CN103839246B - Method and apparatus for obtaining image contour line - Google Patents
Method and apparatus for obtaining image contour line Download PDFInfo
- Publication number
- CN103839246B CN103839246B CN201210472406.0A CN201210472406A CN103839246B CN 103839246 B CN103839246 B CN 103839246B CN 201210472406 A CN201210472406 A CN 201210472406A CN 103839246 B CN103839246 B CN 103839246B
- Authority
- CN
- China
- Prior art keywords
- image
- contour line
- edge pixel
- characteristic vector
- pixel point
- 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
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for obtaining an image contour line. The method comprises the following steps: obtaining an image and calculating gradient information of the image; calculating a structure feature of the image according to the gradient information; calculating a feature vector of the structure feature; extracting a vertical component of the feature vector and extracting an edge pixel point of the image based on the vertical component of the feature vector; and generating a contour line according to the edge pixel point. In addition, the invention also provides an apparatus for obtaining an image contour line. With the method and the apparatus, the accuracy can be improved.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of method and device for obtaining image contour line.
Background technology
In the image processing arts, it usually needs the contour line of the subregion in image is obtained by rim detection, use
In the differentiation subregion and whole image.For example, human region contour line in the picture can be obtained by rim detection, from
And take out from image by human region.
In conventional art, the method for obtaining image contour line generally calculates the gradient information of each pixel of image, then will
The gradient information of image is compared with threshold value, the pixel for obtaining gradient information more than threshold value as edge pixel point, finally
The edge pixel for getting point is coupled together the contour line to form image.
However, being set in threshold value by the method for the gradient information and threshold value acquisition image contour line of pixel in conventional art
When putting less, the contour line in image is more, is unfavorable for defined area scope；When threshold value arranges larger, the contour line for obtaining
Larger space then occurs.Therefore, the method for obtaining image contour line in conventional art is obtaining the accurate of image contour line
There is obvious deficiency in property.
The content of the invention
Based on this, it is necessary to provide a kind of method of the acquisition image contour line that can improve accuracy.
A kind of method for obtaining image contour line, including：
Image is obtained, the gradient information of described image is calculated；
The architectural feature of described image is calculated according to the gradient information；
Calculate the characteristic vector of the architectural feature；
The vertical component of the characteristic vector is extracted, and described image is extracted according to the vertical component of the characteristic vector
Edge pixel point；
Contour line is generated according to the edge pixel point.
Additionally, there is a need to the device for providing a kind of acquisition image contour line that can improve accuracy.
A kind of device for obtaining image contour line, including：
Gradient information acquisition module, for obtaining image, calculates the gradient information of described image；
Architectural feature acquisition module, for calculating the architectural feature of described image according to the gradient information；
Characteristic vector acquisition module, for calculating the characteristic vector of the architectural feature；
Edge pixel point acquisition module, for extracting the vertical component of the characteristic vector, and according to the characteristic vector
Vertical component extract described image edge pixel point；
Contour generating module, for generating contour line according to the edge pixel point.
The method and apparatus of above-mentioned acquisition image contour line, first obtains the gradient information of image, further according to the gradient of image
The architectural feature of acquisition of information image, and the characteristic vector of the architectural feature of image is further calculated, then according to described
The vertical component of characteristic vector extracts the edge pixel point of image.So that the edge pixel point for extracting is relative in conventional art
The space obtained by threshold value between the edge pixel point on contour line is less, so as to improve the image contour line for getting
Accuracy.
Description of the drawings
Fig. 1 is the flow chart of the method for acquisition image contour line in one embodiment；
Fig. 2 is the structural representation of the device of acquisition image contour line in one embodiment；
Fig. 3 is the structural representation of the device of acquisition image contour line in another embodiment.
Specific embodiment
In one embodiment, as shown in figure 1, it is a kind of obtain image contour line method, including：
Step S102, obtains image, calculates the gradient information of image.
