Evaluation of image resolution and super-resolution on face recognition performance

While researchers strive to improve automatic face recognition performance, the relationship between image resolution and face recognition performance has not received much attention. This relationship is examined systematically and a framework is developed such that results from super-resolution techniques can be compared. Three super-resolution techniques are compared with the Eigenface and Elastic Bunch Graph Matching face recognition engines. Parameter ranges over which these techniques provide better recognition performance than interpolated images is determined.

Action’s place in the venture creation process

This study examined the effect that venture creation action has on the outcomes of nascent entrepreneurship. A conceptual model was developed which proposes action as a fundamental mechanism in venture creation. Thus, action should rightly be considered as a means which transmits the effects of venture resource endowments on to venture creation outcomes. This conceptual model was empirically supported in a random sample of nascent ventures. Ventures with higher levels of human or social capital were found to be more active in venture creation. In turn, more active venture attempts were more likely to achieve improved venture creation outcomes. Further, human and social capital, on their own, exhibit little direct influence on the venture outcomes achieved. These findings confirm action’s central place in the venture creation process.

Re/presenting readings of the indigenous literary terrain

In this study I investigate the spectrum of authoring, publishing and everyday reading of three texts - My Place (Morgan 1987), Jandamarra and the Bunuba Resistance (Pedersen and Woorunmurra 1995) and Carpentaria (Wright 2006). I have addressed this study within the field of production and consumption, utilising amongst others the work of Edward Said (1978, 1983) and Stanley Fish (1980). I locate this work within the holism of Kombu-merri philosopher, Mary Graham's 'Aboriginal Inquiry' (2008), which promotes self-reflexivity and a concern for others as central tenets of such inquiry. I also locate this work within a postcolonial framework and in recognition of the dynamic nature of that phenomenon I use Aileen MoretonRobinson's (2003) adoption of the active verb, "postcolonising"(38). In apprehending selected texts through the people who make them and who make meaning from them - authors, publishers and everyday readers, I interviewed members of each cohort within a framework that recognises the exercise of agency in their respective practices as well as the socio-historical contexts to such textual practices. Although my research design can be applied to other critical arrangements of texts, my interest here lies principally in texts that incorporate the subjects of Indigenous worldview and Indigenous experience; and in texts that are Indigenous authored or Indigenous co-authored.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

Visual route recognition with a handful of bits

In this paper we use a sequence-based visual localization algorithm to reveal surprising answers to the question, how much visual information is actually needed to conduct effective navigation? The algorithm actively searches for the best local image matches within a sliding window of short route segments or 'sub-routes', and matches sub-routes by searching for coherent sequences of local image matches. In contract to many existing techniques, the technique requires no pre-training or camera parameter calibration. We compare the algorithm's performance to the state-of-the-art FAB-MAP 2.0 algorithm on a 70 km benchmark dataset. Performance matches or exceeds the state of the art feature-based localization technique using images as small as 4 pixels, fields of view reduced by a factor of 250, and pixel bit depths reduced to 2 bits. We present further results demonstrating the system localizing in an office environment with near 100% precision using two 7 bit Lego light sensors, as well as using 16 and 32 pixel images from a motorbike race and a mountain rally car stage. By demonstrating how little image information is required to achieve localization along a route, we hope to stimulate future 'low fidelity' approaches to visual navigation that complement probabilistic feature-based techniques.

A toolbox for animal call recognition

Monitoring the natural environment is increasingly important as habit degradation and climate change reduce theworld’s biodiversity.We have developed software tools and applications to assist ecologists with the collection and analysis of acoustic data at large spatial and temporal scales.One of our key objectives is automated animal call recognition, and our approach has three novel attributes. First, we work with raw environmental audio, contaminated by noise and artefacts and containing calls that vary greatly in volume depending on the animal’s proximity to the microphone. Second, initial experimentation suggested that no single recognizer could dealwith the enormous variety of calls. Therefore, we developed a toolbox of generic recognizers to extract invariant features for each call type. Third, many species are cryptic and offer little data with which to train a recognizer. Many popular machine learning methods require large volumes of training and validation data and considerable time and expertise to prepare. Consequently we adopt bootstrap techniques that can be initiated with little data and refined subsequently. In this paper, we describe our recognition tools and present results for real ecological problems.

g4c2c: A model for citizen engagement at arms' length from government

The recognition that Web 2.0 applications and social media sites will strengthen and improve interaction between governments and citizens has resulted in a global push into new e-democracy or Government 2.0 spaces. These typically follow government-to-citizen (g2c) or citizen-to-citizen (c2c) models, but both these approaches are problematic: g2c is often concerned more with service delivery to citizens as clients, or exists to make a show of ‘listening to the public’ rather than to genuinely source citizen ideas for government policy, while c2c often takes place without direct government participation and therefore cannot ensure that the outcomes of citizen deliberations are accepted into the government policy-making process. Building on recent examples of Australian Government 2.0 initiatives, we suggest a new approach based on government support for citizen-to-citizen engagement, or g4c2c, as a workable compromise, and suggest that public service broadcasters should play a key role in facilitating this model of citizen engagement.

Space, place and power : the spatial turn in literacy research

Place matters to literacy because the meanings of our language and actions are always materially and socially placed in the world (Scollon & Scollon, 2003). We cannot interpret signs, whether an icon, symbol, gesture, word, or action, without taking into account their associations with other meanings and objects in places. This chapter maps an emergent strand of literacy research that foregrounds place and space as constitutive, rather than a backdrop for the real action. Space and place are seen as relational and dynamic, not as fixed and unchanging. Space and place are socially produced, and hence, can be contested, re-imagined and re-made. In bringing space and place into the frame of literacy studies we see a subtle shift – a rebalancing of the semiotic with the materiality of lived, embodied, and situated experience. ...

Between a rock and a hard place : what do public sector leaders learn from the past as they lead into the future

The purpose of this paper is to bring leadership context into sharper focus and to suggest there are strong constraints on public leaders’ discretion to lead in ways consistent with NPM or NPL. Much of the existing public leadership research focuses on the individual leader and tends to give little attention to the influence of context. This lack of focus on leader context adversely affects our ability to build public leadership capacity. We draw on prior research to establish that (1) there are strong contextual constraints on public leaders’ capacity to lead in ways consistent with NPL, (2) public leaders are subject to contradictory messages and for the most part these contradictions are unacknowledged and unresolved, the impact of which is confusion and informal power-politics, (3) the task of leader transition from traditional leadership to new public leadership is very much underestimated and requires a new way to think about leadership development. On the basis of this analysis, we argue that public leaders find themselves between a rock and a hard place.

The culture of the journey as structure of the landscape: an inquiry on mobility facilities and identity of place

The structure of the travel, meant as cultural activity, is proposed as a key to read and design the urban or rural landscape.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

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.