CN109583421A - Face identification system and method - Google Patents
Face identification system and method Download PDFInfo
- Publication number
- CN109583421A CN109583421A CN201811541785.8A CN201811541785A CN109583421A CN 109583421 A CN109583421 A CN 109583421A CN 201811541785 A CN201811541785 A CN 201811541785A CN 109583421 A CN109583421 A CN 109583421A
- Authority
- CN
- China
- Prior art keywords
- face
- photo
- identified
- characteristic value
- reference picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Abstract
The present invention relates to a kind of face identification methods, comprising: chooses reference picture, extracts the characteristic value of known face in the reference picture；Photo to be identified is pre-processed, the face position in photo to be identified is taken out；The characteristic value at the face position in photo to be identified is extracted, and recognition of face is carried out according to the characteristic value of known face in the characteristic value at the face position in the photo to be identified and the reference picture.The invention further relates to a kind of face identification systems.The present invention can reduce the development cost of face recognition products, allow to easily be deployed in the application scenarios such as family, small business, and convenient for safeguarding and extension.
Description
Technical field
The present invention relates to a kind of face identification system and methods.
Background technique
Face recognition technology has been widely suitable for identification field as emerging technology in the ascendant, including
But be not limited to mobile phone unlock, the payment of brush face, bank account authentication etc..This will greatly improve the convenience of our daily lifes
Property, and the safety index in our daily life can be improved to a certain extent.
The recognition of face of current main-stream mainly passes through the positive face photo of interception people, is uploaded to high-performance server by network
It returns after being calculated as a result, to carry out the certification of user identity.
But existing face recognition technology is substantially to belong to the public scope of society, user group lesser for demand,
Such as small business and domestic consumer, deployment and inconvenient for use and higher cost.Meanwhile with the increase of user group, face is known
The case where Pi Pei not making mistakes, happens occasionally, so that public throw doubt upon for the safety of the technology.
Summary of the invention
In view of this, it is necessary to provide a kind of face identification system and methods.
The present invention provides a kind of face identification system, which includes that the system includes the selection mould being electrically connected with each other
Block, preprocessing module and identification module, in which: the selecting module is extracted in the reference picture for choosing reference picture
The characteristic value of known face；The preprocessing module is taken out in photo to be identified for pre-processing to photo to be identified
Face position；The identification module is used to extract the characteristic value at the face position in photo to be identified, and according to described to be identified
The characteristic value of known face carries out recognition of face in the characteristic value and the reference picture at the face position in photo.
Wherein, the characteristic value of the face is the relative position information of facial contour, including but not limited to: the position of eyes
It sets, the position of nose, the position of the corners of the mouth, the position put on face contour curve.
It is described to photo to be identified carry out pretreatment include: from photo to be identified taking-up face position, to the taking-up
Face position carry out whitening processing.
Known face in the characteristic value according to the face position in the photo to be identified and the reference picture
Characteristic value carries out recognition of face, comprising:
For individual photo to be identified, using correlation distance is calculated, final recognition result is determined:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors, ρXYValue
Between -1~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
Known face in the characteristic value according to the face position in the photo to be identified and the reference picture
Characteristic value carries out recognition of face, further includes: is determined most for continuously intercepting multiple pictures under video environment by voting mechanism
Whole recognition result.
The present invention provides a kind of face identification method, and this method comprises the following steps: a. selection reference picture, described in extraction
The characteristic value of known face in reference picture；B. photo to be identified is pre-processed, takes out the face in photo to be identified
Position；C. the characteristic value at the face position in photo to be identified is extracted, and according to the spy at the face position in the photo to be identified
The characteristic value of known face carries out recognition of face in value indicative and the reference picture.
Wherein, the characteristic value of the face is the relative position information of facial contour, including but not limited to: the position of eyes
It sets, the position of nose, the position of the corners of the mouth, the position put on face contour curve.
It is described to photo to be identified carry out pretreatment include: from photo to be identified taking-up face position, to the taking-up
Face position carry out whitening processing.
The step c is specifically included:
For individual photo to be identified, using correlation distance is calculated, final recognition result is determined:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors, ρXYValue
Between -1~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
The step c further include: determined finally for continuously intercepting multiple pictures under video environment by voting mechanism
Recognition result.
The present invention devises a set of technological frame for not needing locally complete recognition of face using internet, passes through
Using Movidius, this convenient neural network accelerates tool, the localization and off line of Lai Shixian authentication, so that testing
Card result does not need to be interconnected with superserver.The development cost for reducing face recognition products, allows to easily portion
The application scenarios such as family, small business are deployed on, and is easy to understand and safeguards, also facilitates using being extended, is more leading
Domain plays a role.The theoretical analysis with experiment is carried out simultaneously for the case where identification fault, giving a set of can obviously drop
The recognition of face frame of low failure rate, improves the safety of system.
Detailed description of the invention
Fig. 1 is the functional block diagram of face identification system of the present invention；
Fig. 2 is the schematic diagram for carrying glasses when the embodiment of the present invention chooses reference picture and bringing range error into；
Fig. 3 is the operation process chart of the present inventor's face recognition method.
Specific embodiment
With reference to the accompanying drawing and specific embodiment the present invention is described in further detail.
As shown in fig.1, being the functional block diagram of face identification system of the embodiment of the present invention.The system includes: selection mould
Block, preprocessing module and identification module.Wherein:
The selecting module is for choosing reference picture.Specifically: choosing reference picture on the local computer and be put into
The photo library of recognition of face, extracts the characteristic value of known face in the reference picture, and is stored.
Further, the selecting module carries out characteristics extraction, the convolutional Neural using convolutional neural networks (CNN)
Network is suitable for the rapidly extracting of image information.It is trained using Google open source projects FaceNet in the present embodiment
Neural network parameter, the network can extract the relative position information of facial contour by training, indicate in the form of vectors
The relative position information of (vector of 1*n), the above-mentioned facial contour indicated in the form of vectors is exactly the characteristic value of face.
Briefly, the characteristic value of the face is exactly the relative position information of facial contour, including but not limited to: eyes
Position, the position of nose, the position of the corners of the mouth, the position put on face contour curve etc..The characteristics extraction of the face goes out
It is returned after coming with the vector form of 1*n.
In the present embodiment, the selection of reference base picture is concerning the basic of identification face success rate.Clearly, good reference map
Piece can provide more accurate feature vector, reduce the risk of misrecognition.In the present embodiment, the selection of reference base picture mainly has
Three criterion below:
1. front light source.Strong front light source makes the feature of face more easy to identify.And if light is bad, easily produces after albefaction
Raw shade, reduces picture quality.
2. higher resolution ratio.Up-sampling can be triggered when converting high-resolution pictures for low resolution picture, so that figure
Piece is more fuzzy, and Feature point recognition is difficult, cannot obtain accurate feature vector.
3. the not ornaments such as wearing spectacles.Practical operation shows that carrying glasses misses the distance for bringing 0.1~0.2 or so into
A possibility that poor (please referring to attached drawing 2), reduction identifies successfully.
The preprocessing module is used to the sensor real time data merged carrying out data processing.Specifically:
The preprocessing module pre-processes photo to be identified, takes out the face position in photo to be identified.Specifically
For:
Carrying out pretreatment to photo to be identified includes:
Firstly, taking out face position from the photo to be identified: being carried out by taking out face position from images to be recognized
It accurately identifies, the success rate of subsequent identification can be greatly improved.
Then, whitening processing is carried out to the face position of the taking-up: whitening processing is carried out to face position, can reduce
The interference of the stronger noise of correlation to feature in background, such as light, the identical background of bulk color of fluorescent lamp etc..Pass through
It has been observed that background light can influence more by force the recognition accuracy of the image of camera reading to a certain extent, albefaction is being carried out
After processing, the influence of this part is significantly reduced.
The identification module is used to carry out the face position in the photo to be identified of above-mentioned taking-up the extraction of feature vector,
And be compared with the characteristic value of the known face of storage, comparing successfully is successfully to identify.
Wherein, feature vector is carried out to the face position in the photo to be identified of above-mentioned taking-up described in the identification module
Extraction include: extract the position of eyes in photo to be identified, the position of nose, the position of the corners of the mouth, face contour curve point position
The feature vector set.
In some embodiments, comparing this step can wrong appearance.When threshold value be arranged it is unreasonable, or due to environment light
Line problem produces erroneous matching, it will generates unpredicted consequence.For identification module described in the present embodiment uses such as lower section
Method reduces error hiding probability:
It is calculated using distance and does not use Euclidean distance, calculated using correlation distance.
Specifically, in the present embodiment, correlation distance is calculated using following formula:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors.This value
Between -1~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
Also final recognition result is determined by voting mechanism for continuously intercepting multiple pictures under video environment: regarding
Under frequency environment, the continuous multiple pictures that intercept are compared respectively, only just give permission after object continuous several times successful match, if
The super n times of failure just count again.
Specifically, voting mechanism is under video environment, the continuous plurality of pictures that intercepts is compared.It is arranged in this example
It is 12, i.e., only continuous 12 certifications illustrate that the personage of photo to be identified is consistent with someone feature in local picture library,
Judge that the personage is internal staff.It malfunctions more than 3 times (including the case where not matching and being matched to other people), by counter O reset
(needing to re-start 12 verifyings).
As shown in fig.3, being the operation process chart of the present inventor's face recognition method.
Step S101 chooses reference picture.Specifically: choosing reference picture on the local computer and be put into recognition of face
Photo library, extract the characteristic value of known face in the reference picture, and stored.
Further, characteristics extraction is carried out using convolutional neural networks (CNN), the convolutional neural networks are suitable for figure
As the rapidly extracting of information.In the present embodiment, using Google open source projects FaceNet, trained neural network is joined
Number, the network can extract the relative position information of facial contour by training, indicate in the form of vectors (1*n to
Amount), the relative position information of the above-mentioned facial contour indicated in the form of vectors is exactly the characteristic value of face.
Briefly, the characteristic value of the face is exactly the relative position information of facial contour, including but not limited to: eyes
Position, the position of nose, the position of the corners of the mouth, the position put on face contour curve etc..The characteristics extraction of the face goes out
It is returned after coming with the vector form of 1*n.
In the present embodiment, the selection of reference base picture is concerning the basic of identification face success rate.Clearly, good reference map
Piece can provide more accurate feature vector, reduce the risk of misrecognition.In the present embodiment, the selection of reference base picture mainly has
Three criterion below:
1. front light source.Strong front light source makes the feature of face more easy to identify.And if light is bad, easily produces after albefaction
Raw shade, reduces picture quality.
2. higher resolution ratio.Up-sampling can be triggered when converting high-resolution pictures for low resolution picture, so that figure
Piece is more fuzzy, and Feature point recognition is difficult, cannot obtain accurate feature vector.
3. the not ornaments such as wearing spectacles.Practical operation shows that carrying glasses misses the distance for bringing 0.1~0.2 or so into
A possibility that poor (please referring to attached drawing 2), reduction identifies successfully.
Step S102 pre-processes photo to be identified, takes out the face position in photo to be identified.Specifically:
Carrying out pretreatment to photo to be identified includes:
Firstly, taking out face position from the photo to be identified: being carried out by taking out face position from images to be recognized
It accurately identifies, the success rate of subsequent identification can be greatly improved.
Then, whitening processing is carried out to the face position of the taking-up: whitening processing is carried out to face position, can reduce
The interference of the stronger noise of correlation to feature in background, such as light, the identical background of bulk color of fluorescent lamp etc..Pass through
It has been observed that background light can influence more by force the recognition accuracy of the image of camera reading to a certain extent, albefaction is being carried out
After processing, the influence of this part is significantly reduced.
Step S103 carries out recognition of face to pretreated photo to be identified according to the reference picture.Specifically:
The extraction of feature vector, and the known people with storage are carried out to the face position in the photo to be identified of above-mentioned taking-up
The characteristic value of face is compared, and comparing successfully is successfully to identify.
Wherein, the extraction that the face position in the photo to be identified to above-mentioned taking-up carries out feature vector includes: to mention
Take the position of eyes in photo to be identified, the position of nose, the position of the corners of the mouth, face contour curve point position feature to
Amount.
In some embodiments, comparing this step can wrong appearance.When threshold value be arranged it is unreasonable, or due to environment light
Line problem produces erroneous matching, it will generates unpredicted consequence.For the present embodiment reduces mistake with the following method
With probability:
It is calculated using distance and does not use Euclidean distance, calculated using correlation distance.
