首页 > 论文 > 激光与光电子学进展 > 56卷 > 2期(pp:21004--1)

基于主成分分析网络的改进图像分类算法

Improved Image Classification Algorithm Based on Principal Component Analysis Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对深层卷积神经网络模型的训练复杂、调参技巧和经验要求高、理论分析难等问题, 提出一种训练效率高、可解释性强以及理论分析简单的图像分类算法。基于主成分分析网络(Principal Component Analysis Network, PCANet)进行特征提取, 并采用宽度神经网络(Flat Neural Network, FNN)分类图像, 最后通过直接计算得到模型参数。根据训练数据集自适应决定宽度神经网络节点数目, 增加节点时不需要重新训练, 只需要调整局部参数。实验表明, 该模型能够快速训练, 较其他非监督分类算法以及传统深层神经网络, 该模型在识别准确率方面具有较强的竞争力。

Abstract

Aiming at the known deficiencies with complex training, strict parameter-tuning skills and experiences, difficult theoretical analysis of deep neural networks, an improved image classification algorithm with high training efficiency, strong interpretability and simple theoretical analysis is proposed, in which the principal component analysis network (PCANet) is used for feature extraction and the flat neural network (FNN) is for classification. In addition, the model parameters can be obtained by direct calculation and the flat neural network adaptively determines the number of nodes according to the training dataset. When the nodes increase, it is not necessary to retrain the model and only the parameters need to be adjusted locally to update the model. The experimental results show that the proposed model can acquire rapid training. Moreover, it possesses more competition in recognition accuracy compared with other unsupervised classification algorithms and traditional deep neural networks.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop56.021004

所属栏目:图像处理

基金项目:国家重点研发计划(2017YFC0804400)

收稿日期:2018-06-27

修改稿日期:2018-07-25

网络出版日期:2018-07-30

作者单位    点击查看

赵小虎:矿山互联网应用技术国家地方联合工程实验室, 江苏 徐州 221008中国矿业大学物联网(感知矿山)研究中心, 江苏 徐州 221008
尹良飞:矿山互联网应用技术国家地方联合工程实验室, 江苏 徐州 221008中国矿业大学信息与控制工程学院, 江苏 徐州 221116
朱亚楠:微软(中国)有限公司, 北京 100080
刘鹏:矿山互联网应用技术国家地方联合工程实验室, 江苏 徐州 221008中国矿业大学物联网(感知矿山)研究中心, 江苏 徐州 221008
王学奎:矿山互联网应用技术国家地方联合工程实验室, 江苏 徐州 221008中国矿业大学信息与控制工程学院, 江苏 徐州 221116
沈雪茹:矿山互联网应用技术国家地方联合工程实验室, 江苏 徐州 221008中国矿业大学信息与控制工程学院, 江苏 徐州 221116

联系人作者:刘鹏(13814538110@163.com)

【1】LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

【2】Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

【3】Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]∥The Twenty-sixth Annual Conference on Neural Information Processing Systems (NIPS),December 3-8, 2012, Lake Tahoe, Nevada, USA. Cambridge, MA: MIT Press, 2012: 1097-1105.

【4】Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE, 2015: 1-9.

【5】He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[J/OL]. Computer Science: Computer Vision and Pattern Recognition, 2016: 770-778. [2018-05-29]. https:∥arxiv.org/abs/1512.03385.

【6】Coates A, Ng A Y Lee H. An analysis of single-layer networks in unsupervised feature learning[C]∥The fourteenth international conference on Artificial Intelligence and Statistics (AISTATS), April 11-13, 2011, Ft. Lauderdale, FL, USA. United States: JMLR, 2011, 15: 215-223.

【7】Chen C L P, Wan J Z. A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction[J]. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 1999, 29(1): 62-72.

【8】Zhou Y C, Peng J T, Chen C L P. Extreme learning machine with composite kernels for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(6): 2351-2360.

