Face image processing method and device

A face image and image technology, applied in the field of face image processing, can solve the problems of poor user experience and low selectivity, and achieve the effect of enhancing similarity and improving flexibility

Inactive Publication Date: 2019-09-24
深圳市紫石文化传播有限公司
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method for human face image processing in the above-mentioned cited documents enhances the similarity of artistic and entertainment processing of human face images by merging the facial shape and facial skin color of the target image and the source image; however, in In the process of fusing the target image and the source image, since the facial features of the target image and the source image are covered and fused, only two processed new face images can be obtained at most, and the user's selectivity is low, resulting in Poor user experience

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
  • Face image processing method and device
  • Face image processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Embodiment 1: the method for face image processing, such as figure 1 shown, including the following steps:

[0050]Step 1, get face image.

[0051] When it is necessary to perform artistic or entertaining processing on the face image, two face images need to be collected, one is the face image to be processed, and the other is the reference face image. The face image to be processed may be an image of a user, or an image of another person; the image of a reference face may be an image of a celebrity, or an image of a user.

[0052] Step 2, locate the facial feature points on the face image.

[0053] When it is necessary to recognize the facial features in the face image, it is necessary to perform facial feature point calibration on the facial features. The calibration method in this embodiment can be a manual calibration method, or it can be based on AAM facial feature points The automatic calibration method may also be an ASM-based automatic calibration method of f...

Embodiment 2

[0068] Embodiment 2: the device for face image processing, such as figure 2 As shown, it includes an acquisition module 101 , a positioning module 102 , an area division module 103 , an extraction module 104 , a face transformation module 105 , a skin color transformation module 106 and an image fusion module 107 . Wherein: the obtaining module 101 is configured to obtain a face image. The positioning module 102 is configured to locate facial feature points on the face image. The area division module 103 is configured to perform area division on the located facial feature points on the human face image, and divide the facial features on the human face image into a plurality of feature areas. The extraction module 104 is configured to simultaneously extract images within the limited range of one or more feature areas on the face image for facial information fusion processing, set the face image to be processed as the target image, and set the face image to be processed as the...

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 a face image processing method and device, for solving the problem that at most two processed new face images can be obtained due to the fact that the face features of a target image and a source image are processed, and the selectivity of a user is low. The technical scheme of the face image processing method and device is characterized by comprising the following steps: obtaining a face image; positioning the face feature points on the face image; carrying out region division on the positioned face feature points on the face image; simultaneously extracting images in a limited range of one or more feature regions on the face image; transforming the image in the corresponding feature region on the target image according to the shape in the feature region on the source image; transforming the image in the corresponding feature region on the target image according to the skin color distribution information in the feature region on the source image; and obtaining different new face images by combining images in one or more feature regions on the source image and the target image, and achieving the effect of improving the selectivity of the face image processed by the user.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, it relates to a method and device for face image processing. Background technique [0002] With the rapid development of smart electronic products, users often perform artistic and entertaining processing on their avatars through mobile phones, tablet computers and computers. Existing face image processing generally adopts the method of combining faces or changing faces, both of which are based on photos to realize image processing, and the similarity between the produced cartoon image and the image itself is relatively low. [0003] A Chinese patent whose announcement number is CN105184249B and whose announcement date is July 18, 2017 has been retrieved. The scheme discloses a method and device for face image processing. The method includes: The feature points are positioned; according to the range defined by the facial feature points, the image of the fa...

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): G06T7/90G06T7/33G06T5/50G06K9/00
CPCG06T7/90G06T5/50G06T7/33G06T2207/20221G06V40/171G06V40/161
Inventor 马凌
Owner 深圳市紫石文化传播有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products