Improved Image Classification Algorithm Based on Principal Component Analysis Network

Xiaohu Zhao; Liangfei Yin; Yanan Zhu; Peng Liu; Xuekui Wang; Xueru Shen

doi:10.3788/LOP56.021004

[1] LeCun Y, Bottou L, Bengio Y et al. . Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 86, 2278-2324(1998). http://doi.ieeecomputersociety.org/resolve?ref_id=doi:10.1109/5.726791&rfr_id=trans/tp/2008/08/ttp2008081415.htm

[2] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 313, 504-507(2006). http://logcom.oxfordjournals.org/cgi/ijlink?linkType=ABST&journalCode=sci&resid=313/5786/504

[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. Cambr, 1097-1105(2012).

[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, 1-9(2015).

[5] He K, Zhang X, Ren S, Pattern Recognitionet al. Deep residual learning for image recognition[J/OL]. 770-778[2018-05-29]. https:∥arxiv., org/abs/1512, 03385(2016).

[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, 15, 215-223(2011).

[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), 29, 62-72(1999). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=740166

[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, 8, 2351-2360(2015). http://ieeexplore.ieee.org/document/6926746/

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

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

[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, 001394-001399(2016).

[12] Ren Y, Suganthan P N, Srikanth Net al. Random vector functional link network for short-term electricity load demand forecasting[J]. 367-, 368, 1078-1093(2016).

[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, 24, 5017-5032(2015). http://ieeexplore.ieee.org/document/7234886

[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, 38, 1724-1726(2013). http://europepmc.org/abstract/med/23938924

[15] Yeom S, Javidi B, Ferraro P et al. Three-dimensional color object visualization and recognition using multi-wavelength computational holography[J]. Optics Express, 15, 9394-9402(2007). http://www.ncbi.nlm.nih.gov/pubmed/19547286

[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, 25, 112-123(2017). http://www.ncbi.nlm.nih.gov/pubmed/28085798

[17] Du Q, Fowler J E. Hyperspectral image compression using JPEG2000 and principal component analysis[J]. IEEE Geoscience and Remote Sensing Letters, 4, 201-205(2007). http://ieeexplore.ieee.org/document/4156154/

[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, 56, 3181-3198(2011). http://pubmedcentralcanada.ca/pmcc/articles/PMC3395474/

[19] Wu J S, Qiu S J, Zeng R et al. Multilinear principal component analysis network for tensor object classification[J]. IEEE Access, 5, 3322-3331(2017). http://ieeexplore.ieee.org/document/7867073/

[20] Han B, Jia Z H, Gao X B. Improved PCANet for aurora images classification[J]. Journal of Xidian University, 1, 83-88(2017).

[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, 494-505(2017).

[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, 559-564(2015).

[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, 44, 0302004(2017).

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

[25] Krizhevsky A. Learning multiple layers of features from tiny mages Toronto,[D]. 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,, 1988-1996(2014).

[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, 16, 295-306(1998). http://www.sciencedirect.com/science/article/pii/S026288569700070X

[28] Yu K, Lin Y, Lafferty J. Learning image representations from the pixel level via hierarchical sparse coding[J]. Proceedings of the IEEE, 1713-1720(2011). http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=5995732

[30] Lee H, Grosse R, Ranganath R et al. Unsupervised learning of hierarchical representations with convolutional deep belief networks[J]. Communications of the ACM, 54, 95-103(2011). http://dl.acm.org/citation.cfm?id=2001295

[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, 2146-2153(2009).

[32] Zeiler M D, Evolutionary Computing, Machine Learning, Preprint ArXiv. ArXiv, 3557, 2013(1301).

[33] Goodfellow I J, Warde-Farley D, Mirza M et al. 2018-05-30]. https:∥arxiv.org/pdf/1302.4389.pdf.(2013).

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

[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, 24, 5017-5032(2015). http://ieeexplore.ieee.org/document/7234886

[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,, 1279-1287(2010).

[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, 1215-1222(2010).

[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,, 244-252(2010).

[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. Cam, 2951-2959(2012).

[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, 29, 1587-1597(2018). http://europepmc.org/abstract/MED/28328517

[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, 28, 2037-2041(2006). http://ieeexplore.ieee.org/document/1717463/

[42] Tan X Y, Triggs B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Transactions on Image Processing, 19, 1635-1650(2010). http://www.ncbi.nlm.nih.gov/pubmed/20172829

[43] Lecun Y, Bottou L, Bengio Y et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 86, 2278-2324(1998). http://doi.ieeecomputersociety.org/resolve?ref_id=doi:10.1109/5.726791&rfr_id=trans/tp/2008/08/ttp2008081415.htm

[44] Vu N S, Caplier A. Enhanced patterns of oriented edge magnitudes for face recognition and image matching[J]. IEEE Transactions on Image Processing, 21, 1352-1365(2012). http://europepmc.org/abstract/MED/21896385