H. Murase et M. Lindenbaum, PARTIAL EIGENVALUE DECOMPOSITION OF LARGE IMAGES USING SPATIAL-TEMPORAL ADAPTIVE METHOD, IEEE transactions on image processing, 4(5), 1995, pp. 620-629
Finding eigenvectors of a sequence of real images has usually been con
sidered to require too much computation to be practical. Our spatial t
emporal adaptive (STA) method reduces the computational complexity of
the approximate partial eigenvalue decomposition based on image encodi
ng, Spatial temporal encoding is used to reduce storage and computatio
n, and then, singular value decomposition (SVD) is applied. After the
adaptive discrete cosine transform (DCT) encoding, blocks that are sim
ilar in consecutive images are consolidated. The computational economy
of our method was verified by tests on different large sets of images
, The results show that this method is 6 to 10 times faster than the t
raditional SVD method for several kinds of real images, The economy of
this algorithm increases with increasing correlation within the image
and with increasing correlation between consecutive images within a s
et, This algorithm is useful for pattern recognition using eigenvector
s, which is a research field that has been active recently.