首页> 外文会议>Information Science and Engineering (ICISE), 2009 >Image Denoising Method Based on Nonsubsampled Contourlet Transform and Bandelet Transform
【24h】

Image Denoising Method Based on Nonsubsampled Contourlet Transform and Bandelet Transform

机译:基于非下采样Contourlet变换和Bandelet变换的图像去噪方法

获取原文

摘要

The wavelet transform used in the second generation bandelet transform cannot capture singularities well, so we replace wavelet transform with nonsubsampled contourlet transform, then we get a new image denoising method base on nonsubsampled contourlet transform and bandelet transform. Numerical test applied on standard images which were contaminated with additive Gaussian white noise show that our method can significantly outperform nonsubsampled contourlet transform and bandelet transform in visual quality, and the PSNR is also increased by more than 0.4 dB.
机译:第二代bandelet变换中使用的小波变换不能很好地捕获奇异点,因此我们用非下采样contourlet变换代替小波变换,然后得到了一种基于非下采样contourlet变换和bandelet变换的新图像去噪方法。对被加性高斯白噪声污染的标准图像进行的数值测试表明,我们的方法在视觉质量上可以显着优于未采样的Contourlet变换和bandelet变换,并且PSNR也提高了0.4 dB以上。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号