Research on the application of deep learning algorithm based PS design software technology in oil painting teaching

Q4 Decision Sciences
Xifeng Qin
{"title":"Research on the application of deep learning algorithm based PS design software technology in oil painting teaching","authors":"Xifeng Qin","doi":"10.1504/ijnvo.2023.133872","DOIUrl":null,"url":null,"abstract":"More and more minors are cultivating oil painting as a hobby. Beginners of oil painting often cannot correctly identify optimised styles and similar painting objects due to the lack of professional knowledge and insufficient aesthetic ability of oil painting. This research addresses this problem by designing a shared convolutional neural network and an improved global convolutional neural network, and combining the two with Photoshop (short name: PS) software processing steps to compose an intelligent oil painting recognition model for beginner teaching. The experimental results of model performance testing show that the recognition model designed in this study has lower training and computation speed. However, the recognition accuracy of various images in the test sample set is higher than that of the comparison oil painting recognition model. Which is significantly higher than the oil painting recognition model built based on GoogleNet, visual geometry group (VGG) and AlexNet neural network algorithms.","PeriodicalId":52509,"journal":{"name":"International Journal of Networking and Virtual Organisations","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Networking and Virtual Organisations","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/ijnvo.2023.133872","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Decision Sciences","Score":null,"Total":0}
引用次数: 0

Abstract

More and more minors are cultivating oil painting as a hobby. Beginners of oil painting often cannot correctly identify optimised styles and similar painting objects due to the lack of professional knowledge and insufficient aesthetic ability of oil painting. This research addresses this problem by designing a shared convolutional neural network and an improved global convolutional neural network, and combining the two with Photoshop (short name: PS) software processing steps to compose an intelligent oil painting recognition model for beginner teaching. The experimental results of model performance testing show that the recognition model designed in this study has lower training and computation speed. However, the recognition accuracy of various images in the test sample set is higher than that of the comparison oil painting recognition model. Which is significantly higher than the oil painting recognition model built based on GoogleNet, visual geometry group (VGG) and AlexNet neural network algorithms.
基于深度学习算法的PS设计软件技术在油画教学中的应用研究
越来越多的未成年人把油画作为一种爱好来培养。油画初学者由于缺乏专业知识和油画审美能力不足,往往不能正确识别最优化的风格和相似的绘画对象。本研究通过设计共享卷积神经网络和改进的全局卷积神经网络,并结合Photoshop(简称PS)软件处理步骤,构建面向初学者教学的智能油画识别模型,解决了这一问题。模型性能测试的实验结果表明,本文设计的识别模型具有较低的训练速度和计算速度。但是,测试样本集中各种图像的识别精度高于对比油画识别模型。这明显高于基于GoogleNet、视觉几何组(visual geometry group, VGG)和AlexNet神经网络算法构建的油画识别模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
International Journal of Networking and Virtual Organisations
International Journal of Networking and Virtual Organisations Decision Sciences-Information Systems and Management
CiteScore
1.40
自引率
0.00%
发文量
25
期刊介绍: IJNVO is a forum aimed at providing an authoritative refereed source of information in the field of Networking and Virtual Organisations.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信