Learning Medical Image Knowledge. We aim to develop Machine Learning and Knowledge Acquisition techniques for automated recognition of features in medical images, and to provide decision support for diagnosis from medical images. The project is innovative in its use of layered learning, where the computer first learns to recognise low-level image features that are then used to learn more complex features. The project is also innovative in combining a variety of automatic learning methods, includ ....Learning Medical Image Knowledge. We aim to develop Machine Learning and Knowledge Acquisition techniques for automated recognition of features in medical images, and to provide decision support for diagnosis from medical images. The project is innovative in its use of layered learning, where the computer first learns to recognise low-level image features that are then used to learn more complex features. The project is also innovative in combining a variety of automatic learning methods, including relational learning, with human-assisted knowledge acquisition methods. The expected outcomes will be new techniques for image understanding, particularly for our test domain, namely, High Resolution Computed Tomography scans of the lung.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE150101655
Funder
Australian Research Council
Funding Amount
$297,036.00
Summary
Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretatio ....Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretation. It will help to alleviate the inter-observer variability and time-consuming process of manual analysis. The project aims to advance fundamental biomedical imaging research in generalised visual structure extraction and classification, and enable large-scale translational research in systems pathology for personalised cancer care.Read moreRead less
Automatic Recognition of Human Activities in Surveillance Videos: Overcoming the Curse of Dimensionality. This project will deliver a technology capable of automatically recognising human activities of interest in surveillance videos. The project will tackle the challenging, huge complexity inherent in the recognition of human activities by novel statistical pattern recognition techniques. The outcome of this project will be an effective activity recognition technology that will help monitor the ....Automatic Recognition of Human Activities in Surveillance Videos: Overcoming the Curse of Dimensionality. This project will deliver a technology capable of automatically recognising human activities of interest in surveillance videos. The project will tackle the challenging, huge complexity inherent in the recognition of human activities by novel statistical pattern recognition techniques. The outcome of this project will be an effective activity recognition technology that will help monitor the security and safety of environments and support the further development of the Australian video surveillance industry.Read moreRead less
Feature Detection and Computer-aided Diagnosis with Longitudinal Tracking of Benign Asbestos-Related Pleural Disease in CT images. This project seeks to develop smart and novel feature extraction and knowledge acquisition techniques to assist radiologists in automated diagnosis and assessment of lung diseases. These outcomes will lead to improved delivery of health services in Australia, including in rural regions. They will lead to more accurate assessment of asbestos related pleural diseases f ....Feature Detection and Computer-aided Diagnosis with Longitudinal Tracking of Benign Asbestos-Related Pleural Disease in CT images. This project seeks to develop smart and novel feature extraction and knowledge acquisition techniques to assist radiologists in automated diagnosis and assessment of lung diseases. These outcomes will lead to improved delivery of health services in Australia, including in rural regions. They will lead to more accurate assessment of asbestos related pleural diseases for compensation and treatment and better followup, leading to earlier treatment and better quality of life for patients suffering from lung diseases. The project will also save costs due to automated assessment as well as the potential for fewer patient scans.Read moreRead less
Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to vi ....Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to video surveillance applications, which can enhance Australia’s homeland security.Read moreRead less
Automatic real-time detection of infiltrated objects for security of airports and train stations. Infiltrated objects represent a very high security threat in critical areas such as airports and train stations. In order to neutralise such a threat, this project will develop new automatic technologies capable of detecting infiltrated objects in sensitive areas in real time, analysing the movements of their original carriers in the nearby areas, and raising attention accordingly. The technologies ....Automatic real-time detection of infiltrated objects for security of airports and train stations. Infiltrated objects represent a very high security threat in critical areas such as airports and train stations. In order to neutralise such a threat, this project will develop new automatic technologies capable of detecting infiltrated objects in sensitive areas in real time, analysing the movements of their original carriers in the nearby areas, and raising attention accordingly. The technologies will be based on the automatic analysis of camera videos made by computers without the need for assessing or storing the identities of common passers-by. The potential of application is huge extending beyond airports and train stations to any public areas.Read moreRead less
Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance witho ....Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.Read moreRead less
Learning kernel-based high-order visual representation for image retrieval. Image retrieval plays a key role in many practical applications. The recent increase of real-world applications calls for higher retrieval accuracy. This project aims to address this issue by exploring advanced visual representation that models the high-order information of image content. This project expects to generate new knowledge in the area of computer vision by developing a novel image retrieval framework. Expecte ....Learning kernel-based high-order visual representation for image retrieval. Image retrieval plays a key role in many practical applications. The recent increase of real-world applications calls for higher retrieval accuracy. This project aims to address this issue by exploring advanced visual representation that models the high-order information of image content. This project expects to generate new knowledge in the area of computer vision by developing a novel image retrieval framework. Expected outcomes include theory development on visual representation and more effective retrieval techniques. This should provide significant benefits, such as improving public information access services, facilitating environmental monitoring, and enhancing smart traffic management.Read moreRead less
In search of relevant things: A novel approach for image analysis. This project aims to investigate how experts’ cognitive processes may be transferred to computers for the automatic recognition of visual features. By merging computer and brain sciences, the project will characterise the way the brains of experts understand what is seen, in order to translate such a process in a new computer vision tool. This should provide significant benefits, such as automatic detection of threats or diseases ....In search of relevant things: A novel approach for image analysis. This project aims to investigate how experts’ cognitive processes may be transferred to computers for the automatic recognition of visual features. By merging computer and brain sciences, the project will characterise the way the brains of experts understand what is seen, in order to translate such a process in a new computer vision tool. This should provide significant benefits, such as automatic detection of threats or diseases in satellite and diagnostic imaging, respectively, among other applications. For the first time, the combination of how a computer analyses an image and how an expert interprets it will be used as a common language to enable machines to process visual information in a manner that mimics the way human brains do.Read moreRead less
A theoretical framework for practical partial fingerprint identification. Fingerprints captured from a crime scene are often partial and poor quality which makes it difficult to identify the criminal suspects from large databases. This project will find mathematical models which can estimate the missing information located in the blank areas of a partial fingerprint and effectively identify it.