This letter presents a face normalization algorithm based on 2-D face model to recognize faces with variant postures from front-view face. A 2-D face mesh model can be extracted from faces with rotation to left or rig...This letter presents a face normalization algorithm based on 2-D face model to recognize faces with variant postures from front-view face. A 2-D face mesh model can be extracted from faces with rotation to left or right and the corresponding front-view mesh model can be estimated according to the facial symmetry. Then based on the inner relationship between the two mesh models, the normalized front-view face is formed by gray level mapping. Finally, the face recognition will be finished based on Principal Component Analysis (PCA). Experiments show that better face recognition performance is achieved in this way.展开更多
In this paper,a stepwise coupled-mode model with the use of the direct global matrix approach is proposed.This method is capable of handling two-dimensional problems with either a point source in cylindrical geometry ...In this paper,a stepwise coupled-mode model with the use of the direct global matrix approach is proposed.This method is capable of handling two-dimensional problems with either a point source in cylindrical geometry or a line source in plane geometry.With the use of the direct global matrix approach,this method is numerically stable.In addition,by introducing appropriately normalized range solutions,this model is free from the numerical overflow problem.Furthermore,we put forward source conditions appropriate for the line-source problem in plane geometry.As a result,this method is capable of addressing the scenario with a line source on top of a sloping bottom.Closed-form expressions for coupling matrices are derived and applied in this paper for handling problems with pressure-release boundaries and a homogeneous water column.The numerical simulations indicate that the proposed model is accurate,efficient,and numerically stable.Consequently,this model can serve as a benchmark model in range-dependent propagation modeling.Although this method is verified by an ideal wedge problem in this paper,the formulation applies to realistic problems as well.展开更多
基金Supported by the National 863 Project(2001AA114140)and NNSF of China (90104013)
文摘This letter presents a face normalization algorithm based on 2-D face model to recognize faces with variant postures from front-view face. A 2-D face mesh model can be extracted from faces with rotation to left or right and the corresponding front-view mesh model can be estimated according to the facial symmetry. Then based on the inner relationship between the two mesh models, the normalized front-view face is formed by gray level mapping. Finally, the face recognition will be finished based on Principal Component Analysis (PCA). Experiments show that better face recognition performance is achieved in this way.
基金supported by the National Natural Science Foundation of China (Grant Nos. 10734100 and 11125420)the Knowledge Innovation Program of Chinese Academy of Sciences
文摘In this paper,a stepwise coupled-mode model with the use of the direct global matrix approach is proposed.This method is capable of handling two-dimensional problems with either a point source in cylindrical geometry or a line source in plane geometry.With the use of the direct global matrix approach,this method is numerically stable.In addition,by introducing appropriately normalized range solutions,this model is free from the numerical overflow problem.Furthermore,we put forward source conditions appropriate for the line-source problem in plane geometry.As a result,this method is capable of addressing the scenario with a line source on top of a sloping bottom.Closed-form expressions for coupling matrices are derived and applied in this paper for handling problems with pressure-release boundaries and a homogeneous water column.The numerical simulations indicate that the proposed model is accurate,efficient,and numerically stable.Consequently,this model can serve as a benchmark model in range-dependent propagation modeling.Although this method is verified by an ideal wedge problem in this paper,the formulation applies to realistic problems as well.
