Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards atomatic feature vector optimization for multimedia applications

: Schreck, Tobias; Fellner, Dieter W.; Keim, Daniel


Association for Computing Machinery -ACM-, Special Interest Group on Applied Computing -SIGAPP-:
23rd Annual ACM Symposium on Applied Computing 2008. Proceedings : SAC 2008, held at the beach at Vila Galé in Fortaleza, Ceará, Brazil, March 16 - 20, 2008
New York: ACM Press, 2008
ISBN: 1-59593-753-7
Symposium on Applied Computing (SAC) <23, 2008, Fortaleza>
Fraunhofer IGD ()
self-organizing map; feature selection; Feature Description; discriminate analysis

We systematically evaluate a recently proposed method for unsupervised discrimination power analysis for feature se- lection and optimization in multimedia applications. A series of experiments using real and synthetic benchmark data is conducted, the results of which indicate the suitability of the method for unsupervised feature selection and optimization. We present an approach for generating synthetic feature spaces of varying discrimination power, modelling main characteristics from real world feature vector extractors. A simple, yet powerful visualization is used to communicate the results of the automatic analysis to the user.