vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff1b362c000000af7e0b0001000600
Hyperspectral images (HSI) have a wide range of spectral information compared to conventional images. This rich spectral information leads to store more information about the image. Even though the hyperspectral images have multiple spectrum bands that makes narrow division of each spectral band in the image. This narrow band division reduces the spatial quality of HSI and hence it necessitates the improvement of the spatial quality of the hyperspectral image. One of the most emerging methods to improve or enhance the hyperspectral image quality is the HS-MS image fusion. Most of the existing image fusion methods neglects the nonlinear data associated with the image. To overcome this limitation, we proposed a nonlinear unmixing-based fusion model, namely Fully Constrained Nonlinear-CNMF (FCN-CNMF) by consider the nonlinearity data associated with the image. To improve the performance of our nonlinear unmixing-based fusion method, we imposed certain constraints on both spectral and spatial data. The constraints include minimum volume simplex with spectral data and total variance and sparsity with spatial data to enhance the quality of the image. We applied all these constraints to both hyperspectral and multispectral images and then fused these data to obtain the final high-quality image. The fused image’s quality is measured using five standard quality measures on four benchmark datasets and found that the proposed method shows superiority over all baseline methods.