Unlock instant, AI-driven research and patent intelligence for your innovation.

Human face image processing method and device

A face image and processing method technology, applied in the field of communication, can solve the problem of low accuracy in highlight areas, and achieve the effect of improving the accuracy and improving the repair effect.

Active Publication Date: 2017-01-04
TENCENT TECH (SHENZHEN) CO LTD +1
View PDF13 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a face image processing method and device to solve the technical problem of low accuracy in the extraction of highlight regions in existing face image processing

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
  • Human face image processing method and device
  • Human face image processing method and device
  • Human face image processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] In this embodiment, a method for processing a human face image is provided, comprising the following steps: acquiring a highlight area of ​​the human face image, the highlight area including a plurality of boundary pixels; acquiring the pixel with the highest probability of skin color in a preset area The pixel value of the pixel value, wherein the preset area is an area of ​​a preset value from the boundary pixel point; according to the pixel value of the pixel point with the largest skin color probability, the pixel value of the boundary pixel point is optimized, so that Acquiring optimized pixel values ​​of the boundary pixels; acquiring an initial repair map corresponding to the highlight region according to the optimized pixel value; performing repair processing on the highlight region according to the initial repair map.

[0032] Such as figure 1 As shown, in the present embodiment, the mobile terminal is used as the subject of implementation, and the processing m...

Embodiment 2

[0048] In this embodiment, a method for processing a human face image is provided, comprising the following steps: acquiring a highlight area of ​​the human face image, the highlight area including a plurality of boundary pixels; acquiring the pixel with the highest probability of skin color in a preset area The pixel value of the pixel value, wherein the preset area is an area of ​​a preset value from the boundary pixel point; according to the pixel value of the pixel point with the largest skin color probability, the pixel value of the boundary pixel point is optimized, so that Acquiring optimized pixel values ​​of the boundary pixels; acquiring an initial repair map corresponding to the highlight region according to the optimized pixel value; performing repair processing on the highlight region according to the initial repair map.

[0049] Such as figure 2 As shown, taking the implementation subject as the mobile terminal as the implementation subject, the processing metho...

Embodiment 3

[0083] In order to better realize the above method, the present invention also provides a processing device for human face images, such as image 3As shown, the face image processing device includes: a first acquisition module 301 , a second acquisition module 302 , an optimization module 303 , a third acquisition module 304 and a restoration module 305 .

[0084] Wherein, the first acquisition module 301 is used to acquire a highlight area of ​​a face image, and the highlight area includes a plurality of boundary pixel points.

[0085] Among them, such as Figure 4 As shown, the first acquisition module 301 includes:

[0086] The acquiring unit 3011 is configured to acquire a face image to be processed, and the face image to be processed is an RGB color image. Wherein, the face image to be processed may be a face image to be processed obtained by the mobile terminal from a local album or a network.

[0087] The denoising unit 3012 is configured to perform denoising process...

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 human face image processing method and device. The processing method comprises the steps that a highlight region of a human face image is acquired, wherein the highlight region comprises a number of boundary pixel points; the pixel value of a pixel point with the maximum skin color probability in a preset region is acquired, wherein the distance from a boundary pixel point to the preset region is a preset value; according to the pixel value of the pixel point with the maximum skin color probability, the pixel value of the boundary pixel point is optimized to acquire the optimized pixel value of the boundary pixel point; according to the optimized pixel value, the initial repair pattern corresponding to the highlight region is acquired; and the highlight region is restored according to the initial repair pattern. According to the invention, the restoring effect of the human face image is improved.

Description

technical field [0001] The invention belongs to the technical field of communication, and in particular relates to a method and device for processing a human face image. Background technique [0002] During the shooting process, due to oily face or light, some areas of the face of the captured photo will show a highlight effect, affecting the normal viewing of the photo by the user, resulting in a bad user experience. [0003] In the prior art, there are already many methods for removing the highlight of the face image, but the extracted highlight area is often not very accurate, especially the accuracy of the pixel points at the junction of the highlight area and the normal area is especially imprecise. , resulting in a poorer effect of the subsequently generated repair image, and the degree of matching with the original image cannot meet the predetermined requirements. [0004] Therefore, the technical problem of how to improve the accuracy of highlight region extraction ...

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): G06T5/00
CPCG06T2207/30201G06T5/77
Inventor 袁同根
Owner TENCENT TECH (SHENZHEN) CO LTD