nach oben

Neural Processing Letters

Erschienen in:

27.10.2021

PCA Dimensionality Reduction Method for Image Classification

verfasst von: Baiting Zhao, Xiao Dong, Yongcun Guo, Xiaofen Jia, Yourui Huang

Erschienen in: Neural Processing Letters | Ausgabe 1/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

The pooling layer has achieved good results in reducing the feature dimension and parameters of convolution neural network (CNN), but it will cause different degrees of information loss. In order to retain as much feature information as possible, we design a pooling method based on Principal Component Analysis (PCA)-P_CAPool. Firstly, all feature maps are traversed with the pooling window in which the data is extracted and stretched into row vectors. With the sliding of the pooling window, all row vectors are arranged in the matrix to form the sample matrix. Then all eigenvectors are extracted from the sample matrix by PCA algorithm to form the eigenvector matrix, which right multiplies the sample matrix to get the principal component matrix. Thirdly, each column of the principal component matrix is weighted with information coefficient which is determined by training to get the pooling vector. Finally, P_CAPool result is obtained by blocks arrangement of pooling vector. P_CAPool is tested with CNN-Quick, NIN, WRN-SAM, GP-CNN on datasets MNIST, CIFAR10/100 and SVHN. We also used AlexNet on Imagenet2012 to test P_CAPool. The experiment results show that compared with traditional pooling methods, P_CAPool could retain information in the pooling window better and improve the image classification accuracy.

Vorheriger Artikel State Estimation for Genetic Regulatory Networks with Two Delay Components by Using Second-Order Reciprocally Convex Approach

Nächster Artikel A Neurodynamic Algorithm for Energy Scheduling Game in Microgrid Distribution Networks

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Zhang L, Zhang L, Du B, You J, Tao D (2019) Hyperspectral image unsupervised classification by robust manifold matrix factorization. Inf Sci 485:154–169. https://doi.org/10.1016/j.ins.2019.02.008MathSciNetCrossRefMATH

Ji X, Henriques JF, Vedaldi A. Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, Seoul, South Korea, 27 Oct 2019–3 Nov 2019; pp. 9865–9874

Xue Z, Du J, Du D, Li G, Huang Q, Lyu S (2019) Deep constrained low-rank subspace learning for multi-view semi-supervised classification. IEEE Signal Process Lett 26:1177–1181. https://doi.org/10.1109/LSP.2019.2923857CrossRef

Du W, Phlypo R, Adalı T (2019) Adaptive feature selection and feature fusion for semi-supervised classification. J Signal Process Syst 91:521–537. https://doi.org/10.1007/s11265-018-1355-xCrossRef

Ying S, Wen Z, Shi J, Peng Y, Peng J, Qiao H (2018) Manifold preserving: an intrinsic approach for semisupervised distance metric learning. IEEE Trans Neural Netw Learn Syst 29:2731–2742. https://doi.org/10.1109/TNNLS.2017.2691005MathSciNetCrossRef

Wu B, Liu Y, Lang B, et al. (2017) DGCNN: disordered graph convolutional neural network based on the gaussian mixture model. Neurocomputing.

Shi H, Zhang Y, Zhang Z, et al (2018) Hypergraph-induced convolutional networks for visual classification . IEEE Trans Neural Netw Learn Syst, 1–10

Fu S, Liu W, Zhou Y, et al (2019) HpLapGCN: hypergraph p-Laplacian graph convolutional networks. Neurocomputing 362

Wang J, Zheng Y, Wang M, Shen Q, Huang J (2021) Object-scale adaptive convolutional neural networks for high-spatial resolution remote sensing image classification. IEEE J Select Top Appl Earth Obser Remote Sens 14:283–299. https://doi.org/10.1109/JSTARS.2020.3041859CrossRef

10.

Tun NL, Gavrilov A, Tun NM, Trieu DM, Aung H (2021) hyperspectral remote sensing images classification using fully convolutional neural network. IEEE Conf Russian Young Res Electr Electron Eng (ElConRus) 2021:2166–2170. https://doi.org/10.1109/ElConRus51938.2021.9396673CrossRef

11.

Patel S, Alnaser AJ (2020) A mathematical overview of machine vision. SoutheastCon 2020:1–6. https://doi.org/10.1109/SoutheastCon44009.2020.9249762CrossRef

12.

Gu Z, Liu X, Wei L (2021) A detection and identification method based on machine vision for bearing surface defects. In: 2021 International Conference on Computer, Control and Robotics (ICCCR), pp. 128–132, https://doi.org/10.1109/ICCCR49711.2021.9349370.

13.

Fan C, Yi J, Tao J, Tian Z, Liu B, Wen Z (2021) gated recurrent fusion with joint training framework for robust end-to-end speech recognition. IEEE/ACM Trans Audio Speech Language Process 29:198–209. https://doi.org/10.1109/TASLP.2020.3039600CrossRef

14.

Subramanian AS et al (2020) Far-field location guided target speech extraction using end-to-end speech recognition objectives. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7299–7303. https://doi.org/10.1109/ICASSP40776.2020.9053692

15.

Arora R, Singh P, Goyal H, Singhal S, Vijayvargiya S (2021) Comparative question answering system based on natural language processing and machine learning question answering system based on natural language processing and machine learning. In: 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), pp. 373-378, https://doi.org/10.1109/ICAIS50930.2021.9396015

16.

Retna VSA, Brundha P, RajKumar G (2021) People’s Behaviour analysis in chat message using natural language processing. In: 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 1128-1133, https://doi.org/10.1109/ICICV50876.2021.9388596

17.

Salehinejad H, Valaee S EDropout: energy-based dropout and pruning of deep neural networks. In: IEEE Transactions on neural networks and learning systems, https://doi.org/10.1109/TNNLS.2021.3069970

18.

Wan L, Zeiler M, Zhang S, Le Cun Y, Fergus R (2013) Regularization of neural networks using dropconnect. In: Proceedings of the 30th international conference on machine learning, Atlanta, GA, USA, 16–21 June 2013; pp 2095–2103

19.

Zhijie Y, Lei W, Li L, Shiming G, Shasha G, Shasha W (March 2021) Bactran: A Hardware Batch Normalization Implementation for CNN Training Engine. IEEE Embed Syst Lett 13(1):29–32. https://doi.org/10.1109/LES.2020.2975055CrossRef

20.

Krizhevsky A, Sutskever I, Hinton GE (Dec 2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, Lake Tahoe, Nevada, USA 3–6:1097–1105

21.

Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. CoRR, arXiv:1409.1556

22.

Balagourouchetty L, Pragatheeswaran JK, Pottakkat B, Ramkumar G (June 2020) GoogLeNet-Based Ensemble FCNet Classifier for Focal Liver Lesion Diagnosis. IEEE J Biomed Health Inform 24(6):1686–1694. https://doi.org/10.1109/JBHI.2019.2942774CrossRef

23.

Yu X, Kang C, Guttery DS, Kadry S, Chen Y, Zhang Y –D (2021) ResNet-SCDA-50 for breast abnormality classification. In: IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18, no. 1, pp. 94–102, https://doi.org/10.1109/TCBB.2020.2986544

24.

Li W, Chen C, Zhang M, Li H, Du Q (2018) Data augmentation for hyperspectral image classification with deep cnn. IEEE Geosci Remote Sens Lett 16:593–597. https://doi.org/10.1109/LGRS.2018.2878773CrossRef

25.

Pham TC, Luong CM, Visani M, Hoang VD (2018) Deep CNN and data augmentation for skin lesion classification. In: Asian conference on intelligent information and database systems, Dong Hoi City, Vietnam, 19–21 May 2018; pp. 573–582

26.

Fei J, Rui T, Song X, Zhou Y, Zhang S (2018) More discriminative convolutional neural network with inter-class constraint for classification. Comput Electr Eng 68:484–489. https://doi.org/10.1016/j.compeleceng.2018.05.002CrossRef

27.

Cao J, Pang Y, Li X, Liang J (2018) Randomly translational activation inspired by the input distributions of ReLU. Neurocomputing 275:859–868. https://doi.org/10.1016/j.neucom.2017.09.031CrossRef

28.

Yu Y, Hao K, Ding Y (2018) A new image classification model based on brain parallel interaction mechanism. Neurocomputing 315:190–197. https://doi.org/10.1016/j.neucom.2018.07.016CrossRef

29.

Shi W, Gong Y, Cheng D, Tao X, Zheng N (2018) Entropy and orthogonality based deep discriminative feature learning for object recognition. Pattern Recogn 81:71–80. https://doi.org/10.1016/j.patcog.2018.03.036CrossRef

30.

Liang M, Hu X (Jun 2015) Recurrent CNNs for object recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA 7–12:3367–3375

31.

Shi W, Gong Y, Tao X, Wang J, Zheng N (2018) Improving CNN Performance Accuracies With Min-Max Objective. IEEE Transactions on Neural Networks and Learning Systems 29:2872–2885. https://doi.org/10.1109/TNNLS.2017.2705682MathSciNetCrossRef

32.

Wang Q-F, Yao K, Zhang R, Hussain A, Huang K (2020) Improving deep neural network performance by integrating kernelized Min-Max objective. Neurocomputing 408:82–90CrossRef

33.

Lee CY, Gallagher P, Tu Z (2018) Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree. IEEE Trans Pattern Anal Mach Intell 40:863–875. https://doi.org/10.1109/TPAMI.2017.2703082CrossRef

34.

Li Z, Fan Y, Liu W (2015) The effect of whitening transformation on pooling operations in convolutional autoencoders. EURASIP Journal on Advances in Signal Processing 2015(1):1–11CrossRef

35.

Sf A , Wl A , DT B, et al. HesGCN: Hessian graph convolutional networks for semi-supervised classification – ScienceDirect. Information Sciences, 2020, 514:484–498.(Fu, S. C.; Liu, W. F.; Tao, D. P.; et al.)

36.

Liu W, Fu S, Zhou Y et al (2020) Human activity recognition by manifold regularization based dynamic graph convolutional networks J.; Neurocomputing.

37.

Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. in Proc. Int. Conf. Learn. Representation (ICLR).

38.

Kaya IE, Pehlivanlı AÇ, Sekizkardeş EG, Ibrikci T (2018) PCA based clustering for brain tumor segmentation of T1w MRI images. Comput Methods Programs Biomed 142:19–28. https://doi.org/10.1016/j.cmpb.2016.11.011CrossRef

39.

Al-Bahri IM, Fageeri SO, Said AM, Sagayee G MA (2021) a comparative study between PCA and sift algorithm for static face recognition, 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), pp. 1–5, https://doi.org/10.1109/ICCCEEE49695.2021.9429610.

40.

Seuret M, Alberti M, Liwicki M, Ingold R (2017) PCA-initialized deep neural networks applied to document image analysis. In: 14th IAPR international conference on document analysis and recognition (ICDAR), Kyoto, Japan, 9–15 November 2017; pp. 877–882

41.

Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) PCANet: a simple deep learning baseline for image classification. IEEE Trans Image Process 24:5017–5032. https://doi.org/10.1109/TIP.2015.2475625MathSciNetCrossRefMATH

42.

Low CY, Teoh ABJ, Toh KA (2017) Stacking PCANet +: An overly simplified convnets baseline for face recognition. IEEE Signal Process Lett 24:1581–1585. https://doi.org/10.1109/LSP.2017.2749763CrossRef

43.

Alahmadi A, Hussain M, Aboalsamh HA et al (2020) PCAPooL: unsupervised feature learning for face recognition using PCA, LBP, and pyramid pooling. Pattern Anal Appl 23(2):673–682CrossRef

44.

