Image processing method and device and terminal equipment

An image processing and image technology, applied in the field of image processing, can solve problems such as image distortion, and achieve the effect that denoising will not produce

Inactive Publication Date: 2018-09-21
GUANGDONG OPPO MOBILE TELECOMM CORP LTD
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides an image processing method, device, and terminal equipment to solve the problem of image distortion generated while removing noise in the prior art

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 processing method and device and terminal equipment
  • Image processing method and device and terminal equipment
  • Image processing method and device and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 A schematic flow chart of an image processing method provided by an embodiment of the present application is shown, and the details are as follows:

[0046] Step S101, obtaining a generation network and a discrimination network;

[0047] Specifically, the obtained generation network can be established based on a residual network (Residual Network, ResNet). In order to facilitate optimization and convergence, the ResNet has at least 2 residual blocks. Preferably, the number of residual blocks of the ResNet is 3.

[0048] Specifically, the discriminant network can be established based on the Visual Geometry Group (VGG) of Oxford University, and the discriminant network based on VGG has more accurate evaluation of pictures and less space.

[0049] Step S102, input the actual images in the image training set into the generating network, and output the corresponding constructed images;

[0050]Wherein, the image training set here may be a commonly used image train...

Embodiment 2

[0105] Figure 5 It shows a schematic structural diagram of an image processing device provided by the embodiment of the present application. For the convenience of description, only the parts related to the embodiment of the present application are shown:

[0106] The image processing device includes: a network acquisition unit 51, a structured image output unit 52, a reconstruction cost function generation unit 53, a judgment result output unit 54 of the discriminant network, an adversarial cost function generation unit 55, a network training unit 56, and an image acquisition unit to be denoised. Unit 57, image denoising unit 58. in:

[0107] A network acquisition unit 51, configured to acquire a generation network and a discrimination network;

[0108] Specifically, the discriminant network can be established based on the VGG of Oxford University.

[0109] Constructed image output unit 52, for inputting the actual image in the image training set into the generating netwo...

Embodiment 3

[0152] Figure 6 It is a schematic diagram of a terminal device provided by an embodiment of the present application. Such as Figure 6 As shown, the terminal device 6 of this embodiment includes: a processor 60 , a memory 61 , and a computer program 62 stored in the memory 61 and operable on the processor 60 . When the processor 60 executes the computer program 62, the steps in the above embodiments of the image processing method are realized, for example figure 1 Steps S101 to S108 are shown. Alternatively, when the processor 60 executes the computer program 62, it realizes the functions of the modules / units in the above-mentioned device embodiments, for example Figure 5 Function of units 51 to 58 shown.

[0153] Exemplarily, the computer program 62 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of c...

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 application of the invention is suitable for the technical field of image processing, and provides an image processing method and device and terminal equipment. The image processing method comprises the following steps: acquiring a generating network and a judging network; inputting an actual image in an image training set into the generating network, outputting a corresponding construction image; generating a reconstruction cost function of the generating network according to the construction image and the actual image; inputting the construction image and the actual image into the judging network, outputting a judging result; generating a confrontation cost function of the judging network according to the judging result, a label of the inputted construction image and a label of the actual image; alternatively training the generating network and the judging network according to the reconstruction cost function, the confrontation cost function and the actual image of the image training set until a judgement is made that the trained generating network meets the requirement; acquiring a to-be-denoised image; inputting the to-be-denoised image into the generating network meeting the requirement, and generating a denoised image. Through the above method, the image is denoised without distortion.

Description

technical field [0001] The present application belongs to the technical field of image processing, and in particular relates to an image processing method, device and terminal equipment. Background technique [0002] In the process of taking pictures, there are many sources of noise, such as sub-sampling, atmospheric factors (such as haze), imaging noise (such as noise caused by camera motion, noise caused by the optical limit of imaging sensors, etc.), geometric motion, projection and additional Noise (such as the noise of the imaging sensor itself), etc., will cause noise in the photos taken. [0003] In order to make the image as clear as possible, the traditional method usually removes the noise of the image through bilinear filtering, median filtering, wavelet transform and other methods. However, traditional image denoising methods may produce image distortion and other problems while removing noise. Contents of the invention [0004] In view of this, the embodimen...

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 Applications(China)
IPC IPC(8): G06T5/00
CPCG06T5/002G06T2207/20081G06T2207/20084
Inventor 张弓
Owner GUANGDONG OPPO MOBILE TELECOMM CORP LTD
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