Projects per year
Personal profile
Personal Statement
Innes is a PhD student at the University of Strathclyde in the Department of Electronic and Electrical Engineering as part of CeSIP. His research focusses developing methods for automatically detecting, counting, and characterising asbestos in microscopy images. These approaches are investigated in the context of nuclear decommissioning, with research being supported by UKRI and Nuclear Restoration Services, with additional collaboration from Franks Portlock Consulting.
Innes graduated from the University of Strathclyde in 2025 with a First Class Honours in Computer and Electronic Systems, where he specialised in image and digital signal processing. During his final year, he focussed his dissertation on the automatic classification and localisation of surface crack features in concrete and asphalt. This project resulted in the development of an accurate and compact system to classify and segment crack features in images, paired with a streamlined user interface allowing for a range of customisable parameters and analysis techniques.
Currently, Innes’ work explores the use of deep learning approaches for the automatic detection and quantification of asbestos fibres within phase contrast microscopy images of air filter samples.
Research Interests
Innes’ current research interests centre on deep learning techniques for image classification, detection, and segmentation. He is also interested in the developments and applications of mathematical morphology techniques for image processing. Innes is focussed on combining modern approaches with traditional image and signal processing algorithms and techniques. The combination of these techniques allows for the investigation of various applications, including the creation of representative synthetic datasets for training deep learning models.
Innes has a keen interest in ensuring approaches using deep learning techniques are explainable. He is investigating uncertainty estimation techniques, as well as approaches for training models and presenting predictions in an interpretable and transparent manner.
Education/Academic qualification
Bachelor of Engineering, BEng (Hons) Computer and Electronic Systems - First Class, University Of Strathclyde
20 Sept 2021 → 30 Jun 2025
Award Date: 30 Jun 2025
Keywords
- Deep Learning
- Asbestos
- Fibre Counting
- Image Processing
- Signal Processing
- Computer Vision
- Nuclear Decommissioning
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
-
SDG 9 Industry, Innovation, and Infrastructure
-
SDG 11 Sustainable Cities and Communities
-
SDG 12 Responsible Consumption and Production
-
SDG 13 Climate Action
Fingerprint
- 2 Similar Profiles
Projects
- 1 Active
-
DTP 2224 University of Strathclyde | Dickson, Innes
Campbell, A. J. (Principal Investigator), Murray, P. (Co-investigator) & Dickson, I. (Research Co-investigator)
EPSRC (Engineering and Physical Sciences Research Council)
1/07/25 → 1/07/29
Project: Research Studentship - Internally Allocated
-
Automated Asbestos Fibre Counting - Poster
Dickson, I., Campbell, A. J., Murray, P., Morgan, C., Lynch, P. & New, J., 16 Jun 2026. 1 p.Research output: Contribution to conference › Poster
Open AccessFile11 Downloads (Pure) -
Automated asbestos fibre counting: a procedurally generated data-driven approach
Dickson, I., Campbell, A. J., Murray, P., Morgan, C., Lynch, P. & New, J., 15 Apr 2026, (Unpublished).Research output: Contribution to conference › Presentation/Speech
Prizes
-
OH2026: Judge's Choice Poster Prize
Dickson, I. (Recipient), 17 Jun 2026
Prize: Prize (including medals and awards)
File