CN1629875A - Distributed human face detecting and identifying method under mobile computing environment - Google Patents
Distributed human face detecting and identifying method under mobile computing environment Download PDFInfo
- Publication number
- CN1629875A CN1629875A CN 200310120624 CN200310120624A CN1629875A CN 1629875 A CN1629875 A CN 1629875A CN 200310120624 CN200310120624 CN 200310120624 CN 200310120624 A CN200310120624 A CN 200310120624A CN 1629875 A CN1629875 A CN 1629875A
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- server
- people
- image
- 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 claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000001815 facial effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 2
- 238000010998 test method Methods 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
This invention relates to a method for identifying a distributive man-face under mobile computing environment including: obtaining images from a camera head of a mobile device and carrying out simple and effective light correction, applying a quick man-face test method to test and calibrate it, the calibrated man-face zone is inserted by water print, the printed image is transferred to a man-face identification server, finally, true/false of said zone image is checked by water-print to identify the man face and transfer the result to the mobile terminal.
Description
Technical field
The present invention relates to mode identification technology, particularly the distributed mobile computing environment human face in conjunction with the detection of people's face and recognition technology, light treatment technology and wireless communication technique detects and recognition methods.
Background technology
In recent years, radio network technique presents the growth momentum of explosion type.Along with development of internet technology, wireless network more and more has influence on daily life.The expansion of wireless network bandwidth and the raising of network reliability make people also become strong day by day for the application demand of intelligent multimedia in the wireless network.These application comprise:
Recognition of face
Expression is analyzed
Content-based video playback
The wireless interactive recreation
Wanted criminal and suspect differentiate or the like
Wherein the detection of people's face is a kind of requisite support technology of these application with recognition technology.
So-called people's face detects position, size, number and the direction that detects people's face exactly in multi-medium data (as digital signals such as image, videos); Recognition of face then is people's face to be detected resulting result discern, and looks like to belong to which people to judge detected face.
Present existing people's face detection and Identification technology all is based on the running environment of desktop computer or even workstation, can't satisfy people's demands of applications in hand-held mobile computing environment.With respect to desktop system, hand-held mobile computing environment has some special service conditions, and this comprises:
A little less than the computing power
Electric energy and data space are limited
The light of environment for use changes greatly
Different user has different use habit or the like
Because the light conditions of mobile computing environment is changeable, detect and the robustness of discerning in order to improve people's face, carry out light and handle the link that is absolutely necessary.The light treatment technology can be handled the picture of catching under various different illumination conditions, reduce illumination variation as far as possible people's face is detected and the influence of discerning.
Because light is handled and people's face detects and identification all is the work of macrooperation amount, therefore, must optimize the algorithm of light processing and detection of people's face and identification, reduce operand, and recognition of face partly is placed on service end carries out, with the computing and storage burden that alleviate handheld device, this is very crucial concerning small type mobile devices.
Summary of the invention
The purpose of this invention is to provide a kind ofly under wireless network environment, detect and recognition methods based on people's face of distributed system.Native system on handheld device in real time, robust ground carries out people's face and detects, and then detected facial image carried out digital watermarking and encrypts the back and send to service end by wireless network, carry out recognition of face and return recognition result in service end.
For achieving the above object, the people's face under this distributed mobile environment detects with identification step and comprises:
1, detect to demarcate: the image that handheld device (palm PC, mobile phone or PDA) is caught carries out the light pre-service and goes forward side by side that pedestrian's face detects and the demarcation of people's face scope;
2, encrypted transmission: the people's face scope that calibrates is carried out sending to service end by wireless network after digital watermarking is encrypted.Service end is verified the digital watermarking that embeds in the image, judges the integrality and the correctness of image;
3, identification and return results: adopt recognition of face training algorithm to carry out recognition of face and the result is returned to handheld device based on built-in type hidden Markov model Hidden MarkovModels (HMM).
Obtain video data from camera, utilize the average of pixel and variance that video data is carried out the light rectification; From image, detect size, the position of people's face; Watermark is embedded in the detected human face region; By wireless network the human face region image is transferred to server then, server carries out very/pseudo-checking this image according to watermark; Discern at last, and recognition result is transferred to the mobile terminal.
Description of drawings
Fig. 1 is that distributed people's face detects and recognition methods overall framework figure under the mobile computing environment of the present invention;
Fig. 2 is that distributed people's face detects process flow diagram with recognition methods under the mobile computing environment of the present invention;
Fig. 3 is that distributed people's face detects training process flow diagram with recognition methods under the mobile computing environment of the present invention.
