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

Intelligent graph modification method based on asymmetric loop generation against loss

An asymmetric and retouching technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve problems such as easy distortion of training results, inability to improve images in multiple ways, and inapplicability of automatic image retouching, etc.

Active Publication Date: 2018-12-21
福建帝视信息科技有限公司
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When using traditional methods for image enhancement, it can only deal with one-sided problems of the image, and cannot improve the image in multiple ways at one time, and is not suitable for automatic image editing; when using traditional neural network-based learning image editing, its requirements are one by one. Matching training data; when the improved neural network CycleGAN is used for image translation, although the problem of data mismatch is solved, the training process is too free and the result is easily distorted

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
  • Intelligent graph modification method based on asymmetric loop generation against loss
  • Intelligent graph modification method based on asymmetric loop generation against loss
  • Intelligent graph modification method based on asymmetric loop generation against loss

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] like Figure 1-7 As shown in one of them, the present invention discloses an intelligent image retouching method based on asymmetric cyclic generation against loss, which is divided into the following steps:

[0100] Step 1, training data preparation phase.

[0101] Described step 1 specifically comprises the following steps:

[0102] Step 1.1, select the training data set: the present invention uses image data with the theme of seaside wedding photos, including unretouched images and retouched image pairs. Among them, the retouched picture is manually repaired by a photo studio retoucher from the unretouched picture. During the retouching process, the retoucher thinned the face and legs of the portrait, added clouds to the background, and removed debris, which made the structure of the unretouched image and the retouched image not completely match to a certain extent.

[0103] Step 1.2, processing the image database to form a paired set of unretouched and retouched ...

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 intelligent image modification method based on asymmetric loop generation and loss resistance, which applies the idea of loop consistency in CycleGAN used for image translation to the field of intelligent image modification, proposes asymmetric loop generation and loss resistance, and applies wGAN to the training of loop generation and loss resistance network. The invention also discloses an intelligent image modification method based on asymmetric loop generation and loss resistance. The invention uses four sub-networks to form a whole network structure, and utilizes asymmetrical loop generation to antagonize the loss to train, and finally the forward generator can improve the color, brightness, portrait effect and other multi-characteristics of the untrimmed image, and improve the visual feeling of the image.

Description

technical field [0001] The invention relates to the field of image enhancement, in particular to an intelligent image retouching method based on asymmetric cycle generation against loss. Background technique [0002] Image retouching belongs to the field of image enhancement, which involves processing and adjusting the tone, texture, and brightness of the image to achieve better visual effects. With the improvement of living standards, people's requirements for photo editing have also increased. Nowadays, photo editing is one of the indispensable technologies for both amateur and professional photography. [0003] Traditional image enhancement methods can be divided into two categories: frequency domain methods and space domain methods. In the frequency domain method, Chen Chunning et al. [6] Gaussian high-pass filter, Butterworth high-pass filter and exponential high-pass filter are improved in frequency domain, and three kinds of homomorphic filters are obtained, and the...

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
CPCG06T2207/20172G06T5/77
Inventor 高钦泉高哲玲刘文哲童同
Owner 福建帝视信息科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com