Research on Denoising Algorithm of Orthopedic CT Image Based on Wavelet Soft Threshold Filtering
Haoyu Liu · 2023
Influenced by relevant conditions, digital images are easily disturbed by external noise in the process of generation, transmission and compression, which makes the image edges and texture details blurred, which is not conducive to the recognition and reading of image information. As far as orthopedic CT images are concerned, when the attenuation coefficients of diseased tissues are very close to those of normal tissues, the existence of noise will reduce the signal-to-noise ratio of the images, which will directly lead to some feature details of the images being submerged in the image noise and unrecognizable. The research on denoising algorithm of orthopedic CT image based on wavelet soft threshold filtering is carried out. In this paper, an improved method based on extreme median filtering and wavelet soft threshold denoising algorithm is proposed to remove the mixed impulse noise and Gaussian white noise in the image. Firstly, the image with mixed noise is filtered by the improved median filtering algorithm based on extreme value, and the impulse noise is removed, so that the image with only Gaussian noise is obtained. The wavelet coefficients obtained are quantized by the improved threshold to obtain the estimated wavelet coefficients. The estimated wavelet coefficients are inversely transformed to reconstruct the image, and the denoised image is obtained. The research shows that wavelet soft threshold filtering has the best denoising effect, MSE, EPI and expert evaluation values are 1.2358, 0.9276 and 88 respectively. This method can protect the edge information and improve the visual effect while effectively denoising, which shows that this method also has high denoising ability.