Postcode segmentation and recognition using projections and bispectral features

A system to segment and recognize Australian 4-digit postcodes from address labels on parcels is described. Images of address labels are preprocessed and adaptively thresholded to reduce noise. Projections are used to segment the line and then the characters comprising the postcode. Individual digits are recognized using bispectral features extracted from their parallel beam projections. These features are insensitive to translation, scaling and rotation, and robust to noise. Results on scanned images are presented. The system is currently being improved and implemented to work on-line.

Super-resolved faces for improved face recognition from surveillance video advances in biometrics

Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for computers and human operators to identify individuals from these videos. To overcome this problem, super-resolution can be used in conjunction with an automated face recognition system to enhance the spatial resolution of video frames containing the subject and narrow down the number of manual verifications performed by the human operator by presenting a list of most likely candidates from the database. As the super-resolution reconstruction process is ill-posed, visual artifacts are often generated as a result. These artifacts can be visually distracting to humans and/or affect machine recognition algorithms. While it is intuitive that higher resolution should lead to improved recognition accuracy, the effects of super-resolution and such artifacts on face recognition performance have not been systematically studied. This paper aims to address this gap while illustrating that super-resolution allows more accurate identification of individuals from low-resolution surveillance footage. The proposed optical flow-based super-resolution method is benchmarked against Baker et al.’s hallucination and Schultz et al.’s super-resolution techniques on images from the Terrascope and XM2VTS databases. Ground truth and interpolated images were also tested to provide a baseline for comparison. Results show that a suitable super-resolution system can improve the discriminability of surveillance video and enhance face recognition accuracy. The experiments also show that Schultz et al.’s method fails when dealing surveillance footage due to its assumption of rigid objects in the scene. The hallucination and optical flow-based methods performed comparably, with the optical flow-based method producing less visually distracting artifacts that interfered with human recognition.

Can audio-visual speech recognition outperform acoustically enhanced speech recognition in automotive environment?

The use of visual features in the form of lip movements to improve the performance of acoustic speech recognition has been shown to work well, particularly in noisy acoustic conditions. However, whether this technique can outperform speech recognition incorporating well-known acoustic enhancement techniques, such as spectral subtraction, or multi-channel beamforming is not known. This is an important question to be answered especially in an automotive environment, for the design of an efficient human-vehicle computer interface. We perform a variety of speech recognition experiments on a challenging automotive speech dataset and results show that synchronous HMM-based audio-visual fusion can outperform traditional single as well as multi-channel acoustic speech enhancement techniques. We also show that further improvement in recognition performance can be obtained by fusing speech-enhanced audio with the visual modality, demonstrating the complementary nature of the two robust speech recognition approaches.

Is there an App for that? : social media uses for road safety

The use of social media has increased dramatically in recent years in the areas of public health and injury prevention, with many organisations creating online and social media content. Despite the adoption of such media by modern society, research relating to the design and evaluation of social media for the promotion of health issues is very much in its infancy. A timely review of the available evidence in relation to the use of social media campaigns from both the road safety and broader public health context will be undertaken. In particular, this paper will address the questions of what social media should be developed, how it should be evaluated, as well as what should be the key measures of success and to what extent do these measures relate to practically significant outcomes, such as behaviour change. Much like more traditional media campaigns, social media may be best regarded as another approach within the array of potential approaches that a health advertising researcher or practitioner may utilise. With younger demographics becoming less likely to engage with more traditional advertising mediums relative to their preference for social media, social media‟s most important role in the road safety advertising context may be to offer the means of delivering road safety messages to high risk, younger road users.

Young children’s beliefs about including others in their play: Social and moral reasoning about inclusion and exclusion

Previous research has emphasised the importance of active citizenship in the early years for the development of a tolerant and cohesive Australian society. This paper presents findings related to young children’s beliefs about exclusion based on gender and race. The findings draw from a larger study exploring the development of children’s moral and social values and teachers’ beliefs and practices related to teaching for moral development, in the early years of school in Australia. This current study examined reasoning about exclusion in early childhood with children aged 5-8 years. One hundred children from seven schools (Preparatory to Grade 3) answered questions relating to two scenarios in which the children had to make a decision about whether to include others of different gender or race in their play. The majority of children believed that others should be included in their play, regardless of their gender or race. When asked to explain, the children primarily gave reasons related to moral concern and fairness. Children were then asked whether they would continue to include or exclude if their friends (social consensus) or teachers (authority) suggested otherwise. The majority of children maintained their beliefs when beliefs to the contrary were voiced by their peers and teachers. The implications of these responses are discussed.

Moral and social development : teachers’ knowledge of learning and teaching strategies in the early years

The intention of the analysis in this paper was to determine, from interviews with eleven early years’ teachers, what knowledge guided their teaching of moral behaviour. Six of the teachers defined moral behaviour in terms of social conventions only. Children’s learning was attributed by five of the teachers to incidental/contextual issues. Nine of the teachers used discussion of issues, in various contexts, as a way of teaching about social and moral issues. The majority of the teachers (n=7) gave the source of their knowledge of pedagogy as practical as opposed to theoretically informed. There was no clear relationship between their definitions, understanding of children’s learning, pedagogy or source of knowledge. Most of the teachers were using discussion, negotiation and reflection to develop the children’s moral and social behaviour. This is probably effective; however, it suggests a strong need for teaching of moral development to be given more prominence and addressed directly in in-service courses so that teachers are clear about their intentions and the most effective ways of achieving them.

The association between playgroup participation, learning competence and social-emotional wellbeing for children aged 4-5 years in Australia

Data from Growing Up in Australia: The Longitudinal Study of Australian Children is used to examine the associations between playgroup participation and the outcomes for children aged 4 to 5 years. Controlling for a range of socio-economic and family characteristics, playgroup participation across the ages of 0-3 years was used to predict learning competence and social-emotional functioning outcomes at age 4-5 years. For learning competence, both boys and girls from disadvantaged families scored 3-4% higher if they attended playgroup when aged 0-1 and 2-3 years compared to boys and girls from disadvantaged families who did not attend playgroup. For social and emotional functioning, girls from disadvantaged families who attended playgroup when they were aged 0-1 and 2-3 years scored nearly 5% higher than those who did not attend. Demographic characteristics also showed that disadvantaged families were the families least likely to access these services. Despite data limitations, this study provides evidence that continued participation in playgroups is associated with better outcomes for children from disadvantaged families.

A social marketing approach to value creation in a Well-Women’s health service

Understanding consumer value is imperative in health care as the receipt of value drives the demand for health care services. While there is increasing research into health-care that adopts an economic approach to value, this paper investigates a non-financial exchange context and uses an experiential approach to value, guided by a social marketing approach to behaviour change. An experiential approach is deemed more appropriate for government health-care services that are free and for preventative rather than treatment purposes. Thus instead of using an illness-paradigm to view health services outcomes, we adopt a wellness paradigm. Using qualitative data gathered during 25 depth interviews the authors demonstrate how social marketing thinking has guided the identification of six themes that represent four dimensions of value (functional, emotional, social and altruistic) evident during the health care consumption process of a free government service.

Neo-planning: Location-based social media to engage Australia’s new digital locals

Community engagement with time poor and seemingly apathetic citizens continues to challenge local governments. Capturing the attention of a digitally literate community who are technology and socially savvy adds a new quality to this challenge. Community engagement is resource and time intensive, yet local governments have to manage on continually tightened budgets. The benefits of assisting citizens in taking ownership in making their community and city a better place to live in collaboration with planners and local governments are well established. This study investigates a new collaborative form of civic participation and engagement for urban planning that employs in-place digital augmentation. It enhances people’s experience of physical spaces with digital technologies that are directly accessible within that space, in particular through interaction with mobile phones and public displays. The study developed and deployed a system called Discussions in Space (DIS) in conjunction with a major urban planning project in Brisbane. Planners used the system to ask local residents planning-related questions via a public screen, and passers-by sent responses via SMS or Twitter onto the screen for others to read and reflect, hence encouraging in-situ, real-time, civic discourse. The low barrier of entry proved to be successful in engaging a wide range of residents who are generally not heard due to their lack of time or interest. The system also reflected positively on the local government for reaching out in this way. Challenges and implications of the short-texted and ephemeral nature of this medium were evaluated in two focus groups with urban planners. The paper concludes with an analysis of the planners’ feedback evaluating the merits of the data generated by the system to better engage with Australia’s new digital locals.

