Improved Adaptive Bilateral Filter

Bilateral filtering is a non-linear filtering method that combines spatial proximity and pixel similarity of an image. It is good to preserve the high-frequency details in the image and smooth the number while preserving the strong edges. The traditional bilateral filtering algorithm needs to preset the spatial standard deviation and the gray scale deviation according to experience, the versatility is poor, the algorithm operation time is long and the effect is not ideal. Therefore, we proposed an adaptive bilateral filtering algorithm based on genetic algorithm. However, since the bilateral filtering preserves too much high-frequency information during denoising, the filtering effect on high-frequency noise is not ideal. Therefore, based on the bilateral filtering algorithm combined with wavelet threshold decomposition and least squares filtering method, an adaptive bilateral filtering algorithm based on wavelet threshold is proposed. Firstly, the low-frequency and high-frequency coefficients of the image are obtained by wavelet decomposition. Then the low-frequency part is processed by the adaptive bilateral filtering algorithm based on the genetic algorithm, and the least-squares filtering method is used to process the high-frequency part in this paper. The experimental results show that the proposed method has a good effect on the removal of random stationary noise.