Giles MB (2008) Collected Matrix Derivative Results for Forward and Reverse Mode Algorithmic Differentiation. In Advances in Automatic Differentiation, 2nd ed.; Bischof, C.H., Bücker, H.M., Hovland, P., Naumann, U., Utke, J. Eds.; Springer: Berlin, Germany, 2008; Volume 3, pp. 35–44, ISBN: 978–3–540–68935–5.

45.

Ionescu C, Vantzos O, Sminchisescu C (2015) Matrix Backpropagation for Deep Networks with Structured Layers. In IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; pp. 2965–2973.

46.

Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia, Orlando, Florida, USA, 03 – 07 November 2014; pp. 675–678

47.

Lin M, Chen Q, Yan S (2013) Network in network. In: Proceedings of International Conference on Learning Representations

48.

Foret P, Kleiner A, Mobahi H, Neyshabur B (2020) Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.0141.

49.

Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: Proceedings of international conference on machine learning, pp. 1319–1327

50.

Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z (2015) Deeply-supervised nets. Artif Intell Stat San Diego California, USA 9–12:562–570

51.

Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2015) Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806. ( J. T. Springenberg, A. Dosovitskiy, T. Brox, and M. Riedmiller,“Striving for simplicity,” in Proc. Int. Conf. Learn. Representations)

52.

Chen T. , Zhang Z. , Ouyang X. , Liu Z. , Shen Z. , Wang Z (2021) "BNN - BN = ?": training binary neural networks without batch normalization. arXiv:2104.08215

53.

Samadzadeh A, Far FS, Javadi A, Nickabadi A, Chehreghani M (2020) Convolutional spiking neural networks for spatio-temporal feature extraction. arXiv:2003.12346

54.

Kabir HM, Abdar M, Jalali SM, Khosravi A, Atiya A, Nahavandi S, Srinivasan D (2020) SpinalNet: deep neural network with gradual input. arXiv:2007.03347

55.

Maaten LVD, Hinton GE (2008) Visualizing data using t-sne. J Mach Learn Res (JMLR) 9:2579–2605MATH

Titel: PCA Dimensionality Reduction Method for Image Classification
verfasst von: Baiting Zhao
Xiao Dong
Yongcun Guo
Xiaofen Jia
Yourui Huang
Publikationsdatum: 27.10.2021
Verlag: Springer US
Erschienen in: Neural Processing Letters / Ausgabe 1/2022
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI: https://doi.org/10.1007/s11063-021-10632-5

Neuer Inhalt

Bildnachweise

VDI-Icon, Profil Icon, inhalt2, Springer Professional Modul/© Springer Fachmedien Wiesbaden GmbH, Nachhaltigkeitsaward Key Visual/© Cometis AG/Global ESG Monitor | Daniel Rupp | Generiert mit KI, Search Icon, Banner Hanser, Frank Urbansky/© Peter Eichler / Leipzig, CO2-Fußabdruck/© Jenny Sturm / stock.adobe.com, Interview Entropie Bild 1/© Bernhard Weßling, Zeitschrift Wissensmanagement Cover, PatentFit-Logo/© Springer Fachmedien Wiesbaden GmbH, Sustainibility Finance/© Robert Kneschke / stock.adobe.com / Springer Fachmedien Wiesbaden GmbH, Zukunftswerkstatt Sales Excellence 2024/© AndreyPopov / Getty Images / iStock, 2023_Antrieb/© supervisuell

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 1/2022

Complex Valued Deep Neural Networks for Nonlinear System Modeling

Multi-view Clustering Based on Low-rank Representation and Adaptive Graph Learning

Solving Mixed Variational Inequalities Via a Proximal Neurodynamic Network with Applications

Detection of Copy-Move Forgery in Digital Image Using Multi-scale, Multi-stage Deep Learning Model

A Neurodynamic Algorithm for Energy Scheduling Game in Microgrid Distribution Networks

Proposal-Based Graph Attention Networks for Workflow Detection

Neuer Inhalt

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.