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

Method for automatically beautifying skin of facial image

A face image and skin technology, applied in the field of automatic face image skin beautification, can solve the problems of image component decomposition, beautification effect deviation, etc.

Inactive Publication Date: 2015-04-22
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing facial skin beautification systems generally only deal with certain skin attributes, and there is still a lot of room for improvement in beautification effects
[0005] In addition, in the original face image, the image components corresponding to the three skin attributes are fused together. The current skin beautification methods generally do not decompose the corresponding image components, resulting in the mutual influence of different skin attribute operations during the beautification process. , resulting in some deviation in the final beautification 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
  • Method for automatically beautifying skin of facial image
  • Method for automatically beautifying skin of facial image
  • Method for automatically beautifying skin of facial image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings.

[0051] The system structure diagram of the present invention is as attached figure 1 As shown, the specific steps are as follows:

[0052] (1) Feature extraction (F): Perform face detection and face feature extraction on the original face image;

[0053] (2) Layer decomposition (D): Decompose the image components of the original face image to obtain the image components corresponding to the brightness, smoothness and color of the human face skin, that is, the brightness layer, the smoothness layer and the color layer;

[0054] (3) Mask generation (M): Use the face feature information extracted in step (1) to generate corresponding masks for the brightness layer, smoothness layer and color layer obtained in step (2), namely Brightness mask, smoothness mask and color mask to control different editing degrees of local areas of human face skin;

[0055] (4) Beautificati...

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 a method for automatically beautifying skin of a facial image. The method comprises the following steps of (1) feature extraction: carrying out face detection and face feature extraction on an original facial image; (2) layer decomposition: carrying out image component composing on the original facial image to obtain a brightness layer, a smoothness layer and a color layer; (3) mask generation: utilizing the face features to respectively generate a corresponding brightness mask, a smoothness mask and a color mask for the brightness layer, the smoothness layer and the color layer; (4) beautification parameter optimization: computing beautification parameters corresponding to the three layers with an average face as a standard template; (5) layer enhancement: utilizing the beautification parameters and the masks to carry out beautification processing on the three layers respectively so as to obtain a beautified brightness layer, a beautified smoothness layer and a beautified color layer; and (6) layer fusion: fusing the three beautified layers to obtain a final face beautification image.

Description

technical field [0001] The invention belongs to the field of face image recognition and processing, in particular to an automatic method for beautifying the skin of a face image. Background technique [0002] The goal of face image skin beautification is to enhance the beauty of the face by processing its skin without changing the important features of the original image. This technology has broad application prospects no matter in daily life such as photography and entertainment, or in professional fields such as advertisement design and film production. [0003] There are many professional image editing tools on the market, but they are not easy for ordinary users to master, even professionals often need complicated operations and a lot of time to achieve good skin beautification effects. Although face skin beautification tools for ordinary users such as Meitu Xiuxiu have appeared recently, it is still unavoidable to avoid more user operations to obtain a good skin proces...

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): G06T5/00
Inventor 金连文梁凌宇
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