Complex Motion Processing in Primate Visual Cortex. As we move through the world, a dynamic visual image is projected onto our retinas. The pattern of movement in the retinal image contains information about three-dimensional structure in the environment and the time of impending collisions. Our visual systems are expert at exploiting this information, enabling us to navigate through complex visual environments at a level far beyond the most sophisticated artificial systems. We plan to investiga ....Complex Motion Processing in Primate Visual Cortex. As we move through the world, a dynamic visual image is projected onto our retinas. The pattern of movement in the retinal image contains information about three-dimensional structure in the environment and the time of impending collisions. Our visual systems are expert at exploiting this information, enabling us to navigate through complex visual environments at a level far beyond the most sophisticated artificial systems. We plan to investigate complex motion processing in the primate brain by recording the responses of neurons in identified regions of the visual cortex of macaque monkeys to a range of behaviourally relevant motion stimuli.Read moreRead less
Stereoscopic Vision at Large Distances. This project measures the benefits of stereopsis, which is a perception of depth obtained from binocular vision, at distances of tens to hundreds of meters. Almost nothing is known of our stereoscopic abilities over this range and thus this is new and fundamental data about human vision. We will investigate how monocular and binocular information is combined at large distances; an issue relevant to sensor fusion, a central problem in neuroscience. The rese ....Stereoscopic Vision at Large Distances. This project measures the benefits of stereopsis, which is a perception of depth obtained from binocular vision, at distances of tens to hundreds of meters. Almost nothing is known of our stereoscopic abilities over this range and thus this is new and fundamental data about human vision. We will investigate how monocular and binocular information is combined at large distances; an issue relevant to sensor fusion, a central problem in neuroscience. The research is also critical for any tasks involving judgments over long distances including the recognition of distant targets and their relationships as well as the visual guidance of vehicles such as helicopters. It will also provide critical information to designers of binocular instruments.Read moreRead less
Robust Beamforming for Radar Imaging. The impact of radar imaging technologies on security and search and rescue operations is indisputable. They play a vital role in safeguarding a country from terrorism and crime, protecting its borders, and predicting adverse weather patterns. Searching for survivors in disaster areas such as earthquakes and fires can greatly benefit from the proposed research. Law-enforcement officers can employ radar imaging technology to enable accurate determination of t ....Robust Beamforming for Radar Imaging. The impact of radar imaging technologies on security and search and rescue operations is indisputable. They play a vital role in safeguarding a country from terrorism and crime, protecting its borders, and predicting adverse weather patterns. Searching for survivors in disaster areas such as earthquakes and fires can greatly benefit from the proposed research. Law-enforcement officers can employ radar imaging technology to enable accurate determination of targets of interest, obstacles, weapons, victims, outlaws, and hostages inside enclosed structures or buildings. The proposed research and its findings will support the development of cutting edge radar imaging research and technology in Australia.Read moreRead less
Efficient data manipulation in document classification. Document Classification has an enormous relevance in an era where large amounts of textual information is available. Document Classification is based on statistical and machine learning techniques that model documents represented as points in a multidimensional space. The Computer Engineering Laboratory (CEL) has ongoing projects using neural networks and other techniques for document classification. We are developing a development environm ....Efficient data manipulation in document classification. Document Classification has an enormous relevance in an era where large amounts of textual information is available. Document Classification is based on statistical and machine learning techniques that model documents represented as points in a multidimensional space. The Computer Engineering Laboratory (CEL) has ongoing projects using neural networks and other techniques for document classification. We are developing a development environment for large classification tasks, and Prof. Lee¡¯s work will focus in managing large amounts of data for them. Using his experience in data compression, databases and web applications, he will produce a set of tools for handling Gigabytes of textual data in our classification environment.Read moreRead less
Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition an ....Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition and an efficient algorithm for constructing and training NNE. Practical outcomes will include research training for early career researchers and new modelling tools for data mining, robotics and multi-agent systems. The project contributes to the national priority area of smart information use.Read moreRead less
