A region-of-interest compressed sensing image reconstruction method based on deep learning

Abstract

The invention discloses a region-of-interest compressed sensing image reconstruction method based on deep learning, which overcomes the problem of low reconstruction quality of an interested region inan image under limited observation resources in the existing compressed sensing image reconstruction method, and comprises the following implementation steps of: (1) constructing an interested regionsensing reconstruction network; (2) training a region-of-interest perception reconstruction network; (3) preprocessing the natural image to be reconstructed; (4) obtaining first observation information; (5) obtaining an initial recovery image; (6) obtaining a region-of-interest image; (7) obtaining second observation information; And (8) reconstructing the perception recovery image. According tothe method, more observation resources are distributed to the region of interest by using a twice observation method, and the texture details of the region of interest in the reconstructed image are clear.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a deep learning-based compressed sensing image reconstruction method for regions of interest in the technical field of image reconstruction. The present invention can be used to obtain higher-quality images of interest regions at equivalent observation rates when natural images are reconstructed. Background technique [0002] With the rapid development of information technology, people's demand for information has increased dramatically. Compressed sensing theory has brought a revolutionary breakthrough to signal acquisition technology. It shows that under certain conditions, the signal can be sampled at a frequency much lower than the Nyquist frequency, and the original signal can be reconstructed with high probability through numerical optimization problems, thus saving Lots of resources. Compared with the traditional optimization solution method, the c...

AI Technical Summary

Problems solved by technology

There are two shortcomings in this method. First, the reconstruction process in this method is completed by the traditional iterative algorithm, which makes the time complexity very high and affects the speed of the algorithm. Second, the extraction of the region of interest in this method Using traditional classification algorithms, the extraction results are not accurate enough

Under fixed observation resources, this method can improve the utilization rate of observation resources by combining two observation resources. However, there are still two shortcomings in this method. First, because only the second The observation information of the first time is used to reconstruct the image, but the first observation information is not used, resulting in a waste of resources; second, this method can only process grayscale images, and cannot perform compressed sensing on color images

Images