Selecting, optimizing and fusing ‘salient’ Gabor features for facial expression recognition

This paper describes a novel framework for facial expression recognition from still images by selecting, optimizing and fusing ‘salient’ Gabor feature layers to recognize six universal facial expressions using the K nearest neighbor classifier. The recognition comparisons with all layer approach using JAFFE and Cohn-Kanade (CK) databases confirm that using ‘salient’ Gabor feature layers with optimized sizes can achieve better recognition performance and dramatically reduce computational time. Moreover, comparisons with the state of the art performances demonstrate the effectiveness of our approach.

Social networking : investigating the features of Facebook application

Research on social networking sites like Facebook is emerging but sparse. The exploratory study investigates the value users derive from self-described ‘cool’ Facebook applications, and explores the features that either encourage or discourage users to recommend application to their friends. Thus the concepts of value and cool are explored in a social networking setting. Our qualitative data shows that consumers derive a combination of functional value along with either social or emotional value from the applications. Female Facebook users indicated self-expression as important, while mates then to use Facebook application to socially compete. Three broad categories emerged for application features; symmetrical features can both encourage or discourage recommendation, asymmetrical features one encourage or discourage but not both, and polar features where different levels of the same feature encourage or discourage. Recommending or not recommending an application tends to be the result of a combination of features rather than one feature in isolation.

Human brain regions required for the dividing and switching of attention between two features of a single object

This combined PET and ERP study was designed to identify the brain regions activated in switching and divided attention between different features of a single object using matched sensory stimuli and motor response. The ERP data have previously been reported in this journal [64]. We now present the corresponding PET data. We identified partially overlapping neural networks with paradigms requiring the switching or dividing of attention between the elements of complex visual stimuli. Regions of activation were found in the prefrontal and temporal cortices and cerebellum. Each task resulted in different prefrontal cortical regions of activation lending support to the functional subspecialisation of the prefrontal and temporal cortices being based on the cognitive operations required rather than the stimuli themselves.

An exploration of varieties of visual attention : ERP findings

A set of five tasks was designed to examine dynamic aspects of visual attention: selective attention to color, selective attention to pattern, dividing and switching attention between color and pattern, and selective attention to pattern with changing target. These varieties of visual attention were examined using the same set of stimuli under different instruction sets; thus differences between tasks cannot be attributed to differences in the perceptual features of the stimuli. ERP data are presented for each of these tasks. A within-task analysis of different stimulus types varying in similarity to the attended target feature revealed that an early frontal selection positivity (FSP) was evident in selective attention tasks, regardless of whether color was the attended feature. The scalp distribution of a later posterior selection negativity (SN) was affected by whether the attended feature was color or pattern. The SN was largely unaffected by dividing attention across color and pattern. A large widespread positivity was evident in most conditions, consisting of at least three subcomponents which were differentially affected by the attention conditions. These findings are discussed in relation to prior research and the time course of visual attention processes in the brain.

An effective model of using negative relevance feedback for information filtering

Over the years, people have often held the hypothesis that negative feedback should be very useful for largely improving the performance of information filtering systems; however, we have not obtained very effective models to support this hypothesis. This paper, proposes an effective model that use negative relevance feedback based on a pattern mining approach to improve extracted features. This study focuses on two main issues of using negative relevance feedback: the selection of constructive negative examples to reduce the space of negative examples; and the revision of existing features based on the selected negative examples. The former selects some offender documents, where offender documents are negative documents that are most likely to be classified in the positive group. The later groups the extracted features into three groups: the positive specific category, general category and negative specific category to easily update the weight. An iterative algorithm is also proposed to implement this approach on RCV1 data collections, and substantial experiments show that the proposed approach achieves encouraging performance.

Improved GMM-based speaker verification using SVM-driven impostor dataset selection

The problem of impostor dataset selection for GMM-based speaker verification is addressed through the recently proposed data-driven background dataset refinement technique. The SVM-based refinement technique selects from a candidate impostor dataset those examples that are most frequently selected as support vectors when training a set of SVMs on a development corpus. This study demonstrates the versatility of dataset refinement in the task of selecting suitable impostor datasets for use in GMM-based speaker verification. The use of refined Z- and T-norm datasets provided performance gains of 15% in EER in the NIST 2006 SRE over the use of heuristically selected datasets. The refined datasets were shown to generalise well to the unseen data of the NIST 2008 SRE.

Data-driven impostor selection for T-norm score normalisation and the background dataset in SVM-based speaker verification

A data-driven background dataset refinement technique was recently proposed for SVM based speaker verification. This method selects a refined SVM background dataset from a set of candidate impostor examples after individually ranking examples by their relevance. This paper extends this technique to the refinement of the T-norm dataset for SVM-based speaker verification. The independent refinement of the background and T-norm datasets provides a means of investigating the sensitivity of SVM-based speaker verification performance to the selection of each of these datasets. Using refined datasets provided improvements of 13% in min. DCF and 9% in EER over the full set of impostor examples on the 2006 SRE corpus with the majority of these gains due to refinement of the T-norm dataset. Similar trends were observed for the unseen data of the NIST 2008 SRE.

