CN104268921A - 3D face expression control method and system - Google Patents
3D face expression control method and system Download PDFInfo
- Publication number
- CN104268921A CN104268921A CN201410462348.2A CN201410462348A CN104268921A CN 104268921 A CN104268921 A CN 104268921A CN 201410462348 A CN201410462348 A CN 201410462348A CN 104268921 A CN104268921 A CN 104268921A
- Authority
- CN
- China
- Prior art keywords
- bone
- face
- size
- headform
- expression control
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
Abstract
The invention provides a 3D face expression control method and system. The method comprises the first step of creating a standard human head model, setting bones for the standard human head model with a face expression picture as reference and setting the number of the bones in an area format by reference to human muscle structure, the second step of adding a skin to the standard human head model so as to set the weight of each bone, wherein the weight of each bone refers to the range in which the bones influence the standard human head model and the value of influence, and the third step of adjusting the positions, directions and sizes of the bones so as to control the expression of the standard human head model. According to the method, any human head and any human body can be input for combination, the simulation effect on details of a human face is good, the computation complexity is low, operation is simple, and the method has good universality.
Description
Technical field
The present invention relates to Expression Animation Technique, particularly, relate to 3D human face expression control method and system.
Background technology
Expression is the sentiment indicator that the mankind and other animals project from physical appearance, and majority refers to that the state that facial muscles and face are formed, common expression comprise indignation, detest, fear, happiness, sadness and surprised etc.Face is by the cooperative motion between facial expression, and stretching skin of face makes corresponding expression.Expression recognition identifies human emotion and plays more and more important effect in man-machine interactive system.
Along with the development of 3D data acquisition technology, the picking rate of 3D data promotes rapidly, compared with traditional 2D data, 3D data have higher resolution, contain more useful information simultaneously, can be good at overcoming the problem of illumination that 2D data run in expression recognition and attitude impact, existing 3D face identification method major part utilizes the entirety of face or simple face is simply divided into several rectangular blocks, reaches the object of Expression Recognition by extracting different proper vectors.
But, adopt the method for prior art, do not consider underlying causes that facial expression produces be due to facial muscles motion, cooperative motion just because of each muscle of face creates different expressions, therefore, the Expression Recognition control method accuracys rate such as existing model deformation are not high, and make complicated needs a large amount of time.
Summary of the invention
For defect of the prior art, the object of this invention is to provide a kind of 3D human face expression control method and system, to control facial expression animation.
According to a kind of 3D human face expression control method provided by the invention, comprise the steps:
Step 1: create a standard headform, for referencial use with personage's expression picture, headform arranges bone to this standard, with reference to human body myoarchitecture with area format setting bone quantity;
Step 2: by adding skin covering to standard headform, to set the weight of every root bone, wherein, the weight of bone refers to that bone affects the scope of standard headform and the size of influence value;
Step 3: adjustment bone site, direction, size, thus the expression of control criterion headform.
Preferably, in step 1, adopt recognition of face mode to come to be obtained by personage's expression picture the face position of personage, thus respectively bone is set up to the facial muscle block of standard headform.
Preferably, in step 1, described reference human body myoarchitecture, with area format setting bone quantity, is specially:
Come zoning according to face's face and movable muscle, then set up the bone of respective numbers according to the region marked off.
Preferably, in described step 2, the weight of the every root bone of described setting, is specially:
According to the movable region of normal person's facial muscles block, the zone of action of Skeletal size and movable scope and muscle masses is matched;
The movable scope of the muscle masses of same direction motion when the scope of single bone impact is normal person's facial exercises;
The size of bone weighted value is designed according to the power of the muscular movement scope of the equidirectional motion of normal person's face.
Preferably, in described step 3, the size of bone and the skull size of normal person's face, hypertrophy and atrophy value match.
According to a kind of 3D human face expression control system provided by the invention, comprise as lower device:
Model creation device: create a standard headform, for referencial use with personage's expression picture, headform arranges bone to this standard, with reference to human body myoarchitecture with area format setting bone quantity;
Bone setting device: by adding skin covering to standard headform, to set the weight of every root bone, wherein, the weight of bone refers to that bone affects the scope of standard headform and the size of influence value;
Expression control device: adjustment bone site, direction, size, thus the expression of control criterion headform.
