[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-650318-105":59,"doc-detail-650318-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","segmenting-technical-drawing-figures-in-us-patents-paper28","Segmenting Technical Drawing Figures in US Patents - paper28","","Image segmentation is central to computer vision for identifying objects within complex scenes, yet it is harder for pixel-level labeling when contextual information is required. Existing work often focuses on natural photographs, while sketched drawings—especially in technical domains—remain under-studied. This study presents heuristic point-shooting and deep learning methods (U-Net, HR-Net, MedT, DETR) for segmenting technical drawings from US patent documents, achieving over 90% accuracy and up to 97% with transformer-based models.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/segmenting-technical-drawing-figures-in-us-patents-paper28/650318/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/segmenting-technical-drawing-figures-in-us-patents-paper28/650318.png","ImageObject",300,407,{"name":92,"@type":93},"Melati","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is technical drawing segmentation in patent documents challenging?","Question",{"text":112,"@type":113},"Pixel-wise prediction requires contextual information, and patent figures are often compound, with subfigures that have their own labels, captions, and reference text.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What methods are proposed for segmenting technical drawings?",{"text":117,"@type":113},"The study introduces a heuristic point-shooting method and deep learning models including U-Net, HR-Net, MedT, and DETR.",{"name":119,"@type":110,"acceptedAnswer":120},"Which approach performs best on the US Patent dataset?",{"text":121,"@type":113},"Transformer-based MedT achieves the highest reported segmentation accuracy at about 97%, and is also described as computationally efficient.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},650318,1793004035,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},962085570644,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Segmenting Technical Drawing Figures in US Patents  \nMd Reshad Ul Hoque1 , Xin Wei2, Muntabir Hasan Choudhury2, Kehinde Ajayi2, Martin Gryder2, Jian Wu2 and Diane Oyen3  \n1 Electrical and Computer Engineering, Old Dominion University, Norfolk, Virginia 2 Computer Science, Old Dominion University, Norfolk, Virginia  \n3 Los Alamos National Laboratory, Los Alamos, New Mexico  \nAbstract  \nImage segmentation is the core computer vision problem for identifying objects within a scene. Segmentation is a challenging task because the prediction for each pixel label requires contextual information. Most recent research deals with the segmentation of natural images rather than drawings. However, there is very little research on sketched image segmentation. In this study, we introduce heuristic (point-shooting) and deep learning-based methods (U-Net, HR-Net, MedT, DETR) to segment technical drawings in US patent documents. Our proposed methods on the US Patent dataset achieved over 90% accuracy where transformer performs well with 97% segmentation accuracy, which is promising and computationally efficient. Our source codes and datasets are available at [https://github.com/GoFigure-LANL/figure-segmentation](https://github.com/GoFigure-LANL/figure-segmentation).  \nKeywords  \nSegmentation, US Patents, Sketched images, CNN, Point-shooting, HR-Net, U-Net, Transformer  \n1. Introduction  \nCombining information contained in text and images isan important aspect of understanding scientific documents. However, patents and scientific documents often contain compound figures containing subfigures, each having its own label, caption, and reference text. To associate individual subfigures with the appropriate caption and reference text, we must first segment the full figure into its individual subfigures. Although much research has been done on figure understanding and extraction for scientific documents, existing methods rely on either (1) manually-designed rules and human-crafted features which do not generalize well for new dataset [1]; or (2) machine learning approaches most of which were trained on natural images [2] . We demonstrate that we cannot simply apply approaches developed for other datasets to patent drawings, and develop a novel approach while addressing questions about how to extend existing methods to novel datasets.  \nImage segmentation has been extensively studied with rule-based methods such as watershed, and machine learning methods applied to natural images [3, 4, 5] . In patent drawings, there are usually white space between individual drawings. A simple sweeping line method, which detect boundaries of subfigures by counting the maximum number of black-pixels along a horizontal (or  \nSDU’22: The AAAI-22 Workshop on Scientific Document Understanding, March 1st, 2022 . Virtual. [Envelope-Open](Envelope-Open mhoqu001@odu.edu)[ mhoqu001@odu.edu](Envelope-Open mhoqu001@odu.edu) (M. R. U. Hoque); [xwei001@odu.edu](xwei001@odu.edu)[ ](xwei001@odu.edu)(X. Wei); [mchou001@odu.edu](mchou001@odu.edu) (M. H. Choudhury);  \n[kajay001@odu.edu](kajay001@odu.edu) (K. Ajayi); [j1wu@odu.edu](j1wu@odu.edu) (J. Wu);  \n[doyen@lanl.gov](doyen@lanl.gov) (D. Oyen)  \n© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4 .0 International (CC BY 4 .0) .  \nCEUR Workshop Proceedings ([CEUR-WS.org](CEUR-WS.org))  \n[http://ceur-ws.org](http://ceur-ws.org)  \n[ISSN 1613-0073](ISSN 1613-0073)  \nvertical) pixel array, e.g., Rane et al. [6], does not work well because (1) other components such as figure labels may be present, and (2) one figure may contain multiple disconnected parts. There are few existing papers on segmenting technical drawings in patent documents. Most existing tools were developed for extracting figures in research papers. For example, Clark and Divvala [7] developed a framework that extracts figures from scientific papers in PDF format. Viziometrics [8], a figure-oriented literature mining sy","cbCaipUDrECawonf","https://ap.wps.com/l/cbCaipUDrECawonf","pdf",6349571,"English","# Introduction\n## Background and Motivation\n## Related Work on Figure/Compound Segmentation\n# Proposed Approach and Methods\n## Heuristic Point-Shooting\n## Deep Learning Baselines (U-Net, HR-Net, MedT, DETR)\n# Experimental Setup and Results\n## Dataset and Accuracy Comparison\n## Transformer-Based Performance","[{\"question\":\"Why is technical drawing segmentation in patent documents challenging?\",\"answer\":\"Pixel-wise prediction requires contextual information, and patent figures are often compound, with subfigures that have their own labels, captions, and reference text.\"},{\"question\":\"What methods are proposed for segmenting technical drawings?\",\"answer\":\"The study introduces a heuristic point-shooting method and deep learning models including U-Net, HR-Net, MedT, and DETR.\"},{\"question\":\"Which approach performs best on the US Patent dataset?\",\"answer\":\"Transformer-based MedT achieves the highest reported segmentation accuracy at about 97%, and is also described as computationally efficient.\"}]","Segmenting Technical Drawing Figures in US Patents - paper28 | PDF",1792824880,15]