Skip to main content

Research Repository

Advanced Search

Deep 3D face recognition using 3D data augmentation and transfer learning (2020)
Conference Proceeding
Smith, M., Smith, L., Huang, N., Hansen, M., & Smith, M. (2020). Deep 3D face recognition using 3D data augmentation and transfer learning

Abstract. Deep convolutional neural networks (DCNNs) have achieved humancomparable performance on challenging 2D face databases, outperforming all previous shallow methods. However, current 3D face recognition research still focuses on non-deep-learn... Read More about Deep 3D face recognition using 3D data augmentation and transfer learning.

Eye centre localisation with convolutional neural network based regression (2020)
Conference Proceeding
Zhang, W., & Smith, M. (2020). Eye centre localisation with convolutional neural network based regression. https://doi.org/10.1109/ICIVC47709.2019.8980972

This paper introduces convolutional neural network regression models based on the Inception-v3 and the DenseNet architectures for accurate and real-time eye centre localisation. At a normalised error of e < 0.05, the proposed method yields an accurac... Read More about Eye centre localisation with convolutional neural network based regression.

Weed classification in grasslands using convolutional neural networks (2019)
Conference Proceeding
Smith, L. N., Byrne, A., Hansen, M. F., Zhang, W., & Smith, M. L. (2019). Weed classification in grasslands using convolutional neural networks. https://doi.org/10.1117/12.2530092

Automatic identification and selective spraying of weeds (such as dock) in grass can provide very significant long-term ecological and cost benefits. Although machine vision (with interface to suitable automation) provides an effective means of achie... Read More about Weed classification in grasslands using convolutional neural networks.

Broad-leaf weed detection in pasture (2018)
Conference Proceeding
Zhang, W., Hansen, M. F., Volonakis, T. N., Smith, M., Smith, L., Wilson, J., …Wright, G. (2018). Broad-leaf weed detection in pasture

Weed control in pasture is a challenging problem that can be expensive and environmentally unfriendly. This paper proposes a novel method for recognition of broad-leaf weeds in pasture such that precision weed control can be achieved with reduced her... Read More about Broad-leaf weed detection in pasture.

2D and 3D face analysis for ticketless rail travel (2018)
Conference Proceeding
Smith, L., Zhang, W., & Smith, M. L. (2018). 2D and 3D face analysis for ticketless rail travel. In Proceedings of the 2018 International Conference on Image Processing, Computer Vision, & Pattern Recognition. , (16-22)

Research is reported into the design, implementation and functionalities of a vision system that employs the human face as a biometric for enabling ticketless rail travel. The system has been developed to optimise performance in the relatively unstru... Read More about 2D and 3D face analysis for ticketless rail travel.

Photometric stereo technique suitability study for plant phenotyping (2017)
Conference Proceeding
Halliday, K., Smith, L., Hansen, M., Smith, M., Bernotas, G., Scorza, L., …Smith, M. (2017). Photometric stereo technique suitability study for plant phenotyping

The dynamic quantification of growth traits is critical for building accurate modelling tools to predict plant behaviour under different growth environments, and consequently in designing strategies to improve plant health and overall yields. We are... Read More about Photometric stereo technique suitability study for plant phenotyping.

High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation (2010)
Conference Proceeding
Smith, M. L., Smith, L. N., Farooq, A. R., Wedowski, R. D., Wedowski, R., Farooq, A., …Smith, M. (2010). High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation. In W. Smari (Ed.), International Conference on High Performance Computing and Simulation (HPCS), 2010, (410-417). https://doi.org/10.1109/HPCS.2010.5547105

We propose a new high speed line tracing algorithm based on a well known differential geometric line extraction algorithm. The previously separate steps of line detection and line tracing are performed simultaneously. This allows the exclusion of non... Read More about High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation.