Dr MICHAEL POUND's Outputs (46)

Practical Aberration Correction using Deep Transfer Learning with Limited Experimental Data (2025)
Journal Article
Kok, Y. E. N., Bentley, A., Parkes, A. J., Somekh, M. G., Wright, A. J., & Pound, M. P. (2025). Practical Aberration Correction using Deep Transfer Learning with Limited Experimental Data. Optics Express, 33(6), 14431-14444. https://doi.org/10.1364/oe.557993

Adaptive optics is a technique for correcting aberrations and improving image quality. When adaptive optics was first used in microscopy, it was common to rely on iterative approaches to determine the aberrations present. It is advantageous to avoid... Read More about Practical Aberration Correction using Deep Transfer Learning with Limited Experimental Data.

High-fidelity wheat plant reconstruction using 3D Gaussian splatting and neural radiance fields (2025)
Journal Article
Pound, M. P., Stuart, L. A. G., Wells, D. M., Atkinson, J. A., Castle-Green, S., & Walker, J. (2025). High-fidelity wheat plant reconstruction using 3D Gaussian splatting and neural radiance fields. GigaScience, 14, Article giaf022. https://doi.org/10.1093/gigascience/giaf022

Background
The reconstruction of 3-dimensional (3D) plant models can offer advantages over traditional 2-dimensional approaches by more accurately capturing the complex structure and characteristics of different crops. Conventional 3D reconstruction... Read More about High-fidelity wheat plant reconstruction using 3D Gaussian splatting and neural radiance fields.

Advancing Saliency Ranking with Human Fixations: Dataset, Models and Benchmarks (2024)
Presentation / Conference Contribution
Deng, B., Song, S., French, A. P., Schluppeck, D., & Pound, M. P. (2024, June). Advancing Saliency Ranking with Human Fixations: Dataset, Models and Benchmarks. Presented at Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA

Saliency ranking detection (SRD) has emerged as a challenging task in computer vision, aiming not only to identify salient objects within images but also to rank them based on their degree of saliency. Existing SRD datasets have been created primaril... Read More about Advancing Saliency Ranking with Human Fixations: Dataset, Models and Benchmarks.

Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra (2024)
Journal Article
Kok, Y. E., Crisford, A., Parkes, A., Venkateswaran, S., Oreffo, R., Mahajan, S., & Pound, M. (2024). Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra. Scientific Reports, 14(1), Article 15902. https://doi.org/10.1038/s41598-024-66857-6

Raman spectroscopy is a rapid method for analysing the molecular composition of biological material. However, noise contamination in the spectral data necessitates careful pre-processing prior to analysis. Here we propose an end-to-end Convolutional... Read More about Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra.

Domain Targeted Synthetic Plant Style Transfer using Stable Diffusion, LoRA and ControlNet (2024)
Presentation / Conference Contribution
Hartley, Z. K., Lind, R. J., Pound, M. P., & French, A. P. (2024, June). Domain Targeted Synthetic Plant Style Transfer using Stable Diffusion, LoRA and ControlNet. Presented at 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA

Synthetic images can help alleviate much of the cost in the creation of training data for plant phenotyping-focused AI development. Synthetic-to-real style transfer is of particular interest to users of artificial data because of the domain shift pro... Read More about Domain Targeted Synthetic Plant Style Transfer using Stable Diffusion, LoRA and ControlNet.

Addressing multiple salient object detection via dual-space long-range dependencies (2023)
Journal Article
Deng, B., French, A. P., & Pound, M. P. (2023). Addressing multiple salient object detection via dual-space long-range dependencies. Computer Vision and Image Understanding, 235, Article 103776. https://doi.org/10.1016/j.cviu.2023.103776

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of detecting multi... Read More about Addressing multiple salient object detection via dual-space long-range dependencies.

Root architecture and leaf photosynthesis traits and associations with nitrogen-use efficiency in landrace-derived lines in wheat (2022)
Journal Article
Kareem, S. H., Hawkesford, M. J., DeSilva, J., Weerasinghe, M., Wells, D. M., Pound, M. P., Atkinson, J. A., & Foulkes, M. J. (2022). Root architecture and leaf photosynthesis traits and associations with nitrogen-use efficiency in landrace-derived lines in wheat. European Journal of Agronomy, 140, Article 126603. https://doi.org/10.1016/j.eja.2022.126603

Root system architecture (RSA) is important in optimizing the use of nitrogen. High-throughput phenotyping techniques may be used to study root system architecture traits under controlled environments. A root phenotyping platform, consisting of germi... Read More about Root architecture and leaf photosynthesis traits and associations with nitrogen-use efficiency in landrace-derived lines in wheat.

Evaluation of synthetic aerial imagery using unconditional generative adversarial networks (2022)
Journal Article
Yates, M., Hart, G., Houghton, R., Torres Torres, M., & Pound, M. (2022). Evaluation of synthetic aerial imagery using unconditional generative adversarial networks. ISPRS Journal of Photogrammetry and Remote Sensing, 190, 231-251. https://doi.org/10.1016/j.isprsjprs.2022.06.010

Image generation techniques, such as generative adversarial networks (GANs), have become sufficiently sophisticated to cause growing concerns around the authenticity of images in the public domain. Although these generation techniques have been appli... Read More about Evaluation of synthetic aerial imagery using unconditional generative adversarial networks.

A review of ultrasonic sensing and machine learning methods to monitor industrial processes (2022)
Journal Article
Bowler, A. L., Pound, M. P., & Watson, N. J. (2022). A review of ultrasonic sensing and machine learning methods to monitor industrial processes. Ultrasonics, 124, Article 106776. https://doi.org/10.1016/j.ultras.2022.106776

Supervised machine learning techniques are increasingly being combined with ultrasonic sensor measurements owing to their strong performance. These techniques also offer advantages over calibration procedures of more complex fitting, improved general... Read More about A review of ultrasonic sensing and machine learning methods to monitor industrial processes.

Identification of QTL and underlying genes for root system architecture associated with nitrate nutrition in hexaploid wheat (2022)
Journal Article
GRIFFITHS, M., ATKINSON, J. A., Gardiner, L. J., SWARUP, R., POUND, M. P., WILSON, M. H., BENNETT, M. J., & WELLS, D. M. (2022). Identification of QTL and underlying genes for root system architecture associated with nitrate nutrition in hexaploid wheat. Journal of Integrative Agriculture, 21(4), 917-932. https://doi.org/10.1016/s2095-3119%2821%2963700-0

The root system architecture (RSA) of a crop has a profound effect on the uptake of nutrients and consequently the potential yield. However, little is known about the genetic basis of RSA and resource adaptive responses in wheat (Triticum aestivum L.... Read More about Identification of QTL and underlying genes for root system architecture associated with nitrate nutrition in hexaploid wheat.

X-ray CT reveals 4D root system development and lateral root responses to nitrate in soil (2022)
Journal Article
Griffiths, M., Mellor, N., Sturrock, C. J., Atkinson, B. S., Johnson, J., Mairhofer, S., York, L. M., Atkinson, J. A., Soltaninejad, M., Foulkes, J. F., Pound, M. P., Mooney, S. J., Pridmore, T. P., Bennett, M. J., & Wells, D. M. (2022). X-ray CT reveals 4D root system development and lateral root responses to nitrate in soil. Plant Phenome Journal, 5(1), Article e20036. https://doi.org/10.1002/ppj2.20036

The spatial arrangement of the root system, termed root system architecture, is important for resource acquisition as it directly affects the soil zone explored. Methods for phenotyping roots are mostly destructive, which prevents analysis of roots o... Read More about X-ray CT reveals 4D root system development and lateral root responses to nitrate in soil.

A fusion spatial attention approach for few-shot learning (2021)
Journal Article
Song, H., Deng, B., Pound, M., Özcan, E., & Triguero, I. (2022). A fusion spatial attention approach for few-shot learning. Information Fusion, 81, 187-202. https://doi.org/10.1016/j.inffus.2021.11.019

Few-shot learning is a challenging problem in computer vision that aims to learn a new visual concept from very limited data. A core issue is that there is a large amount of uncertainty introduced by the small training set. For example, the few image... Read More about A fusion spatial attention approach for few-shot learning.

Domain adaptation and federated learning for ultrasonic monitoring of beer fermentation (2021)
Journal Article
Bowler, A. L., Pound, M. P., & Watson, N. J. (2021). Domain adaptation and federated learning for ultrasonic monitoring of beer fermentation. Fermentation, 7(4), Article 253. https://doi.org/10.3390/fermentation7040253

Beer fermentation processes are traditionally monitored through sampling and off-line wort density measurements. In-line and on-line sensors would provide real-time data on the fermentation progress whilst minimising human involvement, enabling ident... Read More about Domain adaptation and federated learning for ultrasonic monitoring of beer fermentation.

Convolutional feature extraction for process monitoring using ultrasonic sensors (2021)
Journal Article
Bowler, A., Pound, M., & Watson, N. (2021). Convolutional feature extraction for process monitoring using ultrasonic sensors. Computers and Chemical Engineering, 155, Article 107508. https://doi.org/10.1016/j.compchemeng.2021.107508

Ultrasonic sensors are a low-cost and in-line technique and can be combined with machine learning for industrial process monitoring. However, training accurate machine learning models for process monitoring using sensor data is dependant on the featu... Read More about Convolutional feature extraction for process monitoring using ultrasonic sensors.

Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning (2021)
Journal Article
Bowler, A., Escrig, J., Pound, M., & Watson, N. (2021). Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning. Fermentation, 7(1), Article 34. https://doi.org/10.3390/fermentation7010034

Beer fermentation is typically monitored by periodic sampling and off-line analysis. In-line sensors would remove the need for time-consuming manual operation and provide real-time evaluation of the fermenting media. This work uses a low-cost ultraso... Read More about Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning.

Predicting Plant Growth from Time-Series Data Using Deep Learning (2021)
Journal Article
Yasrab, R., Zhang, J., Smyth, P., & Pound, M. P. (2021). Predicting Plant Growth from Time-Series Data Using Deep Learning. Remote Sensing, 13(3), 1-17. https://doi.org/10.3390/rs13030331

Phenotyping involves the quantitative assessment of the anatomical, biochemical, and physiological plant traits. Natural plant growth cycles can be extremely slow, hindering the experimental processes of phenotyping. Deep learning offers a great deal... Read More about Predicting Plant Growth from Time-Series Data Using Deep Learning.

Volumetric Segmentation of Cell Cycle Markers in Confocal Images Using Machine Learning and Deep Learning (2020)
Journal Article
Khan, F. A., Voß, U., Pound, M. P., & French, A. P. (2020). Volumetric Segmentation of Cell Cycle Markers in Confocal Images Using Machine Learning and Deep Learning. Frontiers in Plant Science, 11, Article 1275. https://doi.org/10.3389/fpls.2020.01275

© Copyright © 2020 Khan, Voß, Pound and French. Understanding plant growth processes is important for many aspects of biology and food security. Automating the observations of plant development—a process referred to as plant phenotyping—is increasing... Read More about Volumetric Segmentation of Cell Cycle Markers in Confocal Images Using Machine Learning and Deep Learning.

Three Dimensional Root CT Segmentation Using Multi-Resolution Encoder-Decoder Networks (2020)
Journal Article
Soltaninejad, M., Sturrock, C. J., Griffiths, M., Pridmore, T. P., & Pound, M. P. (2020). Three Dimensional Root CT Segmentation Using Multi-Resolution Encoder-Decoder Networks. IEEE Transactions on Image Processing, 29, 6667-6679. https://doi.org/10.1109/TIP.2020.2992893

© 1992-2012 IEEE. We address the complex problem of reliably segmenting root structure from soil in X-ray Computed Tomography (CT) images. We utilise a deep learning approach, and propose a state-of-the-art multi-resolution architecture based on enco... Read More about Three Dimensional Root CT Segmentation Using Multi-Resolution Encoder-Decoder Networks.

RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures (2019)
Journal Article
Yasrab, R., Atkinson, J. A., Wells, D. M., French, A. P., Pridmore, T. P., & Pound, M. P. (2019). RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures. GigaScience, 8(11), Article giz123. https://doi.org/10.1093/gigascience/giz123

BACKGROUND: In recent years quantitative analysis of root growth has become increasingly important as a way to explore the influence of abiotic stress such as high temperature and drought on a plant's ability to take up water and nutrients. Segmentat... Read More about RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures.

Supporting data for "RootNav 2.0: Deep Learning for Automatic Navigation of Complex Plant Root Architectures" (2019)
Data
French, A., Wells, D. M., Atkinson, J., Pound, M., Yasrab, R., & Pridmore, T. (2019). Supporting data for "RootNav 2.0: Deep Learning for Automatic Navigation of Complex Plant Root Architectures". [Data]. https://doi.org/10.5524/100651

We present a new image analysis approach that provides fully-automatic extraction of complex root system architectures from a range of plant species in varied imaging setups. Driven by modern deep-learning approaches, RootNav 2.0 replaces previously... Read More about Supporting data for "RootNav 2.0: Deep Learning for Automatic Navigation of Complex Plant Root Architectures".