Abstract
A fuzzy model for a noisy image sequence is given, and the possibility distribution function for an estimate of the original image is deduced. An optimal estimate criterion, called the maximum possibility criterion, is presented, and the fuzzy image smoothing algorithm is derived. This algorithm can be realized by a simple digital structure with the desirable property of reduced memory requirements. For the average relative error, the algorithm performs better than the conventional average of multiple images algorithm with the distinct advantage of suppressing noise in the case of a small number of images.
| Original language | English |
|---|---|
| Pages (from-to) | 74-78 |
| Number of pages | 5 |
| Journal | Proceedings - International Conference on Pattern Recognition |
| Volume | 2 |
| Publication status | Published - 1990 |
| Event | Proceedings of the 10th International Conference on Pattern Recognition - Atlantic City, NJ, USA Duration: 16 Jun 1990 → 21 Jun 1990 |