Name
Abstract | ||
|---|---|---|
In machine vision features are the basis for almost any kind of high-level postprocessing such as classification. A new method is developed that uses the inherent flexibility of feature calculation to optimize the features for a certain classification task. By tuning the parameters of the feature calculation the accuracy of a subsequent classification can be significantly improved and the decision boundaries can be simplified. The focus of the methods is on surface inspection problems and the features and classifiers used for these applications. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1007/978-3-540-79547-6_43 | ICVS |
Keywords | Field | DocType |
machine vision feature,inherent flexibility,certain classification task,decision boundary,feature calculation,classification robustness,adaptive feature,new method,subsequent classification,surface inspection problem,machine vision,classification | Computer vision,Machine vision,Pattern recognition,Computer science,Feature (computer vision),Robustness (computer science),Feature (machine learning),Artificial intelligence,Linear classifier,Machine learning | Conference |
Volume | ISSN | ISBN |
5008 | 0302-9743 | 3-540-79546-4 |
Citations | PageRank | References |
3 | 0.42 | 15 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Christian Eitzinger | 1 | 164 | 15.33 |
| Manfred Gmainer | 2 | 3 | 0.42 |
| Wolfgang Heidl | 3 | 103 | 7.01 |
| Edwin Lughofer | 4 | 1940 | 99.72 |