Abstract | ||
---|---|---|
Principal component analysis (PCA) minimizes the mean square error (MSE) and is sensitive to outliers. In this paper, we present a new rotational-invariant PCA based on maximum correntropy criterion (MCC). A half-quadratic optimization algorithm is adopted to compute the correntropy objective. At each iteration, the complex optimization problem is reduced to a quadratic problem that can be efficiently solved by a standard optimization method. The proposed method exhibits the following benefits: 1) it is robust to outliers through the mechanism of MCC which can be more theoretically solid than a heuristic rule based on MSE; 2) it requires no assumption about the zero-mean of data for processing and can estimate data mean during optimization; and 3) its optimal solution consists of principal eigenvectors of a robust covariance matrix corresponding to the largest eigenvalues. In addition, kernel techniques are further introduced in the proposed method to deal with nonlinearly distributed data. Numerical results demonstrate that the proposed method can outperform robust rotational-invariant PCAs based on L(1) norm when outliers occur. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/TIP.2010.2103949 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
image processing,correntropy,half-quadratic optimization,principal component analysis (pca),standard optimization method,robust principal component analysis,robust principal,mean square error,robust rotational-invariant,complex optimization problem,pca,maximum correntropy criterion,mse,new rotational-invariant,maximum entropy methods,robust,correntropy objective,component analysis,half-quadratic optimization algorithm,eigenvector,eigenvalues and eigenfunctions,principal component analysis,covariance matrix,algorithms,kernel,rule based,eigenvectors,algorithm design,algorithm design and analysis,robust optimization,optimization,optimization problem,robustness,entropy | Mathematical optimization,Outlier,Mean squared error,Robust principal component analysis,Robustness (computer science),Covariance matrix,Kernel method,Optimization problem,Mathematics,Principal component analysis | Journal |
Volume | Issue | ISSN |
20 | 6 | 1941-0042 |
Citations | PageRank | References |
106 | 2.87 | 18 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ran He | 1 | 1790 | 108.39 |
Hu Bao-Gang | 2 | 1386 | 83.23 |
Wei-Shi Zheng | 3 | 2915 | 140.63 |
Xiang-Wei Kong | 4 | 212 | 15.09 |