Noise reduction method of weldment radiographic image based on wavelet transform and bilateral filtering

In order to solve the problem that the noise reduction effect of the traditional threshold function is not ideal, a new threshold function between the soft and hard threshold was constructed, which could solve the problem of discontinuity, and could make the estimated wavelet coefficient which was greater than the threshold part gradually approach the original wavelet coefficient. At the same time, an improved algorithm was proposed to process the radiographic image after wavelet transform, the utmost image denoising was achieved , and the edge information and details of the image was protected. Experimental results showed that compared with the traditional wavelet transform method, the PSNR of the processed image by the improved algorithm was increase by 28.2 dB after algorithm improvement, and the structural similarity could reach 99.1%, the better denoising and edge protection effects were obtained.