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

A high-quality face generation method based on a multi-scale residual network

A face generation and multi-scale technology, applied in biological neural network models, image data processing, 3D modeling, etc., can solve problems such as blurring, low image resolution, difficulty in meeting the needs of image feature extraction and recognition, and achieve Reduced time and cost, low blur effect

Inactive Publication Date: 2019-06-18
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the problem of high-quality face generation, the obtained image not only contains a lot of noise, but also has a certain degree of blur, and its image resolution is too low to meet the needs of subsequent image feature extraction and recognition.

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 high-quality face generation method based on a multi-scale residual network
  • A high-quality face generation method based on a multi-scale residual network
  • A high-quality face generation method based on a multi-scale residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] This embodiment discloses a high-quality human face generation method based on a multi-scale residual network. The generation method includes steps: a data set design step, a model design and training step, and a model prediction step.

[0038] Among them, the technology in network model design mainly involves the following types of technologies: 1) Increase of network depth: use the improved residual network to increase the depth of the network and improve the fitting ability of the network; 2) Multi-scale network framework: design three A sub-network of three levels enables the image to be generated from low resolution to high resolution, from rough to fine; 3) Network parameter sharing: share the parameters of the long-term memory module between the sub-networks, so that the parameters of the network greatly reduced.

[0039] TensorFlow framework and Pycharm development environment: The TensorFlow framework is a development framework based on the python language, which...

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 high-quality face generation method based on a multi-scale residual network, and the method comprises the following steps: a data set design step: integrating a current mainstream face data set, and generating a data pair of a low-quality face and a high-quality face through software; A model design and training step: designing a multi-scale residual network, and performing model training by using data pairs to obtain a network model weight; And a model prediction step: carrying out model processing on the face image obtained in reality to obtain a prediction result.According to the invention, a deep learning network technology is applied to a generation task of a high-quality face to generate a color face image with high resolution, low fuzzy degree and low noise; And by using a deep learning network method, the time and cost of manual drawing can be reduced, and a solid foundation is laid for subsequent face feature extraction and recognition.

Description

technical field [0001] The invention relates to the technical field of deep learning applications, in particular to a high-quality human face generation method based on a multi-scale residual network. Background technique [0002] In recent years, video surveillance has been popularized in large and medium-sized cities across the country, and has been widely used in the construction of social security prevention and control systems, and has become a powerful technical means for public security organs to investigate and solve crimes. Especially in mass incidents, major cases and double robbery cases, evidence clues obtained from video surveillance videos play a key role in the rapid detection of cases. At present, domestic public security organs mainly use video surveillance videos to search for clues and evidence of crimes after the event. Due to the impact of shooting time, space and environment, even if investigators successfully obtain video surveillance videos near the c...

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): G06T17/00G06K9/00G06K9/62G06N3/04
Inventor 谢巍余孝源潘春文周延
Owner SOUTH CHINA 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
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