Super-resolution reconstruction method based on learning and adaptive trilateral filtering regularization

Abstract

The invention provides a super-resolution reconstruction method based on learning and adaptive trilateral filtering regularization. The super-resolution reconstruction method specifically comprises the following steps: inputting a low-resolution image block sequence; calculating a dictionary D1 of the low-resolution image blocks and a dictionary Dh of the high-resolution image blocks correspondingto the low-resolution image blocks; obtaining a high-resolution initial interpolation image through a non-uniform interpolation method; calculating sparse representation sparse alpha based on the learning dictionary D1; then, based on the learning dictionary Dh, calculating a high-frequency prior image block hi; down-sampling the obtained high-frequency prior image until the size is the same as that of the high-resolution initial interpolation image to obtain a down-sampled high-frequency prior image, and finally superposing the down-sampled high-frequency prior image and the high-resolutioninitial interpolation image to generate a high-resolution iterative initial image; and calculating a regularization parameter lambda and combining with a trilateral filtering method, and calculating and reconstructing a high-resolution image by adopting a loop iteration mode.

Description

technical field [0001] The present invention relates to a super-resolution reconstruction method based on learning and adaptive trilateral filter regularization, an image super-resolution reconstruction method based on learning prior and adaptive trilateral filter regularization in order to reconstruct an image close to the original pure signal The signal is specifically applied to super-resolution filtering reconstruction of multi-view images under the surface state of the aircraft skin. Background technique [0002] Image denoising is a basic task in digital image processing. The central task of this work is to ensure that the image is not transition-smoothed while removing the noise in the image. Since both noise and edge structure belong to the high-frequency components in the image, noise removal and the preservation of detailed information such as edge structure and texture in the image are a pair of contradictions. Therefore, when designing a denoising filter, vario...

AI Technical Summary

Problems solved by technology

In addition, considering that in the application of super-resolution reconstruction, the registration method actually used cannot accurately obtain the registration parameters between frames, in order to reduce the impact of registration errors, alternate estimation and cyclic iteration are used to estimate Reconstruction results, so as to improve the robustness and adaptive ability of the algorithm while improving the step edge and non-step edge preservation ability of the reconstructed image

Images