A fast image super-resolution reconstruction method based on deep learning

A technology of super-resolution reconstruction and deep learning, which is applied to the improved algorithm of the training process of the deep network dual-branch structure, and the field of fast image super-resolution reconstruction, which can solve the problem of large memory space load, reduce the ringing phenomenon, reduce training Effects of reduced burden and good edge information

Inactive Publication Date: 2019-05-17
KUNMING UNIV OF SCI & TECH
View PDF8 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Step1, select the image training set and test set, and process to obtain low-resolution image blocks and high-resolution image blocks; in the step Step1, select the high-resolution image BSD200 data set that includes 200 png format and 91 bmp format for use The image set Train91 is used as the model training set, and Set5...

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 fast image super-resolution reconstruction method based on deep learning
  • A fast image super-resolution reconstruction method based on deep learning
  • A fast image super-resolution reconstruction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Embodiment 1: as Figure 1-5 As shown, a fast image super-resolution reconstruction method based on deep learning includes the following steps:

[0036] Step1, select the image training set and test set, and process to obtain low-resolution image blocks and high-resolution image blocks; in the step Step1, select the high-resolution image BSD200 data set that includes 200 png format and 91 bmp format for use The image set Train91 is used as the model training set, and Set5, Set14, BSD100, and Urban100 are selected as the standard test set; in order to solve the problem of excessive memory space load, when the magnification factor is 3, the image is cut into 48×48 low-resolution images Image block (Low Resolution, LR) and the corresponding 144×144 high-resolution image block y HR (High Resolution, HR);

[0037] Step2. Use the deep neural network to perform feature extraction on the low-resolution image, refine the feature of the nested network, and sub-pixel up-sampling...

Embodiment 2

[0049] Embodiment 2: as Figure 1-5 As shown, a fast image super-resolution reconstruction method based on deep learning includes the following steps:

[0050] Step1, select the training set and test set according to the model training scheme and process it: the present invention continues to use the commonly used training data sets for image super-resolution reconstruction, i.e. BSD200 and Train91, wherein the former contains 200 high-resolution natural images in png format The scene image, which contains 91 high-resolution flower images in bmp format.

[0051] In the training data preparation stage, considering that the image set is too small (a total of 291 images) is prone to overfitting, the training data set is enhanced to generate a data set eight times larger than the original image (a total of 2328 images); In order to solve the problem of excessive memory space load, when the magnification factor is 3, the training image is cut into low-resolution image blocks of 48...

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 fast image super-resolution reconstruction method based on deep learning, and belongs to the field of image processing. The method comprises the following steps of selectingan image training set and a test set, and performing feature extraction, nested network feature refinement and sub-pixel up-sampling operation on a low-resolution image by using a deep neural networkto obtain high-resolution detail residual information of the image; carrying out transposition convolution processing on the low-resolution image to obtain high-resolution space low-frequency featureinformation of the image; combining the high-resolution detail residual information of the image with the high-resolution space low-frequency characteristic information to obtain a high-resolution reconstruction result of image estimation; performing loss value measurement on the high-resolution reconstruction result of the image estimation and the high-resolution image block; updating the network weight by using an Adam operator to obtain a trained network model; and inputting a low-resolution image into the trained network model to obtain a high-resolution reconstructed image. According tothe method, the super-resolution reconstruction of the image is accelerated, and a good reconstruction effect is kept.

Description

technical field [0001] The invention relates to a fast image super-resolution reconstruction method based on deep learning, in particular to convolution network parameter adjustment in deep learning, loss function optimization, and an improved algorithm for the training process of deep network double-branch structure, belonging to the technical field of image processing . Background technique [0002] Single image super-resolution reconstruction technology (Single Image Super-Resolution, SISR) refers to a given single low-resolution image, through a specific algorithm to restore the details of the image lost due to downsampling, so as to obtain more detailed information , The process of high pixel density images with more delicate picture quality. Due to the ability to recover finer details with limited information, this technology has been widely used in various application scenarios, such as high-definition television broadcasting, video surveillance, and satellite 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
IPC IPC(8): G06T3/40
Inventor 刘辉梁祖仲
Owner KUNMING UNIV OF SCI & TECH
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