A semantic image restoration method based on a DenseNet generative adversarial network

A repair method and image generation technology, applied in the field of deep learning and image processing, can solve problems such as the accuracy of the repair area and the visual effect that need to be improved

Inactive Publication Date: 2019-04-02
BEIJING UNIV OF TECH
View PDF6 Cites 78 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the model can learn the basic semantic information of the image, the accuracy and visual effect of the inpainted area need to be improved

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 semantic image restoration method based on a DenseNet generative adversarial network
  • A semantic image restoration method based on a DenseNet generative adversarial network
  • A semantic image restoration method based on a DenseNet generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Method of the present invention comprises the following steps:

[0075] Step 1. Data preprocessing stage. Set the size of the collected data to obtain the size required for training.

[0076] Step 2. Build the stage of generating confrontation network. The generation confrontation network model is composed of a generation network G and a discriminative network D. The generation network G adopts a network structure in which the encoder is connected to the decoder, where the encoder is composed of a DenseNet module and a convolutional layer, and the decoder is composed of a DenseNet module and a deconvolution layer. At the same time, there is a skip-connection between the encoder and the decoder. The encoder down-samples the input image to extract abstract features. The decoder upsamples the encoded feature data through deconvolution to make the output data size consistent with the input image size. The discriminant network is composed of convolutional layer and full...

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 semantic image restoration method based on a DenseNet generative adversarial network. The method comprises the following steps of preprocessing collected images, and constructing a training and testing data set; constructing a DenseNet generative adversarial network; training a DenseNet generation adversarial network stage; and finally, realizing repair processing of thedefect image by using the trained network. Under the framework of the generative adversarial network, the DenseNet structure is introduced, a new loss function is constructed to optimize the network,the gradient disappearance is reduced, network parameters are reduced, meanwhile, transmission and utilization of features are improved, and the similarity and visual effect of large-area semantic information missing image restoration are improved and improved. Examples show that face image restoration with serious defect information can be achieved, and compared with other existing methods, the restoration results better conform to visual cognition.

Description

technical field [0001] The invention relates to a semantic image restoration method based on a DenseNet generation confrontation network, belonging to the fields of deep learning and image processing. Background technique [0002] Image inpainting technology is to use the known area of ​​the image to restore the lost information, so that the restored image can maximize the restoration of the original image and conform to the human visual sense. Image restoration technology first appeared in the Renaissance and was used to protect and restore medieval literary works. In recent years, computing-based digital image restoration technology has attracted attention and gradually developed. The existing restoration algorithms have been able to repair the strip scratches in the picture and the background filling of small areas, etc., but they still have considerable limitations for image restoration with serious lack of semantic information. Semantic image restoration requires effe...

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): G06T5/00G06N3/04
CPCG06T5/008G06N3/045
Inventor 任坤孟丽莎范春奇黄泷王普
Owner BEIJING 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