{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/spectral-unmixing-of-hyperspectral-imagery","title":"Spectral Unmixing of Hyperspectral Imagery using Multilayer NMF","arxiv_id":"1408.2810","date":"2014-08-12","proceeding":null,"authors":["Roozbeh Rajabi","Hassan Ghassemian"],"abstract":"Hyperspectral images contain mixed pixels due to low spatial resolution of\nhyperspectral sensors. Spectral unmixing problem refers to decomposing mixed\npixels into a set of endmembers and abundance fractions. Due to nonnegativity\nconstraint on abundance fractions, nonnegative matrix factorization (NMF)\nmethods have been widely used for solving spectral unmixing problem. In this\nletter we proposed using multilayer NMF (MLNMF) for the purpose of\nhyperspectral unmixing. In this approach, spectral signature matrix can be\nmodeled as a product of sparse matrices. In fact MLNMF decomposes the\nobservation matrix iteratively in a number of layers. In each layer, we applied\nsparseness constraint on spectral signature matrix as well as on abundance\nfractions matrix. In this way signatures matrix can be sparsely decomposed\ndespite the fact that it is not generally a sparse matrix. The proposed\nalgorithm is applied on synthetic and real datasets. Synthetic data is\ngenerated based on endmembers from USGS spectral library. AVIRIS Cuprite\ndataset has been used as a real dataset for evaluation of proposed method.\nResults of experiments are quantified based on SAD and AAD measures. Results in\ncomparison with previously proposed methods show that the multilayer approach\ncan unmix data more effectively.","url_abs":"http://arxiv.org/abs/1408.2810v1","url_pdf":"http://arxiv.org/pdf/1408.2810v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"spectral-unmixing-of-hyperspectral-imagery","repo_url":"https://github.com/roozbehrajabi/mlnmf","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"hyperspectral-unmixing","task_name":"Hyperspectral Unmixing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}