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

Real-time human face deforming method and system

A face deformation and face technology, applied in image data processing, instruments, calculations, etc., can solve problems such as unnatural connection between changing areas and unchanged areas, unnatural overall image effect, and incapable of real-time video processing.

Active Publication Date: 2016-06-29
SHENZHEN SENSETIME TECH CO LTD
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of science and technology, the performance improvement of hardware devices and the enhancement of image processing technology have enabled many camera devices to perform image processing by themselves, and some of the image processing can produce the effect of a distorting mirror, but currently such processing is based on static images. The video cannot be processed in real time, and most of them have the problem of unnatural connection between the changing area and the unchanging area in the picture, making the overall effect of the processed image unnatural

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
  • Real-time human face deforming method and system
  • Real-time human face deforming method and system
  • Real-time human face deforming method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In a basic embodiment, a real-time face deformation method is provided. The method includes the following steps, such as figure 1 Shown:

[0017] S100. Detect human faces in the image, and determine the number of feature points to be extracted through automatic recognition;

[0018] S200: Use the detected image as an input of the cascade regression model to obtain facial feature points;

[0019] S300. Determine multiple feature points of the facial features to be deformed. Based on the determined feature points and their influence radius, in the case where the influence radius of the deformed facial features is not exactly the same, calculate the new position and new position of each pixel affected by the deformation. grayscale value;

[0020] S400, using the new position and new gray value of each pixel calculated in step S300 to update the relevant pixel on the image.

[0021] In this embodiment, the above method can be used to deform the face in the real-time video, and the o...

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 real-time human face deforming method and system. The method comprises: detecting a human face in an image, and determining the number of feature points to be extracted in the automatic identification way; taking the detected image as input of a cascade regression model, and obtaining human face feature points; determining multiple feature points of the five sense organs to be deformed, and on the basis of the determined feature points and influence radiuses thereof, calculating a new position and a new gray value of each pixel point that is affected by deformation, in the condition that influence radiuses of the five deformed sense organs are not completely the same; and updating related pixel points on the image by using the new position and the new gray value of each pixel point which is obtained by calculation. The system is realized based on the method and provides convenience for application of the method. The method and the system of the invention have the characteristics of rapid human face feature point extraction, accurate positioning and natural overall human face deformation effect.

Description

Technical field [0001] The present disclosure relates to the field of computer graphics and image processing, in particular to a real-time face deformation method and system. Background technique [0002] With the development of science and technology, the performance of hardware equipment and the enhancement of image processing technology have enabled many camera devices to perform image processing by themselves, and some of the image processing can produce a haha ​​mirror effect, but this type of processing is currently based on static pictures. The video cannot be processed in real time, and most of the problems exist that the connection between the changing area and the unchanged area in the picture is unnatural, making the overall effect of the processed image unnatural. Summary of the invention [0003] In response to some of the above problems, the present disclosure provides a real-time face deformation method and system. The method can perform deformation processing on th...

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): G06T5/00G06T7/00
CPCG06T2207/10004G06T5/80
Inventor 郭玉京左冬冬马堃王贵杰徐立
Owner SHENZHEN SENSETIME TECH CO LTD
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