Yadav, P.P.Shetty, A.Raghavendra, B.S.Narasimhadhan, A.V.2026-02-062022International Geoscience and Remote Sensing Symposium (IGARSS), 2022, Vol.2022-July, , p. 3199-320221536996https://doi.org/10.1109/IGARSS46834.2022.9884485https://idr.nitk.ac.in/handle/123456789/29871Hyperspectral images provide ample information which is needed to be analyzed carefully by the spectral processing algorithms for identifying objects, finding minerals etc. Spectral matching algorithms (SMAs) which make use of similarity measures discriminate and identify earth surface features by comparing spectral signatures with the ground-truth. SMAs that discriminate overall patterns capturing the diagnostic features of spectral signatures is of great use. In view of this, in this paper, we explore spectral gradient as a diagnostic feature to discriminate spectral signatures. Applicability of the proposed spectral gradient which is incorporated with SMAs in distinguishing spectrally distinct signatures is experimented in the following cases: (i) discriminating endmember signatures (ii) mixed pixel identification (iii) clustering spectral signatures of different classes and (iv) endmember extraction. Overall, the experimental results on a benchmark mineral Cuprite dataset library of five minerals have shown significantly improved performance in discriminating various spectral signatures. © 2022 IEEE.clusteringendmember extractionmixed pixel identificationsimilarity measuresSpectral gradient