Robust video stabilisation algorithm using feature point selection and delta optical flow

In this study, the authors propose a novel video stabilisation algorithm for mobile platforms with moving objects in the scene. The quality of videos obtained from mobile platforms, such as unmanned airborne vehicles, suffers from jitter caused by several factors. In order to remove this undesired jitter, the accurate estimation of global motion is essential. However it is difficult to estimate global motions accurately from mobile platforms due to increased estimation errors and noises. Additionally, large moving objects in the video scenes contribute to the estimation errors. Currently, only very few motion estimation algorithms have been developed for video scenes collected from mobile platforms, and this paper shows that these algorithms fail when there are large moving objects in the scene. In this study, a theoretical proof is provided which demonstrates that the use of delta optical flow can improve the robustness of video stabilisation in the presence of large moving objects in the scene. The authors also propose to use sorted arrays of local motions and the selection of feature points to separate outliers from inliers. The proposed algorithm is tested over six video sequences, collected from one fixed platform, four mobile platforms and one synthetic video, of which three contain large moving objects. Experiments show our proposed algorithm performs well to all these video sequences.

An investigation into how work-related road safety can be enhanced

Despite the facts that vehicle incidents continue to be the most common mechanism for Australian compensated fatalities and that employers have statutory obligations to provide safe workplaces, very few organisations are proactively and comprehensively managing their work-related road risks. Unfortunately, limited guidance is provided in the existing literature to assist practitioners in managing work-related road risks. The current research addresses this gap in the literature. To explore how work-related road safety can be enhanced, three studies were conducted. Study one explored the effectiveness of a range of risk management initiatives and whether comprehensive risk management practices were associated with safety outcomes. Study two explored barriers to, and facilitators for, accepting risk management initiatives. Study three explored the influence of organisational factors on road safety outcomes to identify optimal work environments for managing road risks. To maximise the research sample and increase generalisability, the studies were designed to allow data collection to be conducted simultaneously drawing upon the same sample obtained from four Australian organisations. Data was collected via four methods. A structured document review of published articles was conducted to identify what outcomes have been observed in previously investigated work-related road safety initiatives. The documents reviewed collectively assessed the effectiveness of 19 work-related road safety initiatives. Audits of organisational practices and process operating within the four researched organisations were conducted to identify whether organisations with comprehensive work-related road risk management practices and processes have better safety outcomes than organisations with limited risk management practices and processes. Interviews were conducted with a sample of 24 participants, comprising 16 employees and eight managers. The interviews were conducted to identify what barriers and facilitators within organisations are involved in implementing work-related road safety initiatives and whether differences in fleet safety climate, stage of change and safety ownership relate to work-related road safety outcomes. Finally, questionnaires were administered to a sample of 679 participants. The questionnaires were conducted to identify which initiatives are perceived by employees to be effective in managing work-related road risks and whether differences in fleet safety climate, stage of change and safety ownership relate to work-related road safety outcomes. Seven research questions were addressed in the current research project. The key findings with respect to each of the research questions are presented below. Research question one: What outcomes have been observed in previously investigated work-related road safety initiatives? The structured document review indicated that initiatives found to be positively associated with occupational road safety both during and after the intervention period included: a pay rise; driver training; group discussions; enlisting employees as community road safety change agents; safety reminders; and group and individual rewards. Research question two: Which initiatives are perceived by employees to be effective in managing work-related road risks? Questionnaire findings revealed that employees believed occupational road risks could best be managed through making vehicle safety features standard, providing practical driver skills training and through investigating serious vehicle incidents. In comparison, employees believed initiatives including signing a promise card commitment to drive safely, advertising the organisation’s phone number on vehicles and consideration of driving competency in staff selection process would have limited effectiveness in managing occupational road safety. Research question three: Do organisations with comprehensive work-related road risk management practices and processes have better safety outcomes than organisations with limited risk management practices and processes? The audit identified a difference among the organisations in their management of work-related road risks. Comprehensive risk management practices were associated with employees engaging in overall safer driving behaviours, committing less driving errors, and experiencing less fatigue and distraction issues when driving. Given that only four organisations participated in this research, these findings should only be considered as preliminary. Further research should be conducted to explore the relationship between comprehensiveness of risk management practices and road safety outcomes with a larger sample of organisations. Research question four: What barriers and facilitators within organisations are involved in implementing work-related road safety initiatives? The interviews identified that employees perceived six organisational characteristics as potential barriers to implementing work-related road safety initiatives. These included: prioritisation of production over safety; complacency towards work-related road risks; insufficient resources; diversity; limited employee input in safety decisions; and a perception that road safety initiatives were an unnecessary burden. In comparison, employees perceived three organisational characteristics as potential facilitators to implementing work-related road safety initiatives. These included: management commitment; the presence of existing systems that could support the implementation of initiatives; and supportive relationships. Research question five: Do differences in fleet safety climate relate to work-related road safety outcomes? The interviews and questionnaires identified that organisational climates with high management commitment, support for managing work demands, appropriate safety rules and safety communication were associated with employees who engaged in safer driving behaviours. Regression analyses indicated that as participants’ perceptions of safety climate increased, the corresponding likelihood of them engaging in safer driving behaviours increased. Fleet safety climate was perceived to influence road safety outcomes through several avenues. Some of these included: the allocation of sufficient resources to manage occupational road risks; fostering a supportive environment of mutual responsibility; resolving safety issues openly and fairly; clearly communicating to employees that safety is the top priority; and developing appropriate work-related road safety policies and procedures. Research question six: Do differences in stage of change relate to work-related road safety outcomes? The interviews and questionnaires identified that participants’ perceptions of initiative effectiveness were found to vary with respect to their individual stage of readiness, with stage-matched initiatives being perceived most effective. In regards to safety outcomes, regression analyses identified that as participants’ progress through the stages of change, the corresponding likelihood of them being involved in vehicle crashes decreases. Research question seven: Do differences in safety ownership relate to work-related road safety outcomes? The interviews and questionnaires revealed that management of road risks is often given less attention than other areas of health and safety management in organisations. In regards to safety outcomes, regression analyses identified that perceived authority and perceived shared ownership both emerged as significant independent predictors of self-reported driving behaviours pertaining to fatigue and distractions. The regression models indicated that as participants’ perceptions of the authority of the person managing road risks increases, and perceptions of shared ownership of safety tasks increases, the corresponding likelihood of them engaging in driving while fatigued or multitasking while driving decreases. Based on the findings from the current research, the author makes several recommendations to assist practitioners in developing proactive and comprehensive approaches to managing occupational road risks. The author also suggests several avenues for future research in the area of work-related road safety.

Cascading appearance-based features for visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state of the art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the speech recognition application also provide similar improvements for speaker recognition. These results suggest that visual speaker recognition can improve considerable when conducted solely through a consideration of the dynamic speech information rather than the static appearance of the speaker's mouth region.

The applicability of biased estimation in model and model order selection

Biased estimation has the advantage of reducing the mean squared error (MSE) of an estimator. The question of interest is how biased estimation affects model selection. In this paper, we introduce biased estimation to a range of model selection criteria. Specifically, we analyze the performance of the minimum description length (MDL) criterion based on biased and unbiased estimation and compare it against modern model selection criteria such as Kay's conditional model order estimator (CME), the bootstrap and the more recently proposed hook-and-loop resampling based model selection. The advantages and limitations of the considered techniques are discussed. The results indicate that, in some cases, biased estimators can slightly improve the selection of the correct model. We also give an example for which the CME with an unbiased estimator fails, but could regain its power when a biased estimator is used.

Structural and cellular features in metaphyseal and diaphyseal periosteum of osteoporotic rats

Despite the important physiological role of periosteum in the pathogenesis and treatment of osteoporosis, little is known about the structural and cellular characteristics of periosteum in osteoporosis. To study the structural and cellular differences in both diaphyseal and metaphyseal periosteum of osteoporotic rats, samples from the right femur of osteoporotic and normal female Lewis rats were collected and tissue sections were stained with hematoxylin and eosin, antibodies or staining kit against tartrate resistant acid phosphatase (TRAP), alkaline phosphatase (ALP), vascular endothelial growth factor (VEGF), von Willebrand (vWF), tyrosine hydroxylase (TH) and calcitonin gene-related peptide (CGRP). The results showed that the osteoporotic rats had much thicker and more cellular cambial layer of metaphyseal periosteum compared with other periosteal areas and normal rats (P\0.001). The number of TRAP? osteoclasts in bone resorption pits, VEGF? cells and the degree of vascularization were found to be greater in the cambial layer of metaphyseal periosteum of osteoporotic rats (P\0.05), while no significant difference was detected in the number of ALP? cells between the two groups. Sympathetic nerve fibers identified by TH staining were predominantly located in the cambial layer of metaphyseal periosteum of osteoporotic rats. No obvious difference in the expression of CGRP between the two groups was found. In conclusion, periosteum may play an important role in the cortical bone resorption in osteoporotic rats and this pathological process may be regulated by the sympathetic nervous system.

Improving automatic speaker verification using SVM techniques

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

Data-driven background dataset selection for SVM-based speaker verification

The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly-informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analysed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mis-matched to the evaluation conditions.