Specifically, in the present embodiment, correlation distance is calculated using following formula:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors.This value
Between -1~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
Also final recognition result is determined by voting mechanism for continuously intercepting multiple pictures under video environment: regarding
Under frequency environment, the continuous multiple pictures that intercept are compared respectively, only just give permission after object continuous several times successful match, if
The super n times of failure just count again.
Specifically, voting mechanism is under video environment, the continuous plurality of pictures that intercepts is compared.It is arranged in this example
It is 12, i.e., only continuous 12 certifications illustrate that the personage of photo to be identified is consistent with someone feature in local picture library,
Judge that the personage is internal staff.It malfunctions more than 3 times (including the case where not matching and being matched to other people), by counter O reset
(needing to re-start 12 verifyings).
It is worth noting that the present invention can be improved frame cpu busy percentage in general device:
Key of the invention is the utilization rate for utilizing multi-process, and reasonable detached process resource to guarantee CPU.It will be from taking the photograph
As head take image with and the interaction of Movidius nerve calculation rod be placed in host process, evaded many problems related with I/O,
Keep calling program more healthy and stronger；By time-consuming more serious albefaction and MTCNN (Muli-Task CNN, multi-layer C NN convolutional Neural net
Network) Multiprocessing is used, accelerate operational efficiency.
Although the present invention is described referring to current better embodiment, those skilled in the art should be able to be managed
Solution, above-mentioned better embodiment is only used to illustrate the present invention, be not intended to limit the scope of protection of the present invention, any in the present invention
Spirit and spirit within, any modification, equivalence replacement, improvement for being done etc. should be included in right of the invention and protect
Within the scope of shield.
Claims (10)
1. a kind of face identification system, which is characterized in that the system includes the selecting module being electrically connected with each other, preprocessing module
And identification module, in which:
The selecting module extracts the characteristic value of known face in the reference picture for choosing reference picture；
The preprocessing module takes out the face position in photo to be identified for pre-processing to photo to be identified；
The identification module is used to extract the characteristic value at the face position in photo to be identified, and according in the photo to be identified
The characteristic value at face position and the characteristic value of known face in the reference picture carry out recognition of face.
2. the system as claimed in claim 1, which is characterized in that the characteristic value of the face is that the relative position of facial contour is believed
Breath, including but not limited to: the position of eyes, the position of nose, the position of the corners of the mouth, the position put on face contour curve.
3. system as claimed in claim 2, which is characterized in that it is described to photo to be identified carry out pretreatment include: from wait know
Face position is taken out in other photo, and whitening processing is carried out to the face position of the taking-up.
4. system as claimed in claim 3, which is characterized in that the spy according to the face position in the photo to be identified
The characteristic value of known face carries out recognition of face in value indicative and the reference picture, comprising:
For individual photo to be identified, using correlation distance is calculated, final recognition result is determined:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors, ρXYValue -1
Between~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
5. system as claimed in claim 4, which is characterized in that the spy according to the face position in the photo to be identified
The characteristic value of known face carries out recognition of face in value indicative and the reference picture, further includes:
Final recognition result is determined by voting mechanism for continuously intercepting multiple pictures under video environment.
6. a kind of face identification method, which is characterized in that this method comprises the following steps:
A. reference picture is chosen, the characteristic value of known face in the reference picture is extracted；
B. photo to be identified is pre-processed, takes out the face position in photo to be identified；
C. the characteristic value at the face position in photo to be identified is extracted, and according to the spy at the face position in the photo to be identified
The characteristic value of known face carries out recognition of face in value indicative and the reference picture.
7. method as claimed in claim 6, which is characterized in that the characteristic value of the face is that the relative position of facial contour is believed
Breath, including but not limited to: the position of eyes, the position of nose, the position of the corners of the mouth, the position put on face contour curve.
8. the method for claim 7, which is characterized in that it is described to photo to be identified carry out pretreatment include: from wait know
Face position is taken out in other photo, and whitening processing is carried out to the face position of the taking-up.
9. method according to claim 8, which is characterized in that the step c is specifically included:
For individual photo to be identified, using correlation distance is calculated, final recognition result is determined:
Wherein, covariance of the score top half between two vectors, lower half portion are the standard deviation of two vectors, ρXYValue -1
Between~1, absolute value is bigger to illustrate that the two degree of correlation is higher, i.e., more similar.