In one embodiment, Sobel Operator can be passed through（Sobel operator）Calculate the gradient information of image.
Matrix of the Sobel Operator comprising two groups of 3x3, respectively x- directions difference matrix and y- directions difference matrix.Can be by
Sobel Operator makees planar convolution with the image for getting, you can draw the gradient information in x- directions and y- directions respectively.Can lead to
Cross equation below：
Calculate the gradient information of image.Wherein, T is the set of the pixel of the image for getting, GxAnd GyRespectively calculate
The horizontal gradient information for arriving and vertical gradient information.
Step S104, calculates the architectural feature of image according to gradient information.
In one embodiment, can be by the structure tensor field of calculating image（struct tensor）Obtain the knot of image
Structure feature.Structure tensor field is the expression of architectural feature.
In the present embodiment, can be according to equation below：
Calculate image spatial feature.Wherein, structure tensor fields of the S for image, GxAnd GyRespectively aforementioned calculated x-
Direction gradient information and y- direction gradient information.
In the present embodiment, also Gaussian Blur can be carried out to image before the structure tensor field of image is calculated, removal is made an uproar
Sound.
Step S106, the characteristic vector of computation structure feature.
In one embodiment, can be according to formula：
A=Gx×Gx, B=Gx×Gy, C=Gy×Gy；
The characteristic vector of computation structure feature.Wherein, A, B, C be the corresponding element value of structure tensor field matrix, λ1And λ2Point
Not Wei structure tensor field matrix eigenvalue, v1And v2The respectively vertical component and tangential component of the characteristic vector of architectural feature.
The direction of the tangential component of the characteristic vector for getting is the direction vector of the pixel, and vertical component is and pixel
The vertical vector in direction vector direction.
Step S108, extracts the vertical component of characteristic vector, and extracts the side of image according to the vertical component of characteristic vector
Edge pixel.
In one embodiment, the step of extracting the edge pixel point of image according to the vertical component of characteristic vector can be concrete
For：
The vertical direction information of the vertical component of characteristic vector is obtained, and Gauss difference algorithm is passed through according to vertical direction information
Extract the edge pixel point of image.
Gaussian difference（DOG, Difference of Gauss）Algorithm is a kind of algorithm for image enhancement.Can be incited somebody to action by DOG algorithms
Marginal area in image strengthens（That is marginal portion signal enhancing, the other parts decay of image）It is right in extraction marginal area afterwards
The edge pixel point answered.
In the present embodiment, the edge pixel point of image can be extracted according to vertical direction information by default DOG functions.
DOG functions can be matlab（A mathematical tool）Built-in function.
Step S110, generates contour line according to edge pixel point.
In one embodiment, can be by the connection of edge pixel point be generated image contour line.
In one embodiment, the step of generating contour line according to edge pixel point can be specially：Extract characteristic vector
Tangential component, and Fuzzy processing is carried out to edge pixel according to tangential component obtain contour line.
In the present embodiment, the step of carrying out Fuzzy processing according to tangential component to edge pixel can be specially：
The tangential direction information of the tangential component of characteristic vector is obtained, and edge pixel is entered in tangential direction information
The process of row Gaussian Blur.
Gaussian Blur（Gaussian Blur）Algorithm is by the pixel the edge pixel point for closing in tangential direction
Colour according to default Gaussian function by weighted average calculation come by edge pixel point extend, so as to edge pixel point two-by-two
Between space completion.Edge pixel point after completion constitutes image contour line.
In the present embodiment, in tangential direction edge pixel can be carried out by calling default Gaussian blurring function
Gaussian Blur process.During Gaussian blurring function can be the obfuscation instrument that OpenCV (a image processing function storehouse) is provided
Gaussian Blur built-in function.
In other embodiments, also obfuscation can be carried out to edge pixel by dynamic fuzzy, radial blur scheduling algorithm
Process.Dynamic fuzzy function corresponding with dynamic fuzzy, radial blur algorithm and radial blur function can be that OpenCV is provided
Obfuscation instrument in built-in function.
In one embodiment, can also be according to default scaling before the step of calculating the gradient information of pixel in image
Ratio carries out diminution process to image.
In the present embodiment, can also be according to scaling to profile after the step of generating contour line according to edge pixel point
Line is amplified process.
In the present embodiment, the scaling for carrying out reducing process is identical with the scaling for being amplified process.Will figure
As carry out reduce process when, can according to scaling by calculate reduce before image in pixel pixel value meansigma methodss come
Generate the pixel value of the pixel of the image after reducing.When image is amplified process, contour line also amplifies therewith.
Diminution process is carried out to image in advance, the image after according to diminution is amplified after generating contour line again so that
When the characteristic vector of gradient information, architectural feature and architectural feature of image is calculated, amount of calculation reduces, and improves and processes effect
Rate.And as the processing and amplifying that carries out of contour line to generating is for waiting than amplifying restoring operation, i.e., to split-phase neighbour in the middle part of contour line
Edge pixel point between position relationship done trickle approximate, without changing the global shape of contour line, therefore, in scaling
When ratio is less than threshold value, the accuracy of the image contour line of generation still can be guaranteed.
In one embodiment, as shown in Fig. 2 it is a kind of obtain image contour line device, including：Gradient information obtains mould
Block 102, architectural feature acquisition module 104, characteristic vector acquisition module 106, edge pixel point acquisition module 108 and contour line
Generation module 110, wherein：
Gradient information acquisition module 102, for obtaining image, calculates the gradient information of image.
In one embodiment, gradient information acquisition module 102 can be used for by Sobel Operator（Sobel
operator）Calculate the gradient information of image.
Matrix of the Sobel Operator comprising two groups of 3x3, respectively x- directions difference matrix and y- directions difference matrix.Can be by
Sobel Operator makees planar convolution with the image for getting, you can draw the gradient information in x- directions and y- directions respectively.Gradient
Data obtaining module 102 can be used for by equation below：
Calculate the gradient information of image.Wherein, T is the set of the pixel of the image for getting, GxAnd GyRespectively calculate
The horizontal gradient information for arriving and vertical gradient information.
Architectural feature acquisition module 104, for calculating the architectural feature of image according to gradient information.
In one embodiment, the structure tensor field that architectural feature acquisition module 104 can be used for by calculating image obtains
The architectural feature of image.Structure tensor field is the expression of architectural feature.
In the present embodiment, architectural feature acquisition module 104 can be used for according to equation below：
Calculate image spatial feature.Wherein, structure tensor fields of the S for image, GxAnd GyRespectively aforementioned calculated x-
Direction gradient information and y- directions vertical gradient information.
In the present embodiment, architectural feature acquisition module 104 can be additionally used in right before the structure tensor field of image is calculated
Image carries out Gaussian Blur, removes noise.
Characteristic vector acquisition module 106, for the characteristic vector of computation structure feature.
In one embodiment, characteristic vector acquisition module 106 can be used for according to formula：
A=Gx×Gx, B=Gx×Gy, C=Gy×Gy；
The characteristic vector of computation structure feature.Wherein, A, B, C be the corresponding element value of structure tensor field matrix, λ1And λ2Point
Not Wei structure tensor field matrix eigenvalue, v1And v2The respectively vertical component and tangential component of the characteristic vector of architectural feature.
The direction of the tangential component of the characteristic vector for getting is the direction vector of the pixel, and vertical component is and pixel
The vertical vector in direction vector direction.
Edge pixel point acquisition module 108, for extracting the vertical component of characteristic vector, and according to the vertical of characteristic vector
The edge pixel point of component extraction image.
In one embodiment, edge pixel point acquisition module 108 is additionally operable to hanging down for the vertical component of acquisition characteristic vector
Straight directional information, and the edge pixel point of image is extracted according to vertical direction information by Gauss difference algorithm.
Gaussian difference（DOG, Difference of Gauss）Algorithm is a kind of algorithm for image enhancement.Can be incited somebody to action by DOG algorithms
Marginal area in image strengthens（That is marginal portion signal enhancing, the other parts decay of image）It is right in extraction marginal area afterwards
The edge pixel point answered.
In the present embodiment, edge pixel point acquisition module 108 can be used to pass through default DOG according to vertical direction information
Function extracts the edge pixel point of image.DOG functions can be matlab（A mathematical tool）Built-in function.
Contour generating module 110, for generating contour line according to edge pixel point.
In one embodiment, contour generating module 110 can be used for by the connection of edge pixel point is generated image wheel
Profile.
In one embodiment, contour generating module 110 can be used to extract the tangential component of characteristic vector, and according to cutting
Line component carries out Fuzzy processing to edge pixel and obtains contour line.
In the present embodiment, contour generating module 110 can be used for the tangential direction of the tangential component for obtaining characteristic vector
Information, and Gaussian Blur process is carried out to edge pixel in tangential direction information.
Gaussian Blur（Gaussian Blur）Algorithm is by the pixel the edge pixel point for closing in tangential direction
Colour according to default Gaussian function by weighted average calculation come by edge pixel point extend, so as to edge pixel point two-by-two
Between space completion.Edge pixel point after completion constitutes image contour line.
In the present embodiment, contour generating module 110 can be used for by calling default Gaussian blurring function in tangent line
Gaussian Blur process is carried out to edge pixel on direction.During Gaussian blurring function can be the obfuscation instrument that OpenCV is provided
Gaussian Blur built-in function.
In other embodiments, contour generating module 110 can be used for by dynamic fuzzy, radial blur scheduling algorithm opposite side
Edge pixel carries out Fuzzy processing.Dynamic fuzzy function corresponding with dynamic fuzzy, radial blur algorithm and radial blur letter
Number can be the built-in function in the obfuscation instrument that OpenCV is provided.
In one embodiment, as shown in figure 3, the device for obtaining image contour line also includes image scaling module 112, use
Diminution process is carried out to image according to default scaling before the gradient information in calculating image, and according to edge
Pixel is amplified process according to scaling after generating contour line to contour line.
In the present embodiment, the scaling for carrying out reducing process is identical with the scaling for being amplified process.Will figure
When processing as carrying out reducing, image scaling module 112 can be used for according to scaling by calculating pixel in the image before reducing
Point pixel value meansigma methodss come generate reduce after image pixel pixel value.When image is amplified process, wheel
Profile also amplifies therewith.
Diminution process is carried out to image in advance, the image after according to diminution is amplified after generating contour line again so that
When the characteristic vector of gradient information, architectural feature and architectural feature of image is calculated, amount of calculation reduces, and improves and processes effect
Rate.And as the processing and amplifying that carries out of contour line to generating is for waiting than amplifying restoring operation, i.e., to split-phase neighbour in the middle part of contour line
Edge pixel point between position relationship done trickle approximate, without changing the global shape of contour line, therefore, in scaling
When ratio is less than threshold value, the accuracy of the image contour line of generation still can be guaranteed.
The method and apparatus of above-mentioned acquisition image contour line, first obtains the gradient information of image, further according to the gradient of image
The architectural feature of acquisition of information image, and the characteristic vector of the architectural feature of image is further calculated, then according to described
The vertical component of characteristic vector extracts the edge pixel point of image.So that the edge pixel point for extracting is relative in conventional art
The space obtained by threshold value between the edge pixel point on contour line is less, so as to improve the image contour line for getting
Accuracy.
