A Fast Non-switching Random-Valued Impulse Noise Denoising Algorithm

被引：0
|
作者：
Xu S.-P. [1 ]
Liu T.-Y. [1 ]
Luo J. [1 ]
Zhang G.-Z. [1 ]
Li C.-X. [1 ]
机构：
[1] School of Information Engineering, Nanchang University, Nanchang, 330031, Jiangxi
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2019年 / 47卷 / 12期
关键词：
Computational efficiency; Convolutional neural network (CNN); Denoising; Noise ratio; Non-switching; Random-valued impulse noise;
D O I：
10.3969/j.issn.0372-2112.2019.12.023
中图分类号：
学科分类号：
摘要：
To improve denoising effect and execution efficiency of the existing switching random-valued impulse noise (RVIN) removal algorithms, we proposed a convolutional neural network (CNN)-based fast non-switching RVIN denoising algorithm (FNRDA), which consists of two serial CNN-based modules, i.e., noise detector and denoiser.Specifically, we first used the noise detector to detect some randomly selected pixels of a given noisy image.Then we divided the number of the detected noisy pixels by the total number of detected pixels to convert it into noise ratio, which can be treated as a measure of the distortion level for the given noisy image.Finally, according to the estimated noise ratio, we exploited the corresponding pre-trained non-switching CNN-based denoising model to remove RVIN efficiently with high quality.Experimental results show that, the proposed non-switching RVIN removal algorithm outperforms the classical switching ones in terms of denoising effect and execution efficiency across various noise ratios.This advantage makes it more attractive and practical in the real-time applications such as image restoration, signal detection, wireless communication, etc. © 2019, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码：2622 / 2629
页数：7
相关论文
共 24 条
  • [1] Xu Q., Li Y.H., Guo Y.J., Et al., Random-valued impulse noise removal using adaptive ranked-ordered impulse detector, Journal of Electronic Imaging, 27, 1, (2018)
  • [2] Garnett R., Huegerich T., Chui C., Et al., A universal noise removal algorithm with an impulse detector, IEEE Transactions on Image Processing, 14, 11, pp. 1747-1754, (2005)
  • [3] Dong Y.Q., Chan R.H., Xu S.F., A detection statistic for random-valued impulse noise, IEEE Transactions on Image Processing, 16, 4, pp. 1112-1120, (2007)
  • [4] Liu L.C., Chen C.L.P., Zhou Y.C., Et al., A new weighted mean filter with a two-phase detector for removing impulse noise, Information Sciences, 315, pp. 1-16, (2015)
  • [5] Turkmen I., The ANN based detector to remove random-valued impulse noise in images, Visual Communication and Image Representation, 34, pp. 28-36, (2016)
  • [6] Soleimany S., Branch Q., Hamghalam M., Et al., A novel random-valued impulse noise detector based on MLP neural network classifier, Proceedings of the 2017 Artificial Intelligence and Robotics (IRANOPEN), pp. 165-169, (2017)
  • [7] Zhou F.-Y., Jin L.-P., Dong J., Review of convolutional neural network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)
  • [8] Li B.-Q., He Y.-Y., He L.-J., Et al., Asymmetric parallel semantic segmentation model based on full convolutional neural network, Acta Electronica Sinica, 47, 5, pp. 1058-1064, (2019)
  • [9] Li K., Li Y.-M., Hu X.-M., Et al., A robust and accurate object tracking algorithm based on convolutional neural network, Acta Electronica Sinica, 46, 9, pp. 2087-2093, (2018)
  • [10] Zhang K., Zuo W.M., Chen Y.J., Et al., Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising, IEEE Transactions on Image Processing, 26, 7, pp. 3142-3155, (2016)
123