Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extrac...Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.展开更多
In recent years, it has shown that a generalized thresholding algorithm is useful for inverse problems with sparsity constraints. The generalized thresholding minimizes the non-convex p-norm based function with p <...In recent years, it has shown that a generalized thresholding algorithm is useful for inverse problems with sparsity constraints. The generalized thresholding minimizes the non-convex p-norm based function with p < 1, and it penalizes small coefficients over a wider range meanwhile applies less bias to the larger coefficients.In this work, on the basis of two-level Bregman method with dictionary updating(TBMDU), we use the modified thresholding to minimize the non-convex function and propose the generalized TBMDU(GTBMDU) algorithm.The experimental results on magnetic resonance(MR) image simulations and real MR data, under a variety of sampling trajectories and acceleration factors, consistently demonstrate that the proposed algorithm can efficiently reconstruct the MR images and present advantages over the previous soft thresholding approaches.展开更多
The imaging speed is a bottleneck for magnetic resonance imaging( MRI) since it appears. To alleviate this difficulty,a novel graph regularized sparse coding method for highly undersampled MRI reconstruction( GSCMRI) ...The imaging speed is a bottleneck for magnetic resonance imaging( MRI) since it appears. To alleviate this difficulty,a novel graph regularized sparse coding method for highly undersampled MRI reconstruction( GSCMRI) was proposed. The graph regularized sparse coding showed the potential in maintaining the geometrical information of the data. In this study, it was incorporated with two-level Bregman iterative procedure that updated the data term in outer-level and learned dictionary in innerlevel. Moreover,the graph regularized sparse coding and simple dictionary updating stages derived by the inner minimization made the proposed algorithm converge in few iterations, meanwhile achieving superior reconstruction performance. Extensive experimental results have demonstrated GSCMRI can consistently recover both real-valued MR images and complex-valued MR data efficiently,and outperform the current state-of-the-art approaches in terms of higher PSNR and lower HFEN values.展开更多
基金the financial support from Natural Science Foundation of Gansu Province(Nos.22JR5RA217,22JR5RA216)Lanzhou Science and Technology Program(No.2022-2-111)+1 种基金Lanzhou University of Arts and Sciences School Innovation Fund Project(No.XJ2022000103)Lanzhou College of Arts and Sciences 2023 Talent Cultivation Quality Improvement Project(No.2023-ZL-jxzz-03)。
文摘Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.
基金the National Natural Science Foundation of China(Nos.6136200161365013 and 51165033)+3 种基金the Natural Science Foundation of Jiangxi Province(Nos.20132BAB211030 and 20122BAB211015)the Technology Foundation of Department of Education in Jiangxi Province(Nos.GJJ 13061 and GJJ14196)the National Postdoctoral Research Funds(No.2014M551867)the Jiangxi Advanced Projects for Postdoctoral Research Funds(No.2014KY02)
文摘In recent years, it has shown that a generalized thresholding algorithm is useful for inverse problems with sparsity constraints. The generalized thresholding minimizes the non-convex p-norm based function with p < 1, and it penalizes small coefficients over a wider range meanwhile applies less bias to the larger coefficients.In this work, on the basis of two-level Bregman method with dictionary updating(TBMDU), we use the modified thresholding to minimize the non-convex function and propose the generalized TBMDU(GTBMDU) algorithm.The experimental results on magnetic resonance(MR) image simulations and real MR data, under a variety of sampling trajectories and acceleration factors, consistently demonstrate that the proposed algorithm can efficiently reconstruct the MR images and present advantages over the previous soft thresholding approaches.
基金National Natural Science Foundations of China(Nos.61362001,61102043,61262084)Technology Foundations of Department of Education of Jiangxi Province,China(Nos.GJJ12006,GJJ14196)Natural Science Foundations of Jiangxi Province,China(Nos.20132BAB211030,20122BAB211015)
文摘The imaging speed is a bottleneck for magnetic resonance imaging( MRI) since it appears. To alleviate this difficulty,a novel graph regularized sparse coding method for highly undersampled MRI reconstruction( GSCMRI) was proposed. The graph regularized sparse coding showed the potential in maintaining the geometrical information of the data. In this study, it was incorporated with two-level Bregman iterative procedure that updated the data term in outer-level and learned dictionary in innerlevel. Moreover,the graph regularized sparse coding and simple dictionary updating stages derived by the inner minimization made the proposed algorithm converge in few iterations, meanwhile achieving superior reconstruction performance. Extensive experimental results have demonstrated GSCMRI can consistently recover both real-valued MR images and complex-valued MR data efficiently,and outperform the current state-of-the-art approaches in terms of higher PSNR and lower HFEN values.
