Image
denoising is aimed at the removal of noise which may corrupt an image
during
its acquisition or transmission. De-noising of the corrupted image by
Gaussian noise using wavelet transform is very effective way because of
its ability to capture the energy of a signal in few larger values.
This paper proposes a threshold selection method for image
de-noising based on the
statistical parameters which depended on sub-band data. The threshold
value is computed based on
the number of coefficients in each scale j of wavelet
decomposition and the noise variance in
various sub-band. Experimental results in PSNR on several test images
are compared for different
de-noise techniques.
| Title: | Analysis the Statistical Parameters of the Wavelet Coefficients for Image Denoising |
| Authors: | Nguyễn, Vĩnh An |
| Keywords: | Thống kê, Tách nhiễu ảnh, Hệ số wavelet |
| Issue Date: | 2013 |
| Publisher: | H. : ĐHQGHN |
| Citation: | 7 tr. |
| Abstract: | Image
denoising is aimed at the removal of noise which may corrupt an image
during
its acquisition or transmission. De-noising of the corrupted image by
Gaussian noise using wavelet transform is very effective way because of
its ability to capture the energy of a signal in few larger values.
This paper proposes a threshold selection method for image
de-noising based on the
statistical parameters which depended on sub-band data. The threshold
value is computed based on
the number of coefficients in each scale j of wavelet
decomposition and the noise variance in
various sub-band. Experimental results in PSNR on several test images
are compared for different
de-noise techniques. |
| URI: | http://repository.vnu.edu.vn/handle/11126/13007 |
| Appears in Collections: | Natural Sciences and Technology |
Nhận xét
Đăng nhận xét