How, What and Who in Human Communication: Movement of Face and Voice. The aim of this project is to identify the essential characteristics of tone, affect, and identity from face and voice using a combination of signal processing, biological, and behavioural techniques in order to develop a comprehensive model of auditory-visual speech processing and communication. This research will significantly improve understanding of the basis of auditory-visual perception and production in tonal languages ....How, What and Who in Human Communication: Movement of Face and Voice. The aim of this project is to identify the essential characteristics of tone, affect, and identity from face and voice using a combination of signal processing, biological, and behavioural techniques in order to develop a comprehensive model of auditory-visual speech processing and communication. This research will significantly improve understanding of the basis of auditory-visual perception and production in tonal languages and in affective communication, facilitate links between neurophysiological processes and auditory-visual speech processing; and contribute to applications in automatic person recognition, automatic speech recognition, text-to-speech systems, and talking head aids for the hearing impaired.Read moreRead less
Internet web page mining. This project aims to study the behaviour of internet search engines designed using a best first search strategy, and to improve on the existing designs. The outcome of the project will be a much better design of internet search engine which can be used to search for specific topics. The benefit to the Australian partner will be the gaining of skills in internet search engine design, originating from the Italian partner's group. The benefit to the Italian partner will be ....Internet web page mining. This project aims to study the behaviour of internet search engines designed using a best first search strategy, and to improve on the existing designs. The outcome of the project will be a much better design of internet search engine which can be used to search for specific topics. The benefit to the Australian partner will be the gaining of skills in internet search engine design, originating from the Italian partner's group. The benefit to the Italian partner will be the gaining of skills in research techniques, e.g., utilising a support vector machine as a classification tool, data mining techniques developed originally by the Australian partner's group, and in further developments of these techniques with specific applications to the internet web page mining problem.Read moreRead less
Extensions to the page scoring algorithm in internet search engine studies. This project proposes to study two extensions to the Page rank equation which is one of the theoretical underpinning of Google's web page scoring engine. In particular, we wish to explore ways to combine page connectivity and page characteristics in the scoring of web pages. This will be the first time a rational way is proposed for combining these two factors. The expected outcome will be a deeper understanding on how t ....Extensions to the page scoring algorithm in internet search engine studies. This project proposes to study two extensions to the Page rank equation which is one of the theoretical underpinning of Google's web page scoring engine. In particular, we wish to explore ways to combine page connectivity and page characteristics in the scoring of web pages. This will be the first time a rational way is proposed for combining these two factors. The expected outcome will be a deeper understanding on how these two factors affect the scores of a web page in a search engine, and hence how they affect the visibility of the page in response to a query.
Read moreRead less
Solving the passport problem: re-designing photo-ID to improve recognition. We aim to contribute to national security and crime prevention by increasing the accuracy with which security staff can check the validity of photo-ID documents such as passports. Research shows that it is surprisingly difficult to determine if the image on a photo-ID document is of the bearer, and as a result it is likely that fraudulent use of photo-ID documents sometimes goes undetected. Our novel approach is to use ....Solving the passport problem: re-designing photo-ID to improve recognition. We aim to contribute to national security and crime prevention by increasing the accuracy with which security staff can check the validity of photo-ID documents such as passports. Research shows that it is surprisingly difficult to determine if the image on a photo-ID document is of the bearer, and as a result it is likely that fraudulent use of photo-ID documents sometimes goes undetected. Our novel approach is to use our knowledge of unfamiliar face perception to develop new image formats for photo-ID documents which increase the accuracy with which security staff can detect identity fraud.Read moreRead less
Acoustic Filter Functions from Morphological Measurements. This project works toward enabling the broadcast of high-fidelity 3D audio. By developing an efficient technique for deriving personalised acoustic filter functions based on image data of the listener's head and ears, we hope to enable high-fidelity 3D audio decoding and rendering. Morphological parameterisation techniques and databases recently developed at the University of York will be combined with the statistical synthesis technique ....Acoustic Filter Functions from Morphological Measurements. This project works toward enabling the broadcast of high-fidelity 3D audio. By developing an efficient technique for deriving personalised acoustic filter functions based on image data of the listener's head and ears, we hope to enable high-fidelity 3D audio decoding and rendering. Morphological parameterisation techniques and databases recently developed at the University of York will be combined with the statistical synthesis techniques and databases developed at the University of Sydney to substantially reduce the development time required for either group alone. Psychoacoustic experiments carried out at the University of Sydney will demonstrate the fidelity of the delivered 3D audio.Read moreRead less