Thu H. McCann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Thu H. McCann has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Li Day
AgResearch Ltd., Te Ohu Rangahau Kai, Palmerston North 4474, New Zealand
8 shared publications - Sheridan C. Mayo
Commonwealth Scientific and Industrial Research Organisation, Clayton, Australia
3 shared publications A. Maksimenko
1 shared publicationAhmed Regina
1 shared publicationAlireza Bab-Hadiashar
School of Engineering, RMIT University, Australia
1 shared publication- Amirali Khodadadian Gostar
School of Engineering, RMIT University, Melbourne, Australia
1 shared publication
Latest Publications
- 18 February 2021
- Published by International Union of Crystallography (IUCr) in Journal of Synchrotron Radiation
- Vol. 28 (2) , 566-575
Automatic segmentation for synchrotron-based imaging of porous bread dough using deep learning approach
In recent years, major capability improvements at synchrotron beamlines have given researchers the ability to capture more complex structures at a higher resolution within a very short time. This opens up the possibility of studying dynamic processes and observing resulting structural changes over time. However, such studies can create a huge quantity of 3D image data, which presents a major challenge for segmentation and analysis. Here tomography experiments at the Australian synchrotron source are examined, which were used to study bread dough formulations during rising and baking, resulting in over 460 individual 3D datasets. The current pipeline for segmentation and analysis involves semi-automated methods using commercial software that require a large amount of user input. This paper focuses on exploring machine learning methods to automate this process. The main challenge to be faced is in generating adequate training datasets to train the machine learning model. Creating training data by manually segmenting real images is very labour-intensive, so instead methods of automatically creating synthetic training datasets which have the same attributes of the original images have been tested. The generated synthetic images are used to train a U-Net model, which is then used to segment the original bread dough images. The trained U-Net outperformed the previously used segmentation techniques while taking less manual effort. This automated model for data segmentation would alleviate the time-consuming aspects of experimental workflow and would open the door to perform 4D characterization experiments with smaller time steps.
- 18 February 2021
- Published by International Union of Crystallography (IUCr) in Journal of Synchrotron Radiation
- Vol. 28 (2) , 566-575
Automatic segmentation for synchrotron-based imaging of porous bread dough using deep learning approach
In recent years, major capability improvements at synchrotron beamlines have given researchers the ability to capture more complex structures at a higher resolution within a very short time. This opens up the possibility of studying dynamic processes and observing resulting structural changes over time. However, such studies can create a huge quantity of 3D image data, which presents a major challenge for segmentation and analysis. Here tomography experiments at the Australian synchrotron source are examined, which were used to study bread dough formulations during rising and baking, resulting in over 460 individual 3D datasets. The current pipeline for segmentation and analysis involves semi-automated methods using commercial software that require a large amount of user input. This paper focuses on exploring machine learning methods to automate this process. The main challenge to be faced is in generating adequate training datasets to train the machine learning model. Creating training data by manually segmenting real images is very labour-intensive, so instead methods of automatically creating synthetic training datasets which have the same attributes of the original images have been tested. The generated synthetic images are used to train a U-Net model, which is then used to segment the original bread dough images. The trained U-Net outperformed the previously used segmentation techniques while taking less manual effort. This automated model for data segmentation would alleviate the time-consuming aspects of experimental workflow and would open the door to perform 4D characterization experiments with smaller time steps.
- 1 September 2018
- Published by Elsevier in Food Hydrocolloids
- Vol. 82, 434-441
Rheological properties and microstructure of soy-whey protein
- 1 September 2018
- Published by Elsevier in Food Hydrocolloids
- Vol. 82, 434-441
Rheological properties and microstructure of soy-whey protein
- 1 January 2018
- Published by Elsevier in Journal of Cereal Science
- Vol. 79, 440-448
High amylose wheat starch increases the resistance to deformation of wheat flour dough
- 1 January 2018
- Published by Elsevier in Journal of Cereal Science
- Vol. 79, 440-448
High amylose wheat starch increases the resistance to deformation of wheat flour dough
- 30 June 2016
- Published by Springer Nature in Food and Bioprocess Technology
- Vol. 9 (11) , 1803-1811
Effect of the Sugar Replacement by Citrus Fibre on the Physical and Structural Properties of Wheat-Corn Based Extrudates
- 30 June 2016
- Published by Springer Nature in Food and Bioprocess Technology
- Vol. 9 (11) , 1803-1811
Effect of the Sugar Replacement by Citrus Fibre on the Physical and Structural Properties of Wheat-Corn Based Extrudates
- 1 May 2016
- Published by Elsevier in Journal of Cereal Science
- Vol. 69, 228-237
Extensional dough rheology – Impact of flour composition and extension speed
- 1 May 2016
- Published by Elsevier in Journal of Cereal Science
- Vol. 69, 228-237
Extensional dough rheology – Impact of flour composition and extension speed
- 1 January 2016
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1696, 020006
Rising dough and baking bread at the Australian synchrotron
- 1 January 2016
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1696, 020006
Rising dough and baking bread at the Australian synchrotron
- 1 August 2014
- Published by Elsevier in Food Research International
- Vol. 62, 701-708
Synergistic effect of milk solids and carrot cell wall particles on the rheology and texture of yoghurt gels
- 1 August 2014
- Published by Elsevier in Food Research International
- Vol. 62, 701-708
Synergistic effect of milk solids and carrot cell wall particles on the rheology and texture of yoghurt gels
- 1 August 2013
- Published by Elsevier in Food Research International
- Vol. 53 (1) , 352-361
Modification of structure and mixing properties of wheat flour through high-pressure processing
- 1 August 2013
- Published by Elsevier in Food Research International
- Vol. 53 (1) , 352-361
Modification of structure and mixing properties of wheat flour through high-pressure processing
- 1 May 2013
- Published by Elsevier in Journal of Cereal Science
- Vol. 57 (3) , 444-452
Effect of sodium chloride on gluten network formation, dough microstructure and rheology in relation to breadmaking
- 1 May 2013
- Published by Elsevier in Journal of Cereal Science
- Vol. 57 (3) , 444-452
Effect of sodium chloride on gluten network formation, dough microstructure and rheology in relation to breadmaking