Efficient Discriminant Viewpoint Selection for Active Bayesian Recognition
International Journal of Computer Vision
Active object recognition based on Fourier descriptors clustering
Pattern Recognition Letters
Aspects of optimal viewpoint selection and viewpoint fusion
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Active planning for underwater inspection and the benefit of adaptivity
International Journal of Robotics Research
| Hi-index | 0.00 |
The objective of active recognition is to iteratively collectthe next "best" measurements (e.g., camera angles orviewpoints), to maximally reduce ambiguities in recognition.However, existing work largely overlooked featureinteraction issues. Feature selection, on the other hand,focuses on the selection of a subset of measurements for agiven classification task, but is not context sensitive (i.e.,the decision does not depend on the current input). Thispaper proposes a unified perspective through conditionalfeature sensitivity analysis, taking into account both currentcontext and feature interactions. Based on differentrepresentations of the contextual uncertainties, we presentthree treatment models and exploit their joint power fordealing with complex feature interactions. Synthetic examplesare used to systematically test the validity of theproposed models. A practical application in medical domainis illustrated using an echocardiography databasewith more than 2000 video segments with both subjective(from experts) and objective validations.