Paper presents the method of two-dimensional canonical correlation analysis (2DCCA) applied to image processing and biometrics. Method is based on representing the image as the sets of its rows (r) and columns (c) and implementation of CCA using these sets (for this reason we named the method as CCArc). CCArc features simple implementation and lower complexity than other known approaches. In applications to biometrics CCArc is suitable to solving the problems when dimension of images (dimension of feature space) is greater than number of images, i.e. when Small Sample Size (SSS) problem exists.
High efficiency of CCArc method is demonstrated for a number of computer experiments. Experiments are described by means of compact notations that simplify use of results in the framework of meta-analysis.
two-dimensional canonical correlation analysis (2DCCA) space of canonical variables feature space dimensionality reduction biometrics