CN110348501A - A kind of realization parking lot license plate Similarity Match Method - Google Patents
A kind of realization parking lot license plate Similarity Match Method Download PDFInfo
- Publication number
- CN110348501A CN110348501A CN201910582303.1A CN201910582303A CN110348501A CN 110348501 A CN110348501 A CN 110348501A CN 201910582303 A CN201910582303 A CN 201910582303A CN 110348501 A CN110348501 A CN 110348501A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- character
- parking lot
- gray
- 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.)
- Withdrawn
Links
Classifications
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The invention discloses a kind of realization parking lot license plate Similarity Match Methods, include the following steps: step 1, license plate image acquisition；Step 2, unified license plate background color；Step 3, image denoising；Step 4, image slant correction；Step 5, Character segmentation；Step 6, character recognition；Step 7, license plate matching enter and leave；Wherein in above-mentioned step one, license plate RGB image is acquired with CCD camera, collected source images are converted into 256 grades of gray level image, then gray scale stretching is carried out with the grey linear transformation of segmentation, carries out binaryzation with dynamic threshold in gray level image license plate area；Wherein in above-mentioned step two, after carrying out binaryzation to different types of license plate grey level image, by calculating separately the size of the number of pixels of two kinds of pixel values in the license plate after binaryzation to determine whether needing inverse；The present invention, identification quickly, improve discrimination, convenient for the normal matching of vehicle entry and exit data.
Description
Technical field
The present invention relates to parking lot field of license plate recognition, specially a kind of realization parking lot license plate similarity mode side
Method.
Background technique
In recent years, with the improvement of people's life quality, automobile has come into huge numbers of families, car owning amount is risen year by year,
Cause parking problem more and more prominent, people start to build parking lot to solve parking problem, and vehicle, which enters and exits, at present stops
All it is that license board information is acquired by camera when the entrance of parking lot, license board information is obtained carrying out identification to automotive license plate, due to vehicle
Board discrimination cannot reach 100%, and Car license recognition video camera has misrecognition, cause vehicle entry and exit data cannot be normal
Match, while bad to the resolution of license plate image, recognition speed is not quick enough, influences the discrepancy of vehicle, therefore, designs a kind of reality
Existing parking lot license plate Similarity Match Method is necessary.
Summary of the invention
The purpose of the present invention is to provide a kind of realization parking lot license plate Similarity Match Methods, to solve above-mentioned background skill
The problem of being proposed in art.
To achieve the above object, the invention provides the following technical scheme:
A kind of realization parking lot license plate Similarity Match Method includes the following steps: step 1, license plate image acquisition；Step
Rapid two, unified license plate background color；Step 3, image denoising；Step 4, image slant correction；Step 5, Character segmentation；Step 6,
Character recognition；Step 7, license plate matching enter and leave；
Wherein in above-mentioned step one, license plate RGB image is acquired with CCD camera, collected source images are converted
At 256 grades of gray level image, gray scale stretching then is carried out with the grey linear transformation of segmentation, the contrast of image is improved, in ash
Binaryzation is carried out with dynamic threshold in degree image license plate area；
Wherein in above-mentioned step two, after carrying out binaryzation to different types of license plate grey level image, pass through difference
The size of the number of pixels of two kinds of pixel values is to determine whether need inverse in license plate after calculating binaryzation, if object pixel
Ratio is greater than 50%, then image is carried out inverse, otherwise without processing, carries out the unification of scape color and color of object, unified
License plate background color；
Wherein in above-mentioned step three, median filter process is carried out to the license plate image after binaryzation, conveys surrounding picture
The biggish pixel of the absolute difference of plain gray value is changed to the gray value close with surrounding pixel gray value, removes those relative to its neck
