Image denoising based on gaussian/bilateral filter and its method noise thresholding

Image Denoising techniques are widely used to remove the noise from the images. Due to the ease of the bilateral filter, it is used very often to remove the noise from the images. In this paper, a novel approach has been proposed to enhanced bilateral filter in conjunction with CNN as a booster to eliminate Gaussian noise from Grey images. Studies reveal that standard CNN using a bilateral filter is the best technique to eliminate Gaussian noise from images along with high PSNR values. This paper also performs a comparative study of the various existing techniques for image denoising with the CNN technique and the applied Bilateral filter Method as a de facto to improve the results in terms of enhanced PSNR values. ECND Net (Enhanced CNN) applied to noisy images with standard deviation σ = 15 gives PSNR values up to 32.81 In comparison to this when both bilateral filter and deep CNN applied, in conjunction produces improved PSNR values up to 34.73 along with the equivalent standard deviation. The results in this work reveal better performance in terms of PSNR as compared to other methods. The test result proves that the bilateral filter Method along with CNN can improve the quality of restored images significantly better.

Download Full-text

An Efficient Image Denoising Scheme for Higher Noise Levels Using Spatial Domain Filters

Biomedical & Pharmacology Journal ◽

10.13005/bpj/1415 ◽

2018 ◽

Vol 11 (2) ◽

pp. 625-634 ◽

Cited By ~ 4

Author(s):

Anchal Anchal ◽

Sumit Budhiraja ◽

Bhawna Goyal ◽

Ayush Dogra ◽

Sunil Agrawal

Keyword(s):

Image Denoising ◽

Analog Circuits ◽

Anisotropic Diffusion ◽

Additive White Gaussian Noise ◽

Bilateral Filter ◽

Noise Levels ◽

Significant Information ◽

Edge Information ◽

Diffusion Filtering ◽

Lower Noise

Image denoising is one of the fundamental image processing problem. Images are corrupted with additive white Gaussian noise during image acquisition and transmission over analog circuits. In medical images the prevalence of noise can be perceived as tumours or artefacts and can lead to first diagnosis. Similarly in satellite images the visibility of images is significantly degraded due to noise, hence the image denoising is of vital importance. There are many denoising mechanisms given in literature are able to work well on lower noise levels but their performance degrades with increasing noise levels. If higher amount of filtering is applied it leads to degradation or removal of edges from the image and hence significant information. In this paper, we proposed an algorithm in which we are able to address the problem of image denoising at higher noise levels while preserving the edge information. The standard bilateral filter does not provides good results at higher noise levels. Hence we proposed to combine robust bilateral filtering with anisotropic diffusion filtering as the anisotropic diffusion perform the smoothing of homogenous regions without blurring the edges. Experimental results show that the proposed method works better for higher Nosie levels in terms of PSNR values and Visual quality.

Download Full-text