| 1,268 | 25 | 116 |
| 下载次数 | 被引频次 | 阅读次数 |
深度学习通过建立深层神经网络来模拟人脑进行分析、学习和解释数据,被广泛用于图像识别领域.首先,简述了深度学习在图像识别中的研究现状;其次,介绍了卷积神经网络、深度置信网络、循环神经网络和生成对抗网络等几种常用于图像识别领域的深度学习网络模型;然后,从人脸识别、动作识别、跌倒检测等方面,论述了深度学习在图像识别领域的典型应用;最后,探讨了该领域的研究难点及发展前景.深度学习可以从不同的图像中自动提取相似的特征并进行分类,识别率高,鲁棒性强,推动了人工智能背景下图像识别的发展.无监督学习、对抗网络等将成为深度学习领域的热点.
Abstract：Deep learning simulates the human brain by building deep neural networks to analyze, learn and interpret data. It is widely used in image recognition. Firstly, the research of deep learning is introduced in image recognition.Meanwhile, the typical network models of deep learning are discussed, such as convolutional neural networks, deep belief networks, recursive neural networks and generative adversarial nets. Then, some applications in image recognition are introduced, such as face recognition, human action recognition and fall detection. Finally, the difficulties and future works are pointed out. Deep learning can automatically extract similar features from different images which can be classified into several categories. It is excellent in recognition rate and robustness. Deep learning promotes the development of image recognition in artificial intelligence. Unsupervised learning and adversarial networks will be a hot topic in the future.
[1]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//Proceedings of the 2016IEEE Conference on Computer Vision and Pattern Recognition,June 27-30,2016,Las Vegas.New York:IEEE Xplore,2016:770-778.
[2]ZHAO H.Character image recognition based on the improved BP neural network[J].Applied Mechanics and Materials,2011,58/59/60(1):2655-2658.
[3]JIN W,ZHANG J Q,ZHANG X.Face recognition method based on support vector machine and particle swarm optimization[J].Expert Systems with Applications,2011,38(4):4390-4393.
[4]MA L,CRAWFORD M M,TIAN J.Local manifold learning-based K-nearest-neighbor for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(11):4099-4109.
[5]DING Y P,LI H J,LI C B,et al.Fall detection based on depth images via wavelet moment[C]//Proceedings of the2017 10th International Congress on Image and Signal Processing,Biomedical Engineering and Informatics,October14-16,2017,Shanghai.New York:IEEE Xplore,2017:P1006.
[6]PEREIRA S,PUN T.Robust template matching for affine resistant image watermarks[J].IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society,2000,9(6):1123-1129.
[7]DU J X,ZHAI C M,WANG Q P.Recognition of plant leaf image based on fractal dimension features[J].Neurocomputing,2013,116(10):150-156.
[8]HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[9]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image Net classification with deep convolutional neural networks[C]//Proceedings of the International Conference on Neural Information Processing Systems,December 3-6,2012,Lake Tahoe,Nevada.Berlin:Springer-Verlag,2012:1097-1105.
[10]ZEILER M D,FERGUS R.Visualizing and understanding convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision,September 6-12,2014,Zurich,Switzerland.Berlin:Springer-Verlag,2013:818-833.
[11]SZEGEDY C,LIU W,JIA Y Q,et al.Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition,June 7-12,2015,Boston.New York:IEEE Xplore,2015:1-9.
[12]HE K M,ZHANG X Y,REN S Q,et al.Delving deep into rectifiers:surpassing human-level performance on Image Net classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision,December7-13,2015,Santiago,Chile.New York:IEEE Xplore,2015:1026-1034.
[13]WU D,PIGOU L,KINDERMANS P J,et al.Deep dynamic neural networks for multimodal gesture segmentation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(8):1583-1597.
[14]SAXENA S,VERBEEK J.Heterogeneous face recognition with CNNs[C]//Proceedings of the 2016 European Conference on Computer Vision,October 8-16,2016,Amsterdam.Berlin:Springer-Verlag,2016:483-491.
[15]GANGWAR A,JOSHI A.Deep Iris Net:deep iris representation with applications in iris recognition and cross-sensor iris recognition[C]//Proceedings of the 2016 IEEE International Conference on Image Processing,September 25-28,2016,Phoenix.New York:IEEE Xplore,2016:2301-2305.
[16]HU C P,BAI X,QI L,et al.Vehicle color recognition with spatial pyramid deep learning[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(5):2925-2934.
[17]KONG Y,DING Z,LI J,et al.Deeply learned view-invariant features for cross-view action recognition[J].IEEE Transactions on Image Processing,2017,26(6):3028-3037.
[18]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradientbased learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[19]SCHERER D,MULLER A,BEHNKE S.Evaluation of pooling operations in convolutional ar chitectures for object recognition[C]//Proceedings of the 20th International Conference on Artificial Neural Networks,September 15-18,2010,Greece.Berlin:Springer-Verlag,2010:92-101.
[20]ROUX N L,BENGIO Y.Representational power of restricted boltzmann machines and deep belief networks[J].Neural Computation,2008,20(6):1631-1649.
[21]HINTON G E.A practical guide to training restricted boltzmann machines[J].Momentum,2012,9(1):599-619.
[22]PINEDA F J.Generalization of back-propagation to recurrent neural networks[J].Physical Review Letters,1987,59(19):2229-2232.
[23]GRAVES A.Long short-term memory[M]//Supervised sequence labelling with recurrent neural networks.Berlin:Springer-Verlag,2012:37-45.
[24]GRAVES A,SCHMIDHUBER J.Frame wise phoneme classification with bidirectional LSTM and other neural network architectures[J].Neural Networks:the Official Journal of the International Neural Network Society,2005,18(5/6):602-610.
[25]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of the International Conference on Neural Information Processing Systems,December 8-13,2014,Canada.New York:Curran Associates,Inc,2014:2672-2680.
[26]RATLIFF L J,BURDEN S A,SASTRY S S.Characterization and computation of local Nash equilibria in continuous games[C]//Proceedings of the 51st Annual Allerton Conference on Communication,Control,and Computing(Allerton),October 2-4,2013,Monticello.New York:IEEE Xplore,2013:917-924.
[27]MIRZA M,OSINDERO S.Conditional generative adversarial nets[EB/OL].(2014-11-06)[2018-03-07].http://arxiv.org/pdf/1411.1784v1.pdf.
[28]DENTON E,CHINTALA S,SZLAM A,et al.Deep generative image models using a laplacian pyramid of adversarial networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems,December 7-12,2015,Montreal,Canada.Cambridge,MA:MIT Press,2015:1486-1494.
[29]RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL].(2016-01-07)[2018-03-07].http://arxiv.org/pdf/1511.06434.pdf.
[30]ARJOVSKY M,BOTTOU L.Towards principled methods for training generative adversarial networks[EB/OL].(2017-01-17)[2018-03-07].http://arxiv.org/pdf/1701.04862.pdf.
[31]张峰.双主体零和博弈逻辑形式系统建构及模型检测研究[J].深圳大学学报(人文社会科学版),2011,28(6):47-53.
[32]ODENA A,OLAH C,SHLENS J.Conditional image synthesis with auxiliary classifier GANs[EB/OL].(2017-07-20)[2018-03-07].https://arxiv.org/pdf/1601.09585.pdf.
[33]REED S,AKATA Z,YAN X C,et al.Generative adversarial text to image synthesis[C]//Proceedings of the 33rd International Conference on Machine Learning,June 19-24,2016,New York.New York:ACM,2016:1060-1069.
[34]LI Y J,LIU S F,YANG J M,et al.Generative face completion[C]//Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition,July 21-26,2017,Honolulu.New York:IEEE Xplore,2017:5892-5900.
[35]BUI H M,LECH M,CHENG E,et al.Using grayscale images for object recognition with convolutional-recursive neural network[C]//Proceedings of the 2016 IEEE Sixth International Conference on Communications and Electronics,July 27-29,2016,Ha Long,Vietnam.New York:IEEE Xplore,2016:321-325.
[36]YALCIN H.Human activity recognition us ing deep belief networks[C]//Proceedings of the 2016 24th Signal Processing and Communication Application Conference,May16-19,2016,Zonguldak,Turkey.New York:IEEE Xplore,2016:1649-1652.