The brighter or darker gray scale of domain pixel；
Wherein in above-mentioned step four, projection is carried out in vertical direction to license plate image and is carried out with Gaussian filter flat
Sliding, all trough points in positioning projection's curve search highest company between all trough points then in corresponding binary map
Logical region, obtained each region are largely exactly each character in license plate, finally choose in each connected domain i.e. character
Test point of the highest and lowest point as Hough transform, detects inclination angle, to be then corrected license plate；
Wherein in above-mentioned step five, character is carried out to license plate image using the method that connected domain and projection combine
Segmentation is marked characters on license plate boundary using four connection labelling methods, forms connected domain；Then judge that the height of each region is wide
The height for whether being substantially equal to characters on license plate region is wide, if differ larger, with regard to carrying out upright projection, it is wide that width is less than characters on license plate
Adjacent area merge, further divided the wide adjacent area of characters on license plate is wider than, finally to each region
Add rectangular shaped rim, extracts single characters on license plate；
Wherein in above-mentioned step six, Standard Template Library is established, wherein the size of the character in Standard Template Library is one
Sample, then character to be identified is standardized, size should be as the character in template library, by character picture to be identified
Character feature and Standard Template Library in all characters matched, calculate similarity；
Wherein in above-mentioned step seven, three grades is divided into according to matched similarity, be divided into four fuzzy diagnosis,
Five approximate identifications are accurately identified with six, wherein four fuzzy diagnosis are to remove initial, subsequent license plate is any two wrong
Normally match admission；Five approximations are identified as removing first Chinese character, and subsequent license plate any wrong one normally matches admission；Six
Position accurately identifies to go the first Chinese character of license plate to be matched, and treats outgoing vehicles according to admission license plate number matching phase knowledge and magnanimity and is driven out to
Parking lot carries out identification matching.
According to the above technical scheme, in the step 1,24 are generally as RGB with the license plate image that CCD camera acquires
Image is converted using classical greyscale transformation formula Gray=0.30R+0.59G+0.11B, and wherein Gray indicates grayscale image
Brightness value, R, G, B respectively indicate in color image red, green, blue color component value.
According to the above technical scheme, in the step 1, illumination is carried out to image using the homomorphic filtering method based on frequency domain
Compensation deals.
According to the above technical scheme, in the step 3, in median filter process, enable a 3*3 template along row or column
The movement in direction is ranked up the grey scale pixel value of template overlay area every time after movement, is replaced with the intermediate value that sequence obtains
The original image pixels gray value of center in template.
According to the above technical scheme, in the step 4, bilinear interpolation is used when rotating to image.
According to the above technical scheme, in the step 6, size normalization is carried out to the single characters on license plate split,
The outer rim of character picture Linear Amplifer or is narrowed down into predetermined size in proportion.
According to the above technical scheme, in the step 1, there are two CCD camera settings, using high-resolution digital image
Sensor and image pick-up card cooperate Image Acquisition.
Compared with prior art, the beneficial effects of the present invention are: removing face by carrying out gray processing processing to license plate image
Color information makes the subsequent Character segmentation algorithm speed of service faster, carries out binary conversion treatment, and unified vehicle to gray scale license plate image
The background of board image and the color of character carry out slant correction processing to the license plate image for having certain tilt angle, using connection
The method that domain is combined with sciagraphy carries out Character segmentation to license plate image, is matched by template matching to single character recognition,
Identification quickly, improves discrimination, convenient for the normal matching of vehicle entry and exit data.
