Abstract
In this paper we propose a scheme for primal vision model. In this scheme, a new spatial-dependent sampling approach based on wavelets' characteristics is proposed to represent an image with partial information and to form multi-frequency channels. A feedback channel imitating the human's `eye movement' is introduced to form a close-loop control. Finally, we attempt to realize the primal vision model with wavelet-based selective attention processing mechanism. Some experiments show that the proposed scheme is reasonable and effective.
| Original language | English |
|---|---|
| Pages | 161-168 |
| Number of pages | 8 |
| State | Published - 1994 |
| Event | Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems - Las Vegas, NV, USA Duration: 2 Oct 1994 → 5 Oct 1994 |
Conference
| Conference | Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems |
|---|---|
| City | Las Vegas, NV, USA |
| Period | 2/10/94 → 5/10/94 |
Fingerprint
Dive into the research topics of 'Wavelet-based primal vision model with selective attention mechanism'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver