Hyperspectral Data Unmixing and Endmember Extraction Process Using Vertex Component Analysis Algorithm

Abstract — The hyperspectral images have very huge number of pixel which stores the reflection of light beam from surface of material or object. Variations in the reflectivity of surface materials across different spectral bands provide a fundamental mechanism for understanding features in remotely-sensed multispectral hyperspectral images. Pixel in such images are mixed pixel because of its spatial resolution. A spectral unmixing is performed on mixed pixels, that contain a linear mixture of pure reflectance ground surface materials or objects called as endmember weighted by correspondent abundance fractio