Generation method and device of cartoon face image and computer storage medium

A face image and cartoon face technology, applied in the field of image processing, can solve the problems of deformation of cartoon face images, reduce the similarity between cartoon face images and real faces, reduce the operability of cartoon face images, etc., and achieve Improve operability and improve the effect of similarity

Pending Publication Date: 2018-10-30
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] During the research and practice of the prior art, the inventors of the present invention found that, in the prior art, since the cartoon face image is obtained through the transformation of the overall style, the human body on the generated cartoon face image The characteristic parts exist in one piece, which makes it impossible to modify or replace a certain characteristic part in the cartoon face image in the future. For example, if you need to adjust a certain characteristic part of the cartoon face image in the future, you can only The adjustment method is carried out. If the size of the eyes needs to be adjusted, it can only be adjusted by stretching the cartoon face image as a whole. However, the overall stretching will cause deformation of other parts of the cartoon face image, which greatly reduces the size of the cartoon face image. The operability of the image will also reduce the similarity between the cartoon face image and the real face

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
  • Generation method and device of cartoon face image and computer storage medium
  • Generation method and device of cartoon face image and computer storage medium
  • Generation method and device of cartoon face image and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0041] This embodiment will be described from the perspective of the terminal.

[0042] Refer to Figure 2a And combine Figure 2b In this embodiment, the method for generating cartoon face images may include the following steps:

[0043] 201. Obtain a face image to be processed.

[0044] The image to be processed may be an image containing a real human face, and the input image may be directly used as the image to be processed, or the input image may also be processed to obtain the image to be processed. In an implementation manner, obtaining the image to be processed may include the following steps (11) to (13):

[0045] (11) Obtain the input image. The input image may be, for example, a photo taken by the user, or a photo selected by the user from an album, or a photo downloaded from the Internet, or the like.

[0046] (12) Use the fully convolutional neural network model to identify the human body region in the input image.

[0047] Fully Convolutional Networks (FCN) can be used to...

no. 2 example

[0158] This embodiment provides a cartoon face image generating device, wherein the cartoon face image generating device may be integrated in a terminal as a whole, or may be a system including a server and a terminal. This embodiment will be described by taking the generation device integrated in the terminal as an example.

[0159] See Picture 11 , The cartoon face image generating device of this embodiment includes a first acquisition module 1101, a recognition module 1102, a second acquisition module 1103, an adjustment module 1104, and a generation module 1105.

[0160] The first obtaining module 1101 is used to obtain a face image to be processed. Specifically, the first acquisition module 1101 can be used to acquire the input image, and then use the fully convolutional neural network model to identify the human body area in the input image, remove the background area except the human body area in the input image, and then obtain the person to be processed Face image. The ...

no. 3 example

[0186] Correspondingly, the embodiment of the present invention also provides a terminal, such as Figure 13 As shown, the terminal may include a radio frequency (RF, Radio Frequency) circuit 1301, a memory 1302 including one or more computer-readable storage media, an input unit 1303, a display unit 1304, a sensor 1305, an audio circuit 1306, and wireless fidelity The (WiFi, Wireless Fidelity) module 1307 includes a processor 1308 with one or more processing cores, a power supply 1309 and other components. Those skilled in the art can understand, Figure 13 The terminal structure shown in does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or a combination of some components, or a different component arrangement. among them:

[0187] The RF circuit 1301 can be used for receiving and sending signals in the process of sending and receiving information or talking. In particular, after receiving the downlink informat...

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 embodiment of the invention discloses a generation method and device of a cartoon face image and a computer storage medium. In the method, a to-be-processed face image is acquired; face feature information is recognized from the to-be-processed face image, and includes five-sense-organ features information; cartoon materials corresponding to all face feature parts in the to-be-processed face image are respectively acquired according to the face feature information to obtain cartoon face materials, and the cartoon face materials include cartoon five-sense-organ materials and other cartoon materials other than the cartoon five-sense-organ materials; adjustment parameters are utilized to respectively adjust each of the cartoon five-sense-organ materials; and the other cartoon materials and the adjusted cartoon five-sense-organ materials are combined to generate the cartoon face image. Through the above manner, operability of the cartoon face image and similarity with the to-be-processed face image can be improved.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device and computer storage medium for generating cartoon face images. Background technique [0002] Cartoon images have bright colors, vivid shapes, high recognition and affinity, and cartoon portraits are favored by users because of their general, concise, and humorous characteristics. In order to meet the needs of users, more and more camera applications or image processing applications have cartoon special effects. For example, users’ avatar photos can be converted into corresponding cartoon face images, so that users can easily create their own cartoon portraits. Increase entertainment fun. At present, it is usually based on the image stylization algorithm to transform the entire face image of the face image to be processed to obtain the cartoon face image. The algorithm mainly deals with the various feature parts of the face in the face image. Edge e...

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): G06T11/00G06V10/764
CPCG06T11/00G06V40/165G06V40/168G06V10/82G06V10/764G06T11/001G06T11/60
Inventor 葛彦昊邢雪源傅斌曾毅榕沈鹏程汪铖杰
Owner TENCENT TECH (SHENZHEN) CO LTD
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