Skip to main content

Advertisement

Springer Nature Link
Log in

Improvement of recognition rate using data augmentation with blurred images

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

This study aims to improve the recognition rate of a recognizer for detecting cracks on concrete surfaces from image data. When developing a recognizer, a clean image is commonly used as training data. Therefore, the recognition rate decreases when blurred images not taken cleanly are used as test data. To improve the recognition rate, the training data were mixed with processed images. In experiment, a simple convolutional neural network was used to confirm the effect of data augmentation. Experimental results showed that adding blurred images to the training data improved the recognition rate for blurred images, regardless of how the images were blurred. For training data without blurred images, the recognition rate for strongly blurred images is about 75%. On the other hand, the recognition rate improves to about 95% for training data that includes strongly blurred images. Thus, including images in which strong blur filters are used for data augmentation is effective in improving the recognition rate of blurred images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data Availability

https://data.mendeley.com/datasets/5y9wdsg2zt/2

References

  1. Ministry of Land, Infrastructure, Transport and Tourism, Roads Bureau, National Roads and Engineering Division (2019) Road Tunnel Periodic Inspection Procedure, March 2019

  2. Kimura U, Krau A, Sakurai T (2018) Automatic crack detection in infrastructure inspection using fully convolutional network. IPSJ Trans Math Model Appl 11(1):12–20 (Japanese)

  3. Chiyonobu M, Iida S, Ishikawa Y, Nishikino M, Kawakami R, Joe K (in press) Estimating concrete interior using a 3D-CNN. Advances in Parallel and Distributed Processing, and Applications

  4. Feng MQ, De Flaviis F, Kim YJ (2002) Use of microwaves for damage detection of fiber reinforced polymer-wrapped concrete structures. J Eng Mech, 128(2)

  5. Akkaya Y, Voigt T, Subramaniam KV (2003) Nondestructive measurement of concrete strength gain by an ultrasonic wave reflection method. Mater Struct 36:507–14

    Article  Google Scholar 

  6. Nakamura S, Takaya S, Maeda Y, Yamamoto T, Miyagawa T (2023) Spalling time prediction by using infrared thermography. Japanese J JSCE E2, 69(4):450–461

  7. Cha YJ, Choi W, Suh G, Mahmoudkhani S, Büyüköztürk O (2017) Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput-Aided Civ Infrastruct Eng 33(9):731–747

    Article  Google Scholar 

  8. Cha YJ, Choi W (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Infrastruct Eng 32(5):361–378

    Article  Google Scholar 

  9. Kim B, Cho KS (2018) Automated vision—based detection of cracks on concrete surfaces using a deep learning technique. Sensors 18(10).

  10. Concrete Crack Images for Classification. https://data.mendeley.com/datasets/5y9wdsg2zt/2. Accessed 6 Sept 2023

  11. PyTorch. https://pytorch.org/. Accessed 6 Sept 2023

Download references

Acknowledgements

We would like to thank Editage (www.editage.jp) for English language editing.

Funding

The authors did not receive any financial support for this study.

Author information

Authors and Affiliations

  1. Graduate School of Humanities and Sciences, Nara Women’s University, Kitauoya-Nishi-machi, Nara, Nara, 6308506, Japan

    Shiori Ishikawa, Miho Chiyonobu & Sayaka Iida

  2. Research Group of Information and Communication Technology for Life, Nara Women’s University, Kitauoya-Nishi-machi, Nara, Nara, 6308506, Japan

    Masami Takata

Authors
  1. Shiori Ishikawa
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Miho Chiyonobu
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sayaka Iida
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Masami Takata
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Shiori Ishikawa or Masami Takata.

Ethics declarations

Ethics approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ishikawa, S., Chiyonobu, M., Iida, S. et al. Improvement of recognition rate using data augmentation with blurred images. J Supercomput 80, 12154–12165 (2024). https://doi.org/10.1007/s11227-024-05901-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-024-05901-8

Keywords