期刊文献+

视觉设计元素智能识别研究综述 被引量:1

Review of Research on Intelligent Recognition of Visual Design Elements
下载PDF
导出
摘要 目的通过对基于图像的视觉设计元素智能识别方法进行梳理和分析,总结该方向的研究进展及存在的挑战,预测未来发展趋势,为相关技术和应用研究者提供参考。方法从设计元素的应用需求出发,给出交互设计和导识系统中设计元素的常用类别。通过综述的形式,以图像为研究对象,将视觉设计元素智能识别方法和相关研究进行整理分类,对比分析视觉设计元素智能识别方法。结果明晰基于图像的设计元素智能识别方法体系,总结视觉设计元素智能识别技术的研究难点和发展趋势。结论视觉设计元素既是交互设计过程中催生艺术灵感的核心基础,也是人工智能时代驱动内容智能生成的重要数据源泉。视觉设计元素智能识别是一个富有挑战但充满机遇的研究领域,相信其将在更多的应用中发挥关键作用,不仅为相关设计产业带来巨大价值,也为人们的生活带来更多便利和美感。 The work aims to sort out and analyze image-based intelligent recognition methods for visual design elements,summarize the research progress and existing challenges in this direction,predict the future development trend,and provide reference for relevant technology and application researchers.Based on the application requirements of design elements,common categories of design elements in interactive design were given.Through a review format,with images as the research object,intelligent recognition methods were classified,related research on visual design elements was reviewed,and different intelligent recognition methods for visual design elements were compared.Research difficulties and development trends of intelligent recognition technology for visual design elements were also summarized.Visual design elements are the core foundation for generating artistic inspiration in the design process,and also an important data source for generative artificial intelligence.It is believed that it will play a key role in more applications,not only bringing tremendous value to related design industries,but also bringing more convenience and aesthetic appeal to people's lives.
作者 张桂煊 张树武 ZHANG Guixuan;ZHANG Shuwu(Beijing University of Posts and Telecommunications,Beijing 100876,China;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)
出处 《包装工程》 CAS 北大核心 2024年第14期6-16,I0007,共12页 Packaging Engineering
基金 国家重点研发计划项目(2021YFF0900600)。
关键词 视觉设计元素 智能识别 深度学习 多模态大模型 visual design elements intelligent recognition deep learning multi-modal large models
  • 相关文献

参考文献4

二级参考文献87

  • 1李平.基于MCT测试评价图学教育与空间认知能力关系的研究[J].工程图学学报,2006,27(3):156-160. 被引量:3
  • 2Marr D.Vision:A Computational Investigation Into the Human Representation and Processing of Visual Information.Cambridge:The MIT Press,2010.
  • 3LeCun Y,Bottou L,Bengio Y,Haffner P.Gradient-based learning applied to document recognition.Proceedings of the IEEE,1998,86(11):2278-2324.
  • 4Ferrari V,Jurie F,Schmid C.From images to shape models for object detection.International Journal of Computer Vision,2009,87(3):284-303.
  • 5Latecki L J,Lakamper R,Eckhardt U.Shape descriptors for non rigid shapes with a single closed contour//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Hilton Head,USA,2000,1:424-429.
  • 6Krizhevsky A.Learning Multiple Layers of Features from Tiny Images[M.S.dissertation].University of Toronto,2009.
  • 7Torralba A,Fergus R,Freeman W T.80 million tiny images:A large dataset for non-parametric object and scene recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11):1958-1970.
  • 8Li FebFei,Fergus R,Perona P.Learning generative visual models from few training examples:An incremental Bayesian approach tested on 101 object categories//Proceedings of the Computer Vision and Pattern Recognition (CVPR),Workshop on Generative-Model Based Vision.Washington,USA,2004:178.
  • 9Griffin G,Holub A D,Perona P.The Caltech 256.Caltech Technical Report CNS-TR-2007-001.
  • 10Lazebnik S,Schmid C,Ponce J.Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).New York,USA,2006:2169-2178.

共引文献242

同被引文献5

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部