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

Face image enhancement method based on generative adversarial network

A facial image, network technology, applied in the field of deep neural network, can solve problems such as the performance impact of recognition algorithm

Active Publication Date: 2018-09-14
HANGZHOU DIANZI UNIV
View PDF9 Cites 84 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Especially in the actual video surveillance scene, the collected face images often have various postures, and most of the extreme postures will greatly affect the performance of our recognition algorithm

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 enhancement method based on generative adversarial network
  • Face image enhancement method based on generative adversarial network
  • Face image enhancement method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be further described below in conjunction with drawings and embodiments.

[0065] like Figure 1-7 As shown, a facial image enhancement method based on generative confrontation network, the specific implementation steps are as follows:

[0066] A given image IP and the corresponding face front view IF in the same scene constitute a binary group, with {I P , I F} as the training set.

[0067] Step (1), data preprocessing

[0068] Data processing is divided into two parts, the first part is to amplify the original data set. The second part unifies all datasets to be used.

[0069] Preprocess the MS-1-celeb data set: Use 3D morphable model (3DMM) to turn the frontal facial images in the data set to any angle to obtain the above-mentioned binary data, image 3 shown;

[0070] Preprocessing of all images used (MS-1-celeb augmented set and Multi-PIE dataset): use the 3DDFA algorithm to extract the facial key points of the image. And the regi...

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 enhancement method based on a generative adversarial network (GAN). The method comprises the following steps of: 1, preprocessing face images having multiple posesby using a 3D dense face alignment method; 2, designing a face enhancement network based on the GAN, and generating the GAN in two steps; 3, according to a task requirement, designing an objective function 4 corresponding to the Step-I and the Step-II, pre-training a recognition model by using MS-1-celeb, and pre-training a TS-GAN model by using augmented data; and 5, using Multi-PIE as a training Set, using a back propagation algorithm (4) to complete the pre-trained TS-GAN model parameters until convergence. The finally trained TS-GAN model can obtain a front face image corresponding to aninput image. Further, the front face image retains original illumination, is true in visual degree, and retains original identity information.

Description

technical field [0001] The present invention relates to a deep neural network for facial image enhancement (image enhancement, IE), in particular to a method for uniformly modeling facial images of arbitrary poses, and the exploration of the final synthesized facial image in the field of face recognition. Background technique [0002] With the development of society, my country's public security system has been gradually established and improved. Especially in the field of video surveillance, the monitoring of public places has covered every scene. Whether it is a crowded square road or a crowded subway station, there are countless surveillance systems deployed in it, providing invisible protection for our lives. While ensuring the multi-dimensional information extraction of the monitoring scene and collecting video resources, in order to make better use of this huge and complex data information, it conducts reasonable analysis and screens out meaningful information. One 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): G06T5/00G06T7/33
CPCG06T7/33G06T2207/30201G06T2207/20081G06T2207/20084G06T5/73
Inventor 俞俊孙可嘉高飞
Owner HANGZHOU DIANZI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com