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

Super-resolution method based on convolutional neural network

A convolutional neural network and super-resolution technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve problems such as high hardware requirements and time loss, and achieve good visual effects

Active Publication Date: 2017-12-22
DALIAN UNIV OF TECH
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0027] The purpose of the present invention is to address the above problems, provide a method that is more suitable for the fusion of super-resolution reconstruction algorithms for a single image, solve the problems of high time loss and high hardware requirements for algorithm implementation, and at the same time aim at the characteristics of different super-resolution algorithms , analyze and select the existing super-resolution algorithm, so that the selected super-resolution algorithm can achieve complementary advantages after fusion, and break through the disadvantages of the existing super-resolution algorithm

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
  • Super-resolution method based on convolutional neural network
  • Super-resolution method based on convolutional neural network
  • Super-resolution method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] figure 1 It is a flowchart of a super-resolution algorithm for fusion based on a convolutional neural network proposed by the present invention. In the figure, k represents the size of the convolution kernel, n represents the number of feature maps, and p represents boundary expansion. The purpose is to ensure that the size of the image before and after the convolution operation remains unchanged, and the step size of each convolution step is set to 1. The network proposed by the present invention can be divided into three parts, joint strategy, feature extraction and deep fusion. This part of the joint strategy is to generate the primary high-resolution image through the bicubic interpolation and FSRCNN of the low-resolution image, and then use the three convolutional layers of the feature extraction part to perform feature extraction. In the final depth fusion part, the The previously extracted features are fused with a 20-layer deep convolutional neural network to o...

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 provides a super-resolution method based on a convolutional neural network, and is aimed at searching a single-image super-resolution method which is fast in speed and high in restoration quality through a deep convolutional neural network. The invention provides a method of super-resolution reconstruction algorithm fusion more suitable for a single image to solve the problems that the time loss is great, hardware demands needed for realization of algorithms are high and the like. For features of different super-resolution algorithms, conventional super-resolution algorithms are analyzed and selected, so the selected super-resolution algorithms achieve advantage complementation after being fused, and the disadvantages for realization of the conventional super-resolution algorithms are overcome.

Description

technical field [0001] Image super-resolution technology (Image Super-Resolution, referred to as SR) is to obtain a high-resolution (High Resolution, referred to as HR) image based on one or more low-resolution (Low Resolution, referred to as LR) images. Being able to provide images with better visual effects and provide more image information is a classic low-level problem in the field of computer vision. It is divided into multi-frame image super-resolution and single-frame image super-resolution (Single Image Super-Resolution, referred to as SISR). The former utilizes multiple similar low-resolution images to reconstruct an image with high resolution. However, SISR only gives a low-resolution image, and restores a high-resolution image with a good visual experience based on limited information. The present invention aims to use a deep convolutional neural network to explore a single image super-resolution method with high speed and high restoration quality. Background t...

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
IPC IPC(8): G06T3/40G06N3/08
CPCG06N3/084G06T3/4076G06T2207/20084
Inventor 杨鑫王鑫许可尹宝才张强
Owner DALIAN UNIV OF TECH
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