[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120541-en":3,"doc-seo-120541-105":30,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120541,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",6,"Technology","Connected AI - Merging Mathematical Morphology and Machine Learning","Connected AI explores how connected morphological filters can act as adaptive feature extractors for machine-learning. By building representations from connected components across multi-threshold image trees, the approach enables efficient filtering, segmentation, and classification while providing scale, rotation, and translation invariance. The poster highlights pattern spectrum features for explainable AI and learning, and surveys applications in remote sensing, disaster response, astronomy, microscopy, and medical imaging, emphasizing parallel and distributed computation at very large scales.","University of Groningen  \nConnected AI  \nWilkinson, M. H. F. ; Bunte, Kerstin  \nIMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below.  \nDocument Version  \nFinal author's version (accepted by publisher, after peer review)  \nPublication date: 2025  \nLink to publication in University of Groningen/UMCG research database  \nCitation for published version (APA):  \nWilkinson, M. H. F. , & Bunte, K. (2025) . Connected AI: Merging Mathematical Morphology and Machine Learning. Poster session presented at AI-Grunn, Groningen, Netherlands.  \nCopyright  \nOther than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) .  \nThe publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment.  \nTake-down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.)  \nDownload date: 23-12-2025  \nConnected AI: Merging Mathematical Morphology and Machine Learning  \nMichael H. F . Wilkinson, Kerstin Bunte,  \nIntelligent Systems Group, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence,  \nUniversity of Groningen, Groningen, the Netherlands  \n[m. h. f. wilkinson@rug. nl](m. h. f. wilkinson@rug. nl) , [k. bunte@rug. nl](k. bunte@rug. nl)  \n\n| \u003Cbr>Introduction\u003Cbr>Connected morphological filters allow efficient filtering, segmentation and classification of images of hude sizes, using mathematical models of perceptual grouping based on connectivity. Using them as adaptive feature extractors for machine-learning methods gives the latter access to non-local information, in ways not possible with other techniques. Furthermore, the features extracted can be scale, rotation, and translation invariant, removing the need for common data augmentation methods. These abilities, plus the development of efficient parallel and distributed algorithms allows application in fields such as remote sensing for precision agriculture using drones, and disaster relief using satellite or aerial images, but also in astronomy, microscopy and medical imaging. This poster gives an overview of the advances so far. |  | \u003Cbr>Connected Filters: the Principle\u003Cbr>Connected filters operate at the level of connected components of images, rather than arbitrary surroundings of pixels. Images are typically transformed into tree representations containing the nesting relations of connected components of different threshold levels in grey scale, and different degrees of colour dissimilarity in colour and hyperspectral cases . These trees can be used for feature extraction but also for image filtering, segmentation and classification. Building the tree typically has O (Nlog N) time complexity, and O (N) memory complexity. Filtering and segmentation are far faster, and typically O (N) . A unique feature of these filters is their ability to include rotation and scale invariance, rather than only translation invariance. |\n| --- | --- | --- |\n|  |  |  |\n| \u003Cbr>Pattern Spectra\u003Cbr>\u003Cbr","cbCaiuMPsquV92rC","https://ap.wps.com/l/cbCaiuMPsquV92rC","pdf",6063813,1,2,"English","en",105,"# Introduction\n## Connected Filters: the Principle\n# Pattern Spectra\n## Self-organising pattern spectra\n# Segmentation in Remote Sensing\n## Differential Attribute Profiles (DAPs)\n# Faint Object Detection in Astronomy\n# Acknowledgments","[{\"question\":\"What is the core idea behind Connected AI?\",\"answer\":\"Connected AI uses connected morphological filters as adaptive feature extractors for machine learning, leveraging non-local information through mathematical models of perceptual grouping based on connectivity.\"},{\"question\":\"How do connected filters represent images for feature extraction?\",\"answer\":\"Images are transformed into tree representations built from connected components across different threshold levels, which support both feature extraction and tasks like filtering, segmentation, and classification.\"},{\"question\":\"What practical applications are presented in the poster?\",\"answer\":\"The poster surveys applications including remote sensing for precision agriculture and disaster relief, pattern-spectrum-based disease detection, faint object detection in astronomy, and related imaging tasks in microscopy and medical imaging.\"}]","Connected AI - Merging Mathematical Morphology and Machine Learning | PDF",1785730567,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"connected-ai-merging-mathematical-morphology-and-machine-learning","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/connected-ai-merging-mathematical-morphology-and-machine-learning/120541/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the core idea behind Connected AI?","Question",{"text":74,"@type":75},"Connected AI uses connected morphological filters as adaptive feature extractors for machine learning, leveraging non-local information through mathematical models of perceptual grouping based on connectivity.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How do connected filters represent images for feature extraction?",{"text":79,"@type":75},"Images are transformed into tree representations built from connected components across different threshold levels, which support both feature extraction and tasks like filtering, segmentation, and classification.",{"name":81,"@type":72,"acceptedAnswer":82},"What practical applications are presented in the poster?",{"text":83,"@type":75},"The poster surveys applications including remote sensing for precision agriculture and disaster relief, pattern-spectrum-based disease detection, faint object detection in astronomy, and related imaging tasks in microscopy and medical imaging.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,111,116,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":109,"slug":110},50,"technology",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},7,"Healthcare",40,"healthcare",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},8,"Research & Report",30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]