An Efficient Method for Tensor Voting Using Steerable Filters
In many image analysis applications there is a need to extract curves in noisy images. To achieve a more robust extraction, one can exploit correlations of oriented features over a spatial context in the image. Tensor voting is an existing technique to extract features in this way. In this paper, we present a new computational scheme for tensor voting on a dense field of rank-2 tensors. Using steerable filter theory, it is possible to rewrite the tensor voting operation as a linear combination of complex-valued convolutions. This approach has computational advantages since convolutions can be implemented efficiently. We provide speed measurements to indicate the gain in speed, and illustrate the use of steerable tensor voting on medical applications.
KeywordsGraphical Processing Unit Noisy Image Graphical Processing Unit Implementation Local Image Feature Tensor Vote
Unable to display preview. Download preview PDF.
- 4.Medioni, G., Mordohai, P.: The Tensor Voting Framework. IMSC Press Multimedia Series. In: Emerging Topics in Computer Vision, pp. 191–252. Prentice-Hall, Englewood Cliffs (2004)Google Scholar
- 7.Heitger, F., von der Heydt, R.: A computational model of neural contour processing. In: Proc. 4th Int. Conf. Computer Vision, pp. 32–40. IEEE Computer Society Press, Washington DC (1993)Google Scholar
- 8.Moreland, K., Angel, E.: The FFT on a GPU. In: SIGGRAPH/Eurographics Workshop on Graphics Hardware, pp. 112–119 (2003)Google Scholar
- 9.Franken, E., van Almsick, M., Rongen, P., ter Haar Romeny, B.: Context-enhanced detection of electrophysiology catheters in X-ray fluoroscopy images. In: Conference Poster, European Conference of Radiology, ECR (2005), http://www.ecr.org/