【9】Huang G B, Bai Z, Kasun L L C, et al. Local receptive fields based extreme learning machine[J]. IEEE Computational Intelligence Magazine, 2015, 10(2): 18-29.

【10】Zhang L, Suganthan P N. A survey of randomized algorithms for training neural networks[J]. Information Sciences, 2016, 364-365: 146-155.

【11】Qiu X, Suganthan P N, Amaratunga G A J. Electricity load demand time series forecasting with empirical mode decomposition based random vector functional link network[J]. Proceedings of the IEEE, 2016: 001394-001399.

【12】Ren Y, Suganthan P N, Srikanth N, et al. Random vector functional link network for short-term electricity load demand forecasting[J]. Information Sciences, 2016, 367-368: 1078-1093.

【13】Chan T H, Jia K, Gao S H, et al. PCANet: A simple deep learning baseline for image classification?[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5017-5032.

【14】Zuo C, Chen Q, Qu W J, et al. Phase aberration compensation in digital holographic microscopy based on principal component analysis[J]. Optics Letters, 2013, 38(10): 1724-1726.

【15】Yeom S, Javidi B, Ferraro P, et al. Three-dimensional color object visualization and recognition using multi-wavelength computational holography[J]. Optics Express, 2007, 15(15): 9394-9402.

【16】Jiao S M, Zhuang Z Y, Zou W B. Fast computer generated hologram calculation with a mini look-up table incorporated with radial symmetric interpolation[J]. Optics Express, 2017, 25(1): 112-123.

【17】Du Q, Fowler J E. Hyperspectral image compression using JPEG2000 and principal component analysis[J]. IEEE Geoscience and Remote Sensing Letters, 2007, 4(2): 201-205.

【18】Gao H, Cai J F, Shen Z, et al. Robust principal component analysis-based four-dimensional computed tomography[J]. Physics in Medicine and Biology, 2011, 56(11), 3181-3198.

【19】Wu J S, Qiu S J, Zeng R, et al. Multilinear principal component analysis network for tensor object classification[J]. IEEE Access, 2017, 5: 3322-3331.

【20】Han B, Jia Z H, Gao X B. Improved PCANet for aurora images classification[J]. Journal of Xidian University, 2017, 1: 83-88.
韩冰, 贾中华, 高新波. 改进的主成分分析网络极光图像分类方法[J]. 西安电子科技大学学报(自然科学版), 2017, 1: 83-88

【21】Wu J, Qiu S, Zeng R, et al. PCANet forcolor image classification in various color spaces[C]∥International Conference on Cloud Computing and Security (ICCCS), June 16-18, 2017, Nanjing, China. Cham, Switzerland: Springer, 2017: 494-505.

【22】Wang Z, Bi Z, Wang C, et al. Traffic lights recognition based on PCANet[C]∥2015 Chinese Automation Congress (CAC), November 27-29, 2015, Wuhan, China. New York: IEEE, 2015: 559-564.

【23】Cheng L Y, Mi G Y, Li S, et al. Quality diagnosis of joints in laser brazing based on principal component analysis-support vector machine model[J]. Chinese Journal of Lasers, 2017, 44(3): 0302004.
程力勇, 米高阳, 黎硕, 等. 基于主成分分析-支持向量机模型的激光钎焊接头质量诊断[J]. 中国激光, 2017, 44(3): 0302004.

【24】LeCun Y, Cortes C. MNIST handwritten digit database[EB/OL].[2018-05-29]. http:∥yann.1ecun.eom/exdb/mnist,2010.

【25】Krizhevsky A, Learning multiple layers of features from tiny mages[D]. Toronto, Canada: University of Toronto, 2009.

【26】Sun Y, Chen Y, Wang X, et al. Deep learning face representation by joint identification-verification[C]∥Twenty-eighth Conference on Neural Information Processing Systems(NIPS), December 8-11,2014, Montreal, Canada. Cambridge, MA: MIT Press, 2014: 1988-1996.

【27】Phillips P J, Wechsler H, Huang J, et al. The FERET database and evaluation procedure for face-recognition algorithms[J]. Image and Vision Computing, 1998, 16(5): 295-306.

【28】Yu K, Lin Y, Lafferty J. Learning image representations from the pixel level via hierarchical sparse coding[J]. Proceedings of the IEEE, 2011: 1713-1720.

【29】Belongie, Serge, Malik, et al. Shape context: a new descriptor for shape matching and object recognition[C]∥The annual conference on Neural Information Processing Systems (NIPS), December 3-8, 2001, Vancouver, British Columbia, Canada. Cambridge, MA: MIT Press, 2001: 831-837.

【30】Lee H, Grosse R, Ranganath R, et al. Unsupervised learning of hierarchical representations with convolutional deep belief networks[J]. Communications of the ACM, 2011, 54(10): 95-103.

【31】Jarrett K, Kavukcuoglu K, LeCun Y. What is the best multi-stage architecture for object recognition?[C]∥2009 IEEE International Conference on Computer Vision (ICCV), September 29 - October 2, 2009, Kyoto, Japan. New York: IEEE, 2009: 2146-2153.

【32】Zeiler M D, Fergus R. Stochastic pooling for regularization of deep convolutional neural networks[J]. Neural and Evolutionary Computing, Machine Learning, Preprint ArXiv, ArXiv: 1301.3557, 2013.

【33】Goodfellow I J, Warde-Farley D, Mirza M, et al. Maxout Networks[Z/OL].2013[2018-05-30]. https:∥arxiv.org/pdf/1302.4389.pdf.

【34】Bruna J, Mallat S. Invariant scattering convolution networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1872-1886.

【35】Chan T H, Jia K, Gao S H, et al. PCANet: A simple deep learning baseline for image classification?[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5017-5032.

【36】Le Q V, Ngiam J, Chen Z, et al. Tiled convolutional neural networks[C]∥The Twenty-Fourth Annual Conference on Neural Information Processing Systems (NIPS 2010), December 6-11, 2010, Vancouver, B.C.,Canada. Cambridge, MA: MIT Press, 2010:1279-1287.

【37】Yu K, Zhang T. Improved local coordinate coding using local tangents[C]∥International Conference on International Conference on Machine Learning(ICML), June 21-24, 2010, Haifa, Israel. New York: ACM, 2010:1215-1222.

【38】Bo L, Ren X, Fox D. Kernel descriptors for visual recognition[C]∥The Twenty-Fourth Annual Conference on Neural Information Processing Systems(NIPS),December 6-11, 2010, Vancouver, CanadaLake. Cambridge, MA: MIT Press, 2010:244-252.

【39】Snoek J, Larochelle H, Adams R P. Practical bayesian optimization of machine learning algorithms[C]∥The Twenty-sixth Annual Conference on Neural Information Processing Systems (NIPS), December 6-11, 2012, Harrahs and Harveys, USA. Cambridge, MA: MIT Press, 2012: 2951-2959.

【40】Pang Y, Sun M, Jiang X, et al. Convolution in Convolution for Network in Network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(5):1587-1597.

【41】Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041.

【42】Tan X Y, Triggs B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Transactions on Image Processing, 2010, 19(6): 1635-1650.

【43】Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.

【44】Vu N S, Caplier A. Enhanced patterns of oriented edge magnitudes for face recognition and image matching[J]. IEEE Transactions on Image Processing, 2012, 21(3): 1352-1365.

引用该论文

Zhao Xiaohu,Yin Liangfei,Zhu Yanan,Liu Peng,Wang Xuekui,Shen Xueru. Improved Image Classification Algorithm Based on Principal Component Analysis Network[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021004

赵小虎,尹良飞,朱亚楠,刘鹏,王学奎,沈雪茹. 基于主成分分析网络的改进图像分类算法[J]. 激光与光电子学进展, 2019, 56(2): 021004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF