Learning Separable Filters
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2754-2761
- https://doi.org/10.1109/cvpr.2013.355
Abstract
Learning filters to produce sparse image representations in terms of over complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the linear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic filter banks to reduce the complexity of the convolutions.Keywords
This publication has 29 references indexed in Scilit:
- Deconvolutional networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Learning to represent visual inputPhilosophical Transactions Of The Royal Society B-Biological Sciences, 2010
- Tensor Decompositions and ApplicationsSiam Review, 2009
- Learning rotational features for filament detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Automatic Centerline Extraction of Irregular Tubular Structures Using Probability Volumes from Multiphoton ImagingPublished by Springer Science and Business Media LLC ,2006
- Sparse image coding using a 3D non-negative tensor factorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004
- Locating blood vessels in retinal images by piecewise threshold probing of a matched filter responseIEEE Transactions on Medical Imaging, 2000
- FOUNDATION OF EVALUATIONJournal of Documentation, 1974
- The Design of Multistage Separable Planar FiltersIEEE Transactions on Geoscience Electronics, 1971