Operation flags for cvCovarMatrix
Namespace: OpenCvSharp
Assembly: OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0.0 (1.0.0.0)
Syntax
Members
| Member name | Value | Description | |
|---|---|---|---|
| Scrambled | 0 | scale * [vects[0]-avg,vects[1]-avg,...]^T * [vects[0]-avg,vects[1]-avg,...] that is, the covariation matrix is count×count. Such an unusual covariation matrix is used for fast PCA of a set of very large vectors (see, for example, Eigen Faces technique for face recognition). Eigenvalues of this "scrambled" matrix will match to the eigenvalues of the true covariation matrix and the "true" eigenvectors can be easily calculated from the eigenvectors of the "scrambled" covariation matrix. [CV_COVAR_SCRAMBLED] | |
| Normal | 1 | scale * [vects[0]-avg,vects[1]-avg,...]*[vects[0]-avg,vects[1]-avg,...]^T that is, cov_mat will be a usual covariation matrix with the same linear size as the total number of elements in every input vector. One and only one of CV_COVAR_SCRAMBLED and CV_COVAR_NORMAL must be specified [CV_COVAR_NORMAL] | |
| UseAvg | 2 | If the flag is specified, the function does not calculate avg from the input vectors, but, instead, uses the passed avg vector. This is useful if avg has been already calculated somehow, or if the covariation matrix is calculated by parts - in this case, avg is not a mean vector of the input sub-set of vectors, but rather the mean vector of the whole set. [CV_COVAR_USE_AVG] | |
| Scale | 4 | If the flag is specified, the covariation matrix is scaled by the number of input vectors. [CV_COVAR_SCALE] | |
| Rows | 8 | Means that all the input vectors are stored as rows of a single matrix, vects[0].count is ignored in this case, and avg should be a single-row vector of an appropriate size. [CV_COVAR_ROWS] | |
| Cols | 16 | Means that all the input vectors are stored as columns of a single matrix, vects[0].count is ignored in this case, and avg should be a single-column vector of an appropriate size. [CV_COVAR_COLS] |
See Also