Preferably, in model creation device, adopt recognition of face mode to come to be obtained by personage's expression picture the face position of personage, thus respectively bone is set up to the facial muscle block of standard headform.
Preferably, in model creation device, described reference human body myoarchitecture, with area format setting bone quantity, is specially:
Come zoning according to face's face and movable muscle, then set up the bone of respective numbers according to the region marked off.
Preferably, in described bone setting device, the weight of the every root bone of described setting, is specially:
According to the movable region of normal person's facial muscles block, the zone of action of Skeletal size and movable scope and muscle masses is matched;
The movable scope of the muscle masses of same direction motion when the scope of single bone impact is normal person's facial exercises;
The size of bone weighted value is designed according to the power of the muscular movement scope of the equidirectional motion of normal person's face.
Preferably, in described expression control device, the size of bone and the skull size of normal person's face, hypertrophy and atrophy value match.
Compared with prior art, the present invention has following beneficial effect:
The present invention can input any number of people and any human body combines, and good to the simulate effect of face details, computation complexity is low, simple to operate, has good universality.
Accompanying drawing explanation
By reading the detailed description done non-limiting example with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the schematic diagram standard number of people being arranged to bone;
Fig. 2 is the schematic diagram of the weight adjusting every root bone;
Fig. 3 is method flow diagram of the present invention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.Following examples will contribute to those skilled in the art and understand the present invention further, but not limit the present invention in any form.It should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, some distortion and improvement can also be made.These all belong to protection scope of the present invention.
The present invention is achieved through the following technical solutions: the method is realized by bone reference mark and facial disfigurement.The method at least comprises following steps:
Step 1: create a standard headform in 3d software, with personage's expression picture (as: smile for referencial use, to cry face, surprised etc.), to this standard, headform arranges bone, with area format setting bone quantity, (with reference to human body myoarchitecture) as shown in Figure 1.By step 1, the present invention has departed from existing the most frequently used some animation expression animation, uses skeleton cartoon more high efficiencyly can make more expression animation, and improves program efficiency.Wherein, described arranges bone with personage's expression picture for reference, refers to the face position carrying out to be obtained by picture personage by face recognition technology, comes whereby to set up bone to facial muscle block respectively.Described with area format setting bone quantity, refer to and come zoning according to face's face and movable muscle, set up the bone of respective numbers.
Step 2: add skin covering to headform, adjusts the weight (weight: every root bone affects the scope of model and the size of influence value) of every root bone as shown in Figure 2.Wherein, skin covering is for bone arranges weighted value, thus just can control bone by weight.The present invention divides face and the muscle of character face according to bone by step 2, for making of more expressing one's feelings, can increase work efficiency.Wherein, the rule of bone adjustment weight is: by the movable region of normal person's facial muscles block, accomplish that Skeletal size and movable scope and muscle activity scope match.Bone coverage is specially: the muscle masses of same direction motion when the scope of single bone impact is normal person's facial exercises.The size of bone influence value is specially: the power according to the muscular movement scope of the equidirectional motion of normal person's face designs bone weight.
Step 3: adjustment bone site and direction size thus Controlling model expression.Each expression can by adjusting the expression animation that (mobile, rotate, convergent-divergent adjusts bone) bone obtains wanting.The present invention, by step 3, make expression animation volume production convenient, and a set of expression goes for different faces.Wherein, the regulation rule of bone site is: the structure being judged personage's face position and muscle masses by face recognition technology.The regulation rule in bone direction is: according to normal person's facial muscle movements direction.The regulation rule of Skeletal size is: according to the skull size of normal person's face, hypertrophy, atrophy value.
Above specific embodiments of the invention are described.It is to be appreciated that the present invention is not limited to above-mentioned particular implementation, those skilled in the art can make various distortion or amendment within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (10)
1. a 3D human face expression control method, is characterized in that, comprises the steps:
Step 1: create a standard headform, for referencial use with personage's expression picture, headform arranges bone to this standard, with reference to human body myoarchitecture with area format setting bone quantity;
Step 2: by adding skin covering to standard headform, to set the weight of every root bone, wherein, the weight of bone refers to that bone affects the scope of standard headform and the size of influence value;
Step 3: adjustment bone site, direction, size, thus the expression of control criterion headform.
