A5103256333- Face recognition and analysis
- Video Surveillance and Tracking Methods
- Biometric Identification and Security
- Cell Image Analysis Techniques
- Color perception and design
- Advanced Image Fusion Techniques
- Gait Recognition and Analysis
- Computational Drug Discovery Methods
- Face and Expression Recognition
- Genetics, Bioinformatics, and Biomedical Research
University of Macau
2023-2024
Southeast University
2012
An efficient feature extraction approach for driving postures from a video camera, which consists of Homomorphic filtering, skin-like regions segmentation and contourlet transform (CT), was proposed. With features extracted posture dataset created at Southeast University (SEU), holdout cross-validation experiments on classification were then conducted using random forests (RF) classifier. Compared with number commonly used methods including linear perceptron classifier, k-nearest-neighbour...
With the accomplishment of deep neural networks, face recognition methods have achieved great success in research and are now being applied at a human level. However, existing models fail to achieve state-of-the-art performance recognizing occluded images, which common scenarios captured real world. One potential reasons for this is lack large-scale training datasets, requiring labour-intensive costly labelling occlusions. To resolve these issues, we propose an Adversarially Learning...