Blurred picture sharpening processing method and system based on deep neural network

A technology of deep neural network and processing method, applied in the field of fuzzy picture clear processing method and system

Active Publication Date: 2019-09-10
SOUTH CHINA UNIV OF TECH
View PDF13 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still many deficiencies in the existing image processing f

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
  • Blurred picture sharpening processing method and system based on deep neural network
  • Blurred picture sharpening processing method and system based on deep neural network
  • Blurred picture sharpening processing method and system based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] This embodiment provides a method for clearing blurred pictures based on a deep neural network. In this embodiment, the method is as follows figure 1 As shown, it is executed on a physical system with the Android platform as the core, including the following steps:

[0044] The original image P is blurred by the fuzzy algorithm to obtain the image

[0045] The original image P and the blurred image Train the BiCycleGAN network as training data;

[0046] In practical application, the blurred image obtained by the image acquisition terminal is transmitted to the server through the Android exchange platform. After receiving the blurred image data, the server calls the trained BiCycleGAN network for clearing processing and returns the processing result to the Android The switching platform, the Android switching platform displays a clear image on the image display end.

[0047] Wherein, the method involves the input domain and output domain of the image in the process...

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 blurred picture sharpening processing method and system based on a deep neural network. The method comprises the following steps of carrying out blurring processing on an original image P through a blurring algorithm to obtain an image, and training a BiCycleGAN network by taking the original image P and the blurred image as the training data; during actual application, transmitting a blurred image needing to be processed to a server, and after the server receives the blurred image data, enabling the server to call the trained BiCycleGAN network to perform sharpeningprocessing and return a processing result. According to the method, the problem of blurring caused by hardware or image content is solved, and the deep neural network is used for solving the problem,so that a processing mode for solving image blurring is expanded.

Description

technical field [0001] The invention relates to the field of image processing and deep learning, in particular to a method and system for clearing blurred pictures based on a deep neural network. Background technique [0002] In recent years, with the rapid development of the mobile Internet, smart phones have become an indispensable part of people's daily life. Smartphone hardware is rapidly iterating, and the computing power of the mobile terminal is getting stronger and stronger. The mobile terminal gradually replaces the PC terminal as the entrance of Internet traffic, and many new needs have been born. Taking pictures is the most popular demand for people whether they are traveling or in daily life. one. In actual shooting, tiny jitters in the photosensitive process are unavoidable. The jitters may come from the photographer himself, or may be caused by the shutter time not being short enough. These jitters will cause overlapping of pixels, resulting in blurred photos ...

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): G06T5/00G06N3/04
CPCG06T5/003G06T2207/20081G06T2207/20084G06N3/045
Inventor 唐珩膑彭德智舒琳王岽然张国雄巫朝政邢晓芬
Owner SOUTH CHINA UNIV OF 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