CN102567716A - Face synthetic system and implementation method - Google Patents
Face synthetic system and implementation method Download PDFInfo
- Publication number
- CN102567716A CN102567716A CN2011104276657A CN201110427665A CN102567716A CN 102567716 A CN102567716 A CN 102567716A CN 2011104276657 A CN2011104276657 A CN 2011104276657A CN 201110427665 A CN201110427665 A CN 201110427665A CN 102567716 A CN102567716 A CN 102567716A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- synthesized
- positive
- positive face
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 28
- 230000001815 facial effect Effects 0.000 claims description 27
- 239000003550 marker Substances 0.000 claims description 15
- 239000000203 mixture Substances 0.000 claims description 12
- 230000015572 biosynthetic process Effects 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 10
- 239000000758 substrate Substances 0.000 claims description 10
- 238000003786 synthesis reaction Methods 0.000 claims description 10
- 238000002611 posturography Methods 0.000 claims description 8
- 238000010189 synthetic method Methods 0.000 claims description 5
- 239000004744 fabric Substances 0.000 claims description 4
- 239000012141 concentrate Substances 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 230000019771 cognition Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Abstract
The invention discloses a face synthetic system and an implementation method. The invention is characterized by comprising a training image library, a synthetic algorithm library, an extraction model, a reference point identifier, a filter and a face image synthesizer, wherein the training image library is used for storing face templates and sample images of the face in different gestures, and each face template is respectively corresponding to two or more than two sample images of the face in different gestures; the synthetic algorithm library is used for storing an algorithm used for fusing the sample images of the face in different gestures into the corresponding face template; the extraction model is based on Bayes tangent outline and is a tool used for extracting an outline and control points of each sample image of the face in one gesture in the training image library; the reference point identifier is used for providing an interface used for browsing a face image to be synthesized for a user and providing a means which is used for directly identifying the center point of eyes and a nose tip point of the face image to be synthesized; and the face image synthesizer is used for selecting a synthetic algorithm, synthesizing the face image to be synthesized into the face image and outputting the face image.
Description
Technical field
The present invention relates to the synthesis system and the implementation method in face recognition technology field, particularly a kind of several non-front faces.
Background technology
Recognition of face have nature, close friend, to the user disturb less, advantage such as susceptible to user acceptance, thereby wide application prospect is arranged.Recognition of face at present comprises two-dimension human face identification and three-dimensional face identification, wherein based on the face identification method of two dimensional image, mainly is through linear or nonlinear dimension reduction method, extracts people's face external appearance characteristic with identification people face.No matter be two dimension or three-dimensional face identification, the prerequisite of carrying out recognition of face is that the front view (FV) that needs acquisition people face just can carry out effectively, accurate recognition.But; Carry out under the applied environment of real-time video monitoring and personal identification at some; Monitored object directly station lets system take a picture to obtain positive face image well; Along with monitored object moves, the probability that supervisory system photographed positive face is very little, often can only be discharged to the figure of other angle of people's face.So,, must solve the problem how several non-front faces accurately synthesize positive face image in order to carry out recognition of face.
One Chinese patent application " based on the synthetic face identification method of positive face image " number of patent application 201110054493.3; Disclose a kind of based on the synthetic face identification method of positive face image; This method mainly comprises step: a) read a plurality of side face images, obtain the control point diagram of each side face image; B) read a positive face image from the front face storehouse, the means such as control point diagram that obtain this positive face image solve several non-front faces and synthesize.But the framing to be synthesized of this method is complicated, carry out only having adopted a kind of composition algorithm in the building-up process, and do not consider that people's face figure of different angles, different gestures should adopt different algorithms according to transformational relation between the two when converting front face to.Simultaneously do not combine artificial aid identification yet, can't bring into play the advantage of network, people's identification.
Summary of the invention
The object of the invention is to above-mentioned existing issue; Raiser face synthesis system and implementation method, it adopts new flow process and system architecture, can improve the synthesis rate of several non-front faces; Bring into play advantages such as network, artificial cognition simultaneously, realize that their advantages merge.
