was correlated against existing data and literature discussing the proliferation of two types of urban development, ‘informal settlement’ (defined here as self-organised communities identifiable but not always synonymous with ‘slums’) and ‘suburbia’ (defined here as master planned communities of generally detached houses prevalent in western society) - the extreme ends of a hypothetical spectrum from ‘planned’ to ‘spontaneous’ urban development. Preliminary results show some cities contain a wide variety of urban form ranging from the highly organic ‘self-organised’ type to the highly planned ‘master planned community’ (in the case of Sao Paulo) while others tend to fall at one end of the planning spectrum or the other (more planned in the cases of Brisbane and Jacksonville; and both highly planned and highly organic in the case of Maputo). Further research will examine the social, economical and political drivers and controls which lead to this diversity or homogeneity of urban form and speculates on the role of self-organisation as a process for the adaptation of urban form.

An analytical tool that quantifies cellular morphology changes from three-dimensional fluorescence images

The most common software analysis tools available for measuring fluorescence images are for two-dimensional (2D) data that rely on manual settings for inclusion and exclusion of data points, and computer-aided pattern recognition to support the interpretation and findings of the analysis. It has become increasingly important to be able to measure fluorescence images constructed from three-dimensional (3D) datasets in order to be able to capture the complexity of cellular dynamics and understand the basis of cellular plasticity within biological systems. Sophisticated microscopy instruments have permitted the visualization of 3D fluorescence images through the acquisition of multispectral fluorescence images and powerful analytical software that reconstructs the images from confocal stacks that then provide a 3D representation of the collected 2D images. Advanced design-based stereology methods have progressed from the approximation and assumptions of the original model-based stereology(1) even in complex tissue sections(2). Despite these scientific advances in microscopy, a need remains for an automated analytic method that fully exploits the intrinsic 3D data to allow for the analysis and quantification of the complex changes in cell morphology, protein localization and receptor trafficking. Current techniques available to quantify fluorescence images include Meta-Morph (Molecular Devices, Sunnyvale, CA) and Image J (NIH) which provide manual analysis. Imaris (Andor Technology, Belfast, Northern Ireland) software provides the feature MeasurementPro, which allows the manual creation of measurement points that can be placed in a volume image or drawn on a series of 2D slices to create a 3D object. This method is useful for single-click point measurements to measure a line distance between two objects or to create a polygon that encloses a region of interest, but it is difficult to apply to complex cellular network structures. Filament Tracer (Andor) allows automatic detection of the 3D neuronal filament-like however, this module has been developed to measure defined structures such as neurons, which are comprised of dendrites, axons and spines (tree-like structure). This module has been ingeniously utilized to make morphological measurements to non-neuronal cells(3), however, the output data provide information of an extended cellular network by using a software that depends on a defined cell shape rather than being an amorphous-shaped cellular model. To overcome the issue of analyzing amorphous-shaped cells and making the software more suitable to a biological application, Imaris developed Imaris Cell. This was a scientific project with the Eidgenössische Technische Hochschule, which has been developed to calculate the relationship between cells and organelles. While the software enables the detection of biological constraints, by forcing one nucleus per cell and using cell membranes to segment cells, it cannot be utilized to analyze fluorescence data that are not continuous because ideally it builds cell surface without void spaces. To our knowledge, at present no user-modifiable automated approach that provides morphometric information from 3D fluorescence images has been developed that achieves cellular spatial information of an undefined shape (Figure 1). We have developed an analytical platform using the Imaris core software module and Imaris XT interfaced to MATLAB (Mat Works, Inc.). These tools allow the 3D measurement of cells without a pre-defined shape and with inconsistent fluorescence network components. Furthermore, this method will allow researchers who have extended expertise in biological systems, but not familiarity to computer applications, to perform quantification of morphological changes in cell dynamics.

Using optical coherence tomography to assess corneoscleral morphology after soft contact lens wear

Purpose. To evaluate the use of optical coherence tomography (OCT) to assess the effect of different soft contact lenses on corneoscleral morphology. Methods. Ten subjects had anterior segment OCT B-scans taken in the morning and again after six hours of soft contact lens wear. For each subject, three different contact lenses were used in the right eye on non-consecutive days, including a hydrogel sphere, a silicone hydrogel sphere and a silicone hydrogel toric. After image registration and layer segmentation, analyses were performed of the first hyper-reflective layer (HRL), the epithelial basement membrane (EBL) and the epithelial thickness (HRL to EBL). A root mean square difference (RMSD) of the layer profiles and the thickness change between the morning and afternoon measurements, was used to assess the effect of the contact lens on the corneoscleral morphology. Results. The soft contact lenses had a statistically significant effect on the morphology of the anterior segment layers (p <0.001). The average amounts of change for the three lenses (average RMSD values) for the corneal region were lower (3.93±1.95 µm for the HRL and 4.02±2.14 µm for the EBL) than those measured in the limbal/scleral region (11.24±6.21 µm for the HRL and 12.61±6.42 µm for the EBL). Similarly, averaged across the three lenses, the RMSD in epithelial thickness was lower in the cornea (2.84±0.84 µm) than the limbal/scleral (5.47±1.71 µm) region. Post-hoc analysis showed that ocular surface changes were significantly smaller with the silicone hydrogel sphere lens than both the silicone hydrogel toric (p<0.005) and hydrogel sphere (p<0.02) for the combined HRL and EBL data. Conclusions. In this preliminary study, we have shown that soft contact lenses can produce small but significant changes in the morphology of the limbal/scleral region and that OCT technology is useful in assessing these changes. The clinical significance of these changes is yet to be determined.