[37]WEN Y D,ZHANG K P,LI Z F,et al.A discriminative feature learning approach for deep face recognition[C]//Proceedings of the 14th European Conference on Computer Vision,October 11-14,2016,Amsterdam,The Netherlands Switzerland:Springer-Verlag,2016:499-515.
[38]HU G S,YANG Y X,YI D,et al.When face recognition meets with deep learning:an evaluation of convolutional neural networks for face recognition[C]//Proceedings of the2015 IEEE International Conference on Computer Vision Workshop,December 7-13,2015,Santiago,Chile.New York:IEEE Xplore,2015:384-392.
[39]YI D,LEI Z,LIAO S C,et al.Learning face representation from scratch[EB/OL].(2014-11-28)[2018-03-07].http://arxiv.org/pdf/1411.7923.pdf.
[40]SUN Y,CHEN Y H,WANG X G,et al.Deep learning face representation by joint identification-verification[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems,December 8-13,2014,Montreal,Canada.Cambridge,MA:MIT Press,2014:1988-1996.
[41]University of Massachusetts Amherst.Labeled faces in the wild[DS/OL].(2017-03-01)[2018-03-07].http://vis-www.cs.umass.edu/lfw/.
[42]ZHANG L,YANG M,FENG X C.Sparse representation or collaborative representation:which helps face recognition?[C]//Proceedings of the 2011 IEEE International Conference on Computer Vision,November 6-13,2011 Barcelona,Spain.Washington DC:IEEE Xplore,2011:471-478.
[43]吴军,肖克聪.基于深度卷积神经网络的人体动作识别[J].华中科技大学学报(自然科学版),2016,44(Sup1):190-194.
[44]KWAPISZ J R,WEISS G M,MOORE S A.Activity recognition using cell phone accelerometers[J].ACM SIGKDD Explorations Newsletter,2010,12(2):74-82.
[45]IJJINA E P,CHALAVADI K M.Human action recognition using genetic algorithms and convolutional neural networks[J].Pattern Recognition,2016,59(C):199-212.
[46]SCHVLDT.Recognition of human actions[DS/OL].(2005-01-18)[2018-03-07].http://www.nada.kth.se/cvap/actions/.
[47]LIU J G,LUO J B,SHAH M.Recognizing realistic actions from videos in the wild[C]//Proceedings of the 2009IEEE Conference on Computer Vision and Pattern Recognition,June 20-25,2009,Miami,FL.New York:IEEE Xplore,2009:1996-2003.
[48]University of Central Florida.UCF101-action recognition data set[DS/OL].(2013-10-17)[2018-03-07].http://crcv.ucf.edu/data/UCF101.php.
[49]Serre Lab.HMDB:a large human motion database[DS/OL].(2011-07-29)[2018-03-07].http://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/#Downloads.
[50]DING Y P,LI H J,LI Z Y.Human motion recognition based on packet convolution neural network[C]//Proceedings of the 12th International Conference on Intelligent Systems and Knowledge Engineering,November 22-24,2017,Nanjing.New York:IEEE Xplore,2017:1-5.
[51]FENG P M,YU M,NAQVI S M,et al.Deep learning for posture analysis in fall detection[C]//Proceedings of the19th International Conference on Digital Signal Processing,August 20-23,2014,Hong Kong.New York:IEEE Xplore,2014:12-17.
[52]JOKANOVIC B,AMIN M.Fall detection using deep learning in range-doppler radars[J].IEEE Transactions on Aerospace and Electronic Systems,2018,54(1):180-189.
[53]LI C B,LI H J,DING Y P,et al.Joint object region location and deep feature learning for fall recognition[C]//Proceedings of the 2017 10th International Congress on Image and Signal Processing,Biomedical Engineering and Informatics,October 14-16,2017,Shanghai.New York:IEEE Xplore,2017:P2155.
基本信息:
DOI：
中图分类号:TP18;TP391.41
引用信息:
[1]李超波,李洪均,徐晨.深度学习在图像识别中的应用[J].南通大学学报(自然科学版),2018,17(01):1-9.
基金信息:
国家自然科学基金项目(61601248);; 江苏省高校自然科学研究面上项目(16KJB510036);; 南通市科技计划项目(MS12016025);; 南通大学-南通智能信息技术联合研究中心(KFKT2017B04);; 国家级大学生创新创业训练计划项目(201710304021Z)