One of ordinary skill in the art will appreciate that all or part of flow process in realizing above-described embodiment method, can be
Instruct related hardware to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory（Read-Only Memory, ROM）Or random access memory（Random Access
Memory, RAM）Deng.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more concrete and detailed, but and
Therefore the restriction to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, some deformations and improvement can also be made, these belong to the guarantor of the present invention
Shield scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (8)
1. it is a kind of obtain image contour line method, including：
Image is obtained, the gradient information of described image is calculated；
The architectural feature of described image is calculated according to the gradient information；
Calculate the characteristic vector of the architectural feature；
The vertical component of the characteristic vector is extracted, and extracts the edge of described image according to the vertical component of the characteristic vector
Pixel, including：The vertical direction information of the vertical component of the characteristic vector is obtained, and according to vertical direction information by height
This difference algorithm extracts the edge pixel point of described image；
Contour line is generated according to the edge pixel point.
2. it is according to claim 1 obtain image contour line method, it is characterised in that it is described according to the edge pixel
Putting the step of generating contour line is：
The tangential component of the characteristic vector is extracted, and the edge pixel point is carried out at obfuscation according to the tangential component
Reason obtains contour line.
3. it is according to claim 2 obtain image contour line method, it is characterised in that it is described according to the tangential component
The step of Fuzzy processing is carried out to the edge pixel point be：
The tangential direction information of the tangential component of the characteristic vector is obtained, and to the edge in the tangential direction information
Pixel carries out Gaussian Blur process.
4. according to any one of claims 1 to 3 acquisition image contour line method, it is characterised in that the calculating institute
Also include before the step of stating the gradient information of image：
Diminution process is carried out to described image according to default scaling；
Also include after the step of generation contour line according to the edge pixel point：
Process is amplified to the contour line according to the scaling.
5. it is a kind of obtain image contour line device, it is characterised in that include：
Gradient information acquisition module, for obtaining image, calculates the gradient information of described image；
Architectural feature acquisition module, for calculating the architectural feature of described image according to the gradient information；
Characteristic vector acquisition module, for calculating the characteristic vector of the architectural feature；
Edge pixel point acquisition module, for extracting the vertical component of the characteristic vector, and hanging down according to the characteristic vector
The edge pixel point of straight component extraction described image；
Contour generating module, for generating contour line according to the edge pixel point；
The edge pixel point acquisition module is additionally operable to the vertical direction information of the vertical component for obtaining the characteristic vector, and root
The edge pixel point of described image is extracted by Gauss difference algorithm according to vertical direction information.
6. it is according to claim 5 obtain image contour line device, it is characterised in that the contour generating module is also
For extracting the tangential component of the characteristic vector, and the edge pixel point is carried out at obfuscation according to the tangential component
Reason obtains contour line.
7. it is according to claim 6 obtain image contour line device, it is characterised in that the contour generating module is also
For obtaining the tangential direction information of the tangential component of the characteristic vector, and to the edge in the tangential direction information
Pixel carries out Gaussian Blur process.
8. according to any one of claim 5 to 7 acquisition image contour line device, it is characterised in that described device is also
Including image scaling module, for before the gradient information of described image is calculated according to default scaling to described image
Carry out diminution process, and after contour line is generated according to the edge pixel point according to the scaling to the profile
