Image filtering method based on DLSS deep learning super-sampling technology

Abstract

The invention discloses an image filtering method based on a DLSS deep learning super-sampling technology. The method comprises the following steps: obtaining an original image IL; generating a contour template from the original image IL by using a DLSS deep learning super-sampling technology; performing difference on the contour template to obtain an initial interpolation image II; extracting a low-frequency image ILL and a high-frequency image ILH based on the original image ILL; dividing the original image IL into a plurality of to-be-matched blocks; generating a plurality of high-frequencyinformation blocks based on a plurality of to-be-matched blocks divided by the original image IL; splicing the obtained high-frequency information blocks into high-frequency information H with an initial interpolation image II size; superposing the high-frequency information H on the initial interpolation image II to synthesize a super-resolution image IH with an original image IL texture feature; and filtering the super-resolution image IH to obtain a target image. According to the method, the DLSS deep learning super-sampling technology is combined with the mathematical morphology, so thatthe detail processing accuracy when the mathematical morphology is adopted to carry out image processing is effectively improved, and the processing time consumption is shortened.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an image filtering method based on DLSS deep learning super sampling technology. Background technique [0002] Mathematical Morphology is a nonlinear image processing and analysis tool. In the process of image filtering, a filter composed of morphological opening and closing operators can be used to obtain a good filtering effect. Due to the diversity of geometric shapes in the image and the characteristics of noise, it is often necessary to select the appropriate morphological structure element in the morphological filter. Morphology also has a good effect on the processing of satellite cloud images. By processing and extracting the structural features of cloud images, the application of cloud images tends to be objective and quantitative, which reduces human errors and improves the accuracy of forecasting and the degree of automation of weather forecasting. The resear...

AI Technical Summary

Problems solved by technology

[0004] Therefore, the problem to be solved in the present invention is how to improve the accuracy of detail processing and shorten the time-consuming processing when image processing is carried out using mathematical morphology.

Images