CN106778706A - A kind of real-time mask video display method based on Expression Recognition - Google Patents
A kind of real-time mask video display method based on Expression Recognition Download PDFInfo
- Publication number
- CN106778706A CN106778706A CN201710068336.5A CN201710068336A CN106778706A CN 106778706 A CN106778706 A CN 106778706A CN 201710068336 A CN201710068336 A CN 201710068336A CN 106778706 A CN106778706 A CN 106778706A
- Authority
- CN
- China
- Prior art keywords
- video
- mask
- storehouse
- expressive features
- recipient
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a kind of real-time mask video display method based on Expression Recognition, including expressive features storehouse, mask storehouse, video sender S ends, video recipient R ends and following steps:Based on the human face expression in expressive features storehouse identification video sender's video, the human face expression feature of present frame is obtained, and the expressive features are sent to video recipient, video recipient selects the mask for meeting the expressive features to be shown from mask storehouse.The present invention is using the smart machine with video acquisition device, based on user, truly expression carries out live chat, cartoon making that is live, being driven based on expression with mask, user is chatted using different masks, it is live, lifted video interactive interest;Or the automation cartoon making driven based on expression is carried out, greatly promote the efficiency of cartoon making.
Description
Technical field
The smart machine with video acquisition device is the present invention relates to the use of, the true expression based on user is entered with mask
The chat of row real-time video, net cast, the cartoon making driven based on expression so that user can be entered using different masks
Row chat, live, the interest of lifting video interactive;Or the cartoon making driven based on expression is carried out, greatly promote animation
The efficiency of making.
Background technology
Video chat, net cast based on smart machine are very universal, add various entertaining on face recently
The figure of decoration chats software, is pursued by young man deeply because it is interesting, and this kind of application is that textures are realized on the face in true man, its Face Changing
Effect is limited.The present invention can replace true man's image with various masks, and real-time synchronization real expresses one's feelings, and realizes such as cartoon
The same social interaction effect.On the other hand, existing cartoon making is that designer makes whole animation by professional tool
Plot, Expression Recognition realizes the automation cartoon making that expression drives during the present invention can be based on true man's video, greatly promotes dynamic
Draw the efficiency for making.
The content of the invention
The technical solution adopted by the present invention is:Initially set up expressive features storehouse E, mask storehouse M;It is then based on the expression special
The human face expression in storehouse E identification video sender's videos is levied, the expressive features of present frame is obtained, and the expressive features are sent to
Video recipient, video recipient selects the mask for meeting the expressive features to be shown from the mask storehouse M.It is of the invention
Technical scheme general flow chart is as shown in Figure 1.
The invention provides a kind of real-time mask video interactive method based on Expression Recognition, including expressive features storehouse E, vacation
Face storehouse M, video sender S ends and video recipient R ends, specific interaction are comprised the following steps:
(1) at the video sender S ends, initialization S ends masks Ms;
(2) at the video sender S ends, by S ends masks MsMark ID (Ms) it is sent to the video recipient R ends;
(3) at the video sender S ends, present frame f is obtainedcurrent, detect face k=face (fcurrent);
(4) at the video sender S ends, based on human face expression in the video of expressive features storehouse E identification S ends, k is obtained
Expressive features ek;
(5) at the video sender S ends, by expressive features ekIt is sent to the video recipient R ends;
(6) at the video sender S ends, go to step (3);
(7) at the video recipient R ends, S ends masks M is receivedsMark ID (Ms);
(8) at the video recipient R ends, expressive features e is receivedk;
(9) at the video recipient R ends, select and show from the mask storehouse M to be designated ID (Ms) and meet table
Feelings feature ekMask Ms(ek);
(10) at the video recipient R ends, go to step (8).
The expressive features storehouse E is that the abstract characteristics of the different expressions of one group of definition are represented.
The mask storehouse M is the set comprising the different masks expressed one's feelings defined in E.
The video sender S ends and the video recipient R ends, in same equipment, or can be based on
Multiple terminals that wired, wireless network is communicated.
At the video recipient R ends, select and show from the mask storehouse M to be designated ID (Ms) and meet expression spy
Levy ekMask Ms(ek), by the serial mask of continuous displaying, so as to realize real-time mask video interactive.
The present invention has advantages below:
(1) video interactive both sides can carry out interaction with the different mask of unrestricted choice, lift the interest of video interactive.
