[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-663519-105":59,"doc-detail-663519-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","automatic-extraction-and-reconstruction-of-drawing-design-elements-based-on-computer-vision-and-neural-networks-research","Automatic Extraction and Reconstruction of Drawing Design Elements Based on Computer Vision and Neural Networks - [Research]","","Automatic extraction and CAD reconstruction method for painting and design elements using computer vision and neural networks. The research investigates using RNN to identify and extract lines, colours, composition and other elements from artwork images, then reconstructs the extracted elements in CAD with a parameterized representation to support later editing and modification. Experimental results show pre-improvement image matching error rates of 9%–10%, reduced to 3%–5% after improvement, with minimum at 9% before and maximum at 4.5% after. Regularization constraints help prevent overfitting and improve test accuracy.",{"@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/automatic-extraction-and-reconstruction-of-drawing-design-elements-based-on-computer-vision-and-neural-networks-research/663519/",{"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/automatic-extraction-and-reconstruction-of-drawing-design-elements-based-on-computer-vision-and-neural-networks-research/663519.png","ImageObject",300,407,{"name":92,"@type":93},"Alex Sinclair","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-28",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of the research?","Question",{"text":112,"@type":113},"To propose a method that automatically extracts painting/design elements from artwork images and reconstructs them in CAD to enable further creative and editing work.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which image elements does the method aim to extract and identify?",{"text":117,"@type":113},"It targets lines, colours, composition, and other design elements from painting and design images.",{"name":119,"@type":110,"acceptedAnswer":120},"How do the experimental results evaluate the improvement?",{"text":121,"@type":113},"The image matching error rate decreases from 9%–10% before improvement to 3%–5% after improvement, with the post-improvement maximum reported as 4.5%.","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},663519,1793228911,{"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":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":36},1099523882182,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Automatic Extraction and Reconstruction of Drawing Design Elements Based on Computer Vision and Neural Networks  \nJincai Huang   \nSchool of Art and Design, Sias University, Xinzheng 451100, China,  \n[18430@sias.edu.cn](18430@sias.edu.cn)  \nCorresponding author: Jincai Huang, [18430@sias.edu.cn](18430@sias.edu.cn)  \nAbstract. The research aims to explore the vision and neural networks in painting and design and propose a method for automatic extraction of painting and design elements and computer-aided design (CAD) reconstruction based on recurring networks. Through this method, it is hoped that automatic extraction and reconstruction of painting design elements can be achieved while providing more creative inspiration. This article investigates how to use RNN to achieve automatic extraction of painting and design elements, including identification and extraction of lines, colours, composition, and other elements. Moreover, the study discusses in detail how to reconstruct the extracted painting design elements in CAD and achieve a parameterized representation of design elements for subsequent editing and modification. The pre-improvement image matching error rate is between 9% and 10%, while the improved matching error rate is between 3% and 5% . This indicates that the improved method significantly reduces the error rate of image matching. The minimum error rate before improvement was 9%, while the maximum error rate after improvement was 4.5%, further verifying the effectiveness of the improvement method. By constraining the model parameters, the regularization term prevents overfitting of the model on the training data, allowing the model to better generalize to the test data and improve the accuracy of matching.  \nKeywords: Computer Vision; Neural Networks; Painting and Design Elements;  \nAutomatic Extraction; CAD Reconstruction  \nDOI: [https://doi.org/10.14733/cadaps.2024.S18.50-65](https://doi.org/10.14733/cadaps.2024.S18.50-65)  \n1 INTRODUCTION  \nIn the field of painting design, artists do hand drawing or design work. With the rapid progress, computer vision and neural networks in the field of art have attracted more and more attention. Artis the crystallization of human civilization and wisdom; however, its complex details and subtle style often make its diagnosis and analysis challenging. We have the opportunity to explore the mysteries of art with new perspectives and methods. Amura et al. [1] explored how to apply these advanced technologies to achieve automatic extraction of design elements from artwork images and combine  \nthem with CAD (Computer Aided Design) systems for 3D reconstruction of artwork. Automatically extract features such as lines, colours, and textures from artwork images through algorithms, providing basic data for subsequent image analysis. Utilize trained neural network models to automatically classify artwork images, such as style, period, author, etc. By comparing the differences between artwork images and normal images, possible traces of repair, damage, or forgery can be automatically detected. Neural networks have powerful learning and generalization abilities. In art feature extraction, neural networks construct deep neural networks to learn complex features and representations in art images, improving the accuracy of image classification and recognition. By utilizing pre-trained neural network models on large-scale datasets and transferring them to other art datasets for fine-tuning, fast feature extraction and recognition can be achieved. By training generative adversarial networks, art images with specific styles or features are generated, providing new possibilities for artistic creation and restoration. These advanced technologies provide artists and designers with new tools and perspectives, making the process of artistic creation and design more intelligent. Designers can use these advanced technologies to realize the automatic extraction and reconstruction of painting design element","cbCaikfg2vhte3bn","https://ap.wps.com/l/cbCaikfg2vhte3bn","pdf",702998,16,"English","# 1 INTRODUCTION","[{\"question\":\"What is the main goal of the research?\",\"answer\":\"To propose a method that automatically extracts painting/design elements from artwork images and reconstructs them in CAD to enable further creative and editing work.\"},{\"question\":\"Which image elements does the method aim to extract and identify?\",\"answer\":\"It targets lines, colours, composition, and other design elements from painting and design images.\"},{\"question\":\"How do the experimental results evaluate the improvement?\",\"answer\":\"The image matching error rate decreases from 9%–10% before improvement to 3%–5% after improvement, with the post-improvement maximum reported as 4.5%.\"}]","Automatic Extraction and Reconstruction of Drawing Design Elements Based on Computer Vision and Neural Networks - [Research] | PDF"]