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

Automatic generation method of face image mask with region perception characteristics

A face image, area perception technology, applied in instruments, character and pattern recognition, computer parts and other directions, can solve the problem of inability to accurately fit the natural transition of the area boundary, improve convenience and breadth, save storage, The effect of improving the effect

Inactive Publication Date: 2015-04-22
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a method for automatically generating a face mask with region-aware characteristics, which can automatically make the mask fit the region boundary and generate a smooth boundary according to the apparent characteristics of the face image Transition, to overcome the shortcomings of the general automatic mask generation method that cannot accurately fit the region boundary and produce a natural transition, and can improve the efficiency of face image editing while ensuring a natural editing effect

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
  • Automatic generation method of face image mask with region perception characteristics
  • Automatic generation method of face image mask with region perception characteristics
  • Automatic generation method of face image mask with region perception characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with the accompanying drawings.

[0031] The system structure diagram of the present invention is as attached figure 1 As shown, the specific steps are as follows:

[0032] (1) Use a cascade classifier based on Haar-like features (such as the Viola-Jones face detector in the open source computer vision library OpenCV) to perform face detection on the original face image;

[0033] (2) According to the detected face, extract the shape feature (Fs) of the face image;

[0034] (3) Extract the brightness features and edge features of the face image (F);

[0035] (4) According to the requirements of specific image editing, using the shape features, edge features and brightness features of the extracted face image, the region-aware mask generation (M) is realized by solving a weighted least squares formula.

[0036] The specific steps of the present invention extracting the face image shape feature (Fs) ar...

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 provides an automatic generation method of face image mask with region perception characteristics. The automatic generation method comprises the following steps: (1) carrying out face detection on an original face image; (2) extracting the shape characteristics of the face image in a face region detected in the step (1); (3) extracting the luminance characteristics and the edge characteristics of the face image; and (4) taking the extracted shape characteristics and edge characteristics as an initial value R for mask generation, taking the extracted luminance characteristics as guide characteristics G for the mask generation, and solving a weighted least square formula to realize the generation of the mask M, wherein the formula is as follows. The automatic generation method overcomes a defect that a general automatic generation method of the mask can not accurately carry out region boundary fitting or generate natural transition, and can guarantee a natural editing effect while face image editing efficiency is improved.

Description

technical field [0001] The invention belongs to the field of face image recognition and optimization processing, in particular to a method for automatically generating a face image mask with area perception characteristics. Background technique [0002] Mask generation is a key technology in face image editing. Its main function is to realize the selection of image editing areas and set adjustment parameters for different local areas. It is widely used in many special effects processing of face images, such as face Digital make-up, face cartoon special effects and face skin modification, etc. [0003] There are two main methods for mask generation, one is manual drawing, and the other is automatic generation. Manually drawing masks requires a certain understanding of relevant image editing tools and operations, which is difficult for non-professional users; even if users have certain professional skills, hand-painting masks involves a large number of complicated manual adju...

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): G06K9/46
CPCG06V40/161G06V40/168
Inventor 梁凌宇金连文
Owner SOUTH CHINA 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