CN105809612A - Method of transforming image into expression and intelligent terminal - Google Patents
Method of transforming image into expression and intelligent terminal Download PDFInfo
- Publication number
- CN105809612A CN105809612A CN201410849811.9A CN201410849811A CN105809612A CN 105809612 A CN105809612 A CN 105809612A CN 201410849811 A CN201410849811 A CN 201410849811A CN 105809612 A CN105809612 A CN 105809612A
- Authority
- CN
- China
- Prior art keywords
- facial characteristics
- features
- expression
- human face
- organ
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention is suitable for the intelligent terminal technology field, and provides a method of transforming image into expression and an intelligent terminal. The method is characterized in that according to an image or a video stream comprising a human face acquired by a camera or a video recorder, a human face area can be identified from the image or the video frame; the original characteristics and the skin color characteristic of the human face area can be extracted, and the original characteristics comprise the face characteristic and the expression characteristic; according to the face characteristic, the expression characteristic, and the skin color characteristic, the simulated expression can be generated. The real-time human face image can be transformed into the vivid and customized expression.
Description
Technical field
The invention belongs to intelligent terminal's technical field, particularly relate to a kind of photo and be converted into method and the intelligent terminal of expression.
Background technology
Along with the development of immediate communication tool in intelligent terminal, such as QQ, MSN, mail, forum etc., interpersonal communication networking more.Owing to these immediate communication tools user is essentially all by display content obtaining information; in order to increase the vividness of chat process; often mutually send various preset expression pictures or real-time human face photo of clapping expresses oneself mood or emotion; in prior art; user needs to ransack substantial amounts of expression storehouse just can find the expression relatively meeting oneself real-time mood; or use template base that photo is converted into the expression of medelling; these express the mode comparison pattern of expression; not vivid; lacking individuality, it is also difficult to increase the cordial feeling of both sides.
Summary of the invention
Embodiments provide a kind of photo and be converted into method and the intelligent terminal of expression, it is intended to solve prior art comparison pattern, not vivid, the problem of lacking individuality.
On the one hand, it is provided that a kind of photo is converted into the method for expression, and described method includes:
Contain image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region；
Extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；
According to described facial characteristics, expressive features and features of skin colors, generate simulation expression.
On the other hand, it is provided that a kind of intelligent terminal, described intelligent terminal includes:
Face datection unit, for containing image or the video flowing of face according to video camera or camera collection, identifies human face region from described image or frame of video；
Feature extraction unit, for extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；
First generates unit, for according to described facial characteristics, expressive features and features of skin colors, generating simulation expression.
In the embodiment of the present invention, contain image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region；Extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；According to described facial characteristics, expressive features and features of skin colors, generate simulation expression, the present invention, it is achieved that real-time face image is converted into vivid, personalized expression.
Accompanying drawing explanation
Fig. 1 is the flowchart that the photo that the embodiment of the present invention one provides is converted into the method for expression；
Fig. 2 is the concrete structure block diagram of the intelligent terminal that the embodiment of the present invention four provides.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
In embodiments of the present invention, contain image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region；Extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；According to described facial characteristics, expressive features and features of skin colors, generate simulation expression.
Below in conjunction with specific embodiment, the realization of the present invention is described in detail:
Embodiment one
Fig. 1 illustrates that what the photo that the embodiment of the present invention one provides was converted into the method for expression realizes flow process, and details are as follows:
It should be noted that present invention is particularly suitable for having photographic head or be connected to the intelligent terminal of video camera, wherein, described intelligent terminal includes mobile phone, PC, panel computer, ipad.
In step S101, contain image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region.
In the present embodiment, obtaining identification human face region by Face datection, be mainly used in the pretreatment of recognition of face in practice from described image or frame of video, namely accurate calibration goes out position and the size of face in the picture.The pattern feature comprised in facial image is very abundant, such as histogram feature, color characteristic, template characteristic, architectural feature and Haar feature etc..Face datection is exactly that the information that this is wherein useful is picked out, and utilizes these features to realize Face datection, obtains effective human face region.
In step s 102, extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features.
In the present embodiment, described primitive character includes facial characteristics, expressive features.Described facial characteristics includes human eye, nose, face, and described expressive features is the transient characteristics that expression shape change produces, including wrinkle.The concrete primitive character that geometrical measurers, macroscopic features method or composite character method specifically can be used to extract described human face region.
As a preferred version, after this step, it is also possible to described human face region to be carried out Feature Dimension Reduction and feature extraction.
Wherein, the primitive character often space dimensionality obtained is very big, such googol evidence and information redundancy will add amount of calculation and the complexity of next step analysis undoubtedly, it is thus desirable to by mapping or change the subspace that high dimensional feature is transformed into low-dimensional or a part for high dimensional feature being extracted, to reduce dimension reduction amount of calculation, conventional Feature Dimension Reduction and the method for extraction mainly include PCA, ICA.
As one of another preferred version, after described human face region is carried out Feature Dimension Reduction and feature extraction by this, described facial characteristics and preset standard feature can also be contrasted, obtain prominent organ in described facial characteristics, deforming described prominent organ, described prominent organ is differ bigger organ with described preset standard feature.
Wherein, by contrasting described facial characteristics and preset standard feature, after getting prominent organ, as eyes are big, process eyes more greatly by deforming exaggerationization more, expressive features can also be strengthened simultaneously, to reach to keep photo face is expressed one's feelings vivid and prominent effect.
As the replaceable of above-mentioned preferred version or and deposit scheme, after described human face region is carried out Feature Dimension Reduction and feature extraction by this, it is also possible to receive the prominent organ that selects from described facial characteristics of user, deform described prominent organ.
Wherein, by receiving the prominent organ that user selects from described facial characteristics, as nose is big, process nose more greatly by deforming exaggerationization more, expressive features can be strengthened simultaneously, to reach to keep photo face is expressed one's feelings vivid and prominent effect.
In step s 103, according to described facial characteristics, expressive features and features of skin colors, generate simulation expression.
In the present embodiment, intelligent terminal, according to described facial characteristics, expressive features and features of skin colors, generates simulation expression.The more true fine and smooth expression of simulation.
After this step, also include the voice expressed one's feelings according to several simulations and receive, synthesize dynamic expression.
Wherein, for video, obtaining several simulation expressions and the voice of this video by processing each frame, intelligent terminal synthesizes dynamic expression.
The present embodiment, it is achieved that real-time face image is converted into vivid, personalized expression, such as caricature, animation etc..
Embodiment two
Fig. 2 illustrates the concrete structure block diagram of the intelligent terminal that the embodiment of the present invention two provides, and for the ease of illustrating, illustrate only the part relevant to the embodiment of the present invention.In the present embodiment, this intelligent terminal includes: includes photographic head or is connected to video camera.
Wherein, Face datection unit 21, for containing image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region；
Feature extraction unit 22, for extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；
First generates unit 23, for according to described facial characteristics, expressive features and features of skin colors, generating simulation expression.
Further, described device also includes:
Feature Dimension Reduction unit 24, for carrying out Feature Dimension Reduction and feature extraction to described human face region.
Further, described stout man's also includes:
First deformation unit 25, is used for contrasting described facial characteristics and preset standard feature, it is thus achieved that prominent organ in described facial characteristics, deforms described prominent organ, and described prominent organ is differ bigger organ with described preset standard feature；
Second deformation unit 26, for receiving the prominent organ that user selects from described facial characteristics, deforms described prominent organ.
Further, described device also includes:
Second generates unit 27, for the voice expressed one's feelings according to several simulations and receive, synthesizes dynamic expression.
The intelligent terminal that the embodiment of the present invention provides can be applied in the embodiment of the method one of aforementioned correspondence, and details, referring to the description of above-described embodiment one, do not repeat them here.
It should be noted that in said system embodiment, included unit is carry out dividing according to function logic, but is not limited to above-mentioned division, as long as being capable of corresponding function；It addition, the concrete title of each functional unit is also only to facilitate mutually distinguish, it is not limited to protection scope of the present invention.
Additionally, one of ordinary skill in the art will appreciate that all or part of step realizing in the various embodiments described above method can be by the hardware that program carrys out instruction relevant and completes, corresponding program can be stored in a computer read/write memory medium, described storage medium, such as ROM/RAM, disk or CD etc..
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all any amendment, equivalent replacement and improvement etc. made within the spirit and principles in the present invention, should be included within protection scope of the present invention.
Claims (8)
1. the method that a photo is converted into expression, it is characterised in that described method includes:
Contain image or the video flowing of face according to video camera or camera collection, from described image or frame of video, identify human face region；
Extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；
According to described facial characteristics, expressive features and features of skin colors, generate simulation expression.
2. the method for claim 1, it is characterised in that also include after the primitive character of the described human face region of described extraction and features of skin colors:
Described human face region is carried out Feature Dimension Reduction and feature extraction.
3. method as claimed in claim 2, it is characterised in that also include after the primitive character of the described human face region of described extraction and features of skin colors:
Contrasting described facial characteristics and preset standard feature, it is thus achieved that prominent organ in described facial characteristics, deform described prominent organ, described prominent organ is differ bigger organ with described preset standard feature；
Or/and
Receive the prominent organ that user selects from described facial characteristics, deform described prominent organ.
4. the method for claim 1, it is characterised in that described according to described facial characteristics, expressive features and features of skin colors, also includes after generating simulation expression:
According to the voice that several simulations are expressed one's feelings and received, synthesize dynamic expression.
5. an intelligent terminal, including photographic head or be connected to video camera, it is characterised in that described intelligent terminal includes:
Face datection unit, for containing image or the video flowing of face according to video camera or camera collection, identifies human face region from described image or frame of video；
Feature extraction unit, for extracting primitive character and the features of skin colors of described human face region, described primitive character includes facial characteristics, expressive features；
First generates unit, for according to described facial characteristics, expressive features and features of skin colors, generating simulation expression.
6. device as claimed in claim 5, it is characterised in that described device also includes:
Feature Dimension Reduction unit, for carrying out Feature Dimension Reduction and feature extraction to described human face region.
7. device as claimed in claim 6, it is characterised in that described stout man's also includes:
First deformation unit, is used for contrasting described facial characteristics and preset standard feature, it is thus achieved that prominent organ in described facial characteristics, deforms described prominent organ, and described prominent organ is differ bigger organ with described preset standard feature；
Second deformation unit, for receiving the prominent organ that user selects from described facial characteristics, deforms described prominent organ.
8. device as claimed in claim 5, it is characterised in that described device also includes:
Second generates unit, for the voice expressed one's feelings according to several simulations and receive, synthesizes dynamic expression.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410849811.9A CN105809612A (en) | 2014-12-30 | 2014-12-30 | Method of transforming image into expression and intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410849811.9A CN105809612A (en) | 2014-12-30 | 2014-12-30 | Method of transforming image into expression and intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105809612A true CN105809612A (en) | 2016-07-27 |
Family
ID=56421497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410849811.9A Pending CN105809612A (en) | 2014-12-30 | 2014-12-30 | Method of transforming image into expression and intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105809612A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529450A (en) * | 2016-11-03 | 2017-03-22 | 珠海格力电器股份有限公司 | Emoticon picture generating method and device |
| CN106789556A (en) * | 2016-11-28 | 2017-05-31 | 腾讯科技（深圳）有限公司 | expression generation method and device |
| CN107370887A (en) * | 2017-08-30 | 2017-11-21 | 维沃移动通信有限公司 | A kind of expression generation method and mobile terminal |
| CN107451560A (en) * | 2017-07-31 | 2017-12-08 | 广东欧珀移动通信有限公司 | User's expression recognition method, device and terminal |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101072207A (en) * | 2007-06-22 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Exchange method for instant messaging tool and instant messaging tool |
| CN101706874A (en) * | 2009-12-25 | 2010-05-12 | 青岛朗讯科技通讯设备有限公司 | Method for face detection based on features of skin colors |
| US20100280829A1 (en) * | 2009-04-29 | 2010-11-04 | Paramesh Gopi | Photo Management Using Expression-Based Voice Commands |
| CN102194108A (en) * | 2011-05-13 | 2011-09-21 | 华南理工大学 | Smiley face expression recognition method based on clustering linear discriminant analysis of feature selection |
| CN102393951A (en) * | 2011-06-30 | 2012-03-28 | Tcl集团股份有限公司 | Deformation method of human face model |
| CN102479388A (en) * | 2010-11-22 | 2012-05-30 | 北京盛开互动科技有限公司 | Expression interaction method based on face tracking and analysis |
| CN102890776A (en) * | 2011-07-21 | 2013-01-23 | 爱国者电子科技(天津)有限公司 | Method for searching emoticons through facial expression |
| CN103886632A (en) * | 2014-01-06 | 2014-06-25 | 宇龙计算机通信科技(深圳)有限公司 | Method for generating user expression head portrait and communication terminal |
| CN104346824A (en) * | 2013-08-09 | 2015-02-11 | 汉王科技股份有限公司 | Method and device for automatically synthesizing three-dimensional expression based on single facial image |
-
2014
- 2014-12-30 CN CN201410849811.9A patent/CN105809612A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101072207A (en) * | 2007-06-22 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Exchange method for instant messaging tool and instant messaging tool |
| US20100280829A1 (en) * | 2009-04-29 | 2010-11-04 | Paramesh Gopi | Photo Management Using Expression-Based Voice Commands |
| CN101706874A (en) * | 2009-12-25 | 2010-05-12 | 青岛朗讯科技通讯设备有限公司 | Method for face detection based on features of skin colors |
| CN102479388A (en) * | 2010-11-22 | 2012-05-30 | 北京盛开互动科技有限公司 | Expression interaction method based on face tracking and analysis |
| CN102194108A (en) * | 2011-05-13 | 2011-09-21 | 华南理工大学 | Smiley face expression recognition method based on clustering linear discriminant analysis of feature selection |
| CN102393951A (en) * | 2011-06-30 | 2012-03-28 | Tcl集团股份有限公司 | Deformation method of human face model |
| CN102890776A (en) * | 2011-07-21 | 2013-01-23 | 爱国者电子科技(天津)有限公司 | Method for searching emoticons through facial expression |
| CN104346824A (en) * | 2013-08-09 | 2015-02-11 | 汉王科技股份有限公司 | Method and device for automatically synthesizing three-dimensional expression based on single facial image |
| CN103886632A (en) * | 2014-01-06 | 2014-06-25 | 宇龙计算机通信科技(深圳)有限公司 | Method for generating user expression head portrait and communication terminal |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529450A (en) * | 2016-11-03 | 2017-03-22 | 珠海格力电器股份有限公司 | Emoticon picture generating method and device |
| CN106789556A (en) * | 2016-11-28 | 2017-05-31 | 腾讯科技（深圳）有限公司 | expression generation method and device |
| CN106789556B (en) * | 2016-11-28 | 2021-03-19 | 腾讯科技（深圳）有限公司 | Expression generation method and device |
| CN107451560A (en) * | 2017-07-31 | 2017-12-08 | 广东欧珀移动通信有限公司 | User's expression recognition method, device and terminal |
| CN107370887A (en) * | 2017-08-30 | 2017-11-21 | 维沃移动通信有限公司 | A kind of expression generation method and mobile terminal |
| CN107370887B (en) * | 2017-08-30 | 2020-03-10 | 维沃移动通信有限公司 | Expression generation method and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359538B (en) | Training method of convolutional neural network, gesture recognition method, device and equipment | |
| US10789453B2 (en) | Face reenactment | |
| US11798261B2 (en) | Image face manipulation | |
| US20190279410A1 (en) | Electronic Messaging Utilizing Animatable 3D Models | |
| CN105513125B (en) | Composograph generating means and method, the recording medium for executing this method | |
| US11783556B2 (en) | Augmented reality content generators including 3D data in a messaging system | |
| US20150213604A1 (en) | Avatar-based video encoding | |
| US11657575B2 (en) | Generating augmented reality content based on third-party content | |
| US11494999B2 (en) | Procedurally generating augmented reality content generators | |
| CN113362263B (en) | Method, apparatus, medium and program product for transforming an image of a virtual idol | |
| CN105809612A (en) | Method of transforming image into expression and intelligent terminal | |
| KR20230162096A (en) | Facial compositing in content for online communities using selection of facial expressions | |
| CN113453027B (en) | Live video and virtual make-up image processing method and device and electronic equipment | |
| CN112149599B (en) | Expression tracking method and device, storage medium and electronic equipment | |
| CN114332365A (en) | Virtual character generation method and device, electronic equipment and storage medium | |
| CN104715505A (en) | Three-dimensional head portrait generating system and generating device and generating method thereof | |
| CN204791190U (en) | Three -dimensional head portrait generation system and device thereof | |
| CN117153195B (en) | Method and system for generating speaker face video based on adaptive region shielding | |
| CN117746340A (en) | Vehicle-mounted display screen interaction method and device | |
| Ali et al. | Cartoonization, Caricature and Emotion Generation from A Single Intensity Frontal Facial Image | |
| Ou et al. | Mapping peking opera facial makeup onto a human face image based on facial landmarks | |
| CN117830527A (en) | Digital person customizable portrait implementing method, system and storage medium | |
| CN112862945A (en) | Record generation method and device | |
| Dong et al. | One Simple Virtual Avatar System Based on Single Image | |
| BRPI0903935B1 (en) | COMPUTER-BASED FACIAL ANIMATION SYNTHESIS SYSTEM BASED ON IMAGE HANDLING |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |