| Title | Stochastic Analysis of Scale-Space Smoothing |
| Authors | Karl Åström, Anders Heyden |
| Alternative Location | http://ieeexplore.ieee.org/..., Restricted Access |
| Alternative Location | http://dx.doi.org/10.1109/I..., Restricted Access |
| Publication | 13th International Conference on Pattern Recognition |
| Year | 1996 |
| Volume | 2 |
| Pages | 305 - 309 |
| Document type | Conference paper |
| Conference name | Proceedings of 13th International Conference on Pattern Recognition |
| Conference Date | 1996-08-25 - 1996-08-29 |
| Conference Location | Vienna, Austria |
| Status | Published |
| Language | eng |
| Publisher | IEEE Comput. Soc. Press |
| Abstract English | In the high-level operations of computer vision it is taken for granted that image features have been reliably detected. This paper addresses the problem of feature extraction by scale-space methods. This paper is based on two key ideas: to investigate the stochastic properties of scale-space representations, and to investigate the interplay between discrete and continuous images. These investigations are then used to predict the stochastic properties of sub-pixel feature detectors |
| Keywords | computer vision, correlation methods, feature extraction, interpolation, smoothing methods, stochastic processes, |
| ISBN/ISSN/Other | ISBN: 0 8186 7282 X |
Questions: webmaster
Last update: 2013-04-11
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)