PCA Whitening Task
Jump to navigation
Jump to search
A PCA Whitening Task is a data processing task that ...
- See: Data De-Meaning.
References
2016
- http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html
- Another pre-processing approach similar to the first one is PCA Whitening. In this process, the data is first centered as described above. Then, you can compute the covariance matrix that tells us about the correlation structure in the data:
X -= np.mean(X, axis = 0) # zero-centercov = np.dot(X.T, X) / X.shape[0] # compute the covariance matrix
- After that, you decorrelate the data by projecting the original (but zero-centered) data into the eigenbasis:
U,S,V = np.linalg.svd(cov) # compute the SVD factorization of the data covariance matrixXrot = np.dot(X, U) # decorrelate the data
- The last transformation is whitening, which takes the data in the eigenbasis and divides every dimension by the eigenvalue to normalize the scale:
Xwhite = Xrot / np.sqrt(S + 1e-5) # divide by the eigenvalues (which are square roots of the singular values)
- Another pre-processing approach similar to the first one is PCA Whitening. In this process, the data is first centered as described above. Then, you can compute the covariance matrix that tells us about the correlation structure in the data:
2005
- (Yang et al., 2005) ⇒ Jian Yang, David Zhang, and Jing-yu Yang. (2005). “Is ICA Significantly Better Than PCA for Face Recognition?.” In: Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, vol. 1, pp. 198-203. IEEE doi:10.1109/ICCV.2005.127
- ABSTRACT: The standard PCA was always used as baseline algorithm to evaluate ICA-based face recognition systems in the previous research. In this paper, we examine the two architectures of ICA for image representation and find that ICA architecture I involves a PCA process by vertically centering (PCA I), while ICA architecture II involves a whitened PCA process by horizontally centering (PCA II). So, it is reasonable to use these two PCA versions as baseline algorithms to revaluate the ICA-based face recognition systems. The experiments were performed on the FERET face database. The experimental results show there is no significant performance differences between ICA architecture I (II) and PCA I (II), although ICA architecture II significantly outperforms the standard PCA. It can be concluded that the performance of ICA strongly depends on its involved PCA process. The pure ICA projection has little effect on the performance of face recognition. …
… We will perform PCA based on the centered observation vectors to whiten the data. The covariance matrix is ...
- ABSTRACT: The standard PCA was always used as baseline algorithm to evaluate ICA-based face recognition systems in the previous research. In this paper, we examine the two architectures of ICA for image representation and find that ICA architecture I involves a PCA process by vertically centering (PCA I), while ICA architecture II involves a whitened PCA process by horizontally centering (PCA II). So, it is reasonable to use these two PCA versions as baseline algorithms to revaluate the ICA-based face recognition systems. The experiments were performed on the FERET face database. The experimental results show there is no significant performance differences between ICA architecture I (II) and PCA I (II), although ICA architecture II significantly outperforms the standard PCA. It can be concluded that the performance of ICA strongly depends on its involved PCA process. The pure ICA projection has little effect on the performance of face recognition. …