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

Method for realizing super resolution for image

A super-resolution and image technology, which is applied in the field of computer vision, can solve the problems of stopping, the speed cannot meet the practical requirements, and does not consider the engineering practicability, etc., and achieve the effect of fast and fast speed

Inactive Publication Date: 2016-11-02
SHENZHEN INST OF FUTURE MEDIA TECH +1
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technology mainly stays in the field of scientific research, and does not consider engineering practicability. Although some super-resolution methods can achieve better results, their speed cannot meet the practical requirements

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
  • Method for realizing super resolution for image
  • Method for realizing super resolution for image
  • Method for realizing super resolution for image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0010] figure 1 It is a schematic flow chart of an embodiment of the present invention.

[0011] The processing steps are described in detail below:

[0012] A1. Data preprocessing: (101, 102 in the figure)

[0013] First, a data set composed of a certain number of pictures is obtained, and then Bicubic (bicubic interpolation) downsampling is performed on the pictures in the data set at a ratio of 3 times, and then Bicubic upsampling is performed to obtain an image with a lower resolution. Then take 33*33 small image blocks for low-resolution images, so that 100 512*512 images can get about 500,000 training set images. We take 20% of them to form the test set to test the final performance of the network, and 10% as the verification set, which is mainly used to select the hyperparameters of the network.

[0014] A2. Design of Convolutional Neural Network Network ( figure 1 Middle 103), in the present embodiment, convolutional neural network has 4 layers altogether:

[0015...

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 relates to a method for realizing super resolution for an image and belongs to the computer vision field. The method includes the following steps of: A1, data preprocessing: a certain number of high-resolution natural images are adopted to form a data set, a certain number of image blocks are extracted from the data set, Bicubic interpolation down-sampling and up-sampling in three times are carried out on the image blocks, and low-resolution images can be obtained; A2, network structure design: a designed convolutional neural network has 4 layers altogether; A3, hyper parameter selection: parameters such as network learning rate, learning momentum and batch_size are determined; and A4, network training and super parameter optimization: the convolutional neural network of all images in the training set from low-resolution images to corresponding high-resolution images is trained, and after any one image is inputted into the trained network, a high-resolution image can be obtained, so that the super resolution of the image can be realized.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for super-resolution of a single image. Background technique [0002] Image super-resolution is to upgrade low-resolution images to high-resolution through certain algorithms. High-resolution images have higher pixel density, more detailed information, and more delicate picture quality. The most direct way to obtain high-resolution images is to use high-resolution cameras, but in practical applications, due to cost and process constraints, most occasions do not use high-resolution, super-resolution cameras for image processing. signal acquisition. Therefore, there is a great application demand for obtaining super-resolution images through certain algorithms. The techniques currently used for super-resolution generally include: (1) methods based on interpolation; (2) methods based on models; (3) methods based on learning. The basic idea of ​​the learning-based method is...

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): G06T3/40
CPCG06T3/4053G06T2207/20081G06T2207/20084
Inventor 王好谦安王鹏王兴政张永兵李莉华戴琼海
Owner SHENZHEN INST OF FUTURE MEDIA 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

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