Title :
Endmember Detection using Enhanced Constrained Optimization in Hyperspectral Imaging
Author_Institution :
Elektrik ve Elektron. Muhendisligi Bolumu, Hacettepe Univ., Ankara, Turkey
Abstract :
A new algorithm is presented for linear spectral mixture analysis that respects the constraints on the end members. The results show that it provides a more robust solution as compared to the ICE and SPICE algorithms due to the use of constrained quadratic optimization for end member detection.
Keywords :
hyperspectral imaging; image processing; mixture models; optimisation; constrained quadratic optimization; end member detection; enhanced constrained optimization; hyperspectral imaging; linear spectral mixture analysis; Conferences; Hyperspectral imaging; Ice; SPICE; Signal processing; Hyperspectral Image Processing; end member detection; quadratic optimization;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2014 22nd
Conference_Location :
Trabzon
DOI :
10.1109/SIU.2014.6830406
