CN107729863B - Human finger vein recognition method - Google Patents
Human finger vein recognition method Download PDFInfo
- Publication number
- CN107729863B CN107729863B CN201711042722.3A CN201711042722A CN107729863B CN 107729863 B CN107729863 B CN 107729863B CN 201711042722 A CN201711042722 A CN 201711042722A CN 107729863 B CN107729863 B CN 107729863B
- Authority
- CN
- China
- Prior art keywords
- value
- gray
- target image
- clustering
- minimum
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 210000003462 vein Anatomy 0.000 title claims abstract description 24
- 230000000694 effects Effects 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000009616 inductively coupled plasma Methods 0.000 claims abstract description 19
- 238000003064 k means clustering Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 3
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
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
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- 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
-
- 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
- G06V40/14—Vascular patterns
Abstract
The invention discloses a human body finger vein recognition method, which comprises the steps of reducing a target image to a set proportion, and carrying out primary clustering on all pixels in the target image according to the gray value of the pixels; deleting the cluster set corresponding to the maximum central value and the minimum central value of the primary clustering, and respectively clustering the gray values in the rest cluster sets again; deleting the class with the maximum central value in the secondary clustering, combining the rest classes in each class into a gray scale set, and updating the gray scale value in the gray scale set according to the maximum gray scale value and the minimum gray scale value in each class to obtain feature map data; extracting pixel values larger than zero in the feature map data, and forming a space point set aiming at each feature map data; calculating a total registration effect value of the target image and the fingerprint image template by adopting an ICP (inductively coupled plasma) algorithm; and when the minimum value in all the total registration effect values is smaller than the set threshold value, the target image and the collector corresponding to the fingerprint image template generating the minimum registration effect value are the same person.
Description
Technical Field
The invention relates to a fingerprint identification technology, in particular to a human body finger vein identification method.
Background
In the fingerprint identification process, because the photosensitive chip is required to work in a high ISO (high photosensitive) mode for acquiring the finger vein image, strong shot noise can be superimposed on the acquired image due to the high photosensitive characteristic of the image, so that a plurality of digital image processing algorithms based on the assumption of smooth images are difficult to work or cannot work; meanwhile, under the strict constraints of identification time and accuracy, conventional large-computation algorithms such as noise removal and image matching are difficult to use.
Therefore, a finger vein recognition algorithm which is insensitive to shot noise and illumination and is suitable for a low-power-consumption and low-performance computing platform is urgently needed to be developed.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a human finger vein identification method with accurate identification.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
provided is a human finger vein recognition method, which includes:
acquiring a fingerprint image of a current acquirer, and intercepting an area where the fingerprint is located as a target image;
reducing the target image to a set proportion, carrying out primary clustering on all pixels in the target image according to the gray value of the pixels by adopting a k-means clustering algorithm, and generating at least five categories;
deleting the cluster set corresponding to the maximum central value and the minimum central value of the primary clustering, and respectively clustering the gray values in the rest cluster sets again in at least three classes by adopting a k-means clustering algorithm;
deleting the class with the maximum central value in the secondary clustering, merging the rest classes in each class into a gray set, marking the gray sets corresponding to the two maximum central values in the reserved primary clustering, and merging the rest gray sets into a gray set;
updating the gray values in the gray set according to the maximum gray value and the minimum gray value in each category to obtain feature map data;
extracting pixel values larger than zero in the feature map data, and forming a space point set aiming at each feature map data;
calculating a total registration effect value of the target image and the fingerprint image template by adopting an ICP (inductively coupled plasma) algorithm according to the space point set of the target image and the template space point set of the fingerprint image template in the database;
and when the minimum value in all the total registration effect values is smaller than the set threshold value, the target image and the collector corresponding to the fingerprint image template generating the minimum registration effect value are the same person.
Further, the human finger vein identification method further comprises the step of calculating the average value of all the total registration effect values when the minimum value of all the total registration effect values is larger than or equal to a set threshold value;
and if the minimum value in all the total registration effect values is smaller than the set multiple of the average value, the target image and the collector corresponding to the fingerprint image template generating the minimum registration effect value are the same person, otherwise, the current collector cannot pass through fingerprint identification.
