Illumination-invariant face recognition from a single image across extreme pose using a dual dimension AAM ensemble in the thermal infrared spectrum

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in practice. While inherently insensitive to visible spectrum illumination changes, IR data introduces specific challenges of its own, most notably sensitivity to factors which affect facial heat emission patterns, e.g. emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, when comparing two thermal IR images of faces, we mutually normalize their poses and facial expressions by using an active appearance model (AAM) to generate synthetic images of the two faces with a neutral facial expression and in the same view (the average of the two input views). This is achieved by piecewise affine warping which follows AAM fitting. A major contribution of our work is the use of an AAM ensemble in which each AAM is specialized to a particular range of poses and a particular region of the thermal IR face space. Combined with the contributions from our previous work which addressed the problem of reliable AAM fitting in the thermal IR spectrum, and the development of a person-specific representation robust to transient changes in the pattern of facial temperature emissions, the proposed ensemble framework accurately matches faces across the full range of yaw from frontal to profile, even in the presence of scale variation (e.g. due to the varying distance of a subject from the camera). The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces and a newly acquired data set of thermal IR motion videos. Our approach achieved perfect recognition performance on both data sets, significantly outperforming the current state of the art methods even when they are trained with multiple images spanning a range of head views.

Global positioning systems : altered representations of place

Global Positioning Systems: altered representations of place, presents an exegesis from the practice led research submitted for the degree of Master of Fine Art at the Victorian College of the Arts. The thesis proposes a particular understanding of altered states of consciousness that is relevant to my practice.  This is outlined by Charles Tart and supported by the Altered States of Consciousness Consortium and explores a psycho-aesthetic experiences and does not involved transcendental states or spiritual associations. These experiences are transformed by an exhaustive application of digital technologies, where mosaic-like complexity emerges that induces sustained disorientation and surrounds a viewer in an immersive space.

Global positioning systems: altered representations of place

Solo exhibition of Master of Fine Art practice

Face recognition with image sets using manifold density divergence

In many automatic face recognition applications, a set of a person's face images is available rather than a single image. In this paper, we describe a novel method for face recognition using image sets. We propose a flexible, semi-parametric model for learning probability densities confined to highly non-linear but intrinsically low-dimensional manifolds. The model leads to a statistical formulation of the recognition problem in terms of minimizing the divergence between densities estimated on these manifolds. The proposed method is evaluated on a large data set, acquired in realistic imaging conditions with severe illumination variation. Our algorithm is shown to match the best and outperform other state-of-the-art algorithms in the literature, achieving 94% recognition rate on average.

The everyday image: reproduction and participation

An exhibition of five small paintings and seven lithographs that explore images of images of the everyday, the gaze and voyeurism. Chicago Art Department, Pilsen, Chicago.

Locally sparsified compressive sensing for improved MR image qualtity

The fact that medical images have redundant information is exploited by researchers for faster image acquisition. Sample set or number of measurements were reduced in order to achieve rapid imaging. However, due to inadequate sampling, noise artefacts are inevitable in Compressive Sensing (CS) MRI. CS utilizes the transform sparsity of MR images to regenerate images from under sampled data. Locally sparsified Compressed Sensing is an extension of simple CS. It localises sparsity constraints for sub-regions rather than using a global constraint. This paper, presents a framework to use local CS for improving image quality without increasing sampling rate or without making the acquisition process any slower. This was achieved by exploiting local constraints. Localising image into independent sub-regions allows different sampling rates within image. Energy distribution of MR images is not even and most of noise occurs due to under-sampling in high energy regions. By sampling sub-regions based on energy distribution, noise artefacts can be minimized. Experiments were done using the proposed technique. Results were compared with global CS and summarized in this paper.

Ghost muscle: stonewalling teams past and present

An imaginative arts project inspired by the Volcanic Plains region of Western Victoria will be showcased in Warrnambool this week where participants will also be able to experience the art of dry stone walling. The aim is to imagine the life of the stones and to re-perform and experience what it might have been like to work alongside a team of stonewallers from the late 1800's out in the fields producing about 30 meters of wall per day. This imaginary archaeology provides lesson in the doing of our ongoing relationship to the land and to place and place-making.

Souvenirs of the senses: collaborative and cross-artform makings

Souvenir hunters are often limited in their selection of souvenirs to objects that evoke an iconic and/or generic relationship to place. For example, a small-scale replica of the Eiffel Tower might substitute for a whole range of other more personal responses to the sensory experience of being in Paris. This paper reports on a collaborative and cross-artform five-day workshop, “Souvenirs of the Senses”, conducted in Qatar in early 2013 as part of Tasmeem Doha: Hybrid Making, a biennial international art and design conference. Two of the three workshop leaders, Patrick West and Jondi Keane, were Australian-based visitors whereas workshop leader Valerie Jeremijenko is permanently based in Qatar. There were five workshop participants from a diverse range of international and Qatari backgrounds. One of the conference themes, “Made in Qatar”, heightened our attention to what it means to be spending time in, and making things in, one place as opposed to any other place. What did it mean to be making something in a country where so many things have to be imported? Building on this line of thought, the second conference theme, “Hybrid Making”, suggested possibilities for undoing traditional modes of souvenir making as part of the creation of more complex objects that might be sutured to the singular experiences of place that happen when a.) established regimes of tourism are disrupted, and b.) experiences of place are curated via a focused awareness of the operations of the senses as sustained within our collaborative, cross-artform workshop environment. What attracts our attention is how objects ripe for “souveniring”, when they are considered as perceptual systems, suggest new ways of experimenting with the fabrication of objects and of artistic and individual relationships to place, and further, how hybrid souvenirs affect the way in which a place is re-membered (put together) and re-made in memory.

Image reduction operators based on non-monotonic averaging functions

Image reduction is a crucial task in image processing, underpinning many practical applications. This work proposes novel image reduction operators based on non-monotonic averaging aggregation functions. The technique of penalty function minimisation is used to derive a novel mode-like estimator capable of identifying the most appropriate pixel value for representing a subset of the original image. Performance of this aggregation function and several traditional robust estimators of location are objectively assessed by applying image reduction within a facial recognition task. The FERET evaluation protocol is applied to confirm that these non-monotonic functions are able to sustain task performance compared to recognition using nonreduced images, as well as significantly improve performance on query images corrupted by noise. These results extend the state of the art in image reduction based on aggregation functions and provide a basis for efficiency and accuracy improvements in practical computer vision applications.

The experience of Singapore in raising awareness of natural and cultural resources

The city-state of Singapore has a major role in the urban development. Majority of the innovative projects are initiated by the government agencies. For this paper, I would like to highlight the two distinct themes of innovation that, I believe preoccupied the authority for its urban issues, they are innovation which concern nature and culture. Land in Singapore is scarce. Natural resources are strictly protected. At the same time they are challenged to return the maximum benefit to their own population. The water catchment area and the prime forest on the whole island is the most valuable natural resources to be preserved. The paper will demonstrate how Singapore challenges with its own resources (water and greenery) in which the holistic planning around these themes become more than just spaces of protection but integrated with the public space system and turned into more valuable spaces for the well being of its population. The second theme is the issue related to culture. Singapore's economy is the most advance compare to other Southeast Asian countries, however when it comes to culture and identity, the city state struggles with the over constructed image of branding Singapore's culture. The paper will discuss several examples around the theme of arts and culture, how the city state bench-mark itself with the world class cities. It is one of the most challenging topic in urban planning and policy making. It is worth discussing on its success and failure. We can learn form Singapore that innovation at the level of policy maker can be achieved in some urban aspects such as the management of natural resources and urban design projects related to it. However when it comes to the issue related to art and culture, the top down policy alone cannot assure the achievement of city's identity as it aspired. Tracing the historical development of the environmental and cultural policies of Singapore the paper intends to study and analyze various case studies reflecting these attempts of natural and cultural instillation. In the process of comparison of these two drastically contrasting actors and approaches, the paper will argue that it has mostly been driven by economic aims, and careful thought. The results have been limited and restrictive. Further arguing that 'creativity' is the essential factor of arts and culture, it evaluates the authenticity and the ultimate implications on cultural spirit.

'Shadow-lands' : the suffering image

"Folio X documents the exhibition '"Shadow-lands': the suffering image" held at Dennys Lascelles Exhibition Gallery, Alfred Deakin Prime Ministerial Library, Deakin University, Waterfront Campus, Geelong, Victoria, Australia, April 18-May 18, 2012. The project was part and parcel of the author's PhD study, "Visual agency in art and architecture" .... and an experimental representation of the values embedded in the photography and film-essays of Chris Marker..."

Pre-service visual art teachers’ perceptions of assessment in online learning

This paper reports on a study conducted into how one cohort of Master of Teaching pre-service visual art teachers perceived their learning in a fully online learning environment. Located in an Australian urban university, this qualitative study provided insights into a number of areas associated with higher education online learning, including that of assessment, the focus of this paper. Authentic assessment tasks were designed within the University’s learning and teaching framework of constructive alignment and were sequenced across the three semesters of the visual art program. Analysis of data collected through a questionnaire and semi-structured interviews revealed that participants largely held very positive attitudes about the suite of online assessment tasks, particularly in light of (a) the collaborative learning that took place, (b) the nature, structure and sequence of the tasks, and (c) the ways in which the tasks contributed to their workplace readiness.

Making student experts within a flipped mechatronics class

The flipped classroom is used to place emphasis on the student, by allowing the students to do their own research which can be applied in the classroom. This may beable to be taken to one extreme by allocating each student an area of expertise that all the other students can approach them about. This has be tried in a fourth year Project Orientated, Design Based Learning (PODBL) class.