Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Human face super-resolution reconstruction method based on generative adversarial network and sub-pixel convolution

A super-resolution reconstruction and sub-pixel technology, applied in the field of face super-resolution reconstruction, can solve the problems of inability to perceive image difference information, inability to produce face reconstruction effects, etc., to improve accuracy, more specific details, and better reconstruction. effect of effect

Active Publication Date: 2017-09-12
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 221 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of method uses the loss function of image pixel-by-pixel difference, and cannot perceive the difference information in the semantic direction of the image, especially for images with distinctive features such as faces, which cannot produce good face reconstruction effects.

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
  • Human face super-resolution reconstruction method based on generative adversarial network and sub-pixel convolution
  • Human face super-resolution reconstruction method based on generative adversarial network and sub-pixel convolution
  • Human face super-resolution reconstruction method based on generative adversarial network and sub-pixel convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] A face super-resolution reconstruction method based on generative confrontation network and sub-pixel convolution, including the following steps:

[0059] A. Use commonly used public face image datasets for preprocessing to produce low-resolution face images and corresponding high-resolution face image training sets;

[0060] B. Construct a generation confrontation network model for training, add a sub-pixel convolution layer to the generation network to achieve super-resolution image generation and introduce a weighted loss function including feature loss;

[0061] C. Input the training set obtained in step A into the generative confrontational network model in turn for model training, adjust parameters, and achieve convergence;

[0062] D. Preprocessing the low-resolution face image to be processed, and inputting the confrontation model obtained in step C to obtain a high-resolution image after super-resolution reconstruction.

[0063] Specific implementation methods...

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 human face super-resolution reconstruction method based on a generative adversarial network and sub-pixel convolution, and the method comprises the steps: A, carrying out the preprocessing through a normally used public human face data set, and making a low-resolution human face image and a corresponding high-resolution human face image training set; B, constructing the generative adversarial network for training, adding a sub-pixel convolution to the generative adversarial network to achieve the generation of a super-resolution image and introduce a weighted type loss function comprising feature loss; C, sequentially inputting a training set obtained at step A into a generative adversarial network model for modeling training, adjusting the parameters, and achieving the convergence; D, carrying out the preprocessing of a to-be-processed low-resolution human face image, inputting the image into the generative adversarial network model, and obtaining a high-resolution image after super-resolution reconstruction. The method can achieve the generation of a corresponding high-resolution image which is clearer in human face contour, is more specific in detail and is invariable in features. The method improves the human face recognition accuracy, and is better in human face super-resolution reconstruction effect.

Description

technical field [0001] The invention relates to the field of image reconstruction methods, in particular to a face super-resolution reconstruction method based on generative confrontation network and sub-pixel convolution. Background technique [0002] In the image field, image resolution has always been one of the main technical indicators that characterize the image observation level. The resolution of an image usually refers to the spatial resolution in image processing. The higher the resolution of the image, the smaller the area of ​​the actual scene represented by a certain number of image pixels, the finer the details of the scene that the image can reflect, and the more abundant information it can provide. The image super-resolution reconstruction technology may enable the transformation of the image from the detection level to the recognition level, or further to the fine resolution level. Image super-resolution reconstruction technology can improve image recognit...

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): G06T3/40G06N3/04
CPCG06T3/4053G06N3/045
Inventor 段翰聪张帆赵子天文慧闵革勇陈超李博洋
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products