Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image super-resolution reconstruction algorithm based on shallow convolution neural network and deep convolution neural network

A convolutional neural network and super-resolution reconstruction technology, which is applied in the field of improvement combining shallow and deep networks, achieves fast reconstruction, low time complexity, and reduced ringing effects

Inactive Publication Date: 2017-10-10
TIANJIN UNIV
View PDF1 Cites 90 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Third, it is necessary to improve the speed of large image processing.

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 super-resolution reconstruction algorithm based on shallow convolution neural network and deep convolution neural network
  • Image super-resolution reconstruction algorithm based on shallow convolution neural network and deep convolution neural network
  • Image super-resolution reconstruction algorithm based on shallow convolution neural network and deep convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0034] The present invention provides a convolutional neural network combining shallow and deep networks, which extracts the image features of low-resolution sample image blocks and high-resolution sample image blocks, and learns the nonlinear mapping relationship between them. The network is trained and tested. The model widens the network, increases the number of parameters, and effectively prevents overfitting. At the same time, different two-way network structures are designed to capture different effective features, and more effective features are conducive to improving the reconstruction effect. The model in this paper is a parallel model composed of deep residual branches and shallow branches. The two inputs of the parallel network are the same LR image, and the HR image is finally obtained through the model in this paper. The basic framework of the...

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 super-resolution reconstruction algorithm based on a shallow convolution neural network and a deep convolution neural network. The method comprises the following steps: 1) selecting a training sample and a testing sample; 2) performing extracting, mapping, upsamping and multi-scale conversion to the deep network characteristics; 3) extracting the characteristics of the shallow network; and 4) combining the shallow network and the deep network. Compared with the prior art, with regard to the single image reconstruction and video sequence reconstruction, the algorithm of the invention can accurately and effectively reconstruct the model of a high-resolution image so as to obtain a good reconstruction effect. In addition, multi-scale detail characteristic extraction is achieved, and the algorithm has better results than that of other existing algorithms. The reconstruction speed is also fast.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to the optimization of convolutional neural networks in deep learning, especially the improvement of the combination of shallow and deep networks. Background technique [0002] Convolutional Neural Networks (CNN) have shown excellent performance in various computer vision fields, such as image classification, object detection, semantic segmentation, and action recognition. In many fields, we all need high-quality images. The super-resolution (Single Image SuperResolution, SISR) reconstruction of a single frame image refers to the reconstruction of a known single low-resolution image into a high-resolution image with higher pixel density, more delicate picture quality and more details. image, so as to meet the demand for higher picture quality. Image super-resolution reconstruction technology has a wide range of applications in various fields such as video surveillance, medical imagin...

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): G06T3/40G06N3/08
CPCG06N3/084G06T3/4053
Inventor 李素梅范如雷国庆侯春萍
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com