(2) cartoon making can be realized based on true man's expression driving, greatly improves the efficiency of cartoon making.
(3) due to expressive features are only transmitted in video interactive and non-video data, the requirement to the network bandwidth substantially reduces,
Can realize that the animation based on true man's expression is interactive under the network environment of limited bandwidth.
Brief description of the drawings
Fig. 1 is a kind of general flow chart of the real-time mask video display method based on Expression Recognition.
Specific embodiment
Below in conjunction with the accompanying drawings, the present invention is expanded on further by specific embodiment.Specific embodiment is merely to illustrate this
Invention rather than limitation the scope of protection of present invention.
Expressive features storehouse E={ E1, E2..., En, there are n kind expressive features.
There is m mask image in mask storehouse, and each mask image has n kinds to express one's feelings, therefore has m × n mask.
Wherein, ij is MijMark, i=1,2 ..., m, j=1,2 ..., n.
Reference picture 1, in step sl, at S ends, the sender-selected mask M for oneself thinking of videoi, initialization S ends mask
Ms=Mi;
In step S2, at S ends, by MsMark ID (Ms)=i is sent to receiving terminal R;
In step S3, at S ends, present frame f is obtainedcurrent, detect face f=face (fcurrent);
In step S4, at S ends, based on expressive features storehouse E, human face expression in the video of S ends is recognized with googlenet algorithms,
Obtain the expressive features e of kk=El, l=[1,2 ..., n];
In step S5, at S ends, by expressive features ekIt is sent to video recipient R ends;
In step S6, at S ends, S3 is gone to step;
In step R1, at R ends, S ends masks M is receivedsMark ID (Ms)=i;
In step R2, at R ends, expressive features e is receivedk=El;
In step R3, at R ends, select and show from the M of mask storehouse to be designated ID (Ms)=i and meet expressive features ek=
ElMask Ms(ek);
In step R4, at R ends, R2 is gone to step.
Although illustrating the present invention, people in the art with reference to certain exemplary embodiments of the invention
Member, can be in shape it should be understood that in the case where the spirit and scope of the present invention defined by claim and its equivalent are not departed from
Various changes are carried out in formula and details.
Claims (5)
1. a kind of real-time mask video display method based on Expression Recognition, it is characterised in that including expressive features storehouse E, mask storehouse
M, video sender S ends and video recipient R ends, and comprise the steps of:
(1) at the video sender S ends, initialization S ends masks Ms;
(2) at the video sender S ends, by S ends masks MsMark ID (Ms) it is sent to the video recipient R ends;
(3) at the video sender S ends, present frame f is obtainedcurrent, detect face k=face (fcurrent);
(4) at the video sender S ends, based on human face expression in the video of expressive features storehouse E identification S ends, the table of k is obtained
Feelings feature ek;
(5) at the video sender S ends, by expressive features ekIt is sent to the video recipient R ends;
(6) at the video sender S ends, go to step (3);
(7) at the video recipient R ends, S ends masks M is receivedsMark ID (Ms);
(8) at the video recipient R ends, expressive features e is receivedk;
(9) at the video recipient R ends, select and show from the mask storehouse M to be designated ID (Ms) and meet expressive features
ekMask Ms(ek);
(10) at the video recipient R ends, go to step (8).
2. method according to claim 1, it is characterised in that:The expressive features storehouse E is taking out for one group of different expression of definition
As character representation.
3. method according to claim 1, it is characterised in that:The mask storehouse M is comprising the different masks expressed one's feelings defined in E
Set.
4. method according to claim 1, it is characterised in that:The video sender S ends and the video recipient R ends,
The multiple terminals that can be communicated in same equipment, or based on wired, wireless network.
5. method according to claim 1, it is characterised in that:At the video recipient R ends, selected from the mask storehouse M
Select and show and be designated ID (Ms) and meet expressive features ekMask Ms(ek), by the serial mask of continuous displaying, realize real-time
Mask video playback.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710068336.5A CN106778706A (en) | 2017-02-08 | 2017-02-08 | A kind of real-time mask video display method based on Expression Recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710068336.5A CN106778706A (en) | 2017-02-08 | 2017-02-08 | A kind of real-time mask video display method based on Expression Recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106778706A true CN106778706A (en) | 2017-05-31 |
Family
ID=58955393
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710068336.5A Pending CN106778706A (en) | 2017-02-08 | 2017-02-08 | A kind of real-time mask video display method based on Expression Recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106778706A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107277642A (en) * | 2017-07-24 | 2017-10-20 | 硕诺科技(深圳)有限公司 | A kind of method that entertaining textures are realized based on video call data stream process |
CN109218648A (en) * | 2018-09-21 | 2019-01-15 | 维沃移动通信有限公司 | A kind of display control method and terminal device |
CN110650306A (en) * | 2019-09-03 | 2020-01-03 | 平安科技(深圳)有限公司 | Method and device for adding expression in video chat, computer equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102890777A (en) * | 2011-07-21 | 2013-01-23 | 爱国者电子科技(天津)有限公司 | Computer system capable of identifying facial expressions |
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 |
CN103440709A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Intelligent human face analyzer |
CN103824059A (en) * | 2014-02-28 | 2014-05-28 | 东南大学 | Facial expression recognition method based on video image sequence |
CN104780339A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading expression effect animation in instant video |
-
2017
- 2017-02-08 CN CN201710068336.5A patent/CN106778706A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102890777A (en) * | 2011-07-21 | 2013-01-23 | 爱国者电子科技(天津)有限公司 | Computer system capable of identifying facial expressions |
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 |
CN103440709A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Intelligent human face analyzer |
CN103824059A (en) * | 2014-02-28 | 2014-05-28 | 东南大学 | Facial expression recognition method based on video image sequence |
CN104780339A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading expression effect animation in instant video |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107277642A (en) * | 2017-07-24 | 2017-10-20 | 硕诺科技(深圳)有限公司 | A kind of method that entertaining textures are realized based on video call data stream process |
CN107277642B (en) * | 2017-07-24 | 2020-09-15 | 硕诺科技(深圳)有限公司 | Method for realizing interesting mapping based on video call data stream processing |
CN109218648A (en) * | 2018-09-21 | 2019-01-15 | 维沃移动通信有限公司 | A kind of display control method and terminal device |
CN110650306A (en) * | 2019-09-03 | 2020-01-03 | 平安科技(深圳)有限公司 | Method and device for adding expression in video chat, computer equipment and storage medium |
CN110650306B (en) * | 2019-09-03 | 2022-04-15 | 平安科技(深圳)有限公司 | Method and device for adding expression in video chat, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10097492B2 (en) | Storage medium, communication terminal, and display method for enabling users to exchange messages | |
CN105373224B (en) | A kind of mixed reality games system based on general fit calculation and method | |
JP6461630B2 (en) | COMMUNICATION SYSTEM, COMMUNICATION DEVICE, PROGRAM, AND DISPLAY METHOD | |
CN106778706A (en) | A kind of real-time mask video display method based on Expression Recognition | |
CN107077720A (en) | Method, device and the equipment of image procossing | |
US20120050325A1 (en) | System and method for providing virtual reality linking service | |
CN103916621A (en) | Method and device for video communication | |
CN106961621A (en) | Use the communication of incarnation | |
CN101930618B (en) | Method for producing individual two-dimensional anime | |
CN107018330A (en) | A kind of guidance method and device of taking pictures in real time | |
CN105512326A (en) | Picture recommending method and system | |
CN107195210A (en) | Two dimension and the three-dimensional teleeducation system combined and control method | |
CN103984488B (en) | A kind of information processing method and electronic equipment | |
CN102624648B (en) | Instant messaging method, device and system and terminal equipment | |
CN110310142A (en) | Elevator card put-on method and device based on crowd's value analysis | |
CN110536095A (en) | Call method, device, terminal and storage medium | |
CN106875470A (en) | The method and system for changing main broadcaster's image of live platform | |
EP4147425A1 (en) | Messaging system with a carousel of related entities | |
CN107070784A (en) | A kind of 3D instant communicating systems based on WebGL and VR technologies | |
CN106780675A (en) | A kind of method and apparatus for showing animation | |
CN106651604A (en) | User rating interaction method, client and electronic device | |
CN108635860A (en) | A kind of game role expression production method in playing | |
CN110166351A (en) | A kind of exchange method based on instant messaging, device and electronic equipment | |
CN106126691A (en) | Method and device for adding friends and electronic equipment | |
Suzuki et al. | Windtherm: A wearable VR device that provides temperature-controlled wind |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
DD01 | Delivery of document by public notice |
Addressee: Chen Bin Document name: Notification that Application Deemed to be Withdrawn |
|
DD01 | Delivery of document by public notice |