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.

Information literacy programs and research : an international review

This paper provides an overview of contemporary information literacy research and practice. While the content is highly selective, the intention has been to highlight international and Australian developments which have achieved significant recognition, which are representative of similar trends in other places, or which are unique in some way. There are three main foci in the paper. Firstly, an exploration of ways of interpreting the idea of information literacy. Secondly, a synthesis of various efforts to seek new directions in educational, community and workplace contexts, beginning with the major initiatives being undertaken in the United States. Thirdly, an introduction to some recent research, concluding with a summary of my own investigation into different ways of experiencing information literacy

Diversity interventions for a socially sustainable construction industry

Major construction sites in Australia have an above average presence of ethnic minorities. These groups and the interfaces between them require effective management in order to meet the social imperatives of sustainable design and construction. A survey of 1155 workers and 204 managers on Sydney construction sites respectively, found a significant level of normalisation of negative forms of cross cultural interaction. Yet it was also found that anti-racism programs are not currently a management priority and that they generally lack sophisticated community relations aspects. This paper presents the results of a desk-top study of leading global companies within and outside the construction sector which have won international awards and recognition for their cultural diversity strategies. A key insight is that the companies profiled see diversity as a key resource and as an opportunity rather than a risk which is best harnessed through long-term and on-going commitment of senior management. These leading companies also recognise that cultural diversity strategies operate at three levels - in terms of its relationship with its own workforce; its relationship with its clients and; its relationships with the communities in which it operates - and if properly managed it can be a source of competitive advantage.

i-vector based speaker recognition on short utterances

Robust speaker verification on short utterances remains a key consideration when deploying automatic speaker recognition, as many real world applications often have access to only limited duration speech data. This paper explores how the recent technologies focused around total variability modeling behave when training and testing utterance lengths are reduced. Results are presented which provide a comparison of Joint Factor Analysis (JFA) and i-vector based systems including various compensation techniques; Within-Class Covariance Normalization (WCCN), LDA, Scatter Difference Nuisance Attribute Projection (SDNAP) and Gaussian Probabilistic Linear Discriminant Analysis (GPLDA). Speaker verification performance for utterances with as little as 2 sec of data taken from the NIST Speaker Recognition Evaluations are presented to provide a clearer picture of the current performance characteristics of these techniques in short utterance conditions.

3D ellipsoid fitting for multi-view gait recognition

Gait recognition approaches continue to struggle with challenges including view-invariance, low-resolution data, robustness to unconstrained environments, and fluctuating gait patterns due to subjects carrying goods or wearing different clothes. Although computationally expensive, model based techniques offer promise over appearance based techniques for these challenges as they gather gait features and interpret gait dynamics in skeleton form. In this paper, we propose a fast 3D ellipsoidal-based gait recognition algorithm using a 3D voxel model derived from multi-view silhouette images. This approach directly solves the limitations of view dependency and self-occlusion in existing ellipse fitting model-based approaches. Voxel models are segmented into four components (left and right legs, above and below the knee), and ellipsoids are fitted to each region using eigenvalue decomposition. Features derived from the ellipsoid parameters are modeled using a Fourier representation to retain the temporal dynamic pattern for classification. We demonstrate the proposed approach using the CMU MoBo database and show that an improvement of 15-20% can be achieved over a 2D ellipse fitting baseline.

Gait energy volumes and frontal gait recognition using depth images

Gait energy images (GEIs) and its variants form the basis of many recent appearance-based gait recognition systems. The GEI combines good recognition performance with a simple implementation, though it suffers problems inherent to appearance-based approaches, such as being highly view dependent. In this paper, we extend the concept of the GEI to 3D, to create what we call the gait energy volume, or GEV. A basic GEV implementation is tested on the CMU MoBo database, showing improvements over both the GEI baseline and a fused multi-view GEI approach. We also demonstrate the efficacy of this approach on partial volume reconstructions created from frontal depth images, which can be more practically acquired, for example, in biometric portals implemented with stereo cameras, or other depth acquisition systems. Experiments on frontal depth images are evaluated on an in-house developed database captured using the Microsoft Kinect, and demonstrate the validity of the proposed approach.