Line is amplified process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210472406.0A CN103839246B (en) | 2012-11-20 | 2012-11-20 | Method and apparatus for obtaining image contour line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210472406.0A CN103839246B (en) | 2012-11-20 | 2012-11-20 | Method and apparatus for obtaining image contour line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103839246A CN103839246A (en) | 2014-06-04 |
| CN103839246B true CN103839246B (en) | 2017-03-22 |
Family
ID=50802716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210472406.0A Active CN103839246B (en) | 2012-11-20 | 2012-11-20 | Method and apparatus for obtaining image contour line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103839246B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268828A (en) * | 2014-09-30 | 2015-01-07 | 可牛网络技术（北京）有限公司 | Image fuzzification processing method and device |
| CN105590068A (en) * | 2015-12-25 | 2016-05-18 | 北京奇虎科技有限公司 | File fingerprint check method and device |
| CN107169976A (en) * | 2017-04-20 | 2017-09-15 | 温州市鹿城区中津先进科技研究院 | The product contour line method for drafting of electric business platform exhibiting pictures big data |
| CN107577424A (en) * | 2017-08-18 | 2018-01-12 | 深圳云天励飞技术有限公司 | Image processing method, apparatus and system |
| CN109949385A (en) * | 2019-03-05 | 2019-06-28 | 上海商汤智能科技有限公司 | A kind of image adaptive method of adjustment, equipment, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5457754A (en) * | 1990-08-02 | 1995-10-10 | University Of Cincinnati | Method for automatic contour extraction of a cardiac image |
| CN101557454A (en) * | 2008-04-09 | 2009-10-14 | 富士施乐株式会社 | Image extracting apparatus, image extracting method and computer readable medium |
| CN101706962A (en) * | 2009-11-27 | 2010-05-12 | 四川长虹电器股份有限公司 | Image edge extraction method |
| CN102289825A (en) * | 2011-07-08 | 2011-12-21 | 暨南大学 | Real-time image edge detection circuit and realization method thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8300949B2 (en) * | 2010-05-18 | 2012-10-30 | Sharp Laboratories Of America, Inc. | Edge detection technique having improved feature visibility |
-
2012
- 2012-11-20 CN CN201210472406.0A patent/CN103839246B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5457754A (en) * | 1990-08-02 | 1995-10-10 | University Of Cincinnati | Method for automatic contour extraction of a cardiac image |
| CN101557454A (en) * | 2008-04-09 | 2009-10-14 | 富士施乐株式会社 | Image extracting apparatus, image extracting method and computer readable medium |
| CN101706962A (en) * | 2009-11-27 | 2010-05-12 | 四川长虹电器股份有限公司 | Image edge extraction method |
| CN102289825A (en) * | 2011-07-08 | 2011-12-21 | 暨南大学 | Real-time image edge detection circuit and realization method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103839246A (en) | 2014-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229490B (en) | Key point detection method, neural network training method, device and electronic equipment | |
| CN103839246B (en) | Method and apparatus for obtaining image contour line | |
| US9536147B2 (en) | Optical flow tracking method and apparatus | |
| CN105590319A (en) | Method for detecting image saliency region for deep learning | |
| CN103218605B (en) | A kind of fast human-eye positioning method based on integral projection and rim detection | |
| CN110910421B (en) | Weak and small moving object detection method based on block characterization and variable neighborhood clustering | |
| CN103473537B (en) | A kind of target image contour feature method for expressing and device | |
| US20150186753A1 (en) | Image Processing Apparatus, Image Processing Method, and Image Processing Program | |
| TWI314301B (en) | Adaptive image sharpening method | |
| CN110111350A (en) | A kind of welding pool edge detection method, device and storage medium | |
| Han et al. | Research and implementation of an improved canny edge detection algorithm | |
| CN105809633A (en) | Color noise removing method and device | |
| JP2011253354A (en) | Image processing apparatus, method and program | |
| CN109410246B (en) | Visual tracking method and device based on correlation filtering | |
| CN110807457A (en) | OSD character recognition method, device and storage device | |
| CN102013101A (en) | Blind detection method of permuted and tampered images subjected to fuzzy postprocessing | |
| CN110321808B (en) | Method, apparatus and storage medium for detecting carry-over and stolen object | |
| Sanmiguel et al. | Pixel-based colour contrast for abandoned and stolen object discrimination in video surveillance | |
| KR101407070B1 (en) | Method of extracting feature for human detection and apparatus for performing the same | |
| CN111899200B (en) | Infrared image enhancement method based on 3D filtering | |
| JP5029545B2 (en) | Image processing method and apparatus | |
| WO2019242388A1 (en) | Obstacle recognition method for library robot based on depth image | |
| Qu et al. | Linear interpolation with edge-preserving adaptive weights | |
| CN107491746B (en) | Face pre-screening method based on large gradient pixel analysis | |
| CN111860161A (en) | Target shielding detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |