[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-648054-105":3,"detail-sidebar-cat-0-en-105":80,"doc-detail-648054-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","advanced-knowledge-extraction-of-physical-design-drawings-deep-learning-based-cad-conversion-framework","Advanced Knowledge Extraction of Physical Design Drawings - Deep Learning-Based CAD Conversion Framework","","Physical engineering design drawings are often difficult to maintain, archive, and reuse in paper form across industries, and simple scanning fails to extract structured information reliably. Converting these drawings into digital Computer-Aided Design (CAD) formats remains challenging because it requires accurate knowledge extraction. This study proposes a deep learning methodology combining object detection (e.g., YOLOv7, Faster R-CNN), edge/line refinement, curve and circle detection, ornament extraction, and integrated OCR for text capture, consolidating results into CSV.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/advanced-knowledge-extraction-of-physical-design-drawings-deep-learning-based-cad-conversion-framework/648054/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/advanced-knowledge-extraction-of-physical-design-drawings-deep-learning-based-cad-conversion-framework/648054.png","ImageObject",300,407,{"name":42,"@type":43},"Genevieve","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-10-23",true,{"@type":52,"interactionType":53,"userInteractionCount":22},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"Why is converting physical design drawings into CAD formats difficult?","Question",{"text":62,"@type":63},"Paper-based drawings are cumbersome to archive and reuse, and extracting information via simple scanning is unreliable. Accurate CAD conversion requires advanced techniques for detecting structural elements, refining geometry, and capturing text.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"What deep learning and image-processing components are used in the proposed approach?",{"text":67,"@type":63},"The method uses object detection models such as YOLOv7 and Faster R-CNN to locate drawing objects, then applies edge detection (e.g., Canny) and curve/circle detection to refine geometric primitives. It also extracts ornaments and integrates OCR for text.",{"name":69,"@type":60,"acceptedAnswer":70},"How is the extracted information stored and evaluated?",{"text":71,"@type":63},"Extracted lines, shapes, and text are consolidated and saved in a structured CSV file format. Accuracy and efficiency of the conversion are assessed, and the study discusses automation benefits and future improvements.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},648054,1792791904,{"code":4,"msg":81,"data":82},"success",[83,87,91,95,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":84,"show_sort_weight":85,"slug":86},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":92,"show_sort_weight":93,"slug":94},"Exam",70,"exam",{"id":96,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},5,"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":96,"slug":129},19,"General","general",{"code":4,"msg":81,"data":131},{"doc_id":78,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":22,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":79,"read_time":144},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Advanced Knowledge Extraction of Physical Design Drawings, Translation and conversion to CAD formats using Deep Learning  \nJesher Joshua M 1 , Ragav V2 , Syed Ibrahim S P C*3  \nVellore Institute of Technology, Chennai Campus, Chennai – 600 127, India  \nAbstract  \nThe maintenance, archiving and usage of the design drawings is cumbersome in physical form in different industries for longer period. It is hard to extract information by simple scanning of drawing sheets. Converting them to their digital formats such as Computer-Aided Design (CAD), with needed knowledge extraction can solve this problem. The conversion of these machine drawings to its digital form is a crucial challenge which requires advanced techniques. This research proposes an innovative methodology utilizing Deep Learning methods. The approach employs object detection model, such as Yolov7, Faster R-CNN, to detect physical drawing objects present in the images followed by, edge detection algorithms such as canny filter to extract and refine the identified lines from the drawing region and curve detection techniques to detect circle. Also ornaments (complex shapes) within the drawings are extracted. To ensure comprehensive conversion, an Optical Character Recognition (OCR) tool is integrated to identify and extract the text elements from the drawings. The extracted data which includes the lines, shapes and text is consolidated and stored in a structured comma separated values(.csv) file format. The accuracy and the efficiency of conversion is evaluated. Through this, conversion can be automated to help organizations enhance their productivity, facilitate seamless collaborations and preserve valuable design information in a digital format easily accessible. Overall, this study contributes to the advancement of CAD conversions, providing accurate results from the translating process. Future research can focus on handling diverse drawing types, enhanced accuracy in shape and line detection and extraction.  \nKeywords: CAD conversion; deep learning; design drawings; digital formats; optical character; knowledge extraction;  \n1. Introduction  \nEngineering and design drawings are prevalently used in various continuous process industries such as power, cement, oil and gas etc., to depict their structural and dimensional technical schematic configuration, process flow, circuits, device functions etc. Preserving them from paper forms to digitized media is important for retrieving the needed information retrievable easily in needed format as they are rich source of technical configuration information. Decoding the scanned drawings typically needs set of image processing techniques to detect and classify various symbols and components.  \nDetecting different components in automated method, may reduce major portion of effort and time. The automated design extraction, validation and storage in standard format enables users to retrieve the count, connections, location, accuracy of components. The proposed system intakes target design images as input and detects various components, objects and text present in the image and storing the extracted objects and texts in CAD file format. Though there are recent advances in image processing and computer vision techniques, the end-to-end solution from transforming the physical diagrams information to structured formats in still incomplete to develop into a matured solution with needed accuracy.  \nThis paper proposes a comprehensive generic framework for digitizing engineering drawings and identify component in the drawings by various algorithms and deep learning techniques to detect edges, lines, curves, objects of different shapes and texts and the extracted information is systematically stored in the needed format.  \n1. Under Graduate Student, School of Computer Science and Engineering, [E-mail address:](E-mail address: jesherjoshua.m2021@vitstudent.ac.in)[ jesherjoshua.m2021@vitstudent.ac.in](E-mail address: jesherjoshua.m2021@vitstud","cbCaifLeUywWXvI7","https://ap.wps.com/l/cbCaifLeUywWXvI7","pdf",1147284,11,"English","# Abstract\n# 1. Introduction\n# 2. Analysis of existing models\n# 3. Proposed Solution","[{\"question\":\"Why is converting physical design drawings into CAD formats difficult?\",\"answer\":\"Paper-based drawings are cumbersome to archive and reuse, and extracting information via simple scanning is unreliable. Accurate CAD conversion requires advanced techniques for detecting structural elements, refining geometry, and capturing text.\"},{\"question\":\"What deep learning and image-processing components are used in the proposed approach?\",\"answer\":\"The method uses object detection models such as YOLOv7 and Faster R-CNN to locate drawing objects, then applies edge detection (e.g., Canny) and curve/circle detection to refine geometric primitives. It also extracts ornaments and integrates OCR for text.\"},{\"question\":\"How is the extracted information stored and evaluated?\",\"answer\":\"Extracted lines, shapes, and text are consolidated and saved in a structured CSV file format. Accuracy and efficiency of the conversion are assessed, and the study discusses automation benefits and future improvements.\"}]","Advanced Knowledge Extraction of Physical Design Drawings - Deep Learning-Based CAD Conversion Framework | PDF",28]