Peter Kovesi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Peter Kovesi has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Eun-Jung Holden
School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, Australia
18 shared publications Daniel Wedge
7 shared publicationsJason C. Wong
4 shared publications- Michael Dentith
The University of Western Australia
4 shared publications Yathunanthan Vasuki
4 shared publications- Shih Ching Fu
International Centre for Radio Astronomy Research, Curtin University, Bentley, WA 6102, Australia
3 shared publications
Latest Publications
- 11 November 2019
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2019 (1) , 1-3
Colour amplifies relief shading
Relief shading has long been recognised as being an effective way of presenting data. However, the interaction of relief shading and colour is perhaps not widely understood, and many software packages do not combine shading and colour in a physically correct manner. When relief shading and colour are correctly exploited an enhancement of the perception of 3D is obtained and, at the same time, a dynamic range compression of the data can be achieved while still retaining a sense of the metric values of the data. However, on the other hand, an inappropriate use of colour has the potential to disrupt the 3D perception induced by relief shading. To obtain the maximum benefit from combining colour with relief shading a low contrast colour map should be used and the shading pattern should be applied to the colour image multiplicatively, not via a transparency blending as is often implemented in GIS packages.
- 11 November 2019
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2019 (1) , 1-3
Colour amplifies relief shading
Relief shading has long been recognised as being an effective way of presenting data. However, the interaction of relief shading and colour is perhaps not widely understood, and many software packages do not combine shading and colour in a physically correct manner. When relief shading and colour are correctly exploited an enhancement of the perception of 3D is obtained and, at the same time, a dynamic range compression of the data can be achieved while still retaining a sense of the metric values of the data. However, on the other hand, an inappropriate use of colour has the potential to disrupt the 3D perception induced by relief shading. To obtain the maximum benefit from combining colour with relief shading a low contrast colour map should be used and the shading pattern should be applied to the colour image multiplicatively, not via a transparency blending as is often implemented in GIS packages.
- 1 May 2019
- Published by Elsevier in Ore Geology Reviews
- Vol. 108, 23-32
The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach
- 1 May 2019
- Published by Elsevier in Ore Geology Reviews
- Vol. 108, 23-32
The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach
- Open Access
- 1 March 2017
- Published by Elsevier in Computers & Geosciences
- Vol. 100, 27-40
An interactive image segmentation method for lithological boundary detection: A rapid mapping tool for geologists
- 1 March 2017
- Published by Elsevier in Computers & Geosciences
- Vol. 100, 27-40
Open AccessAn interactive image segmentation method for lithological boundary detection: A rapid mapping tool for geologists
- 1 August 2015
- Published by Elsevier in Journal of Structural Geology
- Vol. 77, 27-44
Insights into the mechanics of en-échelon sigmoidal vein formation using ultra-high resolution photogrammetry and computed tomography
- 1 August 2015
- Published by Elsevier in Journal of Structural Geology
- Vol. 77, 27-44
Insights into the mechanics of en-échelon sigmoidal vein formation using ultra-high resolution photogrammetry and computed tomography
- 12 May 2015
- Published by Springer Nature in Mathematical Geosciences
- Vol. 47 (5) , 521-545
Classification of Gold-Bearing Particles Using Visual Cues and Cost-Sensitive Machine Learning
- 12 May 2015
- Published by Springer Nature in Mathematical Geosciences
- Vol. 47 (5) , 521-545
Classification of Gold-Bearing Particles Using Visual Cues and Cost-Sensitive Machine Learning
- 22 April 2015
- Published by Society of Exploration Geophysicists
- Vol. 1, 501-504
Integrated exploration platform: 2D and 3D data visualizations through interactivity
Summary: Mineral explorers are challenged to integrate a vast amount and variety of data into a single coherent interpretation. Geological interpretation, in general, is a difficult and subjective task as human biases can result in highly uncertain outcomes. This on-going collaborative research between CET and GSWA aims to address this challenge by facilitating improved utilization of GSWA data to support explorers operating in Western Australia. The Integrated Exploration Platform aims to harness the power of human computer interaction coupled with visualization and image analysis, to maximize geological knowledge gain whilst minimizing visual biases in multi-data interpretation. This is partially achieved through novel visualization methods that allow multiple datasets simultaneously, and novel visualization methods for more effective comprehension of 3D volumetric data.
