A picture synthesis method based on a generative adversarial network

A picture synthesis and network technology, applied in the biological neural network model, neural learning method, image data processing, etc., can solve the problems of cumbersome operation and time-consuming, and achieve the effect of simplifying the operation steps, generating realistic images and high practical value

Pending Publication Date: 2019-03-08
BEIJING INSTITUTE OF GRAPHIC COMMUNICATION
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, compared to using GANs, this method is more time-consuming, cum

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
  • A picture synthesis method based on a generative adversarial network
  • A picture synthesis method based on a generative adversarial network
  • A picture synthesis method based on a generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The following is a detailed explanation of the image synthesis method based on the generated confrontation network in conjunction with the accompanying drawings. The basic process is as follows figure 1 shown.

[0032] 1. Collect sample pictures from the network and preprocess the sample pictures.

[0033] This generative confrontation network needs to collect and download a large number of samples on the Internet, and after a large amount of training, it can learn a probability distribution and generate data. All pictures need to have a resolution greater than 128X128, and the picture content includes landscapes and portraits. The portrait pictures come from the CelebA picture collection, and the landscape pictures come from the network picture collection obtained by Python crawling web pages. Make these pictures into two sample sets. Sample set A includes N portrait pictures from the CelebA sample set, and sample set B stores N landscape pictures collected by the a...

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 relates to a picture synthesis method based on a generative adversarial network, which is used for carrying out feature extraction and fusion on pictures in different domains to generatea new picture, and comprises the following steps of firstly collecting and sorting picture samples, and grouping the picture samples to ensure that each group of pictures has the same feature; then constructing and training an adversarial network, and initializing network parameters; then selecting an appropriate loss function and an optimization method; then transmitting the samples into the generative adversarial network to start training; and finally properly adjusting the network parameters according to the training result, so that a better result is expected to be obtained. According tothe invention, the image content is synthesized, a new image is generated, manual operation is simplified, and the working efficiency is improved.

Description

technical field [0001] The invention relates to a picture synthesis method based on a generative confrontation network, and belongs to the technical fields of deep learning and digital graphics and image processing. Background technique [0002] With the development of computer hardware and neural networks, artificial intelligence has gradually gained people's attention, and it is also playing an increasingly important role in people's lives. Deep learning originated from the development of neural networks. Its concept was proposed by Hinton et al. in 2006. Its purpose is to simulate the human brain to analyze and interpret data. People hope to find a deep neural network model through deep learning, which can represent the probability distribution among various data encountered in artificial intelligence applications, such as image processing, natural language processing, etc. [0003] Deep learning can be divided into supervised learning, semi-supervised learning and unsup...

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): G06T3/40G06N3/08
CPCG06N3/088G06T3/4038Y02T10/40
Inventor 解凯何翊卿李桐李婷孙磬宇
Owner BEIJING INSTITUTE OF GRAPHIC COMMUNICATION
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