Filter Networks for Efficient Estimation of Local 3-D Structure
2005 (English)In: IEEE International Conference on Image Processing (ICIP). 11-14 Sept, Genoa, Italy, 2005, Vol. 3, 573-576 p.Conference paper (Refereed)
Linear filtering is a fundamental operation in signal processing, but for multidimensional signals the practical use is severely limited by the computer power available. Decomposition of filters into a layered structure of sparse subfilters, i.e. a filter network, significantly reduces the number of multiplications required for each data sample. A filter network, here used for phase invariant estimation of local 3-D structure, provides a flexible solution for linear filtering, especially suited for applying a set of filters on signals of higher dimensionality. The filter network presented, is twice as efficient as convolution based on the fast Fourier transform (FFT) and outperforms standard convolution by a factor exceeding 50 in terms of multiplications and additions performed.
Place, publisher, year, edition, pages
2005. Vol. 3, 573-576 p.
filter design, filter network, sparse filters, efficient filtering, local structure
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-13026DOI: 10.1109/ICIP.2005.1530456OAI: oai:DiVA.org:liu-13026DiVA: diva2:17687