Image compressed sensing reconstruction method, system, equipment and medium

An image compression and image technology, applied in image enhancement, image coding, image data processing, etc., can solve the problems of poor reconstruction effect and low rate-distortion performance, achieve wide applicability, wide application prospects, and improve image reconstruction capabilities Effect

Pending Publication Date: 2022-07-12
XI AN JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the technical problems existing in the prior art, the present invention provides an image compression sensing reconstruction method, system, equipment and medium to solve the problem of the compression reconstruction algorithm based on compression sensing compared to the traditional image at an extremely low sampling rate. The compression algorithm has the technical problems of low rate-distortion performance and poor reconstruction effect

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image compressed sensing reconstruction method, system, equipment and medium
  • Image compressed sensing reconstruction method, system, equipment and medium
  • Image compressed sensing reconstruction method, system, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0104] This embodiment provides an image compressed sensing reconstruction method, which specifically includes the following steps:

[0105] Step 1. Build the grayscale image Gaussian noise denoising network model based on image prior modeling; the grayscale image Gaussian noise denoising network model based on image prior modeling includes several levels of noise models; The first-level noise model includes the first convolutional layer, the first multi-scale fusion module, the first supervised attention module, the second multi-scale fusion module, the channel merging module, the second supervised attention module, the second convolutional layer, the attention The force module, the first residual connection module, the third convolutional layer and the second residual connection module; wherein, the upper-level noise model is the preprocessing model of the next-level noise model, which is used to perform the next-level noise model. Fine-tune training.

[0106] The working p...

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

No PUM Login to view more

Abstract

The invention discloses an image compressed sensing reconstruction method, system and device and a medium, and the method comprises the steps: carrying out the degradation processing of a to-be-processed original image through a preset first de-noising model, and obtaining a degraded image; performing compression reconstruction processing on the degraded image by using an improved approximate message passing algorithm based on deep learning to obtain an image compression sensing reconstruction result; wherein the improved approximate message passing algorithm based on deep learning is an algorithm for replacing a de-noising device in the approximate message passing algorithm based on deep learning with a preset second de-noising device model; the preset first de-noising device model and the preset second de-noising device model are both gray level image Gaussian noise de-noising device network models based on image prior modeling; according to the method, the noise statistical distribution of the de-noising device and the de-noising capability curve are used for further fine division of the noise interval used by the algorithm, and the image reconstruction capability is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and particularly relates to an image compressed sensing reconstruction method, system, device and medium. Background technique [0002] With the continuous development of information technology, the total amount of information is also increasing. The huge amount of information and higher real-time performance put forward higher requirements for the transmission and storage of signals. As one of the main carriers of information, images and videos, The interactive technology of images and videos has greatly influenced the development of communication technologies; therefore, efficient image and video compression algorithms have gradually become a hotspot of academic and industrial research. [0003] Compressed sensing theory is a new type of image compression theory, which states that when the signal can be sparsely represented, it can be sampled at a sampling frequency far less th...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T9/00G06T5/00G06N3/04G06N3/08G06V10/80G06V10/82G06K9/62
CPCG06T9/002G06T5/002G06N3/08G06N3/048G06N3/045G06F18/253
Inventor 侯兴松李子昂
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap