@article{fdi:010089569,
  title = {{A}ssessment of spectral reduction techniques for endmember extraction in unmixing of hyperspectral images},
  author = {{G}eorge, {E}. {B}. and {T}ernikar, {C}. {R}. and {G}hosh, {R}. and {K}umar, {D}. {N}. and {G}omez, {C}{\'e}cile and {A}hmad, {T}. and {S}ahadevan, {A}. {S}. and {G}upta, {P}. {K}. and {M}isra, {A}.},
  editor = {},
  language = {{ENG}},
  abstract = {{S}pectral mixture modelling is one of the most important techniques for classifying hyperspectral data at sub-pixel resolution. {T}he identification of spectrally pure endmembers for estimating their corresponding abundances is an important step in spectral unmixing. {T}he application of spectral reduction prior to endmember extraction would optimize the process by increasing the sensitivity of the algorithms to the most distinctive and informative features of the dataset. {T}he objective of this study is to compare different spectral reduction techniques prior to endmember extraction on six real hyperspectral datasets, including an {A}irborne {V}isible {I}nfra{R}ed {I}maging {S}pectrometer-{N}ext {G}eneration ({AVIRIS}-{NG}) image over {I}ndian sub-continent. {T}he endmembers identified from different combinations of spectral reduction and endmember extraction techniques are used for linear spectral unmixing on the original datasets. {T}he performance of such combinations after unmixing were compared in terms of pixel reconstruction error and also the computation time for each dataset. {S}pectral reduction by both feature extraction techniques like {P}rincipal {C}omponent {A}nalysis ({PCA}), {I}ndependent {C}omponent {A}nalysis ({ICA}), {M}inimum {N}oise {F}raction ({MNF}), and a feature selection technique based on {P}artial {I}nformational {C}orrelation ({PIC}) measure were analysed. {T}he {PIC} based spectral reduction was found to perform well in terms of reconstruction error and computation time when combined with {N}-{FINDR} endmember algorithm. {T}his approach could be adopted for spectral reduction in unmixing of datasets with similar endmember classes.},
  keywords = {{AVIRIS}-{NG} ; {E}ndmember extraction ; {S}pectral reduction ; {S}pectral unmixing ; {P}artial information correlation ; {R}econstruction error},
  booktitle = {},
  journal = {{A}dvances in {S}pace {R}esearch},
  volume = {73},
  numero = {2},
  pages = {1237--1251},
  ISSN = {0273-1177},
  year = {2024},
  DOI = {10.1016/j.asr.2022.06.028},
  URL = {https://www.documentation.ird.fr/hor/fdi:010089569},
}