Compressive Sensing Image Reconstruction Method Based on Deep Learning
A technology of region of interest and compressed sensing, which is applied in the field of region of interest compressed sensing image reconstruction, can solve problems such as waste of resources, inaccurate extraction results, and affecting algorithm speed
Active Publication Date: 2021-09-10
XIDIAN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
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
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] The present invention will be further described below in conjunction with the accompanying drawings.
[0042] refer to figure 1 , to further describe the specific implementation steps of the present invention.
[0043] Step 1. Construct the region-of-interest-aware reconstruction network.
[0044] The region-of-interest extraction sub-network in the region-of-interest-aware reconstruction network is constructed, which includes an eight-layer initial unified observation recovery module and a six-layer salient target region extraction module.
[0045] The structure of the initial unified observation recovery module is as follows: first convolution layer → deconvolution layer → second convolution layer → first residual block → second residual block → third residual block → third volume Product layer → fourth convolutional layer.
[0046] Set the parameters of each layer of the initial unified observation recovery module.
[0047] The parameters of each layer of the fir...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a deep learning-based method for reconstructing images of compressed sensing regions of interest, which overcomes the problem of low reconstruction quality of regions of interest in images under limited observation resources in existing compressed sensing image reconstruction methods, and realizes The steps are: (1) constructing the region-of-interest perceptual reconstruction network; (2) training the region-of-interest perceptual reconstruction network; (3) preprocessing the natural image to be reconstructed; (4) obtaining the first observation information ; (5) Obtain the initial restoration image; (6) Obtain the image of the region of interest; (7) Obtain the second observation information; (8) Reconstruct the perceptual restoration image. The present invention uses the method of two observations to allocate more observation resources for the region of interest, 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...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/50G06T3/00
Inventor 谢雪梅毛思颖王陈业赵至夫石光明
Owner XIDIAN UNIV