期刊:
Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011,2011年2:91-94
通讯作者:
Wu, D.(dr.wudi@gmail.com)
作者机构:
[Wu, Di] National Engineering Research Center for E-Learning, Huazhong Normal University, Wuhan, China;[Ying, Feng; Chengwei, Zhang] Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China
期刊:
Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011,2011年2:95-98
通讯作者:
Wu, D.(dr.wudi@gmail.com)
作者机构:
[Wu, Di] National Engineering Research Center for E-Learning, Huazhong Normal University, Wuhan, China;[Li, Xiaojing; Chengwei, Zhang] Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China
会议名称:
The 29th Chinese Control Conference(第二十九届中国控制会议)
会议时间:
2010-07-29
会议地点:
北京
会议主办单位:
[Liao Haibin;Chen Qinghu] Wuhan Univ, Sch Elect Informat, Wuhan 430079, Peoples R China.^[Wang Hongyong] Henan Univ Technol, Sch Informat Sci & Engn, Zhengzhou 450001, Peoples R China.^[Zhao Qianqian] Huazhong Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
会议论文集名称:
The 29th Chinese Control Conference(第二十九届中国控制会议)论文集
关键词:
Face Recognition;Singular Value Decomposition;Deformable Model;Sparse Representation
摘要:
Presently, face recognition has two main barriers, which are the variation of illumination, expression, pose and the occlusion and disguise respectively. The problem of robust identification human faces with varying expression and illumination, as well as occlusion and disguise will be researched in this paper. Firstly, singular value decomposition will be used for the face image, casting the singular value vector of test face image as a linear combination of the singular value vectors of face database and used deformable model representation; then, match optimization deformable model for solving combinatorial coefficient; finally, according to the sparse nature of coefficients for classification, and use slice-weighted strategy to further improve the robustness. Experimental results on Extended Yale B Database and AR Database shows that this method is very effective for face recognition and can significantly improve the robustness and stability of disguise and occlusion.
摘要:
As a method of learning, research learning has become the focus in the reform of education that is aimed at developing student's innovative spirit and practice ability in China. Well-known paradigms like e-learning and m-learning have been revolutionizing traditional concepts of learning because the fast developing information technologies are available. In this paper, we approach the concept of Wireless Sensor Networks (WSNs) and their potential to improve the quality of teaching and learning in research learning. Wireless Sensor Network for Research Learning (RlWSNs) proposed is a solution of research learning based on WSNs, to potentiate the contact between learners and the object of learning. In addition, the paper presents an experimental example that students are known of the importance of indoor ventilation. Students have emotional and rational understanding using RlWSNs. The results show that the learning effects are improved.
期刊:
Proceeding - 5th International Conference on Computer Sciences and Convergence Information Technology, ICCIT 2010,2010年:192-197
通讯作者:
Tan, G.
作者机构:
[Tan, Guoxin; Liu, Tanghai] National Engineering Research Center for E-Learning, Huazhong Normal University, Wuhan, China
摘要:
It is a very challenging task to interactively build a realistic character model. In this paper, by introducing the stretching model and the vector differential adjustor, a character modeling method based on vector difference is proposed. With this method, firstly, a reference model, a vertical stretching model and a horizontal stretching model are constructed in accordance with the model structure of the human body;secondly, the vector differences of control points are obtained between the horizontal stretching model and the reference model, and between the vertical stretching model and the reference model;and then a vector difference adjustor is employed to interactively adjust the control points in the reference model;lastly, a realistic character model is automatically generated based on the control points' coordinates. Experimental results show that this method can overcome the problems associated with other methods, such as: the need to master professional model software, system requirements for large cumbersome model databases, cracks or holes generated in the result model, and make it easy for users to interactively build a realistic character model.