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

A method and system for intelligent beauty based on convolutional neural network

A convolutional neural network and beauty technology, applied in the field of image processing, can solve the problem of inability to provide beauty parameters, and achieve the effect of avoiding parameter adjustment, avoiding stereotypes, and improving beauty effects.

Active Publication Date: 2022-04-08
HANGZHOU QUWEI SCI & TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the configuration in the cloud requires the user to use the Internet, and the beauty parameters cannot be given in a no-network environment

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 method and system for intelligent beauty based on convolutional neural network
  • A method and system for intelligent beauty based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, this embodiment proposes a method of intelligent beauty based on convolutional neural network, including:

[0048] S1. Detect the face key points of the image to be beautiful;

[0049]The core of performing beautification on the human face image is to perform beautification on each feature of the human face, therefore, for the input human face image, the present invention first detects the key points of the human face. Face key points include key features such as nose, mouth, eyes, etc. The present invention does not limit the specific face key point detection method, and any kind of face key point detection algorithm can be used, such as a priori rule-based method, a geometry-based Shape methods, methods based on grayscale information, etc., can also use third-party face SDK. For example, when using the face SDK of ArcSoft Technology, an array A of 101 face key points is detected. When performing face key point detection, the face needs to...

Embodiment 2

[0072] Such as figure 2 As shown, the present embodiment proposes a deep learning-based intelligent aesthetic system, including:

[0073] The detection module is used to detect the face key points of the image to be beautiful;

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 an intelligent beautification method and system based on a convolutional neural network. The intelligent beautification method includes steps: S1, detecting the key points of the human face of the image to be beautified; S2, constructing a convolutional neural network (CNN) for face beautification Type network; S3, input the described CNN face beauty network with the image to be beautiful and key points of human face, and obtain the key points of human face after beauty; S4, based on the key points of the human face of the image to be beautiful The key points of the human face after point and beautification are deformed to generate the beautification image. The present invention adopts a deep learning algorithm to extract facial feature ratio feature information from a large amount of beautiful faces, deeply understand the relationship between the details of the beauty and the face from the massive data, and realize the intelligent face beauty.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an intelligent beauty-beautification method and system based on a convolutional neural network. Background technique [0002] With the development of the field of artificial intelligence AI technology, intelligent terminal equipment has also been continuously developed. Taking photos with cameras is becoming more and more popular, among which beauty photos are the most frequently used camera usage scenarios. Portrait beauty, make-up, and filters have almost become the rigid needs of people's life for taking pictures and photography. At present, most of the portrait beauty algorithms in mobile portrait photo beautification or PC image processing software are based on the parameter adjustment of traditional deformation algorithms. Due to the fixed parameters, the deformation effect is single and stereotyped, and it is impossible to make perfect based on the personality characterist...

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 Patents(China)
IPC IPC(8): G06T5/00G06V40/16G06V10/82G06V10/40G06N3/04G06N3/08
CPCG06T5/005G06N3/08G06T2207/20081G06T2207/20084G06T2207/30201G06V40/161G06V40/168G06N3/045
Inventor 胡耀武李云夕熊永春杨金江
Owner HANGZHOU QUWEI SCI & 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

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