MAP Signal Reconstruction with Non Regular Grids
The estimation of a scalar function f using a regular grid has been extensively used in image analysis. This amounts to approximate f by a linear combination of known basis functions. However, this approach is usually not efficient. This paper proposes a more efficient algorithm, based on the use of a non regular grid, which achieves better accuracy with less basis functions. Experimental results are provided to illustrate the performance of the proposed technique.
KeywordsBasis Function Energy Function Regular Grid Admissible Function Gibbs Distribution
Unable to display preview. Download preview PDF.
- 1.Lehmann, T., Spitzer, C.: Survey: Interpolation Methods in Medical Image Processing. IEEE Trans. on Medical Imaging 18(11) (November 1999)Google Scholar
- 2.Thévenaz, P., Blu, T., Unser, M.: Interpolation Revisited. IEEE TMI 19(7) (July 2000)Google Scholar
- 3.Jonas, A., Kiryati, N.: Digital Representation Schemes for 3D Curves, Pattern Recognition, 1803-1816 (1997) Google Scholar
- 4.Sederat, H., Nishimura, D.G.: On the Optimality of the Gridding Recosntuction Algorithm. IEEE TMI 19(4) (April 2000)Google Scholar
- 5.Barrutia, M., Blu, T., Unser, M.: Non-Uniform to Uniform Grid Conversion Using Least-Squares Splines. In: Proceedings of the Tenth European Signal Processing Conference (EUSIPCO 2000) Tampere, Finland, September 4-8, vol. IV, pp. 1997–(2000)Google Scholar
- 6.Rasche, V., et al.: Resampling of Data Between Arbitrary Grids Using Convolution Interpolation. IEEE TMI 18(5) (May 1999)Google Scholar
- 7.Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE PAMI, 721–741 (, November 1984)Google Scholar