nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo searchdiv qikanlogo popupnotification paper paperNew
2017, 03, v.28;No.140 82-86+90
卷积神经网络综述
基金项目(Foundation): 国家自然科学基金项目(U1404617);; 河南省科技开放合作项目(162106000015);; 河南省高校科技创新团队项目(16IRTSTHN026)
邮箱(Email):
DOI:
摘要:

归纳总结国内外卷积神经网络的结构,分析卷积神经网络的基本原理,阐述卷积神经网络在图像识别中的相关应用及取得的最新研究成果,指出了卷积神经网络在图像识别应用中存在的不足以及未来的发展方向。

Abstract:

In recent years,convolution neural network has become a research hotspot in the field of image recognition,and has extensive research value and application space.This article summarizes the structure of foreign convolution neural network,analyzes the basic principle of convolution neural network,elaborates the related application of convolution neural network in image recognition and the latest research achievement,and finally points out the shortcomings of the convolution neural network in image recognition and the future development direction.

参考文献

[1]Hinton C E,Osindero S,Teh Y W.A Fast Learning Algorithm for Deep Belief Nets[J].Neural Computation,2006,18(7):1527-1554.

[2]Lee H,Crosse R,Rancanath R,et al.Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations[C]//ICML D9:Proceedings of the 26th Annual International Conference on Machine Learning.New York:ACM,2009:609-616.

[3]Huanc C B,Lee H,Erik C.Learning Hierarchical Representations for Face Verification with Convolutional Deep Belief Networks[C]//CVPR 12:Proceedings of the2012IEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2012:2518-2525.

[4]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based Learning Applied to Document Recognition[C]//Proceedings of the IEEE International Conference on Robotics&Automation Leuven.Belgium:IEEE,1998:2278-2324.

[5]Lecun Y,Boser B,Denker J S,et al.Backpropagation Applied to Handwritten Zip Code Recognition[J].Neural Computation,2008,1(4):541-551.

[6]Krizhevsky A,Sutskever I,Hinton G E.Imagenet Classification with Deep Convolutional Neural Networks[C]//Proceedings of Advances in Neural Information Processing Systems.Cambridge,MA:MIT Press,2012:1106-1114.

[7]Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-scale Image Recognition[EB/OL].[2014-09-03].http://xueshu.baidu.com.

[8]赵志宏,杨邵普,马增强.基于卷积神经网络LeNet-5的车牌字符识别研究[J].系统仿真学报,2010,22(3):638-641.

[9]陆璐,张旭东,赵莹,等.基于卷积神经网络的车牌照字符识别研究[C]//第十二届全国图象图形学学术会议.北京:中国图形图像学会,2005.

[10]李飞鹏.卷积神经网络及其应用[D].大连:大连理工大学,2014.

[11]康明.手写体数字识别技术研究[D].武汉:武汉理工大学,2010.

[12]黄琳,张尤赛.应用深层卷积神经网络的交通标志识别[J].现代电子技术,2015,38(13):101-106.

[13]Stallkamp J,Schlipsing M,Salmen J,et al.Benchmarking Machine Learning Algorithms for Traffic Sign Recognition[J].Neural Networks,2012,32(2):323-332.

[14]Bottou L,Bengio Y,Cun Y L.Global Training of Document Processing Systems Using Graph Transformer Networks[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Juan,Puerto Rico:IEEE,1997:489-494.

[15]李媛媛.卷积神经网络优化及其在图像识别中的应用[D].沈阳:沈阳工业大学,2016.

[16]Sermanet P,Eigen D,Zhang X,et al.Overfeat:Integrated Recognition,Localizational and Dection Using Convolutional Networks[EB/OL].[2016-05-16].http://arxiv org/abs/1312.6229.

[17]Hinton G E,Salakhutdinov R R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,313(5786):504-507.

[18]Torralba A,Fergus R,Weiss Y.Small Codes and Large Image Databases for Recognition[C]//2008IEEE Conference on Computer Vision And Pattern Recognition.Anchorage:IEEE,2008:2262-2276.

[19]Kussul E M,Baidyk T N,Vunsch D C,et al.Permutation Coding Technique for Image Recognition Systems[J].IEEE Transaction on Neural Networks,2006,17(6):1556-1579.

[20]Szecedy C,Liu W,Jia Y,et al.Going Deeper with Convolutions[C]//Proceedings of the 2015IEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2015:1-8.

[21]Crishick R,Donahue J,Darrell T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//Proceedings of the 2014IEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2014:80-87.

[22]He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[EB/OL].[2015-12-10].http://www.Research gate.Net/publication.

[23]Long J,Shelhamer E,Darrell T.Fully Convolutional Networks for Semantic Segmentation[C]//Proceedings of the 201sIEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2015:3431-3440.

[24]Ciresan D,Meier U,Schmidhuber J.Multi-column Deep Neural Networks for Image Classification[J].Computer Vision and Pattern Recognition,2012,157(10):3642-3649.

基本信息:

DOI:

中图分类号:TP183;TP391.41

引用信息:

[1]张庆辉,万晨霞.卷积神经网络综述[J].中原工学院学报,2017,28(03):82-86+90.

基金信息:

国家自然科学基金项目(U1404617);; 河南省科技开放合作项目(162106000015);; 河南省高校科技创新团队项目(16IRTSTHN026)

检 索 高级检索