Incremental PCA algorithm for fringe pattern demodulation

This work proposes a new algorithm for demodulating fringe patterns using principal component analysis (PCA). The algorithm is based on the incremental implantation of the singular value decomposition (SVD) technique for computing the principal values associated with a set of fringe patterns. Instead of processing an entire set of interferograms, the proposed algorithm proceeds in an incremental way, processing sequentially one (as minimum) interferogram at a given time. The advantages of this procedure are twofold. Firstly, it is not necessary to store the whole set of images in memory, and, secondly, by computing a phase quality parameter, it is possible to determine the minimum number of images necessary to accurately demodulate a given set of interferograms. The proposed algorithm has been tested for synthetic and experimental interferograms showing a good performance.