Embodiment
The process of Fig. 1 is as follows:
People's face testing process
(1) obtains two field picture: image capturing is come in by the camera C on the handheld device.Because we will handle each frame, from video flowing, image is extracted frame by frame.
(2) light is handled: detection and Identification have tremendous influence to people's face owing to light, and this comprises the influence of different angles, varying strength and shade.Simultaneously and since the computing power of mobile device a little less than, can not adopt complicated light model.Adopt the average and the variance of pixel value to correct the influence of light to each pixel of image here, the pixel value that is about to each pixel deducts average, divided by variance, multiply by a coefficient then.Through above-mentioned processing, thereby eliminate the influence of light as much as possible to people's face pixel value.
(3) carrying out people's face detects: the image after handling through light is carried out people's face detect.
(4) demarcate surveyed area: image is through after the detection module, and we will obtain coordinate, the size of people face part.Calibrate human face region by these coordinates.
The encrypted transmission process
(1) embed digital watermark: because that the security of wireless transmission path and reliability are compared cable network is poor, so we must guarantee to transmit the integrality and the correctness of data.This will realize by embed digital watermark in picture.In order to improve transmission speed, the object that we handle is the human face region in the image simultaneously.This zone is to come out through remarkable face Detection and Extraction in the last process.Detected human face region is embedded the integer wavelet watermark fast, so as server end carry out this area image true/pseudo-checking.
(2) wireless transmission: the human face region image of embed watermark arrives server end by wireless network transmissions.Radio path herein can be a WLAN (wireless local area network), also can be GPRS network.
(3) Distribution calculation process: because the backstage has many identified servers to carry out data processing, so the communication of coordinating between handheld terminal and the server is very important.We add acting server between handheld terminal and identified server, this acting server is a computing machine that is moving specific schedule software, and the concrete steps of this dispatcher software are illustrated in Fig. 2.Acting server similarly is a commander in chief, and the request that numerous handheld terminals are sent is redirected on the different servers, can reduce data like this and wait for the processed time.Face database on the Servers-all all is consistent, and at people's face registration phase, all databases also all are to upgrade synchronously.As shown in Figure 2, processing procedure is as follows:
A) acting server receives the request back of processing and seeks the recognition of face server that is in idle condition, and the recognition of face server is a computing machine that is moving the recognition of face program, and the concrete steps of this program are illustrated in Fig. 2.If do not have server to be in idle condition then the wait of ranking, otherwise the processing request that will receive sends to the server that is in idle condition, be busy state with this server-tag simultaneously;
B) the recognition of face server is verified the digital watermarking that embeds in the image, if find that data are changed or destroyed, just notifies handheld terminal to resend data, and the notification agent server lays oneself open to idle condition simultaneously;
C) the recognition of face server returns to handheld terminal with recognition result and sends message to acting server after not ruined data processing is finished, and tells acting server to lay oneself open to idle condition.
Recognition of face
1) based on the recognition of face training algorithm of built-in type hidden Markov model.Before carrying out recognition of face, register earlier, and the facial image of registration is trained, so that the identification of back.What adopt among the present invention is that the proportionate relationship at inner each position of analyst's face is discerned people's face.Therefore, adopt hidden Markov model to train in the training stage.But people's face pixel data is very huge, if directly with the hidden Markov model training, can cause model excessive, so that can't discern.Adopt built-in type hidden Markov model among the present invention, people's face is divided five states such as forehead, eyes, nose, mouth, chin, and each state is a hidden Markov chain.In the time of training the hidden Markov parameter training between five big states is come out, and the hidden Markov model of each state inside is trained out.Everyone face just obtains an Embedded hidden Markov model like this.
2) based on the recognition of face of built-in type hidden Markov model.Detect the image that obtains according to people's face, use viterbi algorithm, obtain under various built-in type hidden Markov model conditions, the various probability of image occur capturing.That model of probability maximum is exactly the most possible model of people's face of capturing.And the corresponding people of each model.So just can identify the pairing people of facial image.
Among Fig. 2, distributed people's face detects and recognition methods under the mobile computing environment, and its treatment step is as follows:
The S2-1 acting server receives the request back of processing and seeks the recognition of face server that is in idle condition,
If S2-2 does not have the server free time then forwards S2-3 to, otherwise forwards S2-4 to,
The S2-3 wait of ranking, and return S2-2 and continue to seek the recognition of face server that is in idle condition,
The processing request that S2-4 will receive sends to the server that is in idle condition, is busy state with this server-tag simultaneously,
S2-5 recognition of face server is verified the digital watermarking that embeds in the image, if find that data are changed or destroyed, just forwards S2-6 to, otherwise forwards S2-7 to,
S2-6 notice handheld terminal resends data, forwards S2-9 then to,
S2-7 carries out recognition of face,
S2-8 sends to mobile phone terminal with recognition result,
S2-9 sends message to acting server, and the notification agent server lays oneself open to idle condition.
