Spectral features recognition based on data mining algorithms

Peijun Du; Hongjun Su; Wei Zhang

doi:10.1117/12.760106

Translator Disclaimer

8 August 2007 Spectral features recognition based on data mining algorithms

Peijun Du; Hongjun Su; Wei Zhang

Author Affiliations +

Proceedings Volume 6752, Geoinformatics 2007: Remotely Sensed Data and Information; 675204 (2007) https://doi.org/10.1117/12.760106
Event: Geoinformatics 2007, 2007, Nanjing, China

Abstract

In order to discover those significant spectral features that are of effectiveness to target identification, some Data Mining algorithms were used to the data sets from USGS spectral library and OMIS hyperspectral remote sensing image. The candidate feature sets were generated by traditional spectral feature extraction approaches at first, and then clustering, statistical analysis and decision tree were used to characterized feature recognition and target identification model design. Derivative spectrum has the superiority of enhancing the characteristic spectral features in contrast with other algorithms. The recognition decision tree based on the knowledge and rules can identify and discriminate targets using the discovered spectral features. The experiment showed that the proposed characterized spectral features recognition approach based on Data Mining algorithm was suitable to hyperspectral remote sensing information processing.

Citation Download Citation

Peijun Du, Hongjun Su, and Wei Zhang "Spectral features recognition based on data mining algorithms", Proc. SPIE 6752, Geoinformatics 2007: Remotely Sensed Data and Information, 675204 (8 August 2007); https://doi.org/10.1117/12.760106

ACCESS THE FULL ARTICLE