Graph Regularized Nonnegative Matrix Factorizationfor Hyperspectral Data Unmixing
عنوان مقاله: Graph Regularized Nonnegative Matrix Factorizationfor Hyperspectral Data Unmixing
شناسه ملی مقاله: ICMVIP07_058
منتشر شده در هفتمین کنفرانس ماشین بینایی و پردازش تصویر ایران در سال 1390
شناسه ملی مقاله: ICMVIP07_058
منتشر شده در هفتمین کنفرانس ماشین بینایی و پردازش تصویر ایران در سال 1390
مشخصات نویسندگان مقاله:
Roozbeh Rajabi - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
Mahdi Khodadadzadeh - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
Hassan Ghassemian - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
خلاصه مقاله:
Roozbeh Rajabi - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
Mahdi Khodadadzadeh - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
Hassan Ghassemian - Faculty of Electrical and Computer EngineeringTarbiat Modares University (TMU)Tehran, Iran
Spectral unmixing is an important tool inhyperspectral data analysis for estimating endmembers andabundance fractions in a mixed pixel. This paper examines theapplicability of a recently developed algorithm called graphregularized nonnegative matrix factorization (GNMF) for thisaim. The proposed approach exploits the intrinsic geometricalstructure of the data besides considering positivity and fulladditivity constraints. Simulated data based on the measuredspectral signatures, is used for evaluating the proposedalgorithm. Results in terms of abundance angle distance (AAD)and spectral angle distance (SAD) show that this method caneffectively unmix hyperspectral data.
کلمات کلیدی: Hyperspectral Imagery; Linear Mixing Model(LMM); Spectral Unmixing; Graph Regularized NonnegativeMatrix Factorization (GNMF)
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/159092/