Among Fig. 3, distributed people's face detects and recognition methods under the mobile computing environment, and its training step is as follows:
S3-1 sets up the HMM model,
S3-2 is evenly cut apart facial image, obtains initialized people's face HMM model parameter,
HMM parameters such as S3-3 initialization observation sequence parameter, observation vector sum state-transition matrix,
S3-4 adopts Embedded Viterbi dividing method to carry out parameter adjustment,
S3-5 comes the estimation model parameter by segmentation calculating mean value K,
Whether the iteration of S3-6 judgment models restrains, and proceeds parameter adjustment if do not restrain then forward S3-4 to.If the convergence would forward S3-7 to,
S3-7 has just obtained the HMM model that trains through after the iteration convergence.
Transmit at wireless network environment with detected human face region, solved two problems:
One, on mobile device, carries out the big problem of calculated amount of multiclass problem classification;
Two, in wireless network environment, be difficult to the big image of real-time Transmission to server end.
Claims (7)
1, distributed people's face detects and recognition methods under a kind of mobile computing environment, comprises step:
Detect to demarcate: the image that handheld device is caught carries out the light pre-service and goes forward side by side that pedestrian's face detects and the demarcation of people's face scope;
Encrypted transmission: the people's face scope that calibrates is carried out sending to service end by wireless network after digital watermarking is encrypted, and service end is verified the digital watermarking that embeds in the image, judges the integrality and the correctness of image;
Identification and return results: adopt recognition of face training algorithm to carry out recognition of face and the result is returned to handheld device based on built-in type hidden Markov model.
2, distributed people's face detects and recognition methods under the mobile computing environment according to claim 1,
Step is as follows: obtain video data from camera, utilize the average of pixel and variance that video data is carried out the light rectification; From image, detect size, the position of people's face; Watermark is embedded in the detected human face region; By wireless network the human face region image is transferred to server then, server carries out very/pseudo-checking this image according to watermark; Discern at last, and recognition result is transferred to the mobile terminal.
3, method according to claim 2 is characterized in that, also comprises step: adopt the average of pixel and variance to carry out the light rectification, this mode is simple and effective, can satisfy the requirement of mobile computing.
4, method according to claim 2 is characterized in that also comprising step: detected human face region is embedded the integer wavelet watermark fast so that server end carry out this area image true/pseudo-checking.
5, method according to claim 2 is characterized in that also comprising step: adopt built-in type hidden Markov model in the recognition of face training, the proportionate relationship at each position of analyst's face improves discrimination and recognition speed greatly.
6, distributed people's face detects and recognition methods under the mobile computing environment according to claim 1, and its treatment step is as follows:
The S2-1 acting server receives the request back of processing and seeks the recognition of face server that is in idle condition,
If S2-2 does not have the server free time then forwards S2-3 to, otherwise forwards S2-4 to,
The S2-3 wait of ranking, and return S2-2 and continue to seek the recognition of face server that is in idle condition,
The processing request that S2-4 will receive sends to the server that is in idle condition, is busy state with this server-tag simultaneously,
S2-5 recognition of face server is verified the digital watermarking that embeds in the image, if find that data are changed or destroyed, just forwards S2-6 to, otherwise forwards S2-7 to,
S2-6 notice handheld terminal resends data, forwards S2-9 then to,
S2-7 carries out recognition of face,
S2-8 sends to mobile phone terminal with recognition result,
S2-9 sends message to acting server, and the notification agent server lays oneself open to idle condition.