Detailed description of the invention
Fig. 1 is algorithm flow chart of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the present invention provides a kind of technical solution:
A kind of realization parking lot license plate Similarity Match Method includes the following steps: step 1, license plate image acquisition；Step
Rapid two, unified license plate background color；Step 3, image denoising；Step 4, image slant correction；Step 5, Character segmentation；Step 6,
Character recognition；Step 7, license plate matching enter and leave；
Wherein in above-mentioned step one, license plate RGB image is acquired with CCD camera, collected source images are converted
At 256 grades of gray level image, gray scale stretching then is carried out with the grey linear transformation of segmentation, the contrast of image is improved, in ash
Binaryzation is carried out with dynamic threshold in degree image license plate area；
Wherein in above-mentioned step two, after carrying out binaryzation to different types of license plate grey level image, pass through difference
The size of the number of pixels of two kinds of pixel values is to determine whether need inverse in license plate after calculating binaryzation, if object pixel
Ratio is greater than 50%, then image is carried out inverse, otherwise without processing, carries out the unification of scape color and color of object, unified
License plate background color；
Wherein in above-mentioned step three, median filter process is carried out to the license plate image after binaryzation, conveys surrounding picture
The biggish pixel of the absolute difference of plain gray value is changed to the gray value close with surrounding pixel gray value, removes those relative to its neck
The brighter or darker gray scale of domain pixel；
Wherein in above-mentioned step four, projection is carried out in vertical direction to license plate image and is carried out with Gaussian filter flat
Sliding, all trough points in positioning projection's curve search highest company between all trough points then in corresponding binary map
Logical region, obtained each region are largely exactly each character in license plate, finally choose in each connected domain i.e. character
Test point of the highest and lowest point as Hough transform, detects inclination angle, to be then corrected license plate；
Wherein in above-mentioned step five, character is carried out to license plate image using the method that connected domain and projection combine
Segmentation is marked characters on license plate boundary using four connection labelling methods, forms connected domain；Then judge that the height of each region is wide
The height for whether being substantially equal to characters on license plate region is wide, if differ larger, with regard to carrying out upright projection, it is wide that width is less than characters on license plate
Adjacent area merge, further divided the wide adjacent area of characters on license plate is wider than, finally to each region
Add rectangular shaped rim, extracts single characters on license plate；
Wherein in above-mentioned step six, Standard Template Library is established, wherein the size of the character in Standard Template Library is one
Sample, then character to be identified is standardized, size should be as the character in template library, by character picture to be identified
Character feature and Standard Template Library in all characters matched, calculate similarity；
Wherein in above-mentioned step seven, three grades is divided into according to matched similarity, be divided into four fuzzy diagnosis,
Five approximate identifications are accurately identified with six, wherein four fuzzy diagnosis are to remove initial, subsequent license plate is any two wrong
Normally match admission；Five approximations are identified as removing first Chinese character, and subsequent license plate any wrong one normally matches admission；Six
Position accurately identifies to go the first Chinese character of license plate to be matched, and treats outgoing vehicles according to admission license plate number matching phase knowledge and magnanimity and is driven out to
Parking lot carries out identification matching.
According to the above technical scheme, in step 1, being generally 24 with the license plate image that CCD camera acquires is RGB image,
It is converted using classical greyscale transformation formula Gray=0.30R+0.59G+0.11B, wherein Gray indicates the bright of grayscale image
Angle value, R, G, B respectively indicate red, green, blue color component value in color image.
According to the above technical scheme, in step 1, illumination compensation is carried out to image using the homomorphic filtering method based on frequency domain
Processing.
According to the above technical scheme, in step 3, in median filter process, enable a 3*3 template along row or column direction
Movement the grey scale pixel value of template overlay area is ranked up, replaces template with the intermediate value that sequence obtains after mobile every time
The original image pixels gray value of interior center.
According to the above technical scheme, in step 4, bilinear interpolation is used when rotating to image.
According to the above technical scheme, in step 6, size normalization is carried out to the single characters on license plate split, by word
The outer rim for according with image Linear Amplifer or narrows down to predetermined size in proportion.
According to the above technical scheme, in step 1, there are two CCD camera settings, is sensed using high-resolution digital image
Device and image pick-up card cooperate Image Acquisition.
Based on above-mentioned, it is an advantage of the current invention that colouring information is removed by carrying out gray processing processing to license plate image,
Make the subsequent Character segmentation algorithm speed of service faster, binary conversion treatment, and unified license plate image are carried out to gray scale license plate image
Background and character color, to have certain tilt angle license plate image carry out slant correction processing, using connected domain and throw
The method that shadow method combines to license plate image carry out Character segmentation, single character recognition is matched by template matching, according to
The similarity matched is divided into three grades, is divided into four fuzzy diagnosis, five approximate identifications and six accurately identify, according to admission
License plate number matching phase knowledge and magnanimity, which treat outgoing vehicles and are driven out to parking lot, carries out identification matching, and identification quickly, improves discrimination, just
In the normal matching of vehicle entry and exit data.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of realization parking lot license plate Similarity Match Method includes the following steps: step 1, license plate image acquisition；Step
Two, unified license plate background color；Step 3, image denoising；Step 4, image slant correction；Step 5, Character segmentation；Step 6, word
Symbol identification；Step 7, license plate matching enter and leave；It is characterized by:
Wherein in above-mentioned step one, license plate RGB image is acquired with CCD camera, collected source images are converted into 256
The gray level image of grade then carries out gray scale stretching with the grey linear transformation of segmentation, the contrast of image is improved, in gray level image
Binaryzation is carried out with dynamic threshold in license plate area；
Wherein in above-mentioned step two, after carrying out binaryzation to different types of license plate grey level image, by calculating separately
The size of the number of pixels of two kinds of pixel values is to determine whether need inverse, if the ratio of object pixel in license plate after binaryzation
Greater than 50%, then image is subjected to inverse, otherwise without processing, carries out the unification of scape color and color of object, unified license plate
Background color；
Wherein in above-mentioned step three, median filter process, transference surrounding pixel ash are carried out to the license plate image after binaryzation
The biggish pixel of the absolute difference of angle value is changed to the gray value close with surrounding pixel gray value, removes those relative to its field picture
The brighter or darker gray scale of element；
Wherein in above-mentioned step four, license plate image project and carried out smoothly with Gaussian filter in vertical direction,
All trough points in positioning projection's curve search highest connection between all trough points then in corresponding binary map
Region, obtained each region are largely exactly each character in license plate, finally choose in each connected domain i.e. that character is most
High and test point of the minimum point as Hough transform, detects inclination angle, to be then corrected license plate；
Wherein in above-mentioned step five, character point is carried out to license plate image using the method that connected domain and projection combine
It cuts, characters on license plate boundary is marked using four connection labelling methods, forms connected domain；Then judging the high width of each region is
The no height for being substantially equal to characters on license plate region is wide, if differ larger, with regard to carrying out upright projection, it is wide that width is less than characters on license plate
Adjacent area merges, and is further divided the wide adjacent area of characters on license plate is wider than, is finally added to each region
Rectangular shaped rim extracts single characters on license plate；
Wherein in above-mentioned step six, Standard Template Library is established, wherein the size of the character in Standard Template Library is the same,
Then character to be identified is standardized, size should be as the character in template library, by the word of character picture to be identified
All characters in symbol feature and Standard Template Library are matched, and similarity is calculated；
Wherein in above-mentioned step seven, three grades is divided into according to matched similarity, is divided into four fuzzy diagnosis, five
Approximation identification is accurately identified with six, wherein four fuzzy diagnosis are to remove initial, any wrong two of subsequent license plate is normally
Match admission；Five approximations are identified as removing first Chinese character, and subsequent license plate any wrong one normally matches admission；Six essences
The first Chinese character for being really identified as license plate is matched, and is treated outgoing vehicles according to admission license plate number matching phase knowledge and magnanimity and is driven out to parking
Field carries out identification matching.
2. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In one, 24 are generally for RGB image, using classical greyscale transformation formula Gray=with the license plate image that CCD camera acquires
0.30R+0.59G+0.11B is converted, and wherein Gray indicates the brightness value of grayscale image, and R, G, B are respectively indicated in color image
Red, green, blue color component value.
3. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In one, illumination compensation process is carried out to image using the homomorphic filtering method based on frequency domain.
4. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In three, in median filter process, 3*3 template moving along row or column direction is enabled, every time after movement, to the template area of coverage
The grey scale pixel value in domain is ranked up, and the original image pixels gray scale of center in template is replaced with the intermediate value that sequence obtains
Value.
5. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In four, bilinear interpolation is used when rotating to image.
6. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In six, size normalization is carried out to the single characters on license plate that splits, by the outer rim of character picture Linear Amplifer in proportion
Or narrow down to predetermined size.
7. a kind of realization parking lot license plate Similarity Match Method according to claim 1, it is characterised in that: the step
In one, there are two CCD camera settings, cooperates Image Acquisition using high-resolution digital image sensor and image pick-up card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582303.1A CN110348501A (en) | 2019-07-01 | 2019-07-01 | A kind of realization parking lot license plate Similarity Match Method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582303.1A CN110348501A (en) | 2019-07-01 | 2019-07-01 | A kind of realization parking lot license plate Similarity Match Method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110348501A true CN110348501A (en) | 2019-10-18 |
Family
ID=68177617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910582303.1A Withdrawn CN110348501A (en) | 2019-07-01 | 2019-07-01 | A kind of realization parking lot license plate Similarity Match Method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110348501A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783765A (en) * | 2020-07-10 | 2020-10-16 | 上海淇毓信息科技有限公司 | Method and device for identifying image characters and electronic equipment |
| CN112819002A (en) * | 2021-03-18 | 2021-05-18 | 苏州科达科技股份有限公司 | License plate recognition result evaluation method and device, electronic equipment and storage medium |
| CN114913705A (en) * | 2022-05-09 | 2022-08-16 | 江苏蓝策电子科技有限公司 | Vehicle positioning method based on Bluetooth AOA |
| CN114973754A (en) * | 2022-05-09 | 2022-08-30 | 江苏蓝策电子科技有限公司 | Vehicle positioning system based on Bluetooth AOA |
-
2019
- 2019-07-01 CN CN201910582303.1A patent/CN110348501A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783765A (en) * | 2020-07-10 | 2020-10-16 | 上海淇毓信息科技有限公司 | Method and device for identifying image characters and electronic equipment |
| CN111783765B (en) * | 2020-07-10 | 2024-03-22 | 上海淇毓信息科技有限公司 | Method and device for recognizing image characters and electronic equipment |
| CN112819002A (en) * | 2021-03-18 | 2021-05-18 | 苏州科达科技股份有限公司 | License plate recognition result evaluation method and device, electronic equipment and storage medium |
| CN114913705A (en) * | 2022-05-09 | 2022-08-16 | 江苏蓝策电子科技有限公司 | Vehicle positioning method based on Bluetooth AOA |
| CN114973754A (en) * | 2022-05-09 | 2022-08-30 | 江苏蓝策电子科技有限公司 | Vehicle positioning system based on Bluetooth AOA |
| CN114913705B (en) * | 2022-05-09 | 2024-02-02 | 江苏蓝策电子科技有限公司 | Vehicle positioning method based on Bluetooth AOA |
| CN114973754B (en) * | 2022-05-09 | 2024-02-02 | 江苏蓝策电子科技有限公司 | Vehicle positioning system based on bluetooth AOA |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348501A (en) | A kind of realization parking lot license plate Similarity Match Method | |
| CN109886896B (en) | Blue license plate segmentation and correction method | |
| JP4396376B2 (en) | Graphic reading method and apparatus, and main color extraction method and apparatus | |
| KR101403876B1 (en) | Method and Apparatus for Vehicle License Plate Recognition | |
| CN107423735B (en) | License plate positioning method utilizing horizontal gradient and saturation | |
| CN108256521B (en) | Effective area positioning method for vehicle body color identification | |
| CN105528609A (en) | Vehicle license plate location method based on character position | |
| CN101122952A (en) | Picture words detecting method | |
| Le et al. | Real time traffic sign detection using color and shape-based features | |
| KR101375567B1 (en) | Partial image extractor and its partial image extracting method | |
| CN108182691B (en) | Method and device for identifying speed limit sign and vehicle | |
| JP2018120445A (en) | Car number recognition apparatus | |
| CN111401364B (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN109800641B (en) | Lane line detection method based on threshold value self-adaptive binarization and connected domain analysis | |
| WO2020130799A1 (en) | A system and method for licence plate detection | |
| CN105654140B (en) | The positioning of rail tank car license number and recognition methods towards complex industrial environment | |
| CN107437241B (en) | Dark channel image defogging method combined with edge detection | |
| CN113053164A (en) | Parking space identification method using look-around image | |
| Yung et al. | Recognition of vehicle registration mark on moving vehicles in an outdoor environment | |
| CN109800693B (en) | Night vehicle detection method based on color channel mixing characteristics | |
| CN109558872B (en) | Vehicle color identification method | |
| CN106815580A (en) | A kind of license plate locating method | |
| TW201419168A (en) | A method and system for license plate recognition under non-uniform illumination | |
| Yang et al. | A novel binarization approach for license plate | |
| CN112070771B (en) | Adaptive threshold segmentation method and device based on HS channel 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191018 |