{"id":503,"date":"2017-05-22T19:03:17","date_gmt":"2017-05-22T19:03:17","guid":{"rendered":"https:\/\/beta.research.ece.ncsu.edu\/osl\/?p=503"},"modified":"2017-05-22T19:04:29","modified_gmt":"2017-05-22T19:04:29","slug":"supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination","status":"publish","type":"post","link":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/","title":{"rendered":"Non-negative tensor factorization for hyperspectral feature extraction"},"content":{"rendered":"<p><strong>Abstract<\/strong>:\u00a0Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first. An example of such a pipeline is computing a filter bank response to extract spatial features followed by a support vector machine (SVM) to discriminate between targets. This decoupling between feature extraction and target discrimination yields features that are suboptimal for discrimination, reducing performance. This performance reduction is especially pronounced when the number of features or available data is limited. In this paper, we propose the use of Supervised Nonnegative Tensor Factorization (SNTF) to jointly perform feature extraction and target discrimination over hyperspectral data products. SNTF learns a tensor factorization and a classification boundary from labeled training data simultaneously. This ensures that the features learned via tensor factorization are optimal for both summarizing the input data and separating the targets of interest. Practical considerations for applying SNTF to hyperspectral data are presented, and results from this framework are compared to decoupled feature extraction\/target discrimination pipelines.<\/p>\n<div class=\"csl-bib-body\">\n<div class=\"csl-entry\">\n<div class=\"csl-left-margin\">D. Anderson, A. Bapst, J. Coon, A. Pung, and M. Kudenov, &#8220;Supervised non-negative tensor factorization for automatic hyperspectral feature extraction and target discrimination,&#8221; in (2017), Vol. 10198, p. 101980Q\u2013101980Q\u201313.<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Abstract:\u00a0Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as&#8230;<\/p>\n","protected":false},"author":103,"featured_media":504,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":"","_members_access_role":[],"_members_access_error":""},"categories":[7],"tags":[],"class_list":["post-503","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-conference-proceedings"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 4.9.10 - aioseo.com -->\n\t<meta name=\"description\" content=\"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"mwkudeno\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 4.9.10\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"OSL | Optical Sensing Lab\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"Non-negative tensor factorization for hyperspectral feature extraction | OSL\" \/>\n\t\t<meta property=\"og:description\" content=\"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2017-05-22T19:03:17+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2017-05-22T19:04:29+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary\" \/>\n\t\t<meta name=\"twitter:title\" content=\"Non-negative tensor factorization for hyperspectral feature extraction | OSL\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#article\",\"name\":\"Non-negative tensor factorization for hyperspectral feature extraction | OSL\",\"headline\":\"Non-negative tensor factorization for hyperspectral feature extraction\",\"author\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/author\\\/mwkudeno\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/wp-content\\\/uploads\\\/sites\\\/27\\\/2017\\\/05\\\/Supervised-tensor-factorization.jpg\",\"width\":970,\"height\":1136},\"datePublished\":\"2017-05-22T19:03:17+00:00\",\"dateModified\":\"2017-05-22T19:04:29+00:00\",\"inLanguage\":\"en-US\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#webpage\"},\"articleSection\":\"Proceedings\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/category\\\/conference-proceedings\\\/#listItem\",\"name\":\"Proceedings\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/category\\\/conference-proceedings\\\/#listItem\",\"position\":2,\"name\":\"Proceedings\",\"item\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/category\\\/conference-proceedings\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#listItem\",\"name\":\"Non-negative tensor factorization for hyperspectral feature extraction\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#listItem\",\"position\":3,\"name\":\"Non-negative tensor factorization for hyperspectral feature extraction\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/category\\\/conference-proceedings\\\/#listItem\",\"name\":\"Proceedings\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/#organization\",\"name\":\"OSL\",\"description\":\"Optical Sensing Lab\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/author\\\/mwkudeno\\\/#author\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/author\\\/mwkudeno\\\/\",\"name\":\"mwkudeno\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#authorImage\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/4d7f79345fade5e02bd393168d3cafc1eff625e1e2a2cb3a46b14a67e0e32238?s=96&d=mm&r=g\",\"width\":96,\"height\":96,\"caption\":\"mwkudeno\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#webpage\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/\",\"name\":\"Non-negative tensor factorization for hyperspectral feature extraction | OSL\",\"description\":\"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/author\\\/mwkudeno\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/author\\\/mwkudeno\\\/#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/wp-content\\\/uploads\\\/sites\\\/27\\\/2017\\\/05\\\/Supervised-tensor-factorization.jpg\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#mainImage\",\"width\":970,\"height\":1136},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/2017\\\/05\\\/22\\\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\\\/#mainImage\"},\"datePublished\":\"2017-05-22T19:03:17+00:00\",\"dateModified\":\"2017-05-22T19:04:29+00:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/#website\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/\",\"name\":\"OSL\",\"description\":\"Optical Sensing Lab\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/osl\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"Non-negative tensor factorization for hyperspectral feature extraction | OSL","description":"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.","canonical_url":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#article","name":"Non-negative tensor factorization for hyperspectral feature extraction | OSL","headline":"Non-negative tensor factorization for hyperspectral feature extraction","author":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/author\/mwkudeno\/#author"},"publisher":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/research.ece.ncsu.edu\/osl\/wp-content\/uploads\/sites\/27\/2017\/05\/Supervised-tensor-factorization.jpg","width":970,"height":1136},"datePublished":"2017-05-22T19:03:17+00:00","dateModified":"2017-05-22T19:04:29+00:00","inLanguage":"en-US","mainEntityOfPage":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#webpage"},"isPartOf":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#webpage"},"articleSection":"Proceedings"},{"@type":"BreadcrumbList","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl#listItem","position":1,"name":"Home","item":"https:\/\/research.ece.ncsu.edu\/osl","nextItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/#listItem","name":"Proceedings"}},{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/#listItem","position":2,"name":"Proceedings","item":"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/","nextItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#listItem","name":"Non-negative tensor factorization for hyperspectral feature extraction"},"previousItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#listItem","position":3,"name":"Non-negative tensor factorization for hyperspectral feature extraction","previousItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/#listItem","name":"Proceedings"}}]},{"@type":"Organization","@id":"https:\/\/research.ece.ncsu.edu\/osl\/#organization","name":"OSL","description":"Optical Sensing Lab","url":"https:\/\/research.ece.ncsu.edu\/osl\/"},{"@type":"Person","@id":"https:\/\/research.ece.ncsu.edu\/osl\/author\/mwkudeno\/#author","url":"https:\/\/research.ece.ncsu.edu\/osl\/author\/mwkudeno\/","name":"mwkudeno","image":{"@type":"ImageObject","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#authorImage","url":"https:\/\/secure.gravatar.com\/avatar\/4d7f79345fade5e02bd393168d3cafc1eff625e1e2a2cb3a46b14a67e0e32238?s=96&d=mm&r=g","width":96,"height":96,"caption":"mwkudeno"}},{"@type":"WebPage","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#webpage","url":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/","name":"Non-negative tensor factorization for hyperspectral feature extraction | OSL","description":"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/#website"},"breadcrumb":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#breadcrumblist"},"author":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/author\/mwkudeno\/#author"},"creator":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/author\/mwkudeno\/#author"},"image":{"@type":"ImageObject","url":"https:\/\/research.ece.ncsu.edu\/osl\/wp-content\/uploads\/sites\/27\/2017\/05\/Supervised-tensor-factorization.jpg","@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#mainImage","width":970,"height":1136},"primaryImageOfPage":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/#mainImage"},"datePublished":"2017-05-22T19:03:17+00:00","dateModified":"2017-05-22T19:04:29+00:00"},{"@type":"WebSite","@id":"https:\/\/research.ece.ncsu.edu\/osl\/#website","url":"https:\/\/research.ece.ncsu.edu\/osl\/","name":"OSL","description":"Optical Sensing Lab","inLanguage":"en-US","publisher":{"@id":"https:\/\/research.ece.ncsu.edu\/osl\/#organization"}}]},"og:locale":"en_US","og:site_name":"OSL | Optical Sensing Lab","og:type":"article","og:title":"Non-negative tensor factorization for hyperspectral feature extraction | OSL","og:description":"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first.","og:url":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/","article:published_time":"2017-05-22T19:03:17+00:00","article:modified_time":"2017-05-22T19:04:29+00:00","twitter:card":"summary","twitter:title":"Non-negative tensor factorization for hyperspectral feature extraction | OSL","twitter:description":"Abstract: Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first."},"aioseo_meta_data":{"post_id":"503","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"Article","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"location":null,"local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2020-12-21 11:17:30","updated":"2025-07-13 08:12:19","seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/research.ece.ncsu.edu\/osl\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/\" title=\"Proceedings\">Proceedings<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tNon-negative tensor factorization for hyperspectral feature extraction\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/research.ece.ncsu.edu\/osl"},{"label":"Proceedings","link":"https:\/\/research.ece.ncsu.edu\/osl\/category\/conference-proceedings\/"},{"label":"Non-negative tensor factorization for hyperspectral feature extraction","link":"https:\/\/research.ece.ncsu.edu\/osl\/2017\/05\/22\/supervised-non-negative-tensor-factorization-for-automatic-hyperspectral-feature-extraction-and-target-discrimination\/"}],"_links":{"self":[{"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/posts\/503","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/users\/103"}],"replies":[{"embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/comments?post=503"}],"version-history":[{"count":4,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/posts\/503\/revisions"}],"predecessor-version":[{"id":508,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/posts\/503\/revisions\/508"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/media\/504"}],"wp:attachment":[{"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/media?parent=503"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/categories?post=503"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/osl\/wp-json\/wp\/v2\/tags?post=503"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}