Adversarial Auto-encoder Based Preprocessing Algorithm for Improving Image Identification and Navigation Accuracy

被引：0
作者：
Kim S.Y. [1 ]
Kang C.H. [2 ]
机构：
[1] School of Mechanical Engineering, Kunsan National University
[2] Department of Mechanical System Engineering, (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology
来源：
Journal of Institute of Control, Robotics and Systems | 2022年 / 28卷 / 11期
关键词：
AAE; EMD; image identification; loss function; navigation accuracy; preprocessing;
D O I：
10.5302/J.ICROS.2022.22.0185
中图分类号：
学科分类号：
摘要：
This paper presents an adversarial auto-encoder (AAE) based preprocessing algorithm for improving image identification and navigation accuracy. The AAE is a fusion of the variational auto-encoder and generative adversarial network. The proposed preprocessing algorithm is a neural network structure for unsupervised image restoration that redesigns the loss function by using the earth mover’s distance (EMD) to improve training efficiency. Using the EMD parameter, it is confirmed that the estimation error was smaller than those of various parameters measuring the distance between the two distributions. In addition, we confirmed that the proposed approach has better efficiency than existing loss functions, such as the mean square error or cross entropy, for artificial intelligence learning. © ICROS 2022.
引用
收藏
页码：999 / 1005
页数：6
相关论文
共 21 条
  • [1] Chung W.Y., Kim S.Y., Park C.G., Kang C.H., Image Dehazing with Scattering Coefficient Estimation using CNN-based Image Regression, Journal of Institute of Control, 27, 11, pp. 890-896, (2021)
  • [2] Kim S.Y., Kang C.H., Training optimization method based on loss function redesign of adversarial auto-encoder, Proc. of KSME Annual Meeting 2021 (In Korean), Gwangju, Korea, pp. 1613-1614, (2021)
  • [3] Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y., Generative adversarial networks, Communications of the ACM, 63, 11, pp. 139-144, (2020)
  • [4] Wang K.C., Vicol P., Lucas J., Gu L., Grosse R., Zemel R., Adversarial distillation of bayesian neural network posteriors, Proc. of International Conference on Machine Learning, pp. 5190-5199, (2018)
  • [5] Kim S.Y., Kang C.H., Knowledge distillation of adversarial auto encoder for underwater navigation, Proc. of 2021 36Th ICROS Annual Conference (In Korean), Yeosu, Korea, pp. 133-134, (2021)
  • [6] Kim S.Y., Kang C.H., Apparatus Operating Method for Image Preprocessing Based on Neural Network and Apparatus of Thereof, (2022)
  • [7] Li S., Kang X., Hu J., Image fusion with guided filtering, IEEE Transactions on Image Processing, 22, 7, pp. 2864-2875, (2013)
  • [8] He C., Qin Y., Cao G., Lang F., Medical image fusion using guided filtering and pixel screening based weight averaging scheme, Journal of Software Engineering, 7, 2, pp. 77-85, (2013)
  • [9] Pham C.C., Ha S.V.U., Jeon J.W., Adaptive guided image filtering for sharpness enhancement and noise reduction, Proc. of Pacific-Rim Symposium on Image and Video Technology, pp. 323-334, (2011)
  • [10] He K., Sun J., Tang X., Guided image filtering, Proc. of European Conference on Computer Vision, pp. 1-14, (2010)
123