Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Image-guided sampling reveals increased stroma and lower glandular complexity in mammographically dense breast tissue

Mammographic density (MD) adjusted for age and body mass index (BMI) is a strong heritable breast cancer risk factor; however, its biological basis remains elusive. Previous studies assessed MD-associated histology using random sampling approaches, despite evidence that high and low MD areas exist within a breast and are negatively correlated with respect to one another. We have used an image-guided approach to sample high and low MD tissues from within individual breasts to examine the relationship between histology and degree of MD. Image-guided sampling was performed using two different methodologies on mastectomy tissues (n = 12): (1) sampling of high and low MD regions within a slice guided by bright (high MD) and dark (low MD) areas in a slice X-ray film; (2) sampling of high and low MD regions within a whole breast using a stereotactically guided vacuum-assisted core biopsy technique. Pairwise analysis accounting for potential confounders (i.e. age, BMI, menopausal status, etc.) provides appropriate power for analysis despite the small sample size. High MD tissues had higher stromal (P = 0.002) and lower fat (P = 0.002) compositions, but no evidence of difference in glandular areas (P = 0.084) compared to low MD tissues from the same breast. High MD regions had higher relative gland counts (P = 0.023), and a preponderance of Type I lobules in high MD compared to low MD regions was observed in 58% of subjects (n = 7), but did not achieve significance. These findings clarify the histologic nature of high MD tissue and support hypotheses regarding the biophysical impact of dense connective tissue on mammary malignancy. They also provide important terms of reference for ongoing analyses of the underlying genetics of MD.

Joint 2D and 3D cues for image segmentation towards robotic applications

This thesis investigates the fusion of 3D visual information with 2D image cues to provide 3D semantic maps of large-scale environments in which a robot traverses for robotic applications. A major theme of this thesis was to exploit the availability of 3D information acquired from robot sensors to improve upon 2D object classification alone. The proposed methods have been evaluated on several indoor and outdoor datasets collected from mobile robotic platforms including a quadcopter and ground vehicle covering several kilometres of urban roads.

Scleral matrix metalloproteinases, serine proteinase activity and hydrational capacity are increased in myopia induced by retinal image degradation

In the avian model of myopia, retinal image degradation quickly leads to ocular enlargement. We now give evidence that regionally specific changes in ocular size are correlated with both biomechanical indices of scleral remodeling, e.g. hydration capacity and with biochemical changes in proteinase activities. The latter include a 72 kDa matrix metalloproteinase (putatively MMP-2), other gelatin-binding MMPs, an acid pH MMP and a serine protease. Specifically, we have found that increases in scleral hydrational capacity parallel increases in collagen degrading activities. Gelatin zymography reveals that eyes with 7 days of retinal image degradation have elevated levels (1.4-fold) of gelatinolytic activities at 72 and 67 kDa M(r) in equatorial and posterior pole regions of the sclera while, after 14 days of treatment, increases are no longer apparent. Lower M(r) zymographic activities at 50, 46 and 37 kDa M(r) are collectively increased in eyes treated for both 7 and 14 days (1.4- and 2.4-fold respectively) in the equator and posterior pole areas of enlarging eyes. Western blot analyses of scleral extracts with an antibody to human MMP-2 reveals immunoreactive bands at 65, 30 and 25 kDa. Zymograms incubated under slightly acidic conditions reveal that, in enlarging eyes, MMP activities at 25 and 28 kDa M(r) are increased in scleral equator and posterior pole (1.6- and 4.5-fold respectively). A TIMP-like protein is also identified in sclera and cornea by Western blot analysis. Finally, retinal-image degradation also increases (~2.6-fold) the activity of a 23.5 kDa serine proteinase in limbus, equator and posterior pole sclera that is inhibited by aprotinin and soybean trypsin inhibitor. Taken together, these results indicate that eye growth induced by retinal-image degradation involves increases in the activities of multiple scleral proteinases that could modify the biomechanical properties of scleral structural components and contribute to tissue remodeling and growth.

University of Glasgow at ImageCLEFPhoto 2009 : optimising similarity and diversity in image retrieval

In this paper we describe the approaches adopted to generate the runs submitted to ImageCLEFPhoto 2009 with an aim to promote document diversity in the rankings. Four of our runs are text based approaches that employ textual statistics extracted from the captions of images, i.e. MMR [1] as a state of the art method for result diversification, two approaches that combine relevance information and clustering techniques, and an instantiation of Quantum Probability Ranking Principle. The fifth run exploits visual features of the provided images to re-rank the initial results by means of Factor Analysis. The results reveal that our methods based on only text captions consistently improve the performance of the respective baselines, while the approach that combines visual features with textual statistics shows lower levels of improvements.

Building community coalitions for the promotion of physical activity: 10,000 steps Rockhampton

The 10,000 Steps Rockhampton project is a multi-strategy community-wide, physical activity intervention based on the simultaneous implementation of five strategies, each identified as 'best practice' for the promotion of physical activity. Several community partners were engaged to develop and implement the strategies during the first eighteen months of the project. These included: the local media (TV, newspaper and radio); the local Division of General Practice and other health professional groups; the Heart Foundation and ‘Just Walk It’; the local council; and several large worksites. A local physical activity task force was also formed to administer a 'micro-grants' scheme, and to guide the development of community based strategies. The presentation will focus on the critical elements involved in developing and maintaining relationships with community partners. These include identification and ‘courting’ of potential partners, strategies for keeping them engaged, and the challenges of maintaining the balance between ‘top-down’ (evidence-based) and ‘bottom-up’ (community-driven) strategies. Data on implementation and uptake of the key strategies will also be presented. These include: 1) process data on the number of health

Health promotion for dogs and humans : the 10,000 steps Rockhampton dog walking intervention

Purpose This paper describes the implementation and evaluation of an intervention aimed at increasing the dog-walking behaviour of residents from a community of approximately 60,000. This intervention was a sub strategy of the 10 000 Steps Rockhampton project – a community intervention aimed at decreasing sedentary behaviour in the adult population. Methods Brochures and posters were developed that promoted dog walking as a means to improve both human and canine health. The brochures were distributed by the local council to over 8 000 homes with the annual dog-renewal registrations. Results Evaluation of the intervention included a telephone survey of a randomly selected sample of Rockhampton residents (n=420) four-months post intervention. Although 63.6% of participants reported that owning a dog increased their physical activity levels, 40% of dog-owners did not walk their dog at all in the last week. The outcome evaluation of the intervention showed that 20.2% of dog-owners recalled receiving the brochure. Overall 15.3% of respondents with a dog in their household reported an increase in their physical activity levels since the intervention, 8.4% reported a decrease. Conclusions The intervention was an innovative and cost-effective way to tap into a section of the population that can benefit from engaging in regular walking behaviour. It was also a unique and useful way to engage local council in physical activity health promotion as part of a larger ongoing community-wide intervention.

Requiem for a beast : a case study in controversy

In 2008, Matt Ottley’s Requiem for a Beast: A Work for Image, Word and Music was awarded the Book of the Year: Picture Book by the Children’s Book Council of Australia (CBCA). Ottley’s book is challenging in its form and content: it uses words, illustrations, and music to tell a sustained, multi-layered narrative about one young man’s attempts to reconcile his family’s and his nation’s shameful history of violence against Aboriginal Australians, while also coming to terms with his own attempts to commit suicide. Given the ways in which the CBCA’s annual book awards are used by teachers, librarians, and parents to select the “best” books for young readers, it is unsurprising that the prizing of Requiem for a Beast stirred up controversy. Responses to the book proliferated across professional and popular outlets—it even received coverage on an Australian tabloid television program—and initiated a variety of conversations about what constitutes appropriate reading for young people. Perhaps more significantly, the controversy over Requiem winning picture book of the year forced the CBCA, teacher librarians, and caregivers to examine (and, often, defend) their roles and responsibilities in the circulation and promotion of children’s literature. This paper reads the Requiem controversies as a case study for understanding the complementary and contradictory roles of institutions and individuals in the ethical circulation of children’s literature in contemporary Australia and beyond.

Deadly Choices or deadly choices? An ethnography of health promotion practice with Indigenous Australians

This presentation provides an overview of my PhD research, which links with the Institute for Urban Indigenous Health (IUIH) and its Deadly Choices team. In the presentation, I introduce my critique of mainstream health promotion practice, highlighting the need for decolonisation of health promotion and the opportunity to learn from health promotion practice that acknowledges Indigenous knowledge, skills and perspectives. I also overview my ethnographic research methodology, which enabled me to be a participant observer with IUIH health promotion practitioners. I canvas some of my findings to date, according to two key areas: the unique way Deadly Choices applies leadership as its model of health promotion practice; and the range of innovative engagement strategies they employed, including the Deadly Choices brand and social media. I conclude by highlighting the counter-narrative and contrast that Deadly Choices provides compared to traditional health promotion approaches with Indigenous people, and identify lessons for decolonisation of heath promotion more broadly.

Promotion of Homologous Recombination and Genomic Stability by RAD51AP1 via RAD51 Recombinase Enhancement

Homologous recombination (HR) repairs chromosome damage and is indispensable for tumor suppression in humans. RAD51 mediates the DNA strand-pairing step in HR. RAD51 associated protein 1 (RAD51AP1) is a RAD51-interacting protein whose function has remained elusive. Knockdown of RAD51AP1 in human cells by RNA interference engenders sensitivity to different types of genotoxic stress, and RAD51AP1 is epistatic to the HR protein XRCC3. Moreover, RAD51AP1-depleted cells are impaired for the recombinational repair of a DNA double-strand break and exhibit chromatid breaks both spontaneously and upon DNA-damaging treatment. Purified RAD51AP1 binds both dsDNA and a D loop structure and, only when able to interact with RAD51, greatly stimulates the RAD51-mediated D loop reaction. Biochemical and cytological results show that RAD51AP1 functions at a step subsequent to the assembly of the RAD51-ssDNA nucleoprotein filament. Our findings provide evidence that RAD51AP1 helps maintain genomic integrity via RAD51 recombinase enhancement.

Looking beyond image and tourism : the role of flagship cultural projects in local arts development

State and local governments frequently look to flagship cultural projects to improve the city image and catalyze tourism but, in the process, often overlook their potential to foster local arts development. To better understand this role, the article examines if and how cultural institutions in Los Angeles and San Francisco attract and support arts-related activity. The analysis reveals that cultural flagships have mixed success in generating arts-based development and that their ability may be improved through attention to the local context, facility and institutional characteristics, and the approach of the sponsoring agencies. Such knowledge is useful for planners to enhance their revitalization efforts, particularly as the economic development potential of arts organizations and artists has become more apparent.

A digital watermarking framework with application to medical image security

Dealing with digital medical images is raising many new security problems with legal and ethical complexities for local archiving and distant medical services. These include image retention and fraud, distrust and invasion of privacy. This project was a significant step forward in developing a complete framework for systematically designing, analyzing, and applying digital watermarking, with a particular focus on medical image security. A formal generic watermarking model, three new attack models, and an efficient watermarking technique for medical images were developed. These outcomes contribute to standardizing future research in formal modeling and complete security and computational analysis of watermarking schemes.

Digital image watermarking: its formal model, fundamental properties and possible attacks

While formal definitions and security proofs are well established in some fields like cryptography and steganography, they are not as evident in digital watermarking research. A systematic development of watermarking schemes is desirable, but at present their development is usually informal, ad hoc, and omits the complete realization of application scenarios. This practice not only hinders the choice and use of a suitable scheme for a watermarking application, but also leads to debate about the state-of-the-art for different watermarking applications. With a view to the systematic development of watermarking schemes, we present a formal generic model for digital image watermarking. Considering possible inputs, outputs, and component functions, the initial construction of a basic watermarking model is developed further to incorporate the use of keys. On the basis of our proposed model, fundamental watermarking properties are defined and their importance exemplified for different image applications. We also define a set of possible attacks using our model showing different winning scenarios depending on the adversary capabilities. It is envisaged that with a proper consideration of watermarking properties and adversary actions in different image applications, use of the proposed model would allow a unified treatment of all practically meaningful variants of watermarking schemes.