Face super-resolution method based on supervised pixel-by-pixel generative adversarial network

A super-resolution, pixel-by-pixel technology, applied in the field of face super-resolution, can solve the problems of large gap between the image and the original image, and the inability to use face recognition, etc., to achieve the effect of improving accuracy and ensuring similarity

Active Publication Date: 2020-01-14
UNIV OF SCI & TECH OF CHINA
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generative confrontation network can restore more realistic texture details, but the traditional unsupervised learning method of generative confrontation network makes the generated image far from the original image, and cannot be used for face recognition, so it needs to be improved for this problem

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
  • Face super-resolution method based on supervised pixel-by-pixel generative adversarial network
  • Face super-resolution method based on supervised pixel-by-pixel generative adversarial network
  • Face super-resolution method based on supervised pixel-by-pixel generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0045] Such as figure 1 Shown, the inventive method is concretely realized as follows:

[0046] Step 1): Read the original face image dataset;

[0047] Establish an original face image data set for training a supervised pixel-by-pixel generation confrontation network (including generator and discriminator), and divide the data set into a training set and a test set

[0048] Step 2): Perform face detection and cropping on the pictures in the data, and filter out qualified training pictures;

[0049] Step 3): Randomly read high-resolution face images in batches for bicubic interpolation and down-sampling to obtain high-resolution-low-resolution face image pairs for supervised generative confrontation networks;

[0050] The face images in the training set are randomly extracted in batches as high-resolution face images, and the high-resolution face im...

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 face super-resolution method based on a supervised pixel-by-pixel generative adversarial network. The method comprises the following steps: firstly, reading an original facepicture data set; then carrying out preprocessing work such as data cutting and cleaning; thirdly, reading the high-resolution face image for bicubic interpolation down-sampling to obtain a high-resolution face image-low-resolution face image pair; fourthly, inputting the low-resolution face image into a generator network to generate a super-resolution face image; and fifthly, respectively inputting the high-resolution face image and the super-resolution image into a pixel-by-pixel discriminator network, calculating a supervised pixel-by-pixel adversarial loss function by using a pixel-by-pixel discrimination matrix output by the pixel-by-pixel discriminator network, and training a generator network by using error back propagation.

Description

technical field [0001] The invention relates to the field of image reconstruction methods, in particular to a face super-resolution method based on a supervised pixel-by-pixel generation confrontation network. Background technique [0002] With the continuous improvement of security standards in crowded areas such as airports, subways, and shopping centers, intelligent surveillance systems based on machine vision have received more and more attention. In order to obtain a wider field of view, most surveillance videos usually collect faces with a small resolution. Compared with clear and high-resolution pictures, the discrimination and information content of small-scale face pictures are greatly reduced. Face recognition systems need super-resolution reconstruction for small-scale face images. The super-resolution reconstruction method can restore the texture details of face images and improve the accuracy of face recognition in low-resolution images. [0003] At present, a...

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): G06T3/40G06N3/04G06N3/08
CPCG06T3/4053G06N3/084G06N3/045
Inventor 凌强张梦磊李峰
Owner UNIV OF 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
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