Title :
The SVD approach for steerable filter design
Author :
Sommer, Gerald ; Michaelis, Markus ; Herpers, Rainer
Author_Institution :
Comput. Sci. Inst., Kiel Univ., Germany
fDate :
31 May-3 Jun 1998
Abstract :
The first processing step in computational early vision usually consists of convolutions with a number of kernels. These kernels often are derived from a mother kernel that is rotated, scaled, or deformed with respect to other degrees of freedom. This paper presents an efficient computational approach to calculate the responses of arbitrary mother kernels with arbitrary deformations. Analytical solutions to this problem in most cases are difficult or not possible. Therefore, a numerical approach that emphasizes an algebraical point of view is presented
Keywords :
computer vision; convolution; filtering theory; singular value decomposition; SVD; arbitrary deformations; computational early vision; convolutions; kernels; steerable filter design; Biomedical informatics; Computer applications; Computer science; Computer vision; Filtering; Filters; Image reconstruction; Interpolation; Kernel; Machine vision;
Conference_Titel :
Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on
Conference_Location :
Monterey, CA
Print_ISBN :
0-7803-4455-3
DOI :
10.1109/ISCAS.1998.694488