[1]武苏雯,赵慧杰,刘 鑫,等.基于迁移学习的图像分类在诗词中的应用研究[J].计算机技术与发展,2021,31(07):215-220.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
　WU Su-wen,ZHAO Hui-jie,LIU Xin,et al.Research on Application of Image Classification Based onTransfer Learning in Poetry[J].,2021,31(07):215-220.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
点击复制

基于迁移学习的图像分类在诗词中的应用研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年07期
页码:
215-220
栏目:
应用前沿与综合
出版日期:
2021-07-10

文章信息/Info

Title:
Research on Application of Image Classification Based onTransfer Learning in Poetry
文章编号:
1673-629X(2021)07-0215-06
作者:
武苏雯; 赵慧杰; 刘 鑫; 王佳豪
中原工学院 计算机学院,河南 郑州 451191
Author(s):
WU Su-wen; ZHAO Hui-jie; LIU Xin; WANG Jia-hao
School of Computer Science,Zhongyuan University of Technology,Zhengzhou 451191,China
关键词:
迁移学习; 图像分类; Nature Image Dataset/ NID; 特征提取; 多 EfficientNet 融合网络
Keywords:
transfer learning; image classification; nature image dataset / NID; feature extraction; multi-EfficientNet fusion network
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 07. 036
摘要:
中国传统诗词中蕴含着丰富的文化内涵。 为了从海量的诗词库中搜索出最符合图像意境的诗词,实现解析图像内容、提取图像特征关键词, 结合项目需求, 提出一种基于迁? 移学习的多 EfficientNet 融合网络的图像分类算法。 收集、整理了基础诗词库,创建了项目专有的诗词意象图像数据集 NID(nature image dataset), 其中共有 9 大类;将在 ImageNet 图像数据集上训练好的 EfficientNet 模型迁移到 NID 中,对 NID 进行特征提取和图像标签匹配度的权值计算,结合每种图像类别训练得到的不同模型权重,融合 9 种模型权重,部署为一个多 EfficientNet 融合网络模型;最后对比了多种深度学习模型在 NID 上的表现性能。 实验结果表明:多 EfficientNet 融合网络模型能够较为准确地解析图像,得到具有区分性的分类特征,并对 NID 的分类效果明显,收敛速度更快,精确率更高,符合项目中对诗词搜索的要求。
Abstract:
There are rich cultural connotations in traditional Chinese poetry. In order to search for the most suitable poetry from the massive poetry dictionary,analyze the content? ?of the image,extract the key words of the image characteristics,combined with the project requirements,an EfficientNet fusion network image classification algorithm based on transfer learning is proposed. The basic poetrylibrary is collected and sorted out,and the project’s proprietary poetry image dataset NID (nature image dataset) is created,which has nine categories. The EfficientNet model,which is trained on the ImageNet image dataset,is migrated to NID to perform feature extraction and image label matching weight calculation. Combined with the different model weights obtained from each image category training,the nine model weights are merged and deployed into a multi-EfficientNet fusion network model. Finally,the performance of various deep learning models on NID is compared. The experiment shows that the multi-EfficientNet fusion network model can analyze images moreaccurately,obtain distinguishing classification features,and have obvious classification effects on NID,with faster convergence speed and higher accuracy,which meets the requirements for poetry search in the project .

相似文献/References:

[1]张江 王年 梁栋 唐俊.基于Laplace谱的图像分类[J].计算机技术与发展,2008,(05):73.
　ZHANG Jiang,WANG Nian,LIANG Dong,et al.Image Classification Based on Laplacian Spectra[J].,2008,(07):73.
[2]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(07):15.
[3]李亚娥,汪西莉.一种自适应的半监督图像分类算法[J].计算机技术与发展,2013,(02):112.
　LI Ya-e,WANG Xi-li.An Adaptive Semi-supervised Image Classification Algorithm[J].,2013,(07):112.
[4]汪旗,贾兆红.基于多示例学习的图像分类算法[J].计算机技术与发展,2014,24(04):88.
　WANG Qi[],JIA Zhao-hong[].Image Categorization by Multi-instance Learning[J].,2014,24(07):88.
[5]李 勇,刘战东,张海军.跨项目软件缺陷预测方法研究综述[J].计算机技术与发展,2020,30(03):98.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 019]
　LI Yong,LIU Zhan-dong,ZHANG Hai-jun.Review on Cross-project Software Defects Prediction Methods[J].,2020,30(07):98.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 019]
[6]娄丰鹏,吴迪,荆晓远,等.增加度量元的迁移学习跨项目软件缺陷预测[J].计算机技术与发展,2018,28(07):103.[doi:10.3969/ j. issn.1673-629X.2018.07.022]
　LOU Feng-peng,WU Di,JING Xiao-yuan,et al.Cross-project Software Defect Prediction Based on Transfer Learning with Metrics[J].,2018,28(07):103.[doi:10.3969/ j. issn.1673-629X.2018.07.022]
[7]刘宇廷,倪颖杰.融合知识迁移学习的微博社团检测模型构建[J].计算机技术与发展,2018,28(09):11.[doi:10.3969/j.issn.1673-629X.2018.09.003]
　LIU Yu-ting,NI Ying-jie.Construction of Weibo Community Detection Model with Knowledge Transfer Learning[J].,2018,28(07):11.[doi:10.3969/j.issn.1673-629X.2018.09.003]
[8]阮航,孙涵.基于 Faster R-CNN 的车辆多属性识别[J].计算机技术与发展,2018,28(10):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
　RUAN Hang,SUN Han.Vehicle Multi-attribute Recognition Based on Faster R-CNN[J].,2018,28(07):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
[9]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(07):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[10]阮航,王立春.基于特征图的车辆检测和分类[J].计算机技术与发展,2018,28(11):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
　RUAN Hang,WANG Li-chun.Vehicle Detection and Classification Based on Feature Map[J].,2018,28(07):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]

更新日期/Last Update: 2021-07-10