| Peer-Reviewed

Layered Feature Recognition Algorithm Based on Combined Convolution

Received: 19 November 2019     Accepted: 11 December 2019     Published: 24 December 2019
Views:       Downloads:
Abstract

In recent years, the deep learning algorithms were gradually understood and accepted. It needs to take too many samples to train. Since the implementation of deep learning algorithm, it seems that the past classical algorithms have become gloomy. In this paper, we get an intelligent pattern recognition model by combining some classical algorithms in the past and extrapolating the convolution algorithm. This new model is based on a single regular sample, with its advanced generalization capabilities far beyond those of deep learning algorithms. Experimental results on MNIST, QMNIST, CMU PIE and Extended Yale B databases indicate that the proposed model is better than the related methods as compared with.

Published in Automation, Control and Intelligent Systems (Volume 7, Issue 4)
DOI 10.11648/j.acis.20190704.11
Page(s) 99-110
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Pattern Recognition, Convolution Algorithm, Single Sample, Face Recognition, Handwritten Digital Recognition

References
[1] C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015, pp. 1–9.
[2] A. K. I. S. R. R. S. Geoffrey E. Hinton, Nitish Srivastava, “Improving neural networks by preventing co-adaptation of feature detectors,” Computer Science, 2012. arXiv: 1207.0580.
[3] M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” Computer Science, 2013. arXiv: 1311.2901.
[4] L. B. Chhavi Yadav, “Cold case: The lost mnist digits,” Computer Science, 2019. arXiv: 1905.10498.
[5] T. Sim, S. Baker, and M. Bsat, “The cmu pose, illumination, and expression database,” IEEE Transactions on Pattern Analysis & Machine Intelligence, 2003, vol. 25, no. 12, pp. 1615–1618.
[6] A. S. Georghiades, P. N. Belhumeur, and D. J. Kriegman, “From few to many: Illumination cone models for face recognition under variable lighting and pose,” IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, vol. 23, no. 6, pp. 643–660.
[7] K. Yu, Y. Lin, and J. Lafferty, “Learning image representations from the pixel level via hierarchical sparse coding,” in CVPR 2011, June 2011, pp. 1713–1720.
[8] M. J. Prewitt, “Object enhancement and extraction,” Picture Processing & Psychopictorics, 1970, pp. 75–149.
[9] S. Ruder, “An overview of gradient descent optimization algorithms,” Computer Science, 2016. arXiv: 1609.04747.
[10] V. T. B. V. O’Toole A J, Leopold D A, “Prototype-referenced shape perception: Adaptation and after-effects in a multidimensional face space,” Journal of Vision, 2001.
[11] X. J. C. H.-y. HAN Xu, LIU Qiang, “Handwritten numeral recognition algorithm based on similar principal component analysis,” Computer Science, 2018, vol. 45 (11A), pp. 278–281, 307.
[12] C. M. Bishop, “Neural networks for pattern recognition,” Agricultural Engineering International the Cigr Journal of Scientific Research & Development Manuscript Pm, 1995, vol. 12, no. 5, pp. 1235-1242.
[13] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, 2006, vol. 313, no. 5786, pp. 504–507.
[14] H. G. LeCun Yann, Bengio Yoshua, “Deep learning”, Nature, 2015.
[15] R. A. Parth Sane, “Pixel normalization from numeric data as input to neural networks,” Computer Science, 2017. arXiv: 1705.01809.
[16] A. D. Samit Bhanja, “Impact of data normalization on deep neural network for time series forecasting,” Computer Science, 2018. arXiv: 1812.05519.
[17] M. S. Maximilian Schmidt, “Normalizing flows for novelty detection in industrial time series data,” Computer Science, 2019. arXiv: 1906.06904.
[18] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, 2014, vol. 15, no. 1, pp. 1929–1958.
[19] W. L. J. Hervé Abdi, “Principal component analysis” Wiley Interdisciplinary Reviews Computational Statistics, 2010, vol. 2 (4), pp. 433–459.
[20] R. H. Hahnloser, Sarpeshkar, R., M. A. Mahowald, R. J. Douglas, and H. S. Seung, “Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit,” Nature, 2000, vol. 405, no. 6789, pp. 947–951.
[21] H. X. Yang and Y. Y. Cai, “Adaptively weighted orthogonal gradient binary pattern for single sample face recognition under varying illumination,” Iet Biometrics, 2016, vol. 5, no. 2, pp. 76–82.
[22] B. Wang, W. Li, W. Yang, and Q. Liao, “Illumination normalization based on weber’s law with application to face recognition,” IEEE Signal Processing Letters, 2011, vol. 18, no. 8, pp. 462–465.
[23] T. Xiaoyang and T. Bill, “Enhanced local texture feature sets for face recognition under difficult lighting conditions,” Amfg, 2007, vol. 4778, no. 6, pp. 1635–1650.
[24] N. S. Vu and A. Caplier, “Illumination-robust face recognition using retina modeling,” in IEEE International Conference on Image Processing, 2010.
[25] D. J. Jobson, Rahman, Z., and G. A. Woodell, “A multiscale retinex for bridging the gap between color images and the human observation of scenes,” IEEE Transactions on Image Processing, 2002, vol. 6, no. 7, pp. 965–976.
[26] T. Zhang, B. Fang, Y. Yuan, Y. T. Yuan, Z. Shang, D. Li, and F. Lang, “Multiscale facial structure representation for face recognition under varying illumination,” Pattern Recognition, 2009, vol. 42, no. 2, pp. 251–258.
[27] Z. Taiping, T. Yuan Yan, F. Bin, S. Zhaowei, and L. Xiaoyu, “Face recognition under varying illumination using gradientfaces,” IEEE Transactions on Image Processing, 2009, vol. 18, no. 11, pp. 2599–2606.
[28] X. Chen and J. Zhang, “Illumination robust single sample face recognition using multi-directional orthogonal gradient phase faces,” Neurocomputing, 2011, vol. 74, pp. 2291–2298.
Cite This Article
  • APA Style

    Shuduo Zhao, Xu Han, Jin Xu, Haiyun Chen, Guanqin Feng, et al. (2019). Layered Feature Recognition Algorithm Based on Combined Convolution. Automation, Control and Intelligent Systems, 7(4), 99-110. https://doi.org/10.11648/j.acis.20190704.11

    Copy | Download

    ACS Style

    Shuduo Zhao; Xu Han; Jin Xu; Haiyun Chen; Guanqin Feng, et al. Layered Feature Recognition Algorithm Based on Combined Convolution. Autom. Control Intell. Syst. 2019, 7(4), 99-110. doi: 10.11648/j.acis.20190704.11

    Copy | Download

    AMA Style

    Shuduo Zhao, Xu Han, Jin Xu, Haiyun Chen, Guanqin Feng, et al. Layered Feature Recognition Algorithm Based on Combined Convolution. Autom Control Intell Syst. 2019;7(4):99-110. doi: 10.11648/j.acis.20190704.11

    Copy | Download

  • @article{10.11648/j.acis.20190704.11,
      author = {Shuduo Zhao and Xu Han and Jin Xu and Haiyun Chen and Guanqin Feng and Chenxin Ma and Wenhao Zhou},
      title = {Layered Feature Recognition Algorithm Based on Combined Convolution},
      journal = {Automation, Control and Intelligent Systems},
      volume = {7},
      number = {4},
      pages = {99-110},
      doi = {10.11648/j.acis.20190704.11},
      url = {https://doi.org/10.11648/j.acis.20190704.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acis.20190704.11},
      abstract = {In recent years, the deep learning algorithms were gradually understood and accepted. It needs to take too many samples to train. Since the implementation of deep learning algorithm, it seems that the past classical algorithms have become gloomy. In this paper, we get an intelligent pattern recognition model by combining some classical algorithms in the past and extrapolating the convolution algorithm. This new model is based on a single regular sample, with its advanced generalization capabilities far beyond those of deep learning algorithms. Experimental results on MNIST, QMNIST, CMU PIE and Extended Yale B databases indicate that the proposed model is better than the related methods as compared with.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Layered Feature Recognition Algorithm Based on Combined Convolution
    AU  - Shuduo Zhao
    AU  - Xu Han
    AU  - Jin Xu
    AU  - Haiyun Chen
    AU  - Guanqin Feng
    AU  - Chenxin Ma
    AU  - Wenhao Zhou
    Y1  - 2019/12/24
    PY  - 2019
    N1  - https://doi.org/10.11648/j.acis.20190704.11
    DO  - 10.11648/j.acis.20190704.11
    T2  - Automation, Control and Intelligent Systems
    JF  - Automation, Control and Intelligent Systems
    JO  - Automation, Control and Intelligent Systems
    SP  - 99
    EP  - 110
    PB  - Science Publishing Group
    SN  - 2328-5591
    UR  - https://doi.org/10.11648/j.acis.20190704.11
    AB  - In recent years, the deep learning algorithms were gradually understood and accepted. It needs to take too many samples to train. Since the implementation of deep learning algorithm, it seems that the past classical algorithms have become gloomy. In this paper, we get an intelligent pattern recognition model by combining some classical algorithms in the past and extrapolating the convolution algorithm. This new model is based on a single regular sample, with its advanced generalization capabilities far beyond those of deep learning algorithms. Experimental results on MNIST, QMNIST, CMU PIE and Extended Yale B databases indicate that the proposed model is better than the related methods as compared with.
    VL  - 7
    IS  - 4
    ER  - 

    Copy | Download

Author Information
  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • School of Information, Southwest Petroleum University, Nanchong, China

  • Sections