Blind nonlinear unmixing using nonnegative matrix factorization based bi-objective autoencoder

Hyperspectral image processing is one of the trending techniques used in many fields such as remote sensing, medical, agriculture, food processing, and military. The unique discrimination hyperspectral images can be for object identification, classification, prediction. One main challenges these tasks mixed pixel problem. unmixing process identifying endmembers their abundance pixels. In linear unmixing, mixture assumed to homogenous patches. Even though models are simple faster performance, most real-world not linear. A modified nonlinear mixture-based sparsity regularized bi-objective autoencoder model based on nonnegative matrix factorization (NMF-BOA) proposed this article. performance analysis shows that our gives competitive results compared state-of-the-art models.