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

Face image super-resolution reconstruction method based on discriminable attribute constraint generative adversarial network

A face image and image technology, which is applied in the field of super-resolution reconstruction of face images, can solve the problems of low accuracy of face verification and loss of detail information of LR face images, etc., to enhance detail information, improve learning ability and performance Enhanced effect

Active Publication Date: 2018-05-01
BEIJING UNIV OF TECH
View PDF3 Cites 84 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies of the prior art, aiming at the problems of LR face image detail information loss and low face verification accuracy, to provide a generative confrontation network based on face attribute constraints

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 image super-resolution reconstruction method based on discriminable attribute constraint generative adversarial network
  • Face image super-resolution reconstruction method based on discriminable attribute constraint generative adversarial network
  • Face image super-resolution reconstruction method based on discriminable attribute constraint generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Below in conjunction with accompanying drawing of description, the embodiment of the present invention is described in detail:

[0047] A face image super-resolution reconstruction method based on discriminable attribute constraints generative adversarial network, the overall flow chart is attached figure 1 shown; the algorithm is divided into offline part and online part; the relationship between offline part and online part is as attached image 3 As shown; the offline part is divided into two stages: sample preprocessing and network training. In the first stage, in order to avoid the interference of the background of the face object, the present invention first preprocesses the face data set in batches, and obtains the aligned HR face image after image preprocessing "face detection, face alignment", and the image size It is unified into M×N pixels; then it is down-sampled by S times, and the LR face image with the size of M / S×N / S is obtained; finally, the LR and HR ...

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 face image super-resolution reconstruction method based on a discriminable attribute constraint generative adversarial network, and belongs to the field of digital images / video signal processing. The method comprises the following steps: firstly, designing a processing flow of face detailed information enhancement; secondly, designing a network structure according to theflow, and acquiring an HR image from an LR image through the network; and lastly, performing face verification accuracy evaluation on the HR image through a face recognition network. Through adoptionof the method, enhancement including LR face image detailed information can be completed, and the accuracy of face verification is increased. Secondly, the generative network completes compensation ofimage high-frequency information firstly, then completes image amplification by subpixel convolution, and finally completes stepwise image amplification through a cascade structure, thereby completing enhancement of image detailed information. An attribute constraint module are trained together with a perception module and an adversarial model in order to perform fine adjustment of the performance of a network reconstructed image. Finally, a reconstructed image of the generative network is input into a face verification network, so that the accuracy of face verification is increased.

Description

technical field [0001] The invention belongs to the field of digital image / video signal processing, and in particular relates to a human face image super-resolution reconstruction method based on a discriminable attribute constraint generation confrontation network. Background technique [0002] With the rapid development and wide application of multimedia technology, high-quality images and videos have more and more application value. In video surveillance, human face is one of the most important objects. However, affected by various factors such as collection distance, ambient light, and compression distortion, face images in applications such as video surveillance are often blurred, low-resolution, and low-quality images, which seriously affect subsequent intelligent face analysis technologies. Applications. Existing methods mostly use image super-resolution restoration methods based on deep learning to improve the image quality of low-resolution images. However, these ...

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): G06T3/40
CPCG06T3/4053G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/30201
Inventor 李晓光孙旭卓力李嘉锋董宁
Owner BEIJING UNIV OF TECH
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