- 22 April 2015
- Published by Society of Exploration Geophysicists
- Vol. 1, 501-504
Integrated exploration platform: 2D and 3D data visualizations through interactivity
Summary: Mineral explorers are challenged to integrate a vast amount and variety of data into a single coherent interpretation. Geological interpretation, in general, is a difficult and subjective task as human biases can result in highly uncertain outcomes. This on-going collaborative research between CET and GSWA aims to address this challenge by facilitating improved utilization of GSWA data to support explorers operating in Western Australia. The Integrated Exploration Platform aims to harness the power of human computer interaction coupled with visualization and image analysis, to maximize geological knowledge gain whilst minimizing visual biases in multi-data interpretation. This is partially achieved through novel visualization methods that allow multiple datasets simultaneously, and novel visualization methods for more effective comprehension of 3D volumetric data.
- 1 November 2014
- Published by Elsevier in Computers & Geosciences
- Vol. 72, 147-155
Interactive multi-image blending for visualization and interpretation
- 1 November 2014
- Published by Elsevier in Computers & Geosciences
- Vol. 72, 147-155
Interactive multi-image blending for visualization and interpretation
- Top Cited Papers
- 1 August 2014
- Published by Elsevier in Computers & Geosciences
- Vol. 69, 22-32
Semi-automatic mapping of geological Structures using UAV-based photogrammetric data: An image analysis approach
- 1 August 2014
- Published by Elsevier in Computers & Geosciences
- Vol. 69, 22-32
Top Cited PapersSemi-automatic mapping of geological Structures using UAV-based photogrammetric data: An image analysis approach
- Open Access
- 1 December 2013
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2013 (1) , 1-4
Interactive multi-image blending for data visualisation and interpretation
The ability to integrate data from a range of different images is often a crucial requirement for successful interpretation. Interactive multi-image blending is presented as a tool for facilitating the interpretation of complex information from multiple data sources. Traditionally, image blending has only been considered for cross-dissolving effects between two images. However, it is common for there to be more than just two images of interest in an interpretation task. We have developed a family of different multi-image blending tools to fill this need. These have been designed to support a number of different interpretation tasks and image types. For image blending to be a useful tool for multiple image interpretation it is important that the association between features and individual input images remain identifiable and distinct within the blend. We argue that interactivity of the blend is an important component for achieving this. Blending can also be usefully employed to interactively explore parameter variations for enhancement techniques. Often the best parameter values to use cannot be known beforehand, and it is common for different regions of an image to require different parameter values for best enhancement. By preparing a set of images processed over a sequence of scales and parameter values, and then interactively blending between these images, the interpretation of a data set can be greatly facilitated.
- 1 December 2013
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2013 (1) , 1-4
Open AccessInteractive multi-image blending for data visualisation and interpretation
The ability to integrate data from a range of different images is often a crucial requirement for successful interpretation. Interactive multi-image blending is presented as a tool for facilitating the interpretation of complex information from multiple data sources. Traditionally, image blending has only been considered for cross-dissolving effects between two images. However, it is common for there to be more than just two images of interest in an interpretation task. We have developed a family of different multi-image blending tools to fill this need. These have been designed to support a number of different interpretation tasks and image types. For image blending to be a useful tool for multiple image interpretation it is important that the association between features and individual input images remain identifiable and distinct within the blend. We argue that interactivity of the blend is an important component for achieving this. Blending can also be usefully employed to interactively explore parameter variations for enhancement techniques. Often the best parameter values to use cannot be known beforehand, and it is common for different regions of an image to require different parameter values for best enhancement. By preparing a set of images processed over a sequence of scales and parameter values, and then interactively blending between these images, the interpretation of a data set can be greatly facilitated.