A despeckling method using stationary wavelet transform and convolutional neural network

  • Kim,Moonheum
  • Lee, Junghyun
  • Jeong, Je chang
Citations

SCOPUS

0

초록

In this paper, a deep convolutional neural network (CNN) is used to remove speckle noise from synthetic aperture radar (SAR) images. However, only applying CNN to remove noise causes an under-fitting problem. To overcome this issue, we suggest to use stationary wavelet transform (SWT) to the images as a pre-processing. Afterward, the resultant sub-band images are utilized to construct the similar sub-band images to the original images by training the CNNs. The training process is carried out by considering a large multi-temporal SAR image and its multi-look version. In the experiment result of this paper, the proposed method showed better performance compared to other denoising algorithms in regard to PSNR and SSIM.

키워드

Convolutional Neural NetworkSARspeckle noiseStationary Wavelet TransformConvolutionDeep neural networksImage compressionNeural networksRadar imagingSpeckleSynthetic aperture radarConvolutional neural networkDe-noising algorithmDeep convolutional neural networksFitting problemsMulti-temporal SAR imagesSpeckle noiseStationary wavelet transformsSynthetic aperture radar (SAR) imagesWavelet transforms
제목
A despeckling method using stationary wavelet transform and convolutional neural network
저자
Kim,MoonheumLee, JunghyunJeong, Je chang
DOI
10.1109/IWAIT.2018.8369651
발행일
2018-05
유형
Conference Paper
저널명
2018 International Workshop on Advanced Image Technology, IWAIT 2018
페이지
1 ~ 4