The present invention realizes through following scheme:
A kind of people's face synthesis system is characterized in that, internal system is provided with training image storehouse, composition algorithm storehouse, extraction model, reference point concentrator marker, filtrator and positive face image synthesizer, wherein:
The training image storehouse is used to store positive face template and different gestures people face master drawing, each positive face template respectively corresponding two or above different gestures people face master drawing;
The composition algorithm storehouse is used to store different gestures people face master drawing is blended in the positive face template employed algorithm corresponding with it;
Extraction model is the extraction model based on Bayes's tangent profile, is used for each posture people face master drawing in the training image storehouse is extracted the instrument at profile and reference mark;
The reference point concentrator marker is used to the user browser interface of facial image to be synthesized is provided, provides direct two means that central point, prenasale directly identify at facial image to be synthesized;
Filtrator; Be used to call each extraction model facial image to be synthesized is extracted profile and reference mark successively; And compare with training image storehouse people's face master drawing respectively; Select the most close profile of mutual reference mark characteristic and extract result and then definite reference mark, and this people's face master drawing posturography as a reference;
Positive face image synthesizer is used for confirming positive face template, and selects composition algorithm, and facial image to be synthesized is synthesized positive face image output.
The implementation method of system:
A kind of synthetic method of several non-front faces is characterized in that, comprises the steps:
Step 1 is set up the training image storehouse, makes it store one or more positive face template, and the different gestures people face master drawing corresponding with each positive face template;
Step 2, system are that each posture people face master drawing is trained an extraction model based on Bayes's tangent profile respectively in the training image storehouse;
Step 3, system are read in all facial images to be synthesized;
The display interface confession user that step 4, reference point concentrator marker form facial image to be synthesized browses, the user directly directly identifies as reference point at two central points, the prenasale of facial image to be synthesized;
Step 5, each extraction model obtains reference point from the reference point concentrator marker successively, and calculates the search initial control point of extraction model according to reference point and image center;
Step 6; Filtrator extracts profile, reference mark with each extraction model; Respectively with the comparing of training image storehouse people's face master drawing, select a most close profile of mutual reference mark characteristic and extract the result as according to confirming final reference mark, and this people's face master drawing posturography as a reference;
Step 7, the selected positive face template of positive face image synthesizer, and utilize the corresponding composition algorithm of reference pose figure, facial image to be synthesized is synthesized positive face image and output.
Description of drawings
Fig. 1 is several non-front face synoptic diagram;
Fig. 2 is the structured flowchart of synthesis system;
Fig. 3 is the core process figure of inventive method.
Embodiment
With reference to figure 2, inventor's face synthesis system is made up of training image storehouse, composition algorithm storehouse, extraction model, reference point concentrator marker, filtrator and positive face image synthesizer etc.They the effect of system and interknit into:
The training image storehouse is used to store positive face template and different gestures people face master drawing, each positive face template respectively corresponding two or above different gestures people face master drawing;
The composition algorithm storehouse is used to store different gestures people face master drawing is blended in the positive face template employed algorithm corresponding with it;
Extraction model is the extraction model based on Bayes's tangent profile, is used for each posture people face master drawing in the training image storehouse is extracted the instrument at profile and reference mark;
The reference point concentrator marker is used to the user browser interface of facial image to be synthesized is provided, provides direct two means that central point, prenasale directly identify at facial image to be synthesized;
Filtrator; Be used to call each extraction model facial image to be synthesized is extracted profile and reference mark successively; And compare with training image storehouse people's face master drawing respectively; Select the most close profile of mutual reference mark characteristic and extract result and then definite reference mark, and this people's face master drawing posturography as a reference;
Positive face image synthesizer is used for confirming positive face template, and selects composition algorithm, and facial image to be synthesized is synthesized positive face image output.Positive face image synthesizer also is used to calculate positive each gray values of pixel points of face image, in the training image storehouse, selects a positive face template as positive face image substrate or the positive face image substrate of the positive face template conduct of Random assignment one width of cloth.
Shown in 1 and 2, system is input as several non-front faces, through system synthetic after, be input as positive people's face figure.The reference point concentrator marker provides the positioning action that carries out picture to be synthesized interface for the user.The user can pass through this locality or the network terminal, and two eye center point, the prenasale of clicking several non-front faces directly identify.After sign is accomplished, be that next step processing of internal system provides Back ground Information with feeding back to the reference point concentrator marker.Wherein, several non-front faces can send to a user and identify, and also can send to a plurality of terminal users and carry out, and make full use of the advantage of cloud computing, distributed collaborative treatment technology etc.In training image storehouse the inside, people's face master drawing that each positive face template should have a plurality of different gestures in advance is corresponding with it, distinguishes a kind of different transfer algorithm of correspondence when not having people's face master drawing of individual posture to be converted into positive face figure simultaneously.People's face master drawing of each posture should be trained an extraction model.The place that other is not mentioned can be implemented according to prior art and actual needs.
Below, be necessary this system's implementation method is further described:
Like Fig. 3, mainly comprise on the whole: set up training image storehouse, training extraction model, carry out the benchmark sign, confirm final reference mark and steps such as reference pose figure and synthetic positive face image through the reference point concentrator marker.More specifically following:
At first set up the training image storehouse, make it store one or more positive face template, and the different gestures people face master drawing corresponding with each positive face template; Different gestures people face master drawing is corresponding respectively a kind ofly to be changed and synthesizes in the algorithm of positive face image.
System is that each posture people face master drawing is trained an extraction model based on Bayes's tangent profile respectively in the training image storehouse;
All facial images to be synthesized are read in system;
The display interface confession user that the reference point concentrator marker forms facial image to be synthesized browses, the user directly directly identifies as reference point at two central points, the prenasale of facial image to be synthesized;
Each extraction model obtains reference point from the reference point concentrator marker successively, and calculates the search initial control point of extraction model according to reference point and image center;
Filtrator extracts profile, reference mark with each extraction model; Respectively with the comparing of training image storehouse people's face master drawing; Select the most close profile of mutual reference mark characteristic and extract the result as according to confirming final reference mark, and this people's face master drawing posturography as a reference;
Positive face image synthesizer judges whether to exist positive face template reference mark characteristic close with the reference mark of facial image to be synthesized, if existence, then with this positive face template as face image substrate just; Otherwise concentrate the positive face template of Random assignment one width of cloth as positive face image substrate from training image; Positive face image synthesizer synthesizes in positive each gray values of pixel points of face image substrate according to the algorithm computation of every facial image corresponding reference posturography to be synthesized; Calculate all images to be synthesized each pixel gray-scale value weighted sum on positive face image then, just form synthetic positive face image output at last.
Claims (7)
1. people's face synthesis system is characterized in that, internal system is provided with training image storehouse, composition algorithm storehouse, extraction model, reference point concentrator marker, filtrator and positive face image synthesizer, wherein:
The training image storehouse is used to store positive face template and different gestures people face master drawing, each positive face template respectively corresponding two or above different gestures people face master drawing;
The composition algorithm storehouse is used to store different gestures people face master drawing is blended in the positive face template employed algorithm corresponding with it;
Extraction model is the extraction model based on Bayes's tangent profile, is used for each posture people face master drawing in the training image storehouse is extracted the instrument at profile and reference mark;
The reference point concentrator marker is used to the user browser interface of facial image to be synthesized is provided, provides direct two means that central point, prenasale directly identify at facial image to be synthesized;
Filtrator; Be used to call each extraction model facial image to be synthesized is extracted profile and reference mark successively; And compare with training image storehouse people's face master drawing respectively; Select the most close profile of mutual reference mark characteristic and extract result and then definite reference mark, and this people's face master drawing posturography as a reference;
Positive face image synthesizer is used for confirming positive face template, and selects composition algorithm, and facial image to be synthesized is synthesized positive face image output.
2. people's face synthesis system as claimed in claim 1 is characterized in that, positive face image synthesizer also is used to calculate positive each gray values of pixel points of face image.
3. people's face synthesis system as claimed in claim 2 is characterized in that, positive face image synthesizer also is used in the training image storehouse, selecting a positive face template as positive face image substrate or the positive face image substrate of the positive face template conduct of Random assignment one width of cloth.
4. the synthetic method of several non-front faces is characterized in that, comprises the steps:
Step 1 is set up the training image storehouse, makes it store one or more positive face template, and the different gestures people face master drawing corresponding with each positive face template;
Step 2, system are that each posture people face master drawing is trained an extraction model based on Bayes's tangent profile respectively in the training image storehouse;
Step 3, system are read in all facial images to be synthesized;
The display interface confession user that step 4, reference point concentrator marker form facial image to be synthesized browses, the user directly directly identifies as reference point at two central points, the prenasale of facial image to be synthesized;
Step 5, each extraction model obtains reference point from the reference point concentrator marker successively, and calculates the search initial control point of extraction model according to reference point and image center;
Step 6; Filtrator extracts profile, reference mark with each extraction model; Respectively with the comparing of training image storehouse people's face master drawing, select a most close profile of mutual reference mark characteristic and extract the result as according to confirming final reference mark, and this people's face master drawing posturography as a reference;
Step 7, the selected positive face template of positive face image synthesizer, and utilize the corresponding composition algorithm of reference pose figure, facial image to be synthesized is synthesized positive face image and output.
5. like the synthetic method of said several the non-front faces of claim 4; It is characterized in that; In the said step 7; Positive face image synthesizer judges whether to exist positive face template reference mark characteristic close with the reference mark of facial image to be synthesized, if existence, then with this positive face template as face image substrate just; Otherwise concentrate the positive face template of Random assignment one width of cloth as positive face image substrate from training image.
6. like the synthetic method of said several the non-front faces of claim 5; It is characterized in that; In the said step 7; Positive face image synthesizer synthesizes in positive each gray values of pixel points of face image substrate according to the algorithm computation of every facial image corresponding reference posturography to be synthesized, calculates all images to be synthesized each pixel gray-scale value weighted sum on positive face image then, just forms synthetic positive face image output at last.
7. like the synthetic method of claim 4,5,6 arbitrary said several non-front faces, it is characterized in that different gestures people face master drawing is corresponding respectively a kind ofly to be changed and synthesize in the algorithm of positive face image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110427665.7A CN102567716B (en) | 2011-12-19 | 2011-12-19 | Face synthetic system and implementation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110427665.7A CN102567716B (en) | 2011-12-19 | 2011-12-19 | Face synthetic system and implementation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102567716A true CN102567716A (en) | 2012-07-11 |
| CN102567716B CN102567716B (en) | 2014-05-28 |
Family
ID=46413094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110427665.7A Expired - Fee Related CN102567716B (en) | 2011-12-19 | 2011-12-19 | Face synthetic system and implementation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102567716B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299250A (en) * | 2014-10-15 | 2015-01-21 | 南京航空航天大学 | Front face image synthesis method and system based on prior model |
| CN106156730A (en) * | 2016-06-30 | 2016-11-23 | 腾讯科技（深圳）有限公司 | The synthetic method of a kind of facial image and device |
| CN106203400A (en) * | 2016-07-29 | 2016-12-07 | 广州国信达计算机网络通讯有限公司 | A kind of face identification method and device |
| CN106295520A (en) * | 2016-07-28 | 2017-01-04 | 维沃移动通信有限公司 | A kind of fat or thin detection method and mobile terminal |
| CN106780660A (en) * | 2016-11-29 | 2017-05-31 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
| CN107038400A (en) * | 2016-02-04 | 2017-08-11 | 索尼公司 | Face identification device and method and utilize its target person tracks of device and method |
| CN107506717A (en) * | 2017-08-17 | 2017-12-22 | 南京东方网信网络科技有限公司 | Without the face identification method based on depth conversion study in constraint scene |
| CN107622227A (en) * | 2017-08-25 | 2018-01-23 | 深圳依偎控股有限公司 | A kind of method, terminal device and the readable storage medium storing program for executing of 3D recognitions of face |
| CN109729274A (en) * | 2019-01-30 | 2019-05-07 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN111291669A (en) * | 2020-01-22 | 2020-06-16 | 武汉大学 | Two-channel depression angle human face fusion correction GAN network and human face fusion correction method |
| CN113763232A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030123713A1 (en) * | 2001-12-17 | 2003-07-03 | Geng Z. Jason | Face recognition system and method |
| CN101034481A (en) * | 2007-04-06 | 2007-09-12 | 湖北莲花山计算机视觉和信息科学研究院 | Method for automatically generating portrait painting |
| CN102103689A (en) * | 2011-03-07 | 2011-06-22 | 北京大学 | Frontal face image synthesis-based face recognition method |
-
2011
- 2011-12-19 CN CN201110427665.7A patent/CN102567716B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030123713A1 (en) * | 2001-12-17 | 2003-07-03 | Geng Z. Jason | Face recognition system and method |
| CN101034481A (en) * | 2007-04-06 | 2007-09-12 | 湖北莲花山计算机视觉和信息科学研究院 | Method for automatically generating portrait painting |
| CN102103689A (en) * | 2011-03-07 | 2011-06-22 | 北京大学 | Frontal face image synthesis-based face recognition method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299250B (en) * | 2014-10-15 | 2018-05-22 | 南京航空航天大学 | Front face image synthetic method and system based on prior model |
| CN104299250A (en) * | 2014-10-15 | 2015-01-21 | 南京航空航天大学 | Front face image synthesis method and system based on prior model |
| CN107038400A (en) * | 2016-02-04 | 2017-08-11 | 索尼公司 | Face identification device and method and utilize its target person tracks of device and method |
| CN106156730A (en) * | 2016-06-30 | 2016-11-23 | 腾讯科技（深圳）有限公司 | The synthetic method of a kind of facial image and device |
| CN106156730B (en) * | 2016-06-30 | 2019-03-15 | 腾讯科技（深圳）有限公司 | A kind of synthetic method and device of facial image |
| CN106295520A (en) * | 2016-07-28 | 2017-01-04 | 维沃移动通信有限公司 | A kind of fat or thin detection method and mobile terminal |
| CN106203400A (en) * | 2016-07-29 | 2016-12-07 | 广州国信达计算机网络通讯有限公司 | A kind of face identification method and device |
| CN106780660A (en) * | 2016-11-29 | 2017-05-31 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
| CN106780660B (en) * | 2016-11-29 | 2019-01-04 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
| CN107506717A (en) * | 2017-08-17 | 2017-12-22 | 南京东方网信网络科技有限公司 | Without the face identification method based on depth conversion study in constraint scene |
| CN107622227A (en) * | 2017-08-25 | 2018-01-23 | 深圳依偎控股有限公司 | A kind of method, terminal device and the readable storage medium storing program for executing of 3D recognitions of face |
| CN109729274A (en) * | 2019-01-30 | 2019-05-07 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN109729274B (en) * | 2019-01-30 | 2021-03-09 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN111291669A (en) * | 2020-01-22 | 2020-06-16 | 武汉大学 | Two-channel depression angle human face fusion correction GAN network and human face fusion correction method |
| CN111291669B (en) * | 2020-01-22 | 2023-08-04 | 武汉大学 | Dual-channel depression angle face fusion correction GAN network and face fusion correction method |
| CN113763232A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102567716B (en) | 2014-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102567716B (en) | Face synthetic system and implementation method | |
| CN109359538B (en) | Training method of convolutional neural network, gesture recognition method, device and equipment | |
| CN105512624B (en) | A kind of smiling face's recognition methods of facial image and its device | |
| WO2019174439A1 (en) | Image recognition method and apparatus, and terminal and storage medium | |
| CN104463117B (en) | A kind of recognition of face sample collection method and system based on video mode | |
| CN107679522B (en) | Multi-stream LSTM-based action identification method | |
| CN104317391B (en) | A kind of three-dimensional palm gesture recognition exchange method and system based on stereoscopic vision | |
| CN103731583B (en) | Intelligent synthetic, print processing method is used for taking pictures | |
| CN106033435B (en) | Item identification method and device, indoor map generation method and device | |
| CN110503703A (en) | Method and apparatus for generating image | |
| CN107341434A (en) | Processing method, device and the terminal device of video image | |
| CN101308571A (en) | Method for generating novel human face by combining active grid and human face recognition | |
| CN104850825A (en) | Facial image face score calculating method based on convolutional neural network | |
| CN105426850A (en) | Human face identification based related information pushing device and method | |
| CN109635727A (en) | A kind of facial expression recognizing method and device | |
| CN107688391A (en) | A kind of gesture identification method and device based on monocular vision | |
| CN110738161A (en) | face image correction method based on improved generation type confrontation network | |
| CN109409994A (en) | The methods, devices and systems of analog subscriber garments worn ornaments | |
| CN102271241A (en) | Image communication method and system based on facial expression/action recognition | |
| CN108388882A (en) | Based on the gesture identification method that the overall situation-part is multi-modal RGB-D | |
| CN110263768A (en) | A kind of face identification method based on depth residual error network | |
| CN105447432A (en) | Face anti-fake method based on local motion pattern | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN106485186A (en) | Image characteristic extracting method, device, terminal device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180408 Address after: 528400 one of 25 floors, 25 floors, 2506 rooms, No. 1, de Zhong square, No. 1 of mice East Road, Guangdong Torch Development Zone Patentee after: Guangdong Zen science and Technology Co.,Ltd. Address before: Room 702, room 7, No. 16, exhibition East Road, Guangdong Torch Development Zone, Guangdong Province Patentee before: ZHONGSHAN IKER DIGITAL TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20190328 Address after: 510000 Room 2609,2610, 30 Huaxia Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Patentee after: Guangdong Xuzhi Travel Technology Co.,Ltd. Address before: 528400 one of the 25 floors of the 1 building of Tazhong square, No. 1 East Convention and exhibition hall, Torch Development Zone, Zhongshan, Guangdong, China. Patentee before: Guangdong Zen science and Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| DD01 | Delivery of document by public notice |
Addressee: Ruan Zhengyu Document name: payment instructions |
|
| DD01 | Delivery of document by public notice | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140528 Termination date: 20211219 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |