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

Image super-resolution enhancement method based on bidirectional recurrent convolutional neural network

A technology of resolution enhancement and recursive convolution, applied in the field of image super-resolution enhancement based on bidirectional recursive convolutional neural network, can solve problems such as inability to obtain high-resolution images, and achieve the effect of increasing the size of the receptive field

Active Publication Date: 2019-03-15
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, limited by imaging hardware devices with limited resolution, people cannot obtain very high-resolution images

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 enhancement method based on bidirectional recurrent convolutional neural network
  • Image super-resolution enhancement method based on bidirectional recurrent convolutional neural network
  • Image super-resolution enhancement method based on bidirectional recurrent convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.

[0034] The main idea of ​​the present invention is: 1) the present invention utilizes the bidirectional recursive convolutional neural network to learn the spatial positional relationship of adjacent image blocks in the image, and assists the learning of the mapping relationship between high and low resolution images; 2) the present invention Utilize the recursive structure in the bidirectional recursive convolutional neural network to increase the size of the receptive field in the process of generating high-resolution image blocks, and improve the accuracy of the generated high-resolution image blocks; 3) the present invention effectively utilizes the distance between adjacent image blocks Consistency const...

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 enhancement method based on a bidirectional recursion convolution nerve network. The method comprises two parts, i.e., model training and resolution enhancement. The model training comprises: obtaining multiple groups of high and low-resolution images comprising the completely same content, extracting high and low-resolution image block sequences through a window sliding method, and accordingly, training a bidirectional recursion convolution nerve network model. The resolution enhancement comprises: segmenting low-resolution images to be processed into a group of low-resolution image blocks to be processed through the window sliding method, generating corresponding high-resolution image blocks through the well trained bidirectional recursion convolution nerve network model, and generating corresponding high-resolution images through fusion. According to the method, space position relations of adjacent image blocks are learnt by full use of the bidirectional recursion convolution nerve network, and accordingly, the high-resolution images comprising detail information such as more edge textures and the like are obtained.

Description

technical field [0001] The invention relates to the fields of digital image processing, machine learning, and computer vision, in particular to an image super-resolution enhancement method based on a bidirectional recursive convolutional neural network. Background technique [0002] With the popularity of digital imaging devices such as cameras and mobile phones, digital images play an increasingly important role in the way humans receive information. Image resolution refers to the number of pixels contained in a digital image. The higher the resolution, the more detailed information the image contains. However, limited by imaging hardware devices with limited resolution, people cannot obtain very high-resolution images. Therefore, how to improve the resolution of existing low-resolution images has great practical application value. Image super-resolution enhancement refers to the process of generating a high-resolution image from an input single or multiple sequences of l...

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
CPCG06T3/4053G06T5/001G06T2207/20081
Inventor 黄凯奇徐冉张俊格
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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