Further, the setting multiple is larger than zero and smaller than one.
Further, according to the maximum gray value and the minimum gray value in each category, a specific formula for updating the gray values in the gray set is as follows:
new_v=(v-min_v)/max_v*255
wherein new _ v is the updated gray value; v is the gray value in the gray set; min _ v is the maximum gray value; max _ v is the minimum grayscale value.
Further, calculating the total registration effect value of the target image and the fingerprint image template by adopting an ICP algorithm according to the spatial point set of the target image and the template spatial point set of the fingerprint image template in the database further comprises:
and registering the space point set and a template space point set of the fingerprint image template in the database by adopting an ICP (inductively coupled plasma) algorithm:
new_sample_rd0_points=Rk*sample_rd0_points+tk
wherein, new _ sample _ rd0Points is a set of spatial points; rkIs a rotation matrix; t is tkIs a translation vector;
calculating the total registration effect value of the target image and the fingerprint image template in the database according to the registration effect value generated in the spatial point set registration process:
fitk=n0*fitk0+n1*fitk1…+nx*fitkx
therein, fitk0、fitk1…fitkxRegistration Effect value, n, for each set of spatial points0、n1…nxA weight coefficient for each spatial point set; fitkIs the registration effect value of the target image.
Further, during the primary clustering, at least three times of primary clustering are carried out, at least five categories are generated each time, one time with the best clustering effect in at least three times of clustering is selected as a primary clustering result, and then the step of deleting the clustering sets corresponding to the maximum central value and the minimum central value of the primary clustering is carried out.
Further, the template space point set obtaining method of the fingerprint image template in the database is the same as the space point set obtaining method of the target image.
Further, a finger vein recognition machine is adopted to obtain a fingerprint image and a fingerprint image template of the collector.
Further, reducing the target image to the set scale is specifically reducing the target image to 0.25 times the original target image.
The invention has the beneficial effects that: the problems of noise interference and reduction of operation amount are solved by reducing the target image, effective information on the original image is effectively maintained, and the identification accuracy is not reduced. In the process of generating the characteristic diagram data, a complete blood vessel image can be separated step by step through a k-means clustering algorithm and a reduction process of gray values.
In the scheme, the image is segmented based on the pixel gray value by using a k-means automatic clustering method, and the image segmentation can be effectively realized under various illumination conditions; and directly utilizing the central value of each cluster, which pixels in the clustering result belong to useless background information can be quickly identified, so that useful blood vessel image information is extracted.
The pixel data of the image is converted into a space point set (also called point cloud) on a three-dimensional space according to the position and gray value information of the pixel data on the image, and then the ICP algorithm of point cloud registration and the template space point set are used for configuration, so that the identification algorithm can still accurately identify even under the condition that the finger position and the gesture are not uniform during sampling, and the identification accuracy and reliability are high.
The registration effect value output by the ICP algorithm is used as similarity measurement between two data point clouds, other special calculation is not needed, and the calculated amount is reduced; the total registration effect value is calculated by using a weighting mode, the quantity and the quality of information contained in each segmentation region are fully utilized, and the final identification accuracy is improved.
Drawings
Fig. 1 is a flowchart of an embodiment of a human finger vein recognition method.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
Referring to fig. 1, fig. 1 shows a flow chart of an embodiment of a human finger vein recognition method; as shown in fig. 1, the method 100 includes steps 101 to 108.
In step 101, acquiring a fingerprint image of a current acquirer, and intercepting an area where the fingerprint is located as a target image; the fingerprint image can be obtained by a finger vein recognition machine.
In step 102, the target image is reduced to a set proportion, and a k-means clustering algorithm is adopted to perform primary clustering on all pixels in the target image according to the gray values of the pixels, and at least five categories are generated.
In practice, the scheme preferably reduces the target image to the set ratio, specifically, reduces the target image to 0.25 times of the original target image.
When the primary clustering is performed, at least three times of primary clustering are performed, at least five categories are generated each time, one of the at least three times of clustering is selected as a primary clustering result, and then the step 103 is performed.
In step 103, deleting the cluster set corresponding to the maximum central value and the minimum central value of the primary cluster, and performing clustering again on the gray values in the remaining cluster sets by using a k-means clustering algorithm; and the central value corresponding to the initial clustering is the average value of all gray values in the clustering set.
In step 104, deleting the class with the largest central value in the secondary clustering, merging the rest classes in each class into a gray set, marking the gray sets corresponding to the two largest central values in the retained primary clustering, and merging the rest gray sets into a gray set; the corresponding center value when clustering again is the average value of all gray values in the gray set.
In step 105, updating the gray values in the gray set according to the maximum gray value and the minimum gray value in each category to obtain feature map data;
in an embodiment of the present invention, a specific formula for updating the gray-scale values in the gray-scale set according to the maximum gray-scale value and the minimum gray-scale value in each category is as follows:
new_v=(v-min_v)/max_v*255
wherein new _ v is the updated gray value; v is the gray value in the gray set; min _ v is the maximum gray value; max _ v is the minimum grayscale value.
In step 106, extracting pixel values larger than zero in the feature map data, and forming a spatial point set for each feature map data; specifically, the pixel value at each feature image, i.e., at position i, j, is vijAnd v isij>0, then is recorded as the midpoint coordinate (i, j, v) in the three-dimensional coordinate spaceij) The spatial point set is a point coordinate in a three-dimensional coordinate space satisfying the condition in the feature map data.
In step 107, calculating a total registration effect value of the target image and the fingerprint image template by adopting an ICP (inductively coupled plasma) algorithm according to the space point set of the target image and the template space point set of the fingerprint image template in the database;
the database stores a plurality of fingerprint image templates of different collectors, and each fingerprint image template needs to acquire a template space point set in the step 101 and the step 106, that is, the acquisition method of the template space point set of the fingerprint image templates in the database is the same as the acquisition method of the space point set of the target image.
In an embodiment of the present invention, calculating the total registration effect value of the target image and the fingerprint image template by using the ICP algorithm according to the spatial point set of the target image and the template spatial point set of the fingerprint image template in the database further includes:
and registering the space point set and a template space point set of the fingerprint image template in the database by adopting an ICP (inductively coupled plasma) algorithm:
new_sample_rd0_points=Rk*sample_rd0_points+tk
wherein, new _ sample _ rd0Points is a set of spatial points; rkIs a rotation matrix; t is tkIs a translation vector;
calculating the total registration effect value of the target image and the fingerprint image template in the database according to the registration effect value generated in the spatial point set registration process:
fitk=n0*fitk0+n1*fitk1…+nx*fitkx
therein, fitk0、fitk1…fitkxRegistration Effect value, n, for each set of spatial points0、n1…nxA weight coefficient for each spatial point set; fitkIs the registration effect value of the target image.
In step 108, when the minimum value of all the total registration effect values is smaller than the set threshold, the target image and the acquirer corresponding to the fingerprint image template generating the minimum registration effect value are the same person.
When the method is implemented, the method for identifying the selected human finger vein further comprises the following steps: when the minimum value in all the total registration effect values is larger than or equal to a set threshold value, calculating the average value of all the total registration effect values;
if the minimum value in all the total registration effect values is smaller than the set multiple of the average value (the set multiple is a number which is larger than zero and smaller than one), the target image and the acquirer corresponding to the fingerprint image template generating the minimum registration effect value are the same person, otherwise, the current acquirer cannot pass through fingerprint identification.
Claims (9)
1. The human finger vein recognition method is characterized by comprising the following steps:
acquiring a fingerprint image of a current acquirer, and intercepting an area where the fingerprint is located as a target image;
reducing the target image to a set proportion, carrying out primary clustering on all pixels in the target image according to the gray value of the pixels by adopting a k-means clustering algorithm, and generating at least five categories;
deleting the cluster set corresponding to the maximum central value and the minimum central value of the primary clustering, and respectively clustering the gray values in the rest cluster sets again in at least three classes by adopting a k-means clustering algorithm;
deleting the class with the maximum central value in the secondary clustering, merging the rest classes in each class into a gray set, marking the gray sets corresponding to the two maximum central values in the reserved primary clustering, and merging the rest gray sets into a gray set;
updating the gray values in the gray set according to the maximum gray value and the minimum gray value in each category to obtain feature map data;
extracting pixel values larger than zero in the feature map data, and forming a space point set aiming at each feature map data;
calculating a total registration effect value of the target image and the fingerprint image template by adopting an ICP (inductively coupled plasma) algorithm according to the space point set of the target image and the template space point set of the fingerprint image template in the database;
when the minimum value of all the total registration effect values is smaller than a set threshold value, the target image and the collector corresponding to the fingerprint image template generating the minimum registration effect value are the same person;
and during primary clustering, performing primary clustering for at least three times, generating at least five categories each time, selecting the one with the best clustering effect among the at least three clusters as a primary clustering result, and then performing a step of deleting the cluster sets corresponding to the maximum central value and the minimum central value of the primary clustering.
2. The human finger vein recognition method of claim 1, further comprising:
when the minimum value in all the total registration effect values is larger than or equal to a set threshold value, calculating the average value of all the total registration effect values;
and if the minimum value in all the total registration effect values is smaller than the set multiple of the average value, the target image and the collector corresponding to the fingerprint image template generating the minimum registration effect value are the same person, otherwise, the current collector cannot pass through fingerprint identification.
3. The human finger vein recognition method of claim 2, wherein the set multiple is greater than zero and less than one.
4. The human finger vein recognition method according to claim 1, wherein the specific formula for updating the gray values in the gray set according to the maximum gray value and the minimum gray value in each category is as follows:
new_v=(v-min_v)/max_v*255
wherein new _ v is the updated gray value; v is the gray value in the gray set; min _ v is the maximum gray value; max _ v is the minimum grayscale value.
5. The human finger vein recognition method of claim 1, wherein the calculating the total registration effect value of the target image and the fingerprint image template by using the ICP algorithm according to the spatial point set of the target image and the template spatial point set of the fingerprint image template in the database further comprises:
and registering the space point set and a template space point set of the fingerprint image template in the database by adopting an ICP (inductively coupled plasma) algorithm:
new_sample_rd0_points=Rk*sample_rd0_points+tk
wherein, new _ sample _ rd0Points is a set of spatial points; rkIs a rotation matrix; t is tkIs a translation vector;
calculating the total registration effect value of the target image and the fingerprint image template in the database according to the registration effect value generated in the spatial point set registration process:
fitk=n0*fitk0+n1*fitk1…+nx*fitkx
therein, fitk0、fitk1…fitkxRegistration Effect value, n, for each set of spatial points0、n1…nxA weight coefficient for each spatial point set; fitkIs the registration effect value of the target image.
6. The human finger vein recognition method according to any one of claims 1 to 5, wherein the template space point set of the fingerprint image template in the database is obtained by the same method as the space point set of the target image.
7. The human finger vein recognition method according to any one of claims 1 to 5, wherein a finger vein recognition machine is used to obtain a fingerprint image and a fingerprint image template of the acquirer.
8. The human finger vein recognition method according to any one of claims 1 to 5, wherein the reduction of the target image to a set scale is specifically to reduce the target image to 0.25 times of an original target image.
