Enhance Visual Recognition Under Adverse Conditions via Deep Networks

@article{Liu2019EnhanceVR,
  title={Enhance Visual Recognition Under Adverse Conditions via Deep Networks},
  author={Ding Liu and Bowen Cheng and Zhangyang Wang and H. Zhang and T. Huang},
  journal={IEEE Transactions on Image Processing},
  year={2019},
  volume={28},
  pages={4401-4412}
}
  • Ding Liu, Bowen Cheng, +2 authors T. Huang
  • Published 2019
  • Computer Science, Mathematics, Medicine
  • IEEE Transactions on Image Processing
  • Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural networks have been extensively exploited in the techniques of low-quality image restoration and high-quality image recognition tasks, respectively, few studies have been done on the important problem of recognition from very low-quality images. This paper… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 18 CITATIONS

    Effects of Image Degradations to CNN-based Image Classification

    VIEW 1 EXCERPT
    CITES METHODS

    Connecting Image Denoising and High-Level Vision Tasks via Deep Learning

    • Ding Liu, B. Wen, +3 authors T. Huang
    • Computer Science, Medicine, Mathematics
    • IEEE Transactions on Image Processing
    • 2020
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Survey of Face Detection on Low-Quality Images

    • Yuqian Zhou, Ding Liu, T. Huang
    • Computer Science
    • 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)
    • 2018
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study

    • W. Yang, Y. Yuan, +65 authors Likun Qin
    • Mathematics, Medicine, Computer Science
    • IEEE Transactions on Image Processing
    • 2020
    VIEW 1 EXCERPT
    CITES METHODS

    Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 53 REFERENCES

    Understanding how image quality affects deep neural networks

    VIEW 1 EXCERPT

    How Image Degradations Affect Deep CNN-Based Face Recognition?

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Studying Very Low Resolution Recognition Using Deep Networks

    Robust Single Image Super-Resolution via Deep Networks With Sparse Prior

    VIEW 1 EXCERPT

    Low-Quality Video Face Recognition with Deep Networks and Polygonal Chain Distance

    VIEW 1 EXCERPT

    Large-Scale Video Classification with Convolutional Neural Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL