• Publications
  • Influence
A Corpus-Based Approach to Speech Enhancement From Nonstationary Noise
It is demonstrated that this can reduce the requirement for prior information about the noise, which can be difficult to estimate for fast-varying noise, and increase the noise immunity and hence the estimation accuracy. Expand
Automatic Recognition of Partial Shoeprints Based on Phase-Only Correlation
Results have shown that the proposed method is very practical and provides high performance when processing low quality partial-prints and the use of a weighting function provides an improvement in the recognition rate in particularly difficult cases. Expand
Automatic Recognition of Shoeprints using Fourier-Mellin Transform
Experimental results show that the proposed method for automatically recognising shoeprint images for use in forensic science is very practical providing attractive performance when processing distorted shoepprint images. Expand
Parallel architectures for image processing
A tutorial introduction to the field of parallel image processing is presented and an application of parallel processing to handwritten postcode recognition is described. Expand
Design and implementation of a novel algorithm for general purpose median filtering on FPGAs
A novel bit serial algorithm which is scalable and easily implemented on small FPGA chips, similar to that of Quicksort, and is based on a 'Bit Voter' (BV) block is presented. Expand
Partial shoeprint retrieval using multiple point-of-interest detectors and SIFT descriptors
A solution for the automatic retrieval of shoeprints which is considerably more robust than existing solutions in the presence of geometric distortions such as scale, rotation and scale distortions and relies on the use of two local point-of-interest detectors whose matching scores are combined. Expand
High-performance 3D median filter architecture for medical image despeckling
A high-sample rate 3D median filtering processor architecture is proposed, based on a novel 3D median filtering algorithm, that can reduce the computing complexity in comparison with the traditionalExpand
Application of fractals to the detection and classification of shoeprints
A novel technique for use in the detection and classification of shoeprint impressions has been developed, based on fractal based feature extraction and pattern matching methods. Expand
Rotation Invariant Matching of Partial Shoeprints
This paper proposes a solution for the problem of rotated partial shoeprint retrieval based on the combined use of local points of interest and SIFT descriptor and demonstrates that such combination can overcome the issue of retrieval of partial prints in the presence of rotation and noise distortions. Expand
Segmentation of Squamous Epithelium from Ultra-large Cervical Histological Virtual Slides
An image segmentation method for the automated identification of Squamous epithelium from virtual slides using robust texture feature vectors in combination with a Support Vector Machine (SVM) to perform classification. Expand