9. The human finger vein recognition method of any one of claims 1-5, wherein the center value corresponding to the first clustering is an average of all gray values in the clustering set, and the center value corresponding to the second clustering is an average of all gray values in the gray set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711042722.3A CN107729863B (en) | 2017-10-30 | 2017-10-30 | Human finger vein recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711042722.3A CN107729863B (en) | 2017-10-30 | 2017-10-30 | Human finger vein recognition method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107729863A CN107729863A (en) | 2018-02-23 |
CN107729863B true CN107729863B (en) | 2020-11-17 |
Family
ID=61203378
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711042722.3A Active CN107729863B (en) | 2017-10-30 | 2017-10-30 | Human finger vein recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107729863B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165639B (en) * | 2018-10-15 | 2021-12-10 | 广州广电运通金融电子股份有限公司 | Finger vein identification method, device and equipment |
CN112102210B (en) * | 2020-11-17 | 2021-03-16 | 北京圣点云信息技术有限公司 | Vein image template updating method and device based on self-learning |
CN112200156B (en) * | 2020-11-30 | 2021-04-30 | 四川圣点世纪科技有限公司 | Vein recognition model training method and device based on clustering assistance |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870808A (en) * | 2014-02-27 | 2014-06-18 | 中国船舶重工集团公司第七一〇研究所 | Finger vein identification method |
CN105975951A (en) * | 2016-05-27 | 2016-09-28 | 国创科视科技股份有限公司 | Finger vein and fingerprint fusion identification method of middle part of finger |
CN105975974A (en) * | 2016-05-10 | 2016-09-28 | 深圳市金脉智能识别科技有限公司 | ROI image extraction method in finger vein identification |
-
2017
- 2017-10-30 CN CN201711042722.3A patent/CN107729863B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870808A (en) * | 2014-02-27 | 2014-06-18 | 中国船舶重工集团公司第七一〇研究所 | Finger vein identification method |
CN105975974A (en) * | 2016-05-10 | 2016-09-28 | 深圳市金脉智能识别科技有限公司 | ROI image extraction method in finger vein identification |
CN105975951A (en) * | 2016-05-27 | 2016-09-28 | 国创科视科技股份有限公司 | Finger vein and fingerprint fusion identification method of middle part of finger |
Non-Patent Citations (2)
Title |
---|
"Categorizing Finger-Vein Images Using a Hierarchal Approach";Dun Tan etc.;《Chinese Conference on Biometric Recognition》;20131231;参见论文第298-305页 * |
"Finger vein indexing based on binary feature";Jayachander Surbiryala etc.;《2015 Colour and Visual Computing Symposium》;20150928;参见论文第2节 * |
Also Published As
Publication number | Publication date |
---|---|
CN107729863A (en) | 2018-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109344701B (en) | Kinect-based dynamic gesture recognition method | |
CN109154978B (en) | System and method for detecting plant diseases | |
CN107977671B (en) | Tongue picture classification method based on multitask convolutional neural network | |
CN108229509B (en) | Method and device for identifying object class and electronic equipment | |
CN109522908B (en) | Image significance detection method based on region label fusion | |
CN109035172B (en) | Non-local mean ultrasonic image denoising method based on deep learning | |
Dibeklioglu et al. | 3D facial landmarking under expression, pose, and occlusion variations | |
CN108537751B (en) | Thyroid ultrasound image automatic segmentation method based on radial basis function neural network | |
CN109684959B (en) | Video gesture recognition method and device based on skin color detection and deep learning | |
CN111145209A (en) | Medical image segmentation method, device, equipment and storage medium | |
CN112633297B (en) | Target object identification method and device, storage medium and electronic device | |
CN108520215B (en) | Single-sample face recognition method based on multi-scale joint feature encoder | |
CN107729863B (en) | Human finger vein recognition method | |
CN110245600B (en) | Unmanned aerial vehicle road detection method for self-adaptive initial quick stroke width | |
CN114359998B (en) | Identification method of face mask in wearing state | |
CN112365497A (en) | High-speed target detection method and system based on Trident Net and Cascade-RCNN structures | |
CN111191569A (en) | Face attribute recognition method and related device thereof | |
CN112037221A (en) | Multi-domain co-adaptation training method for cervical cancer TCT slice positive cell detection model | |
Gurrala et al. | A new segmentation method for plant disease diagnosis | |
CN107564008A (en) | Rapid SAR image segmentation method based on crucial pixel fuzzy clustering | |
Batule et al. | Leaf disease detection using image processing and support vector machine (SVM) | |
CN112507924B (en) | 3D gesture recognition method, device and system | |
CN112215303B (en) | Image understanding method and system based on self-learning attribute | |
CN111199228B (en) | License plate positioning method and device | |
CN117115117A (en) | Pathological image recognition method based on small sample, electronic equipment and storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |