Pre-detection and dual-dictionary sparse representation based face recognition algorithm in non-sufficient training samples

Face recognition based on few training samples is a challenging task. In daily applications, sufficient training samples may not be obtained and most of the gained training samples are in various illuminations and poses. Non-sufficient training samples could not effectively express various facial conditions, so the improvement of the face recognition rate under the non-sufficient training samples condition becomes a laborious mission. In our work, the facial pose pre-recognition(FPPR) model and the dualdictionary sparse representation classification(DD-SRC) are proposed for face recognition. The FPPR model is based on the facial geometric characteristic and machine learning, dividing a testing sample into full-face and profile. Different poses in a single dictionary are influenced by each other, which leads to a low face recognition rate. The DD-SRC contains two dictionaries, full-face dictionary and profile dictionary, and is able to reduce the interference. After FPPR, the sample is processed by the DD-SRC to find the most similar one in training samples. The experimental results show the performance of the proposed algorithm on olivetti research laboratory(ORL) and face recognition technology(FERET) databases, and also reflect comparisons with SRC, linear regression classification(LRC), and two-phase test sample sparse representation(TPTSSR).

M-TIMES SECANT-LIKE MULTI-PROJCTION METHOD FOR SPARSE MINIMIZATION PROBLEM

In this paper, we present m time secant like multi projection algorithm for sparse unconstrained minimization problem. We prove this method are all q superlinearly convergent to the solution about m≥1 . At last, we from some numerical results, discuss how to choose the number m to determine the approximating matrix properly in practical use.

Robust Topology Optimization of Periodic Multi-Material Functionally Graded Structures under Loading Uncertainties

This paper presents a robust topology optimization design approach for multi-material functional graded structures under periodic constraint with load uncertainties.To characterize the random-field uncertainties with a reduced set of random variables,the Karhunen-Lo`eve(K-L)expansion is adopted.The sparse grid numerical integration method is employed to transform the robust topology optimization into a weighted summation of series of deterministic topology optimization.Under dividing the design domain,the volume fraction of each preset gradient layer is extracted.Based on the ordered solid isotropic microstructure with penalization(Ordered-SIMP),a functionally graded multi-material interpolation model is formulated by individually optimizing each preset gradient layer.The periodic constraint setting of the gradient layer is achieved by redistributing the average element compliance in sub-regions.Then,the method of moving asymptotes(MMA)is introduced to iteratively update the design variables.Several numerical examples are presented to verify the validity and applicability of the proposed method.The results demonstrate that the periodic functionally graded multi-material topology can be obtained under different numbers of sub-regions,and robust design structures are more stable than that indicated by the deterministic results.

An adaptive image sparse reconstruction method combined with nonlocal similarity and cosparsity for mixed Gaussian-Poisson noise removal

Compressed sensing(CS) has achieved great success in single noise removal. However, it cannot restore the images contaminated with mixed noise efficiently. This paper introduces nonlocal similarity and cosparsity inspired by compressed sensing to overcome the difficulties in mixed noise removal, in which nonlocal similarity explores the signal sparsity from similar patches, and cosparsity assumes that the signal is sparse after a possibly redundant transform. Meanwhile, an adaptive scheme is designed to keep the balance between mixed noise removal and detail preservation based on local variance. Finally, IRLSM and RACoSaMP are adopted to solve the objective function. Experimental results demonstrate that the proposed method is superior to conventional CS methods, like K-SVD and state-of-art method nonlocally centralized sparse representation(NCSR), in terms of both visual results and quantitative measures.

A CLASS OF FACTORIZATION UPDATE ALGORITHM FOR SOLVING SYSTEMS OF SPARSE NONLINEAR EQUATIONS

In this paper, we establish a class of sparse update algorithm based on matrix triangular factorizations for solving a system of sparse equations. The local Q-superlinear convergence of the algorithm is proved without introducing an m-step refactorization. We compare the numerical results of the new algorithm with those of the known algorithms, The comparison implies that the new algorithm is satisfactory.

A Comparative Study of Stochastic Collocation Methods for Flow in Spatially Correlated Random Fields

Stochastic collocation methods as a promising approach for solving stochastic partial differential equations have been developed rapidly in recent years.Similar to Monte Carlo methods,the stochastic collocation methods are non-intrusive in that they can be implemented via repetitive execution of an existing deterministic solver without modifying it.The choice of collocation points leads to a variety of stochastic collocation methods including tensor product method,Smolyak method,Stroud 2 or 3 cubature method,and adaptive Stroud method.Another type of collocation method,the probabilistic collocation method(PCM),has also been proposed and applied to flow in porous media.In this paper,we discuss these methods in terms of their accuracy,efficiency,and applicable range for flow in spatially correlated random fields.These methods are compared in details under different conditions of spatial variability and correlation length.This study reveals that the Smolyak method and the PCM outperform other stochastic collocation methods in terms of accuracy and efficiency.The random dimensionality in approximating input random fields plays a crucial role in the performance of the stochastic collocation methods.Our numerical experiments indicate that the required random dimensionality increases slightly with the decrease of correlation scale and moderately from one to multiple physical dimensions.

A Comparison of Deterministic, Reliability-Based Topology Optimization under Uncertainties

Reliability and optimization are two key elements for structural design. The reliability~ based topology optimization （RBTO） is a powerful and promising methodology for finding the optimum topologies with the uncertainties being explicitly considered, typically manifested by the use of reliability constraints. Generally, a direct integration of reliability concept and topol- ogy optimization may lead to computational difficulties. In view of this fact, three methodologies have been presented in this study, including the double-loop approach （the performance measure approach, PMA） and the decoupled approaches （the so-called Hybrid method and the sequential optimization and reliability assessment, SORA）. For reliability analysis, the stochastic response surface method （SRSM） was applied, combining with the design of experiments generated by the sparse grid method, which has been proven as an effective and special discretization technique. The methodologies were investigated with three numerical examples considering the uncertainties including material properties and external loads. The optimal topologies obtained using the de- terministic, RBTOs were compared with one another; and useful conclusions regarding validity, accuracy and efficiency were drawn.