CN106823374A - Talking Avatar hands based on android system swim the construction method of software - Google Patents
Talking Avatar hands based on android system swim the construction method of software Download PDFInfo
- Publication number
- CN106823374A CN106823374A CN201710030650.4A CN201710030650A CN106823374A CN 106823374 A CN106823374 A CN 106823374A CN 201710030650 A CN201710030650 A CN 201710030650A CN 106823374 A CN106823374 A CN 106823374A
- Authority
- CN
- China
- Prior art keywords
- face
- voice
- video
- photo
- doll
- 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
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
- A63F13/65—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition
- A63F13/655—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition by importing photos, e.g. of the player
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/164—Detection; Localisation; Normalisation using holistic features
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (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)
- Processing Or Creating Images (AREA)
- Toys (AREA)
Abstract
The present invention discloses the construction method that a kind of Talking Avatar hands based on android system swim software, comprises the following steps：（1）Design the general frame of Talking Avatar softwares；（2）Talking Avatar systematic functions are realized, including：The portrait photographs inside human face photo, or selection mobile phone photo album can be shot according to mobile phone camera；Then, fly recognition of face interface based on University of Science and Technology's news, after realizing importing human face photo, generate a Talking Avatar function similar to photo face.（3）Realize that Talking Avatar change the outfit function.（4）By user recording, recording file is obtained and preserved.（5）Video record is carried out to mobile phone screen, according to the content of recording file, corresponding expression and limb action is mixed to Talking Avatar.（6）Stop screen recording, generate one section of video, and sharing platform is moved based on Mob, by video sharing to each social platform, compared to prior art, the present invention has not only increased the function of Talking Avatar generations and video sharing newly, and more vivid.
Description
Technical field
It is coupled to the present invention relates to a kind of recognition of face, object for appreciation, voice recording and calls, the recording of mobile phone screen and shares
Technical field.
Background technology
With mobile technology develop rapidly and using Android operation system cellphone subscriber popularization, based on movement
All kinds of hands trip software at end more receives favor.One typical example is the mobile phone pets released by Outfit7 companies
Using game " sociable tom cat ", the software is a lovely pet cat doll, and it can touch doll not in user
With body part when make various reactions, and the content described in user can be intactly repeated with funny sound.Record
Tom cat repeats the video that user speaks, and can also be uploaded to YouTube, Facebook, Sina microblogging or circle of friends, and
Kith and kin are sent to by Email, the very big of user for therefore suffering from each ages is liked.But, due to user
The change of colony, such simple Talking Avater hands trip software can no longer meet the demand of different user colony, than
Such as：User wishes to see the Talking Avatar images for not being pet cat, being user oneself with their interactions on screen, or
It is other novel images that person says, so could preferably be applicable the demand of different user；User also is intended to many letters
Single practical software function is also joined, and can so allow a software to possess various function, it is also possible to reduce user's hand
The occupancy of machine internal memory.
The content of the invention
Goal of the invention：In order to make up the nowadays not comprehensive enough deficiency of such mobile phone games functional coverage, the present invention is provided
A kind of Talking Avatar hands based on android system swim the construction method of software.The present invention is except with above-mentioned Tom
Beyond the function that cat also has, user can also click on button and call front camera to take pictures or import in oneself mobile phone
Photo, then system one doll-shaped similar to user is generated as, the doll-shaped is as that can complete use by appearance identification technology
A series of actions that family is specified, generates Avatar.Afterwards by click on the icon at interface to apparel modeling in choose
Complete to change the outfit Avatar by selecting the moulding oneself liked.When user says one section of word against Avatar, it can be answered
State out this section of words, and corresponding limb action and abundant facial expression etc. are made according to different content of speaking.When
After user is completed to the recording of Avatar, can be repeated and its acted carries out screen recording, clicks on and preserves and can preserve
To locally, user can find the video file to this section of video file in corresponding storing path is preserved, and be shared by clicking on
Button is shared to social platforms such as circle of friends, microbloggings.
Technical scheme：A kind of Talking Avatar hands based on android system swim the construction method of software, its function
Feature mainly includes following aspect：
Function 1：User imports a photo, by recognition of face, obtains the value of user face individual features point, Ran Housheng
Into a doll-shaped similar with user as i.e. Talking Avatar；Human face detection has loosely changed the requirement to face, can be many
Angle is detected to face, according to symmetrical mapping, completion characteristic point information, detectable scope be with front as origin just
Minus 45 degree.After getting characteristic point information, face is carried out to characteristic point information than the treatment of row scaling, reapply Euclidean distance similar
Degree algorithm, calculates the Similarity value with each group picture in face database respectively, and it is carried out to unify comparing, and the choice of bubbling method is maximum
Similarity face, that is, be most like face.Relevant information record is got, Avatar storehouses are sent to, docked with Avatar storehouses, then selected
Corresponding Avatar faces, synthesize doll face；
Function 2：The software can be changed the outfit and replacing background according to user preferences to Talking Avatar；
Talking Avatar cell phone softwares provide various dress ornament and background, for user's selection；
Function 3：Talking Avatar can record user's word and then repeated；Realize voice-text
The voice conversion algorithm of sheet-voice；
Function 4：Talking Avatar can be identified according to user's word, obtain corresponding keyword, such as " you,
I, he etc. " when these keywords are found in voice, doll can make corresponding limbs facial expressions and acts；KMP keyword extraction algorithms
Keyword is obtained from text, according to the binding relationship between animation of keyword.And Dynamic trigger animation, between character repertoire
Dynamic binding is realized between animation library, synonymous triggering is supported；
Function 5：User can be according to the demand of oneself, recorded video being selected when certain, and arbitrary
When stop recording, the video sharing that user can also record is in the social platforms such as microblogging, circle of friends, QQ spaces.Call
Mob movement sharing platforms to video are recorded and synthesized, and are stored in user account afterwards.Can divide after uploaded videos
Enjoy each social platform, it is also possible to check video file.
The present invention uses Eclipse developing instruments, realizes a mobile phone games with multi-functional doll-shaped elephant.It is right
In the synthesis and identification of face, interrogate winged human face characteristic point using University of Science and Technology and obtain, then by recognition of face-synthesis mechanism.People
Face identification-synthesis mechanism is divided into three phases：Training stage, cognitive phase and choice phase.Training stage intends face
Fixed, test and collection data.Cognitive phase is obtained by human face similarity degree algorithm and is most like face.Choice phase is exactly to read parameter,
Specific face is chosen, the human face segmentation of doll is finally realized.For the conversion of sound, voice conversion algorithm is used, it is real
The voice system of existing voice-text-voice；Dynamic binding is realized between character repertoire and animation library, it is middle dynamic by text triggering
Draw；Realize that animation is synchronous with voice to play.For video sharing, Mob game sharing platforms are refer to, carry out the recording of video
And synthesis.Share afterwards in different social platforms；The video file for recording synthesis can also be checked.
Mainly realize that step is as follows：
Step 1：Make use of University of Science and Technology to interrogate and fly calling for recognition of face interface, by one photo of user input or shooting
One photo, identifies the face on photo, obtains the position of characteristic point on face on photo, is then calculated by human face similarity degree
Method matches the feature of correspondingly sized people in our databases, generates doll；
Step 2：Then the selection according to user can select the clothes of consumer taste, carry out the function that changes the outfit；
Step 3：Doll repeats voice and limbs facial expressions and acts function then depends on University of Science and Technology to interrogate rumours justice synthesis interface and language
Sound dictation interface is called, and we can allow doll typing user what is said or talked about by calling interface, by identification, then by KMP,
Data in BM algorithmic match databases, see with the presence or absence of keyword, if there is keyword, then can also be done while repeating voice
Go out corresponding action, conversely, not acting, but still have the repetition of voice；
Step 4：Using the video record interface of Mob game sharing platforms, Video Composition, video record, video point are called
Interface is enjoyed, one section of video is recorded, and we can share in major social platforms such as Sina weibo, circle of friends.
The present invention uses above-mentioned technical proposal, has the advantages that：The generation doll similar to user；Language can be realized
The recording of sound, and can realize expressing one's feelings and act；Consumer's Experience is improved；Doll with good friend's share oneself is played.
Brief description of the drawings
Fig. 1 is architectural framework figure of the invention；
Fig. 2 is the functional framework figure of software；
Fig. 3 is the use flow chart of software.
Specific embodiment
With reference to specific embodiment, the present invention is furture elucidated, it should be understood that these embodiments are merely to illustrate the present invention
Rather than limitation the scope of the present invention, after the present invention has been read, those skilled in the art are to various equivalences of the invention
The modification of form falls within the application appended claims limited range.
As shown in Fig. 2 describing the concrete function distribution of the modules of application in detail, five modules are broadly divided into：
Talking Avatar generations, Talking Avatar recording and repetition, Talking Avatar limb actions, Talking
Avatar changes the outfit and shares with video record.
As shown in figure 3, click to enter carry out the selection of men and women's pattern after, by user using sex as distinguishing mesh
's：User is allowed to obtain more preferable Consumer's Experience and the more conducively management of resource.Enter among different patterns, led by photograph album
Enter a photo, or call utilizing camera interface to shoot photo, by recognition of face-synthesis mechanism synthesis doll-shaped as.May be used also
With according to the age tone color different with regional selection, synthesis ratio compared with characteristic doll, such as Cantonese, Hunan words, old man, child
Etc..Recognition of face-synthesis mechanism is on the basis of news fly recognition of face and feature point detection, to be calculated by human face similarity degree
Each face is calculated in method, with face database, and then bubbling method is chosen out and is most like face.Doll storehouse is sent information to, with doll storehouse
Docked, matching doll-shaped as.After synthesis doll, background and clothes can be changed according to the personal preference of user.In section
Under the support of big news rumours sound, user can be input into information by text or voice two ways.Doll can play voice,
While corresponding limbs facial expressions and acts of setting out.Voice conversion algorithm is accomplished that on voice, is depended on University of Science and Technology to interrogate rumours justice and is closed
Into calling for interface and voice dictation interface, realize being changed by the voice of voice-text-voice, internal expression text through passing through again
Data in KMP, BM algorithmic match database, see with the presence or absence of keyword, if there is keyword, then are gone back while repeating voice
Corresponding action can be made, conversely, not acting, but the repetition of voice is still had；The pass that fusion KMP, BM algorithm are realized
Keyword extraction algorithm, by dynamic binding between backstage character repertoire and animation library, supports synonymous triggering.Text is obtained by keyword to remember
Record and send information to character repertoire, Dynamic trigger animation after character repertoire matching realizes play synchronous with voice.It is finally video
Sharing function is recorded, Mob movement sharing platforms is have invoked and video is recorded and synthesized, record one section of video, synthetic video
And store in user account.Each social platform can be shared after uploaded videos, such as share Sina weibo, circle of friends
Deng, it is also possible to check the video file of synthesis.
Claims (1)
1. a kind of Talking Avatar hands based on android system swim the construction method of software, it is characterised in that：Use
Eclipse developing instruments, realize a mobile phone games with multi-functional doll-shaped elephant；For the synthesis and knowledge of face
Not, interrogate winged human face characteristic point using University of Science and Technology to obtain, then by recognition of face-synthesis mechanism；Recognition of face-synthesis mechanism
It is divided into three phases：Training stage, cognitive phase and choice phase；
Data are drafted face, tested and collected to training stage；Cognitive phase is obtained by human face similarity degree algorithm and is most like
Face；Choice phase is exactly to read parameter, chooses specific face, finally realizes the human face segmentation of doll；For the conversion of sound,
Voice conversion algorithm is used, the voice system of voice-text-voice is realized；Realized between character repertoire and animation library dynamic
State is bound, and animation is triggered in centre by text；Realize that animation is synchronous with voice to play；For video sharing, Mob game is refer to
Sharing platform, carries out the recording and synthesis of video；
Share afterwards in different social platforms；The video file for recording synthesis can also be checked；
Mainly realize that step is as follows：
Step 1：Make use of University of Science and Technology to interrogate and fly calling for recognition of face interface, by one photo of user input or shooting one
Photo, identifies the face on photo, the position of characteristic point on face on photo is obtained, then by human face similarity degree algorithm
The feature of correspondingly sized people in our databases is fitted on, doll is generated；
Step 2：Then the selection according to user can select the clothes of consumer taste, carry out the function that changes the outfit；
Step 3：Doll repeats voice and limbs facial expressions and acts function then depends on University of Science and Technology's news rumours justice synthesis interface and voice to listen
Calling for interface is write, we can allow doll typing user what is said or talked about by calling interface, by identification, then be calculated by KMP, BM
Data in method matching database, see with the presence or absence of keyword, if there is keyword, then phase can be also made while repeating voice
The action answered, conversely, not acting, but still has the repetition of voice；
Step 4：Using the video record interface of Mob game sharing platforms, Video Composition, video record, video sharing is called to connect
Mouthful, one section of video is recorded, and we can share in major social platforms such as Sina weibo, circle of friends.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030650.4A CN106823374A (en) | 2017-01-17 | 2017-01-17 | Talking Avatar hands based on android system swim the construction method of software |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030650.4A CN106823374A (en) | 2017-01-17 | 2017-01-17 | Talking Avatar hands based on android system swim the construction method of software |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106823374A true CN106823374A (en) | 2017-06-13 |
