Data Fusion at Different Levels
This paper summarizes the main characteristics of data fusion at different levels (sensor, features, scores and decisions). Although it is presented in the framework of biometric applications it is general for all the pattern recognition applications because this presentation is focused in the main blocks of a general pattern recognition system. Thus, the application in mind will imply a different sensor, feature extractor, classifier and decision maker but data fusion will be performed in a similar way.
KeywordsData Fusion Opinion Fusion Speaker Recognition Biometric System False Acceptance Rate
Unable to display preview. Download preview PDF.
- 2.Minsky, M.: logical versus analogical or symbolic versus connectionist or neat versus scruffy. AI magazine 12, 34–51 (1991)Google Scholar
- 3.Ross, A.A., Nandakumar, K., Jain, A.K.: Handbook of multibiometrics. Springer, Heidelberg (2006)Google Scholar
- 8.Willems, M., Forret, P.: Layered Biometric Verification. White paper, Keyware Technologies (December 1997)Google Scholar
- 9.Monte-Moreno, E., Chetouani, M., Faundez-Zanuy, M., Sole-Casals, J.: Maximum likelihood Linear Programming Data Fusion for Speaker Recognition. Speech Communication. Elsevier, Amsterdam (in press), doi:10.1016/j.specom.2008.05.009Google Scholar