Martin R. Varley

Study of hand-dorsa vein recognition

A new hand-dorsa vein recognition method based on Partition Local Binary Pattern (PLBP) is presented in this paper. The proposed method employs hand-dorsa vein images acquired from a low-cost, near infrared device. After preprocessing, the image is divided into sub-images. LBP uniform pattern features are extracted from all the sub-images, which are combined to form the feature vector for token vein texture features. The method is assessed using a similarity measure obtained by calculating the Chi square statistic between the feature vectors of the tested sample and the target sample. Integral histogram method, original LBP and Partition LBP with 16, 32, 64 sub-images are tested on a database of 2040 images from 102 individuals built up by a custom-made acquisition device. The experimental results show that Partition LBP performs better than original LBP, Circular Partition LBP performs better than Rectangular Partition LBP, and when the image was divided into 32 performs better than others.

Hand vein recognition based on multiple keypoints sets

Biometric authentication based on hand vein patterns has grown in popularity as a way to confirm personal identity. However, the imaging quality and variability of the vein images acquired by the near-infrared (NIR) device present challenges to achieve high classification accuracy. In this paper, a novel method for hand vein recognition by fusion of multiple sets of keypoints from the scale-invariant feature transform (SIFT) is proposed. While the use of SIFT enables classification to be unaffected by imaging quality and variability, the fusion reduces information redundancies and improves the discrimination power. The proposed method is tested on a database of 2040 images, and the experiment results show a good classification performance with a result of 97.95% recognition rate.

A computationally efficient method for automatic registration of orthogonal x-ray images with volumetric CT data

The paper presents a computationally efficient 3D-2D image registration algorithm for automatic pre-treatment validation in radiotherapy. The novel aspects of the algorithm include (a) a hybrid cost function based on partial digitally reconstructed radiographs (DRRs) generated along projected anatomical contours and a level set term for similarity measurement; and (b) a fast search method based on parabola fitting and sensitivity-based search order. Using CT and orthogonal x-ray images from a skull and a pelvis phantom, the proposed algorithm is compared with the conventional ray-casting full DRR based registration method. Not only is the algorithm shown to be computationally more efficient with registration time being reduced by a factor of 8, but also the algorithm is shown to offer 50% higher capture range allowing the initial patient displacement up to 15 mm (measured by mean target registration error). For the simulated data, high registration accuracy with average errors of 0.53 mm +/- 0.12 mm for translation and 0.61 +/- 0.29 degrees for rotation within the capture range has been achieved. For the tested phantom data, the algorithm has also shown to be robust without being affected by artificial markers in the image.

EMG Biofeedback Based VR System for Hand Rotation and Grasping Rehabilitation

Individuals who have upper limb movement problems include people with cerebral palsy (CP) and stroke victims. Both these conditions lead to difficulties in daily activities such as reaching, grasping etc. Virtual reality (VR), which could provide a repetitive multimodal task-oriented rehabilitation environment for patients to undertake self-training in safety, is considered to be a suitable tool for medical health rehabilitation. Using electromyography (EMG) biofeedback in rehabilitation could provide patients with opportunities to improve the ability by assessing their muscle activity response and learning self-control of movement during specific training tasks. This paper presents a study on developing EMG as an important interactive tool in a VR based system for hand rotation and grasping motion rehabilitation. The input interface includes an EMG system and a real-time magnetic motion tracking system, and the output interface is a PC monitor. The developed EMG biofeedback based VR system enables the user to interact with virtual objects in real-time with multiform feedback. Ten healthy subjects participated in the preliminary task evaluation test, and the results suggest that the specified skills have improved during training. The beneficial effects of the developed system indicate the potential values for further clinical application.

Improved Video Mosaic Construction by Accumulated Alignment Error Distribution.

Mosaic techniques have been used to obtain images with a large field of view from video sequences by assembling individual overlapping images. In existing methods of mosaic construction only consecutive frames are aligned. Accumulation of small alignment errors occur, and in the case of the image path returning to a previous position in the mosaic (looping path), a significant mismatch between non-consecutive frames will result. A new method for ensuring the consistency of the positions of all images in a mosaic is proposed. From the resulting improvement in mosaic quality, the new method enables construction of mosaics with a very large field of view.

Optimum bit allocation and decomposition for high quality audio coding

Current audio compression schemes are capable of reducing the per channel bit rate of high quality audio signals from 16 bits per sample to around 2-4 bits per sample. In these schemes, knowledge of psychoacoustics is utilised and a uniform or nonuniform frequency decomposition method is used. In this paper we derive the optimum bit allocation to achieve the highest perceptual quality under a fixed bit rate, for an arbitrarily decomposed, critically sampled, filter bank. The resultant optimum bit allocation gives rise to a shaped reconstruction noise floor approximately parallel to the masking threshold level. Perceptual coding gain is defined and should be maximized for an optimum decomposition performed by the filter bank. Optimum band splitting is discussed and it is pointed out that decomposition in the manner of critical band splitting does not lead to optimal performance.

Hand-Dorsa Vein Recognition Based on Coded and Weighted Partition Local Binary Patterns

In this paper, a new feature descriptor is presented and proposed for personal verification based on near infrared images of hand-dorsa veins. This new feature descriptor is a modification of the previously proposed partition local binary patterns (PLBP) by adding feature weighting and error correction coding (ECC). While addition of feature weighting aims to reduce the influence of insignificant local binary patterns, addition of ECC aims to increase the distances between feature classes by utilizing the systematic redundancy that has been widely used to achieve reliable data transmission in noisy channels. Using a large database with more than two thousand hand-dorsa vein images, the resulting new feature descriptor, named Coded and Weighted PLBP (WCPLBP), is shown to be more effective than the original PLBP without feature weighting and ECC, and offers a better performance in recognition of hand-dorsa vein images with a correct recognition rate reaching approximately 99% using a simple nearest neighbor classifier.

Neuro-Fuzzy Prediction-Based Adaptive Filtering Applied to Severely Distorted Magnetic Field Recordings

This letter presents an adaptive filtering technique, based upon neuro-fuzzy prediction, to enhance magnetic field signal recordings affected by significant anomalies of magnetotelluric origin such as magnetic storms, rain, and cultural noise. A neuro-fuzzy model has been developed and trained to predict the magnetic field signal in the absence of any sizeable disturbances. Thus, at the occurrence of a significant distortion of nonmagnetotelluric origin, the neuro-fuzzy model predicts the healthy magnetic field signal in parallel to the distortion, thereby significantly reducing the latter. Testing the trained system using unseen data verifies the reliability of the model and demonstrates the effectiveness of the neuro-fuzzy prediction-based adaptive filtering method

An Extension of Iterative Closest Point Algorithm for 3D-2D Registration for Pre-treatment Validation in Radiotherapy

The paper presents a novel feature-based 3D-2D registration method to align a pair of orthogonal X-ray images to the corresponding CT volumetric data with full 6 degrees of freedom by combining the Iterative Closest Point (ICP) and Z-buffer algorithms. The proposed method has been evaluated using simulated data as well as skull phantom data. For the latter, the alignment errors were found to vary from 0.04 mm to 3.3 mm with an average of 1.27 mm for translation, and from 0.02 to 1.64 with an average of 0.82 for rotation. With the accuracy comparing favourably against other feature-based registration methods and the computational load being much less than intensity-based registration methods, the proposed method provides a good basis for validation of patient and machine set-up in the pretreatment procedure in radiotherapy.

Improved coding of transform coefficients in JPEG-like image compression schemes

Abstract This paper describes a new approach to the coding of transform coefficients used in transform-based image compression schemes such as JPEG. Experimental results demonstrate the advantages of this scheme in terms of a significant entropy reduction leading to improved compression. The scheme employs an adaptive zigzag-reordering technique, which operates on rectangular sub-blocks of coefficients. Initially, the sub-block dimensions are determined so as to retain all non-zero coefficients. A subsequent development employs a neural network to selectively discard isolated non-zero coefficients, producing smaller sub-blocks and further improvements in coding efficiency. A hardware implementation of the reordering algorithm is also discussed.