Depth reduction of RGB image data and reduction of point noise based on metric learning method

In this paper, a method of data depth reduction based on metric learning method in reducing point noise in different images is proposed. In order to be more accurate in reviving depth from data, noise variance is also calculated for each separate scale. In this way, our method becomes more sensitive to noise detection. The quantitative and qualitative results obtained from the implementation and calculation of the PSNR parameter of this method show that the proposed method of this paper has given a good answer compared to previous methods for noise elimination and has performed better in maintaining sharp corners and sharp features.