2. 3D human face expression control method according to claim 1, it is characterized in that, in step 1, adopt recognition of face mode to come to be obtained by personage's expression picture the face position of personage, thus respectively bone is set up to the facial muscle block of standard headform.
3. 3D human face expression control method according to claim 1, is characterized in that, in step 1, described reference human body myoarchitecture, with area format setting bone quantity, is specially:
Come zoning according to face's face and movable muscle, then set up the bone of respective numbers according to the region marked off.
4. 3D human face expression control method according to claim 1, is characterized in that, in described step 2, the weight of the every root bone of described setting, is specially:
According to the movable region of normal person's facial muscles block, the zone of action of Skeletal size and movable scope and muscle masses is matched;
The movable scope of the muscle masses of same direction motion when the scope of single bone impact is normal person's facial exercises;
The size of bone weighted value is designed according to the power of the muscular movement scope of the equidirectional motion of normal person's face.
5. 3D human face expression control method according to claim 1, is characterized in that, in described step 3, the size of bone and the skull size of normal person's face, hypertrophy and atrophy value match.
6. a 3D human face expression control system, is characterized in that, comprises as lower device:
Model creation device: create a standard headform, for referencial use with personage's expression picture, headform arranges bone to this standard, with reference to human body myoarchitecture with area format setting bone quantity;
Bone setting device: by adding skin covering to standard headform, to set the weight of every root bone, wherein, the weight of bone refers to that bone affects the scope of standard headform and the size of influence value;
Expression control device: adjustment bone site, direction, size, thus the expression of control criterion headform.
7. 3D human face expression control system according to claim 6, it is characterized in that, in model creation device, adopt recognition of face mode to come to be obtained by personage's expression picture the face position of personage, thus respectively bone is set up to the facial muscle block of standard headform.
8. 3D human face expression control system according to claim 6, is characterized in that, in model creation device, described reference human body myoarchitecture, with area format setting bone quantity, is specially:
Come zoning according to face's face and movable muscle, then set up the bone of respective numbers according to the region marked off.
9. 3D human face expression control system according to claim 6, is characterized in that, in described bone setting device, the weight of the every root bone of described setting, is specially:
According to the movable region of normal person's facial muscles block, the zone of action of Skeletal size and movable scope and muscle masses is matched;
The movable scope of the muscle masses of same direction motion when the scope of single bone impact is normal person's facial exercises;
The size of bone weighted value is designed according to the power of the muscular movement scope of the equidirectional motion of normal person's face.
10. 3D human face expression control system according to claim 6, is characterized in that, in described expression control device, the size of bone and the skull size of normal person's face, hypertrophy and atrophy value match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410462348.2A CN104268921A (en) | 2014-09-12 | 2014-09-12 | 3D face expression control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410462348.2A CN104268921A (en) | 2014-09-12 | 2014-09-12 | 3D face expression control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268921A true CN104268921A (en) | 2015-01-07 |
Family
ID=52160440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410462348.2A Pending CN104268921A (en) | 2014-09-12 | 2014-09-12 | 3D face expression control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268921A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654537A (en) * | 2015-12-30 | 2016-06-08 | 中国科学院自动化研究所 | Expression cloning method and device capable of realizing real-time interaction with virtual character |
| CN106485774A (en) * | 2016-12-30 | 2017-03-08 | 当家移动绿色互联网技术集团有限公司 | Expression based on voice Real Time Drive person model and the method for attitude |
| CN108717730A (en) * | 2018-04-10 | 2018-10-30 | 福建天泉教育科技有限公司 | A kind of method and terminal that 3D personage rebuilds |
| CN110111417A (en) * | 2019-05-15 | 2019-08-09 | 浙江商汤科技开发有限公司 | Generation method, device and the equipment of three-dimensional partial body's model |
| CN111292427A (en) * | 2020-03-06 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Bone displacement information acquisition method, device, equipment and storage medium |
| CN112090082A (en) * | 2020-09-27 | 2020-12-18 | 完美世界(北京)软件科技发展有限公司 | Facial skeleton processing method and device, electronic equipment and storage medium |
| CN117392292A (en) * | 2023-10-20 | 2024-01-12 | 联通在线信息科技有限公司 | 3D digital person generation method and system |
| CN117392292B (en) * | 2023-10-20 | 2024-04-30 | 联通在线信息科技有限公司 | 3D digital person generation method and system |
-
2014
- 2014-09-12 CN CN201410462348.2A patent/CN104268921A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654537A (en) * | 2015-12-30 | 2016-06-08 | 中国科学院自动化研究所 | Expression cloning method and device capable of realizing real-time interaction with virtual character |
| CN105654537B (en) * | 2015-12-30 | 2018-09-21 | 中国科学院自动化研究所 | It is a kind of to realize and the expression cloning method and device of virtual role real-time interactive |
| CN106485774A (en) * | 2016-12-30 | 2017-03-08 | 当家移动绿色互联网技术集团有限公司 | Expression based on voice Real Time Drive person model and the method for attitude |
| CN108717730A (en) * | 2018-04-10 | 2018-10-30 | 福建天泉教育科技有限公司 | A kind of method and terminal that 3D personage rebuilds |
| CN108717730B (en) * | 2018-04-10 | 2023-01-10 | 福建天泉教育科技有限公司 | 3D character reconstruction method and terminal |
| CN110111417A (en) * | 2019-05-15 | 2019-08-09 | 浙江商汤科技开发有限公司 | Generation method, device and the equipment of three-dimensional partial body's model |
| US11367236B2 (en) | 2019-05-15 | 2022-06-21 | Zhejiang Sensetime Technology Development Co., Ltd | Method, apparatus and device for generating three-dimensional local human body model |
| CN111292427A (en) * | 2020-03-06 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Bone displacement information acquisition method, device, equipment and storage medium |
| CN112090082A (en) * | 2020-09-27 | 2020-12-18 | 完美世界(北京)软件科技发展有限公司 | Facial skeleton processing method and device, electronic equipment and storage medium |
| CN117392292A (en) * | 2023-10-20 | 2024-01-12 | 联通在线信息科技有限公司 | 3D digital person generation method and system |
| CN117392292B (en) * | 2023-10-20 | 2024-04-30 | 联通在线信息科技有限公司 | 3D digital person generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790589B1 (en) | System and method for creating avatars or animated sequences using human body features extracted from a still image | |
| CN104268921A (en) | 3D face expression control method and system | |
| CN105513125B (en) | Composograph generating means and method, the recording medium for executing this method | |
| CN104541306B (en) | Neurobehavioral animation system | |
| CN107274466A (en) | The methods, devices and systems that a kind of real-time double is caught | |
| CN103208133B (en) | The method of adjustment that in a kind of image, face is fat or thin | |
| CN110163054A (en) | A kind of face three-dimensional image generating method and device | |
| CN110599573B (en) | Method for realizing real-time human face interactive animation based on monocular camera | |
| CN107274464A (en) | A kind of methods, devices and systems of real-time, interactive 3D animations | |
| CN104732590A (en) | Sign language animation synthesis method | |
| CN100440257C (en) | 3-D visualising method for virtual crowd motion | |
| CN108776773A (en) | A kind of three-dimensional gesture recognition method and interactive system based on depth image | |
| CN102567716B (en) | Face synthetic system and implementation method | |
| CN109409274B (en) | Face image transformation method based on face three-dimensional reconstruction and face alignment | |
| Wu et al. | Establishment virtual maintenance environment based on VIRTOOLS to effectively enhance the sense of immersion of teaching equipment | |
| CN104574481B (en) | A kind of non-linear amending method of three-dimensional character animation | |
| CN110349232A (en) | Generation method, device, storage medium and the electronic equipment of image | |
| CN111383642B (en) | Voice response method based on neural network, storage medium and terminal equipment | |
| CN106502382A (en) | Active exchange method and system for intelligent robot | |
| CN109711356A (en) | A kind of expression recognition method and system | |
| CN110503707A (en) | A kind of true man's motion capture real-time animation system and method | |
| CN106326980A (en) | Robot and method for simulating human facial movements by robot | |
| CN109739353A (en) | A kind of virtual reality interactive system identified based on gesture, voice, Eye-controlling focus | |
| CN114630738A (en) | System and method for simulating sensing data and creating perception | |
| CN103208130B (en) | Large-scale group performance animation synthetic method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150107 |
|
| WD01 | Invention patent application deemed withdrawn after publication |