Skip to main content

Similar Gesture Recognition via an Optimized Convolutional Neural Network and Adam Optimizer

  • 258 Accesses

Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST,volume 388)

Abstract

The recognition significance of similar sign language (or confusing gesture) in sign language recognition is highlighted, and the goal is to realize the recognition of such gesture and sign language based on deep learning with an optimized convolutional neural network and the Adam optimizer. The convolutional layer and the pooling layer are connected alternately. The locally connected image data and parameter features are used to extract the shared pooling layer, and the image resolution reduction of image data sampling and the reducibility of iterative training are used to achieve the extraction precision requirements of feature points. In addition, the information transfer between layers is realized through convolution, the introduction of pooling layer and RELU activation function to realize nonlinear mapping and reduce the data dimension. We also use the batch normalization method for faster convergence and dropout method to reduce overfitting. Ten experiments were carried out on a nine-layer “CNN-BN-ReLU-AP-DO” method, with an average accuracy of 97.50 ± 1.65%. The overall accuracy is relatively high, and gesture recognition can be conducted effectively.

Keywords

  • Gesture recognition
  • CNN
  • Batch normalization
  • Dropout
  • Adam
  • Data augmentation

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-82565-2_4
  • Chapter length: 19 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-82565-2
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   109.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.

References

  1. Lee, J.S., Lee, Y.J., Lee, E.H..: Hand region extraction and gesture recognition from video stream with complex background through entropy analysis. In: Proceedings of the 26th Annual International Conference of the IEEE EMBS, pp. 1–10 (2004)

    Google Scholar 

  2. Wu, X., Zhang, Q., Xu, Y.: A review of the development of gesture recognition research. Electron. Sci. Technol. 26(6), 71–174 (2013). https://doi.org/10.3969/j.issn.1007-7820.2013.06.053

    CrossRef  Google Scholar 

  3. Jiang, L., Ruan, Q.: Research on gesture recognition technology based on neural network. J. Beijing Jiaotong Univ. 30(6), 32–36 (2006). https://doi.org/10.3969/j.issn.1673-0291.2006.05.008

    CrossRef  Google Scholar 

  4. Feng, Z., Jiang, Y.: A review of gesture recognition research. J. Univ. Jinan (Sci. Technol.) 4, 336–341 (2013)

    Google Scholar 

  5. Gao, Y., Jia, C., Chen, H., Jiang, X.: Chinese fingerspelling sign language recognition using a nine-layer convolutional neural network. EAI Endorsed Trans. e-Learn. 7(20), e2 (2021)

    Google Scholar 

  6. Liu J, Zhao H. School of mechanical and electrical engineering and automation. J. Autom. EI CSCD, 31 (2020)

    Google Scholar 

  7. Zhang, Y., Li, L.: Realization of face feature point recognition based on cascaded convolutional neural network. J. Lanzhou Univ. Technol. 3, 105–109 (2020)

    Google Scholar 

  8. Long, Y., Li, Y., Tao, W., et al.: Text sentiment analysis based on cascade convolution and attention mechanism. J. Taiyuan Normal Univ.: Nat. Sci. 2, 30–36 (2020)

    Google Scholar 

  9. Jiang, X., Chang, L., Zhang, Y.D.: Classification of Alzheimer’s disease via eight-layer convolutional neural network with batch normalization and dropout techniques. J. Med. Imaging Health Inform. 10(5), 1040–1048 (2020)

    CrossRef  Google Scholar 

  10. Xiao, J., Tian, H., Zou, W.: Stereo matching based on convolution neural network. Inform. Technol. Inform. 38(8), 0815017 (2018)

    Google Scholar 

  11. Yuan, M., Zhou, C., Huang, H., et al.: Survey on convolutional neural network pooling methods. Softw. Eng. Appl. 5, 360–372 (2020)

    Google Scholar 

  12. Wang, S.Y., Teng, G.W.: Optimization design of ReLU activation function in convolutional neural network. Inform. Commun. 1673(1131), 42–43 (2018)

    Google Scholar 

  13. M GCMMD: Noisy activation functions. arXiv preprint arXiv 1603:00391 (2016)

    Google Scholar 

  14. Jiang, A., Wang, W.: Research on optimization of ReLU activation function. Transducer Microsyst. Technol. 2, 50–52 (2018)

    Google Scholar 

  15. Liu, J., Zhao, H., Luo, X., Xu, Y.: Research progress of deep learning batch normalization and its related algorithms. Acta Autom. Sinica 46(6), 1090–1120 (2020)

    MATH  Google Scholar 

  16. Han, M.: Research and implementation of dropout method based on selective area drop, 003028, https://doi.org/10.27005/d.cnki.gdzku (2020)

  17. Xie, F., Gong, J., Wang, Y.: Facial expression recognition method based on skin color enhancement and block PCA. J. Nanjing Normal Univ. (Eng. Technol. Ed.) 02, 49–56 (2017)

    Google Scholar 

  18. Cai, L., Ye, Y., Gao, X., Li, Z., Zhang, C.: An improved visual SLAM based on affine transformation for ORB feature extraction. Optik 227, 165421 (2021). https://doi.org/10.1016/j.ijleo.2020.165421

    CrossRef  Google Scholar 

  19. Wang, Y., Biyun, X., Kwak, M., Zeng, X.: A noise injection strategy for graph autoencoder training. Neural Comput. Appl. 33(10), 4807–4814 (2020). https://doi.org/10.1007/s00521-020-05283-x

    CrossRef  Google Scholar 

  20. Zhang, X., Zuo, C., Shen, D.: Gamma nonlinear error correction method based on deep learning. G01B11/25, 1–10.

    Google Scholar 

  21. Jiang, X., Satapathy, S.C., Yang, L., Wang, S.-H., Zhang, Y.-D.: A survey on artificial intelligence in Chinese sign language recognition. Arab. J. Sci. Eng. 45(12), 9859–9894 (2020). https://doi.org/10.1007/s13369-020-04758-2

    CrossRef  Google Scholar 

Download references

Acknowledgements

This work was supported by Natural Science Foundation of Jiangsu Higher Education Institutions of China (19KJA310002), The Philosophy and Social Science Research Foundation Project of Universities of Jiangsu Province (2017SJB0668).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xianwei Jiang .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Gao, Y., Jia, C., Qiao, Y., Huang, X., Lei, J., Jiang, X. (2021). Similar Gesture Recognition via an Optimized Convolutional Neural Network and Adam Optimizer. In: Fu, W., Xu, Y., Wang, SH., Zhang, Y. (eds) Multimedia Technology and Enhanced Learning. ICMTEL 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 388. Springer, Cham. https://doi.org/10.1007/978-3-030-82565-2_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-82565-2_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-82564-5

  • Online ISBN: 978-3-030-82565-2

  • eBook Packages: Computer ScienceComputer Science (R0)