Accelerated nonlinear Gaussianization for feature extraction

A. P. Condurache, A. Mertins


In a multi-class classification setup, the Gaussianization represents a nonlinear feature extraction transform with the purpose of achieving Gaussian class-conditional densities in the transformed space. The computational complexity of such a transformation increases with the dimension of the processed feature space in such a way that only relatively small dimensions can be processed. In this contribution we describe how to reduce the computational burden with the help of an adaptive grid. Thus, the Gaussianization transform is able to also handle feature spaces of higher dimensionality, improving upon its practical usability. On both artificially generated and real-application data, we demonstrate a decrease in computation complexity in comparison to the standard Gaussianization, while maintaining the effectiveness.
Original languageEnglish
Title of host publicationProc. of International Conference on Pattern Recognition Applications and Methods (ICPRAM)
Number of pages6
Place of PublicationBarcelona, Spain
Publication date01.03.2013
Pages121 - 126
ISBN (Print)978-989856541-9
Publication statusPublished - 01.03.2013
Event2nd International Conference on Pattern Recognition Applications and Methods - Barcelona, Spain
Duration: 15.02.201318.02.2013
Conference number: 97007


Dive into the research topics of 'Accelerated nonlinear Gaussianization for feature extraction'. Together they form a unique fingerprint.

Cite this