7, distributed people's face detects and recognition methods under the mobile computing environment according to claim 6, and its training step is as follows:
S3-1 sets up the HMM model,
S3-2 is evenly cut apart facial image, obtains initialized people's face HMM model parameter,
S3-3 initialization observation sequence parameter, observation vector sum state-transition matrix HMM parameter,
S3-4 adopts Embedded Viterbi dividing method to carry out parameter adjustment,
S3-5 comes the estimation model parameter by segmentation calculating mean value K,
Whether the iteration of S3-6 judgment models restrains, and proceeds parameter adjustment if do not restrain then forward S3-4 to.If the convergence would forward S3-7 to,
S3-7 has just obtained the HMM model that trains through after the iteration convergence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200310120624 CN1284111C (en) | 2003-12-15 | 2003-12-15 | Distributed human face detecting and identifying method under mobile computing environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200310120624 CN1284111C (en) | 2003-12-15 | 2003-12-15 | Distributed human face detecting and identifying method under mobile computing environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1629875A true CN1629875A (en) | 2005-06-22 |
CN1284111C CN1284111C (en) | 2006-11-08 |
Family
ID=34843952
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 200310120624 Expired - Fee Related CN1284111C (en) | 2003-12-15 | 2003-12-15 | Distributed human face detecting and identifying method under mobile computing environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN1284111C (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100357960C (en) * | 2006-03-08 | 2007-12-26 | 北京邮电大学 | Parallel and distributing type identifying human face based on net |
CN101075868B (en) * | 2006-05-19 | 2010-05-12 | 华为技术有限公司 | Long-distance identity-certifying system, terminal, server and method |
CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
CN101114909B (en) * | 2007-08-17 | 2011-02-16 | 上海博康智能信息技术有限公司 | Full-automatic video identification authentication system and method |
WO2013000142A1 (en) * | 2011-06-30 | 2013-01-03 | 深圳市君盛惠创科技有限公司 | Mobile phone user identity authentication method, cloud server and network system |
CN101944998B (en) * | 2007-01-16 | 2013-03-13 | 株式会社东芝 | System and server apparatus for biometric authentication |
CN103384234A (en) * | 2012-05-04 | 2013-11-06 | 深圳市腾讯计算机系统有限公司 | Method and system for face identity authentication |
CN104281799A (en) * | 2013-07-09 | 2015-01-14 | 宏达国际电子股份有限公司 | Electronic device selectively enabling a facial unlock function and method thereof |
CN104952026A (en) * | 2014-03-31 | 2015-09-30 | 腾讯科技(深圳)有限公司 | Method of processing image and device thereof |
CN106682590A (en) * | 2016-12-07 | 2017-05-17 | 浙江宇视科技有限公司 | Processing method and server for monitoring service |
WO2018040028A1 (en) * | 2016-08-31 | 2018-03-08 | 张北江 | Method and system for recognizing face in video |
CN108596063A (en) * | 2018-04-13 | 2018-09-28 | 唐山新质点科技有限公司 | A kind of face identification method and system |
CN110020519A (en) * | 2019-01-08 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of identity checking method, device and electronic equipment |
CN110489240A (en) * | 2019-08-22 | 2019-11-22 | Oppo广东移动通信有限公司 | Image-recognizing method, device, cloud platform and storage medium |
CN111460992A (en) * | 2020-03-31 | 2020-07-28 | 北京奇艺世纪科技有限公司 | Object recognition, correction model training and face recognition method and device |
CN112149564A (en) * | 2020-09-23 | 2020-12-29 | 上海交通大学烟台信息技术研究院 | Face classification and recognition system based on small sample learning |
-
2003
- 2003-12-15 CN CN 200310120624 patent/CN1284111C/en not_active Expired - Fee Related
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100357960C (en) * | 2006-03-08 | 2007-12-26 | 北京邮电大学 | Parallel and distributing type identifying human face based on net |
CN101075868B (en) * | 2006-05-19 | 2010-05-12 | 华为技术有限公司 | Long-distance identity-certifying system, terminal, server and method |
CN101944998B (en) * | 2007-01-16 | 2013-03-13 | 株式会社东芝 | System and server apparatus for biometric authentication |
CN101114909B (en) * | 2007-08-17 | 2011-02-16 | 上海博康智能信息技术有限公司 | Full-automatic video identification authentication system and method |
CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
CN101957911B (en) * | 2010-09-29 | 2012-11-28 | 汉王科技股份有限公司 | Face identification method and system |
WO2013000142A1 (en) * | 2011-06-30 | 2013-01-03 | 深圳市君盛惠创科技有限公司 | Mobile phone user identity authentication method, cloud server and network system |
US9813909B2 (en) | 2011-06-30 | 2017-11-07 | Guangzhou Haiji Technology Co., Ltd | Cloud server for authenticating the identity of a handset user |
US8861798B2 (en) | 2011-06-30 | 2014-10-14 | Shenzhen Junshenghuichuang Technologies Co., Ltd. | Method for authenticating identity of handset user |
US9537859B2 (en) | 2011-06-30 | 2017-01-03 | Dongguan Ruiteng Electronics Technologies Co., Ltd | Method for authenticating identity of handset user in a cloud-computing environment |
US8983145B2 (en) | 2011-06-30 | 2015-03-17 | Shenzhen Junshenghuichuang Technologies Co., Ltd | Method for authenticating identity of handset user |
CN103384234B (en) * | 2012-05-04 | 2016-09-28 | 深圳市腾讯计算机系统有限公司 | Face identity authentication and system |
CN103384234A (en) * | 2012-05-04 | 2013-11-06 | 深圳市腾讯计算机系统有限公司 | Method and system for face identity authentication |
CN104281799A (en) * | 2013-07-09 | 2015-01-14 | 宏达国际电子股份有限公司 | Electronic device selectively enabling a facial unlock function and method thereof |
CN104952026A (en) * | 2014-03-31 | 2015-09-30 | 腾讯科技(深圳)有限公司 | Method of processing image and device thereof |
CN104952026B (en) * | 2014-03-31 | 2019-09-27 | 腾讯科技(深圳)有限公司 | The method and device of image procossing |
WO2018040028A1 (en) * | 2016-08-31 | 2018-03-08 | 张北江 | Method and system for recognizing face in video |
CN106682590B (en) * | 2016-12-07 | 2023-08-22 | 浙江宇视科技有限公司 | Processing method of monitoring service and server |
CN106682590A (en) * | 2016-12-07 | 2017-05-17 | 浙江宇视科技有限公司 | Processing method and server for monitoring service |
CN108596063A (en) * | 2018-04-13 | 2018-09-28 | 唐山新质点科技有限公司 | A kind of face identification method and system |
CN110020519A (en) * | 2019-01-08 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of identity checking method, device and electronic equipment |
CN110489240A (en) * | 2019-08-22 | 2019-11-22 | Oppo广东移动通信有限公司 | Image-recognizing method, device, cloud platform and storage medium |
CN111460992A (en) * | 2020-03-31 | 2020-07-28 | 北京奇艺世纪科技有限公司 | Object recognition, correction model training and face recognition method and device |
CN112149564A (en) * | 2020-09-23 | 2020-12-29 | 上海交通大学烟台信息技术研究院 | Face classification and recognition system based on small sample learning |
CN112149564B (en) * | 2020-09-23 | 2023-01-10 | 上海交通大学烟台信息技术研究院 | Face classification and recognition system based on small sample learning |
Also Published As
Publication number | Publication date |
---|---|
CN1284111C (en) | 2006-11-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN1284111C (en) | Distributed human face detecting and identifying method under mobile computing environment | |
JP6789402B2 (en) | Method of determining the appearance of an object in an image, equipment, equipment and storage medium | |
CN109784181B (en) | Picture watermark identification method, device, equipment and computer readable storage medium | |
CN101048783A (en) | Photographic document imaging system | |
US20150010203A1 (en) | Methods, apparatuses and computer program products for performing accurate pose estimation of objects | |
US20100009713A1 (en) | Logo recognition for mobile augmented reality environment | |
WO2014058243A1 (en) | Incremental visual query processing with holistic feature feedback | |
JP6216516B2 (en) | Digital watermark embedding method and digital watermark detection method | |
EP2956891A2 (en) | Segmenting objects in multimedia data | |
KR20180004898A (en) | Image processing technology and method based on deep learning | |
CN1849613A (en) | Apparatus and method for feature recognition | |
CN112104869B (en) | Video big data storage and transcoding optimization system | |
CN114627502A (en) | Improved YOLOv 5-based target recognition detection method | |
US20160125253A1 (en) | Method and apparatus for image matching | |
Chen et al. | Context-aware image compression optimization for visual analytics offloading | |
CN110222647B (en) | Face in-vivo detection method based on convolutional neural network | |
CN116092178A (en) | Gesture recognition and tracking method and system for mobile terminal | |
CN115941939A (en) | Video frame alignment method, device, equipment and storage medium | |
CN113469869B (en) | Image management method and device | |
Hu et al. | A Transfer Attack to Image Watermarks | |
CN111654668A (en) | Monitoring equipment synchronization method and device and computer terminal | |
CN113283423B (en) | Natural scene distortion text image correction method and system based on generation network | |
Zhang et al. | Crossvision: Real-time on-camera video analysis via common roi load balancing | |
CN1570953A (en) | Human face detecting method under mobile computing environment | |
CN111985396A (en) | Pregnant woman emotion monitoring and recognition 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20061108 Termination date: 20151215 |
|
EXPY | Termination of patent right or utility model |