A5029072757- Biometric Identification and Security
- Rice Cultivation and Yield Improvement
- Agricultural Systems and Practices
- Pasture and Agricultural Systems
- Face recognition and analysis
- Forensic Fingerprint Detection Methods
- Forensic and Genetic Research
- Image and Signal Denoising Methods
- Generative Adversarial Networks and Image Synthesis
- Pacific and Southeast Asian Studies
- AI in cancer detection
- Face and Expression Recognition
- Plant Ecology and Taxonomy Studies
- Advanced Computational Techniques and Applications
- Data Management and Algorithms
- Rangeland Management and Livestock Ecology
- Underwater Acoustics Research
- Agriculture and Rural Development Research
- Botany, Ecology, and Taxonomy Studies
- Forensic Anthropology and Bioarchaeology Studies
- Neural Networks and Applications
- Ruminant Nutrition and Digestive Physiology
- Agriculture, Soil, Plant Science
- Soil Mechanics and Vehicle Dynamics
- Blind Source Separation Techniques
Tsinghua University
2018-2022
University Town of Shenzhen
2018-2022
Jinggangshan University
2014
Chinese Academy of Tropical Agricultural Sciences
2006-2008
Tropical Crops Genetic Resources Institute
2006-2008
National Beef Cattle Industrial Technology System
2007
In finger vein verification, the most important and challenging part is to robustly extract patterns from low-contrast infrared images with limited a priori knowledge. Although recent convolutional neural network (CNN)-based methods for verification have shown powerful capacity feature representation promising perspective in this area, they still two critical issues address. First, these CNN-based unexceptionally utilize fully connected layers, which restrict size of process increase...
As an emerging biometric technology, finger vein recognition has attracted much attention in recent years. However, single-sample is a practical and longstanding challenge this field, referring to only one image per class the training set. In recognition, illumination variations under low contrast lack of information intra-class severely affect performance. Despite its high robustness against noise variations, sparse representation rarely been explored for recognition. Therefore, paper, we...
In this paper, a novel method that utilizes feature-level fusion of finger vein (FV) and dorsal texture (FDT) images is proposed for human identification. Motivated by Weber's law, we present α-trimmed Weber representation (α-TWR) to enhance the foreground lines (FLs), i.e., vessels underneath skin line-like on skin. The α-TWR robust illumination variation, as validated basic reflective transmitted imaging model. Cross section asymmetrical coding (CSAC) performed extract features each pixel....
Nonlinear approximation is widely used in signal processing. Real-life signals can be modeled as functions of bounded variation. Thus the variable knot approximating function could self- adaptively chosen by balancing total variation target function. In this paper, we adopt continuous piecewise linear instead existing constants approximation. The results experiments show that new method superior to old one.
Unimodal analysis of finger-vein (FV) and finger dorsal texture (FDT) has been investigated intensively for personal recognition. Unfortunately, it is not robust to segmentation error noise. Motivated by distribution trait FV FDT in a finger, we present multimodal recognition method, called weighted sparse fusion identification (WSFI), which uses images with applied at the pixel level. Firstly, new fused test sample, sum per-pixel, obtained, weight values are computed according...