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

A Computational Method for Single Image Super-resolution with Dual-Channel Convolutional Neural Networks

A convolutional neural network, super-resolution technology, applied in the field of single-image super-resolution computing, can solve problems such as unsatisfactory high-frequency features

Inactive Publication Date: 2019-12-03
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The SRCNN model proves that it is simple and feasible to directly learn the end-to-end mapping between LR and HR, and the effect is also very good, but the reconstructed high-frequency features are still not satisfactory

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
  • A Computational Method for Single Image Super-resolution with Dual-Channel Convolutional Neural Networks
  • A Computational Method for Single Image Super-resolution with Dual-Channel Convolutional Neural Networks
  • A Computational Method for Single Image Super-resolution with Dual-Channel Convolutional Neural Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The present invention will be described in detail below in conjunction with the accompanying drawings and implementation examples.

[0079] For the color RGB image, first convert it into a YCbCr image, perform super-resolution reconstruction on the Y component, and use bicubic interpolation to enlarge the Cb and Cr components, and then convert the YCbCr image into an RGB image; for the grayscale image, directly in Super-resolution reconstruction is performed on the grayscale image.

[0080] Such as figure 1 As shown, a single-image super-resolution calculation method based on a dual-channel input convolutional neural network includes the following steps:

[0081] (1) The LR sample image y used for training is interpolated and enlarged to the image X l , image X l Same size as original HR.

[0082] (2) Use the morphological component analysis method to decompose the LR image obtained in step (1), and extract the texture part of the LR image; use the same method to e...

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 a two-channel convolutional neural network-based single image super-resolution calculation method. The method comprises the steps of (1) performing fuzzy degradation processing on a known high-resolution image to obtain a low-resolution image with the same size; (2) decomposing the obtained low-resolution image after the fuzzy processing in the step (1) into a texture part and a smooth structure part of the low-resolution image, and obtaining a texture part and a smooth structure part of the high-resolution image; (3) combining the low-resolution texture part obtained in the step (2) and an original low-resolution image to obtain a two-channel input, and obtaining an output of the high-resolution texture part; (4) combining the obtained output of the high-resolution texture part in the step (3) and the original low-resolution image to obtain a final image super-resolution reconstruction result, thereby finishing super-resolution reconstruction; and (5) calculating a difference value between the high-resolution texture parts obtained in the steps (4) and (2) to obtain texture part loss, and minimizing a sum of the texture loss and image loss to optimize network structure parameters.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a single-image super-resolution calculation method of a dual-channel convolutional neural network, which is applicable to various computer vision tasks, such as face recognition, target tracking, license plate recognition and the like. Background technique [0002] Single image super-resolution (SR, Super-Resolution) technology refers to the process of restoring a low-resolution (LR, Low-Resolution) image into a high-resolution (HR, High-Resolution) image by software. This technology has a wide range of applications, such as video surveillance, medical imaging, remote sensing satellite imaging, etc. Existing SR rate algorithms can be divided into three categories: interpolation-based [1], reconstruction-based [2] and learning-based methods [3-10]. Among them, the image SR algorithm based on learning learns the functional mapping relationship between LR and H...

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 Patents(China)
IPC IPC(8): G06T3/40G06T5/00
CPCG06T3/4053G06T5/003G06T2207/10004G06T2207/20081G06T2207/20084
Inventor 李春平贾慧秒周登文
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
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