{"id":14195,"date":"2025-07-23T11:54:38","date_gmt":"2025-07-23T16:54:38","guid":{"rendered":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/?p=14195"},"modified":"2026-04-17T00:00:19","modified_gmt":"2026-04-17T04:00:19","slug":"histogram-layers-for-neural-engineered-features","status":"publish","type":"post","link":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/2025\/07\/23\/histogram-layers-for-neural-engineered-features\/","title":{"rendered":"Histogram Layers for Neural &#8220;Engineered&#8221; Features"},"content":{"rendered":"<h2>Abstract:<\/h2>\n<p>In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks. In this paper, we explore whether these features can be learned through histogram layers embedded in a neural network and, therefore, be leveraged within deep learning frameworks. By using histogram features, local statistics of the feature maps from the convolution neural networks can be used to better represent the data. We present neural versions of local binary pattern and edge histogram descriptors that jointly improve the feature representation and perform image classification. Experiments are presented on benchmark and real-world datasets.<\/p>\n<h2>Links:<\/h2>\n<p><a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/11099042\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-470 size-full\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/arxiv.png\" alt=\"Histogram Layers for Neural \u201cEngineered\u201d Features\" width=\"90\" height=\"90\" \/><\/a><a href=\"https:\/\/arxiv.org\/abs\/2403.17176\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-470 size-full\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/arxiv.png\" alt=\"Histogram Layers for Neural Engineered Features\" width=\"90\" height=\"90\" \/><\/a><\/p>\n<h2>Citation:<\/h2>\n<pre><code>J. Peeples, S. A. Kharsa, L. Saleh and A. Zare, \"Histogram Layers for Neural \u201cEngineered\u201d Features,\" in IEEE Transactions on Artificial Intelligence, July 2025, doi: 10.1109\/TAI.2025.3593445.<\/code><\/pre>\n<pre class=\"verbatim select-on-click\" title=\"click to copy to clipboard\"><code>@article{peeples2025histogram,\ntitle={Histogram Layers for Neural \u201cEngineered\u201d Features},\nauthor={Peeples, Joshua and Al Kharsa, Salim and Saleh, Luke and Zare, Alina},\njournal={IEEE Transactions on Artificial Intelligence},\nyear={2025},\npublisher={IEEE}\n}\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Abstract: In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks. In this paper, we explore whether these features can be learned through histogram [&hellip;]<\/p>\n","protected":false},"author":28,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"single-templates\/single-sidebar-none.php","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"featured_post":"off","footnotes":"","_links_to":"","_links_to_target":""},"categories":[19,13],"tags":[35,121,169,181,223,265,301,357,419,425,507,615],"class_list":["post-14195","post","type-post","status-publish","format-standard","hentry","category-journal_paper","category-publication","tag-image-classification","tag-benchmark-datasets","tag-computer-vision","tag-convolutional-neural-networks","tag-deep-learning","tag-edge-histogram-descriptors","tag-feature-learning","tag-histogram-features","tag-learned-descriptors","tag-local-binary-patterns","tag-neural-networks","tag-real-world-datasets"],"acf":[],"_links":{"self":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/14195","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/users\/28"}],"replies":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/comments?post=14195"}],"version-history":[{"count":3,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/14195\/revisions"}],"predecessor-version":[{"id":16591,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/14195\/revisions\/16591"}],"wp:attachment":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/media?parent=14195"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/categories?post=14195"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/tags?post=14195"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}