基于迁移学习的蕾丝花边图像检索技术
|
摘要
针对服饰制造工厂对蕾丝花边图像检索效率低、准确率低的问题,利用深度迁移学习的思想,用经典的神经网络模型GoogLeNet(Inception V3)网络对需求企业的一个包含3377种花边图像库进行特征提取,搭建三层全链接网络学习归类特征向量,对3377种花边图像进行分类、训练、测试,达到准确有效的图像检索效果,最终实现"以图搜图"的图像检索功能,满足企业实际需求。随着深度学习的不断发展,各类训练模型逐渐成熟,各类模型迁移学习的能力也不断增强,使用像GoogLeNet(Inception V3)这类具有强大迁移学习功能的模型,可以极大程度地缩短训练时间,并且达到相对理想的效果。在本项目中,花边检索正确率达到100%。
引文
[1]庄福振,罗平,何清,等.迁移学习研究进展[J].软件学报,2015,26(01):26-39.
[2]Donahue J,Jia Y,Vinyals O,et al.DeCAF:A Deep Convolutional Activation Feature for Generic Visual Recognition[C]//International Conference on International Conference on Machine Learning.JMLR.org,2014:I-647.
[3]曹霞,李岳阳,罗海驰,等.基于Android的蕾丝花边检索系统的研究与实现[J].计算机应用与软件,2017,34(01):191-197+229.
[4]Russakovsky O,Deng J,Su H,et al.Image Net Large Scale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[5]Lécun Y,Bottou L,Bengio Y,et al.Gradient-based Learning Applied to Document Recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[6]Hinton G E,Srivastava N,Krizhevsky A,et al.Improving neural Networks by Preventing Co-adaptation of Feature Detectors[J].Computer Science,2012,3(4):págs.212-223.
[7]Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].Computer Science,2014.
[8]Szegedy C,Vanhoucke V,Ioffe S,et al.Rethinking the Inception Architecture for Computer Vision[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEEComputer Society,2016:2818-2826.
[9]孙惠萍.图像检索中基于强化学习的相关反馈技术研究[D].苏州:苏州大学,2008.
[10]才云科技Caicloud,郑泽宇,顾思宇.TensorFlow:实战Google深度学习框架[M].北京:电子工业出版社,2017:159-160.
[2]Donahue J,Jia Y,Vinyals O,et al.DeCAF:A Deep Convolutional Activation Feature for Generic Visual Recognition[C]//International Conference on International Conference on Machine Learning.JMLR.org,2014:I-647.
[3]曹霞,李岳阳,罗海驰,等.基于Android的蕾丝花边检索系统的研究与实现[J].计算机应用与软件,2017,34(01):191-197+229.
[4]Russakovsky O,Deng J,Su H,et al.Image Net Large Scale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[5]Lécun Y,Bottou L,Bengio Y,et al.Gradient-based Learning Applied to Document Recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[6]Hinton G E,Srivastava N,Krizhevsky A,et al.Improving neural Networks by Preventing Co-adaptation of Feature Detectors[J].Computer Science,2012,3(4):págs.212-223.
[7]Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].Computer Science,2014.
[8]Szegedy C,Vanhoucke V,Ioffe S,et al.Rethinking the Inception Architecture for Computer Vision[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEEComputer Society,2016:2818-2826.
[9]孙惠萍.图像检索中基于强化学习的相关反馈技术研究[D].苏州:苏州大学,2008.
[10]才云科技Caicloud,郑泽宇,顾思宇.TensorFlow:实战Google深度学习框架[M].北京:电子工业出版社,2017:159-160.