The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)

Korea Information Electronic Communication Technology (한국정보전자통신기술학회)
권호 표지
DOI QR코드

DOI QR Code

DCGAN-based Compensation for Soft Errors in Face Recognition systems based on a Cross-layer Approach

얼굴인식 시스템의 소프트에러에 대한 DCGSN 기반의 크로스 레이어 보상 방법

  • Received : 2021.10.16
  • Accepted : 2021.10.26
  • Published : 2021.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a robust face recognition method against soft errors with a deep convolutional generative adversarial network(DCGAN) based compensation method by a cross-layer approach. When soft-errors occur in block data of JPEG files, these blocks can be decoded inappropriately. In previous results, these blocks have been replaced using a mean face, thereby improving recognition ratio to a certain degree. This paper uses a DCGAN-based compensation approach to extend the previous results. When soft errors are detected in an embedded system layer using parity bit checkers, they are compensated in the application layer using compensated block data by a DCGAN-based compensation method. Regarding soft errors and block data loss in facial images, a DCGAN architecture is redesigned to compensate for the block data loss. Simulation results show that the proposed method effectively compensates for performance degradation due to soft errors.

본 논문에서는 DCGAN 기반의 크로스 레이어 보상 방법을 이용하여 소프트에러의 영향을 줄이는 얼굴인식 기법을 제안한다. JPEG 파일의 데이터 블록에서 소프트에러가 발생할 때, 이 블록들은 제대로 복호화되지 않을 수 있다. 이전 연구에서 해당 블록들은 얼굴 사진들의 평균 이미지를 이용해 대체하였으며, 인식률을 어느 정도 향상하였다. 본 논문에서는 이전 연구의 확장으로 DCGAN 기반의 보상 기법을 다룬다. 패리티 비트 검사기를 이용하는 임베디드 시스템 레이어에서 소프트에러가 발생할 때, 이 에러는 애플리케이션 레이어에서 DCGAN을 이용하여 보상된다. 얼굴 이미지의 소프트에러를 보상하기 위해서 DCGAN 구조를 이용하여 블록 데이터의 손실을 보상한다. 시뮬레이션 결과를 통하여, 제안된 방식이 소프트에러로 인한 성능 악화를 효율적으로 보상한다는 것을 보인다.

Keywords

Acknowledgement

This Paper was supported by Korea Institute for Advancement of Technology (KIAT) grant funded by the Korea Gove rnment (MOTIE) in 2021. (No. 1415172733)

References

  1. R. Baumann, "Soft errors in advanced computer systems", IEEE Design & Test of Computers, 22, 3, pp. 258-266, 2005. https://doi.org/10.1109/MDT.2005.69
  2. G. M. Jeong, et al. "Robust face recognition against soft-errors using a cross-layer approach", International Journal of Computers Communications & Control, 11, 5, pp. 657-665, 2016. https://doi.org/10.15837/ijccc.2016.5.2020
  3. G. M. Jeong, et al. "Effect of soft errors in iterative learning control and compensation using cross-layer approach", International Journal of Computers Communications & Control, 14, 3, pp. 359-374, 2019. https://doi.org/10.15837/ijccc.2019.3.3513
  4. K. Lee, et al. "Mitigating the impact of hardware defects on multimedia applications: a cross-layer approach", Proceedings of the 16th ACM international conference on Multimedia, pp. 319-328, 2008.
  5. A. T. Ardelean, L. M. Sasu, "Pose Manipulation with Identity Preservation", International Journal of Computers Communications & Control, 15, 2, April, 2020.
  6. I. J. Goodfellow, et al. "Generative Adversarial Nets", Advances in Neural Information Processing Systems, 27, 2014.
  7. P. Isola, et al. "Image-to-Image Translation with Conditional Adversarial Networks", IEEE Conference on computer vision and pattern recognition, pp. 1125-1134, 2017.
  8. A. Radford, et al. , "Unsupervised representation learning with deep convolutional generative adversarial networks", arXiv:1511.06434, 2015.
  9. Yale Face Database, http://vision.ucsd.edu/content/yale-face-database.
  10. K. Fukunaga, "Introduction to Statistical Pattern Recognition", Academic Press, 1990.
  11. C, Cortes, V. Vapnik, "Support-vector networks", Machine Learning, 20, 3, pp. 273-297, 1995. https://doi.org/10.1007/BF00994018
  12. C. Liu, H. Wechsler, "Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition". IEEE Transactions on Image Processing, 11, 4, pp. 467-476, 2002. https://doi.org/10.1109/TIP.2002.999679