A5070076820- Face recognition and analysis
- Medical Image Segmentation Techniques
- Image and Signal Denoising Methods
- Face and Expression Recognition
- Robotics and Sensor-Based Localization
- Osteoarthritis Treatment and Mechanisms
- Muscle activation and electromyography studies
- Lower Extremity Biomechanics and Pathologies
- Advanced Image Fusion Techniques
- Advanced Vision and Imaging
- Ultrasonics and Acoustic Wave Propagation
- Advanced Image and Video Retrieval Techniques
- Medical Imaging Techniques and Applications
- Sensor Technology and Measurement Systems
- Biometric Identification and Security
- 3D Shape Modeling and Analysis
- Image Retrieval and Classification Techniques
- Image and Object Detection Techniques
- Computer Graphics and Visualization Techniques
- Manufacturing Process and Optimization
- Image Processing Techniques and Applications
- Hand Gesture Recognition Systems
- Digital Filter Design and Implementation
- Blind Source Separation Techniques
- Emotion and Mood Recognition
University of Central Lancashire
2011-2025
Physical Sciences (United States)
2014
In this paper, a new hybrid medical image segmentation method in the level-set framework is proposed. The uses both objectpsilas boundary and region information to achieve robust accurate results. can help detect precise location of target object prevent leakage problem. Experimental results on synthetic as well real 2D 3D images are also shown paper with emphasis comparisons between Chan-Vese method.
By performing repeated sit-stand-sit movements to create stress on knee joints, short transient bursts of high frequency acoustic emission (AE) released by the joints were acquired from two age matched groups consisting healthy and osteoarthritic (OA) knees, significant differences between these discovered signal analysis performed. The is based a four-phase model two-feature descriptor AE bursts. four phases are derived joint angle measurement during movement, they consist...
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 images acquired by near-infrared (NIR) device present challenges achieve high classification accuracy. In this paper, novel method for recognition fusion multiple sets keypoints from scale-invariant feature transform (SIFT) is proposed. While use SIFT enables be unaffected variability, reduces information redundancies improves...
This paper presents a biometric identification system based on near-infrared imaging of dorsal hand veins and matching the keypoints that are extracted from vein images by scale-invariant feature transform. The whole is covered in detail, which includes device used, image processing methods proposed for geometric correction, region-of-interest extraction, enhancement pattern segmentation, as well classification extraction keypoints. In addition to several constraints introduced minimise...
In consideration of an increasing demand to adopt the biometric technology minimize potential security risks, paper presents a consumer-level system for automatic physical access control. Through development near infrared imaging device acquisition dorsal hand vein patterns and computation efficient image processing methods, proposed is shown possess range desirable operation characteristics real-world use, which include reliable in identification, convenient high security, fast response,...
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 undertake self-training safety, is considered be suitable tool medical health rehabilitation. Using electromyography (EMG) biofeedback opportunities improve the ability by...
Our objective was to determine the efficacy and feasibility of a new approach for identifying candidate biomarkers knee osteoarthritis (OA), based on selecting promising candidates from range high-frequency acoustic emission (AE) measurements generated during weight-bearing movement. Candidate AE identified by this could then be validated in larger studies use future clinical trials stratified medicine applications common health condition. A population cohort participants with pain...
The construction of a hybrid wavelet threshold is presented based on fuzzy combination an unbiased risk estimate and asymptotic near-minimax fixed for noise suppression. optimality the proposed demonstrated by recovering Gaussian envelope sinusoidal signal embedded in additive white good poor signal-to-noise ratio scenarios.
Presented in this paper is a novel real-time virtual reality game developed to enable two participants play table tennis immersively with each other's avatar shared environment. It uses wireless hybrid inertial and ultrasonic tracking system provide the positions orientations of both head (view point) hand (racket) player, as well large rear-projection stereoscopic screens view-dependent 3D display Additionally, physics-based ball animation model designed for game, which includes fast...
A novel method is proposed to segment objects in medical images whose boundaries can be described as closed curves. Based on an image with the enhanced boundary of object interest, segmentation consists three key steps, namely, polar transformation, dynamic programming and curve fitting. 3D volumetric data segmented a slice-by-slice basis by only specifying one point inside interest pole for transformation. The also shown able very weak boundaries.
The paper presents a computationally efficient 3D–2D image registration algorithm for automatic pre-treatment validation in radiotherapy. novel aspects of the include (a) hybrid cost function based on partial digitally reconstructed radiographs (DRRs) generated along projected anatomical contours and level set term similarity measurement; (b) fast search method parabola fitting sensitivity-based order. Using CT orthogonal x-ray images from skull pelvis phantom, proposed is compared with...
In this paper, a new feature descriptor is presented and proposed for personal verification based on near infrared images of hand-dorsa veins. This modification the previously partition local binary patterns (PLBP) by adding weighting error correction coding (ECC). While addition aims to reduce influence insignificant patterns, ECC increase distances between classes utilizing systematic redundancy that has been widely used achieve reliable data transmission in noisy channels. Using large...
Immersive visualisation is increasingly being used for comprehensive and rapid analysis of objects in 3D object dynamic behaviour 4D. Challenges are therefore presented to provide natural user interaction enable effortless virtual manipulation. Presented this paper the development evaluation a human-computer system based on hand gestures. By employing hybrid inertial ultrasonic tracking absolute positions orientations userpsilas head hands as well pair high degrees-of-freedoms data gloves...
Face is an essential medium for complex non-verbal communication between humans. Its articulation plays important role in everyday life, including: manifestation of emotional and awareness states, cognitive activity, personality or wellbeing. With the advances 3-D imaging technology ever increasing computing power, automatic analysis facial using sequences has become viable. This paper describes a newly developed high-resolution, comprehensive dynamic database which designed not only...