Name
Abstract | ||
|---|---|---|
Probability theory provides a sound theoretical foundation for handling uncertainty in computer vision. Its objective interpretation allows us to use data for improving the quantitative and qualitative structure of our KB. An important challenge in vision is to find which are the important features to recognize the different objects in the world, and a probabilistic approach provides a useful tool for advancing in this direction. |
Year | DOI | Venue |
|---|---|---|
1991 | 10.1007/3-540-54659-6_110 | ECSQARU |
Keywords | Field | DocType |
handling uncertainty,knowledge-based computer vision,computer vision,knowledge base,probability theory | Computer vision,Applied probability,Computer science,Artificial intelligence,Probabilistic logic,Probability theory,Machine learning | Conference |
Volume | ISSN | ISBN |
548 | 0302-9743 | 3-540-54659-6 |
Citations | PageRank | References |
3 | 1.11 | 4 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| L. Enrique Sucar | 1 | 1016 | 118.72 |
| Duncan Fyfe Gillies | 2 | 97 | 17.86 |