Family
ID=59124755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710030650.4A Pending CN106823374A (en) | 2017-01-17 | 2017-01-17 | Talking Avatar hands based on android system swim the construction method of software |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106823374A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558853A (en) * | 2018-12-05 | 2019-04-02 | 维沃移动通信有限公司 | A kind of audio synthetic method and terminal device |
| CN110135215A (en) * | 2018-02-02 | 2019-08-16 | 上海大学 | A kind of virtual social method based on the transplanting of Avatar expression |
| CN110215683A (en) * | 2019-07-11 | 2019-09-10 | 龙马智芯（珠海横琴）科技有限公司 | A kind of electronic game system of role playing game |
| CN111599342A (en) * | 2019-02-21 | 2020-08-28 | 北京京东尚科信息技术有限公司 | Tone selecting method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419499A (en) * | 2008-11-14 | 2009-04-29 | 东南大学 | Multimedia human-computer interaction method based on cam and mike |
| WO2010076819A1 (en) * | 2008-12-30 | 2010-07-08 | Giochi Preziosi S.P.A. | A portable electronic apparatus for acquiring an image and using such image in a video game context |
| CN102221886A (en) * | 2010-06-11 | 2011-10-19 | 微软公司 | Interacting with user interface through metaphoric body |
| CN103218842A (en) * | 2013-03-12 | 2013-07-24 | 西南交通大学 | Voice synchronous-drive three-dimensional face mouth shape and face posture animation method |
| US20140267413A1 (en) * | 2013-03-14 | 2014-09-18 | Yangzhou Du | Adaptive facial expression calibration |
| CN104732590A (en) * | 2015-03-09 | 2015-06-24 | 北京工业大学 | Sign language animation synthesis method |
-
2017
- 2017-01-17 CN CN201710030650.4A patent/CN106823374A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419499A (en) * | 2008-11-14 | 2009-04-29 | 东南大学 | Multimedia human-computer interaction method based on cam and mike |
| WO2010076819A1 (en) * | 2008-12-30 | 2010-07-08 | Giochi Preziosi S.P.A. | A portable electronic apparatus for acquiring an image and using such image in a video game context |
| CN102221886A (en) * | 2010-06-11 | 2011-10-19 | 微软公司 | Interacting with user interface through metaphoric body |
| CN103218842A (en) * | 2013-03-12 | 2013-07-24 | 西南交通大学 | Voice synchronous-drive three-dimensional face mouth shape and face posture animation method |
| US20140267413A1 (en) * | 2013-03-14 | 2014-09-18 | Yangzhou Du | Adaptive facial expression calibration |
| CN104732590A (en) * | 2015-03-09 | 2015-06-24 | 北京工业大学 | Sign language animation synthesis method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135215A (en) * | 2018-02-02 | 2019-08-16 | 上海大学 | A kind of virtual social method based on the transplanting of Avatar expression |
| CN110135215B (en) * | 2018-02-02 | 2021-11-05 | 上海大学 | Virtual social method based on Avatar expression transplantation |
| CN109558853A (en) * | 2018-12-05 | 2019-04-02 | 维沃移动通信有限公司 | A kind of audio synthetic method and terminal device |
| CN111599342A (en) * | 2019-02-21 | 2020-08-28 | 北京京东尚科信息技术有限公司 | Tone selecting method and system |
| CN110215683A (en) * | 2019-07-11 | 2019-09-10 | 龙马智芯（珠海横琴）科技有限公司 | A kind of electronic game system of role playing game |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10042536B2 (en) | Avatars reflecting user states | |
| Milner | The world made meme: Public conversations and participatory media | |
| CN105917404B (en) | For realizing the method, apparatus and system of personal digital assistant | |
| Whittaker et al. | “All around me are synthetic faces”: the mad world of AI-generated media | |
| CN106823374A (en) | Talking Avatar hands based on android system swim the construction method of software | |
| WO2018045358A1 (en) | Generating theme-based videos | |
| CN108363492A (en) | A kind of man-machine interaction method and interactive robot | |
| CN107977928A (en) | Expression generation method, apparatus, terminal and storage medium | |
| CN104918670A (en) | Location based augmentation for story reading | |
| CN104956317A (en) | Speech modification for distributed story reading | |
| CN105190699A (en) | Karaoke avatar animation based on facial motion data | |
| US8874444B2 (en) | Simulated conversation by pre-recorded audio navigator | |
| Hernandez | " Miss, you look like a Bratz doll": On chonga girls and sexual-aesthetic excess | |
| CN110309327A (en) | Audio generation method, device and the generating means for audio | |
| US20190147229A1 (en) | Methods and systems for playing musical elements based on a tracked face or facial feature | |
| CN112819933A (en) | Data processing method and device, electronic equipment and storage medium | |
| King | Articulating digital stardom1 | |
| Alexandersson et al. | Girl bosses, punk poodles, and pink smoothies: Girlhood as Enterprising Femininity | |
| KR20240052043A (en) | Dialogue-guided augmented reality experience | |
| O’Meara et al. | Aberrant AI creations: co-creating surrealist body horror using the DALL-E Mini text-to-image generator | |
| Zhang et al. | Auggie: Encouraging Effortful Communication through Handcrafted Digital Experiences | |
| Jermyn | Barefaced: Ageing women stars,‘no make-up’photography and authentic selfhood in the 2017 Pirelli calendar | |
| CN110166345A (en) | Resource sharing method, resource acquiring method, device and storage medium | |
| Nicholas et al. | Expanding the design space for technology-mediated theatre experiences | |
| Firstenberg et al. | Designing and developing for Google Glass: Thinking differently for a new platform |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |