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

Image or video quality enhancement method based on convolution neural networks

A convolutional neural network and quality enhancement technology, applied in image enhancement, image analysis, image data processing, etc., to achieve the effect of video or image quality enhancement and quality enhancement

Active Publication Date: 2017-12-15
BEIHANG UNIV
View PDF8 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the current problem that image or video quality needs to be adapted to multiple intelligent terminals, and image or video quality needs to be realized according to terminal conditions, the present invention provides an image or video quality enhancement method based on convolutional neural network. Currently, there is no such method based on volume Research on Video or Image Quality Enhancement by Productive Neural Network

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 or video quality enhancement method based on convolution neural networks
  • Image or video quality enhancement method based on convolution neural networks
  • Image or video quality enhancement method based on convolution neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below in conjunction with accompanying drawing and specific examples the present invention will be further described:

[0031] A kind of video (or image) quality enhancement method based on convolutional neural network of the present invention, such as figure 1 As shown, first, design a convolutional neural network for video (or image) quality enhancement, named network A, and then use several training videos (or images) to train network A; then design a higher computational complexity The convolutional neural network of , named network B, and then train network B with several training videos (or images). When using the method of the present invention, first select a more suitable convolutional neural network from network A and network B according to the computing power of the device or the remaining power to specify the computational complexity, and then input the video (or image) whose quality is to be enhanced into In the selected network, the video (or image) with ...

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 or video quality enhancement method based on convolution neural networks, and belongs to the field of computer vision. The method comprises the steps of firstly, designing the two convolution neural networks for video quality enhancement, wherein the two networks have different computational complexities; secondly, selecting a plurality of training images or videos to train parameters in the two convolution neural networks; thirdly, selecting the convolution neural network with the more suitable computational complexity according to actual needs to input the images or videos with the quality to be enhanced into the selected network; finally, outputting the images or videos after quality enhancement through the network. According to the image or video quality enhancement method based on the convolution neural networks, the quality of the videos can be effectively enhanced; a user can select the specified convolution neural network with the more suitable computational complexity to enhance the quality of the images or videos according to the computational capacity or remaining power capacity of equipment.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to an image or video quality enhancement method based on a convolutional neural network. Background technique [0002] In the field of computer vision, video quality enhancement has an important impact on improving video (or image) quality and improving video (or image) visual effects; video (or image) quality enhancement generally refers to improving the quality of damaged video (or image) the quality of. In the current communication system, the problem of limited channel bandwidth exists widely, so the video (or image) transmission needs to go through the process of compression coding, in this process, the video (or image) quality will be lost; at the same time, the transmission channel often exists Noise, which will also lead to the loss of video (or image) quality after channel transmission; therefore, video (or image) quality enhancement has become a key issue in the field of co...

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): G06T5/00
CPCG06T2207/10004G06T2207/10016G06T2207/20081G06T2207/20084G06T5/73
Inventor 徐迈杨韧王祖林
Owner BEIHANG UNIV
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