10. method as claimed in claim 9, which is characterized in that the step c further include:
Final recognition result is determined by voting mechanism for continuously intercepting multiple pictures under video environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811541785.8A CN109583421A (en) | 2018-12-17 | 2018-12-17 | Face identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811541785.8A CN109583421A (en) | 2018-12-17 | 2018-12-17 | Face identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583421A true CN109583421A (en) | 2019-04-05 |
Family
ID=65929747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811541785.8A Pending CN109583421A (en) | 2018-12-17 | 2018-12-17 | Face identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583421A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111245103A (en) * | 2020-03-31 | 2020-06-05 | 贵州电网有限责任公司 | Display and storage system of power grid transformer nameplate based on neural computing rod |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344914A (en) * | 2007-07-09 | 2009-01-14 | 上海耀明仪表控制有限公司 | Human face recognition method based on characteristic point |
| CN102194131B (en) * | 2011-06-01 | 2013-04-10 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| CN104484669A (en) * | 2014-11-24 | 2015-04-01 | 苏州福丰科技有限公司 | Mobile phone payment method based on three-dimensional human face recognition |
| CN106960214A (en) * | 2017-02-17 | 2017-07-18 | 北京维弦科技有限责任公司 | Object identification method based on image |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
-
2018
- 2018-12-17 CN CN201811541785.8A patent/CN109583421A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344914A (en) * | 2007-07-09 | 2009-01-14 | 上海耀明仪表控制有限公司 | Human face recognition method based on characteristic point |
| CN102194131B (en) * | 2011-06-01 | 2013-04-10 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| CN104484669A (en) * | 2014-11-24 | 2015-04-01 | 苏州福丰科技有限公司 | Mobile phone payment method based on three-dimensional human face recognition |
| CN106960214A (en) * | 2017-02-17 | 2017-07-18 | 北京维弦科技有限责任公司 | Object identification method based on image |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111245103A (en) * | 2020-03-31 | 2020-06-05 | 贵州电网有限责任公司 | Display and storage system of power grid transformer nameplate based on neural computing rod |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Del Rio et al. | Automated border control e-gates and facial recognition systems | |
| Zuo et al. | Real-time embedded face recognition for smart home | |
| Bansal et al. | Face recognition using PCA and LDA algorithm | |
| CN100557625C (en) | Face identification method and device thereof that face component feature and Gabor face characteristic merge | |
| CN109255299A (en) | Identity identifying method and device, electronic equipment and storage medium | |
| CN106529414A (en) | Method for realizing result authentication through image comparison | |
| CN103530659B (en) | With reference to the face identification method and attendance checking system of original and symmetrical face facial image | |
| CN107438854A (en) | The system and method that the image captured using mobile device performs the user authentication based on fingerprint | |
| US9330312B2 (en) | Multispectral detection of personal attributes for video surveillance | |
| CN107680294A (en) | House property information querying method, system, terminal device and storage medium | |
| Paul et al. | Extraction of facial feature points using cumulative histogram | |
| Haji et al. | Real time face recognition system (RTFRS) | |
| CN110427972A (en) | Certificate video feature extraction method, apparatus, computer equipment and storage medium | |
| CN104217503A (en) | Self-service terminal identity identification method and corresponding house property certificate printing method | |
| CN108230536A (en) | One kind is to light variable security index identification method and device | |
| CN204143555U (en) | The Certificate of House Property printing terminal of identification self-aided terminal and correspondence | |
| Galbally et al. | Study on face identification technology for its implementation in the Schengen information system | |
| CN104217504A (en) | Identity recognition self-service terminal and corresponding certificate of house property printing terminal | |
| CN109977837A (en) | Pedestrian based on human body attitude invariant features recognition methods again | |
| CN109583421A (en) | Face identification system and method | |
| Pilania et al. | Exploring face detection and recognition in steganography | |
| Sun et al. | Opportunities and challenges for biometrics | |
| WO2023192808A1 (en) | Authentication of age, gender, and other biometric data from live images of users | |
| Bouma et al. | Authentication of travel and breeder documents | |
| CN114373213A (en) | Juvenile identity recognition method and device based on face recognition |
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 |
Application publication date: 20190405 |
|
| RJ01 | Rejection of invention patent application after publication |