- Advanced Image Fusion Techniques
- Image and Video Quality Assessment
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- Biometric Identification and Security
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Advanced Battery Technologies Research
- Robotics and Sensor-Based Localization
- Electric and Hybrid Vehicle Technologies
- Pediatric Urology and Nephrology Studies
- User Authentication and Security Systems
- Image and Video Stabilization
- Advanced Steganography and Watermarking Techniques
- Crystallography and molecular interactions
- High voltage insulation and dielectric phenomena
- Bladder and Urothelial Cancer Treatments
- Wastewater Treatment and Nitrogen Removal
- Forensic Fingerprint Detection Methods
- Optical Systems and Laser Technology
- Forensic and Genetic Research
- Advanced Decision-Making Techniques
- Traumatic Brain Injury and Neurovascular Disturbances
- Image and Signal Denoising Methods
- Face recognition and analysis
National Institute of Measurement and Testing Technology
2024
Zhejiang University
2004-2018
Baoding People's Hospital
2018
Dongguan University of Technology
2017
Zhejiang Province Institute of Architectural Design and Research
2016
University of Science and Technology of China
2011-2014
Institute of Intelligent Machines
2011-2014
Hefei University of Technology
2014
Nanyang Technological University
2012
Stony Brook University
2011
Subspace learning methods are very sensitive to the illumination, translation, and rotation variances in image recognition. Thus, they have not obtained promising performance for palmprint recognition so far. In this paper, we propose a new descriptor of named histogram oriented lines (HOL), which is variant gradients (HOG). HOL changes has robustness against small transformations because slight translations rotations make value changes. Based on HOL, even some simple subspace can achieve high rates.
In this paper, the problem of Palmprint Recognition Across Different Devices (PRADD) is investigated, which has not been well studied so far. Since there no publicly available PRADD image database, we created a non-contact database containing 12,000 grayscale captured from 100 subjects using three devices, i.e., one digital camera and two smart-phones. Due to acquisition used, rotation scale changes between different images same palm are inevitable. We propose robust method calculate width,...
The pervasion of 3-D technologies over the years gives rise to increasing demands accurate and efficient stereoscopic image quality assessment (SIQA) methods, designed automatically supervise optimize video processing systems. Though 2-D IQA has attracted considerable attention, its counterpart is yet be well explored. In this paper, a no-reference SIQA method using convolution neural network (CNN) for feature extraction proposed. proposed method, CNN model trained from scratch classify...
With the booming of 3-D image processing in entertainment industry and multimedia applications todays, technology for assessing quality stereoscopic faces more challenging tasks than its 2-D counterparts, such as binocular combination, stereo matching, rivalry. In this paper, a novel assessment method is proposed by jointly exploring fusion rivalry models. quality-aware feature extraction stage, multi-scale combination energy responses are first generated from reference distorted...
In this paper, a new Local Binary Pattern (LBP) and Ternary based palmprint identification method is proposed. our method, LBP or LTP descriptor applied to the energy direction representations of extracted by modified finite radon transformation (MFRAT). Experimental results obtained from Hong Kong Polytechnic University (PolyU) Palmprint Database demonstrate that proposed has higher rates than other methods.
Bladder cancer is reported to be the fifth leading cause of deaths in United States. Recent advances medical imaging technologies, such as magnetic resonance (MR) imaging, make virtual cystoscopy a potential alternative clinical optical with advantages being safe and non-invasive method for evaluation entire bladder detection abnormalities. To help reduce interpretation time reading fatigue readers or radiologists using MR cystoscopy, computer-aided scheme widely employed, where thickness...
Partial discharge detection is an effective method for evaluating the insulation condition of cable accessories. Ultra-high-frequency detecting partial has strong anti-interference ability. Therefore, a broadband, circularly polarized Archimedean planar spiral antenna used as sensor. After determining parameters through theoretical calculations, simulate and design antenna. Analyze influence different inner diameter values on performance. Exponential gradient microstrip balun added to...
Based on BAYES data processing theory, a new method of fuzzy probability is proposed for the parameter reliability small sample. Prior distribution obtained by stochastic weighted method, then posterior got conjugate distribution. In end, formula membership function constructed, and events solved.The study this paper aims at which deduced in condition that mean known deviation unknown normal population At same time using information sample actual experiment, fully utilizes prior information,...
Image quality assessment (IQA) is desired to evaluate the perceptual of an image in a manner consistent with subjective rating. Considering characteristics hierarchical visual cortex, novel full reference IQA method proposed this paper. Quality-aware features that human system sensitive are extracted describe comprehensively. Concretely, log Gabor filters and local tetra patterns employed capture spatial frequency texture features, which attractive primary secondary respectively. Moreover,...
The atomization device is the main content of development atomized system, but in process unlocking degree emergency and operation means will affect results, reduce use effect device. This paper proposes a fingerprint identification method to analyze system device, take level better, shorten formulation time process. Then, market data comprehensively evaluated. Finally, continuous monitoring used unlock output final results. research results show that can get more than 95% better mining...
Building an accurate model to describe supercapacitor's dynamic characteristics is the basis for energy management strategy and system simulation analysis. This paper presents support vector machine regression (SVMR) based modeling approach which can nonlinear property during process of charging discharging. The concrete has four steps. Firstly, real-time synchronous acquisition data current terminal voltage from discharging experiments on supercapacitor were chosen divided as training...