CN104573656B - A kind of car plate color determination methods based on connected region information - Google Patents
A kind of car plate color determination methods based on connected region information Download PDFInfo
- Publication number
- CN104573656B CN104573656B CN201510013056.5A CN201510013056A CN104573656B CN 104573656 B CN104573656 B CN 104573656B CN 201510013056 A CN201510013056 A CN 201510013056A CN 104573656 B CN104573656 B CN 104573656B
- Authority
- CN
- China
- Prior art keywords
- image
- connected region
- car plate
- license plate
- vertical edge
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of car plate color determination methods based on connected region information, comprises the following steps:License plate image is subjected to size normalized;Obtain the significant character region in the license plate image Jing Guo size normalized;License plate image behind acquisition significant character region is subjected to contrast enhancing;Using vertical edge detective operators, the two-value vertical edge figure for passing through the license plate image that contrast strengthens is obtained;Two-value vertical edge figure based on license plate image, obtain the optimal width of character stroke;Morphology operations are carried out, obtain the prospect connected region image and background connected region image of car plate;Optimization prospect connected region image;Gray average corresponding to gray average corresponding to statistics prospect connected region and background connected region;Judge car plate color type.The judged result of the present invention is more accurate, and is disturbed for car plate colour cast and stain etc., has stronger robustness.
Description
Technical field
The present invention relates to field of license plate recognition, and in particular to a kind of car plate color based on connected region information judges
Method.
Background technology
Car plate color is a key character of car plate, and in our countries, the color type of car plate is not unique, main bag
Four types are contained:Blue bottom wrongly written or mispronounced character, yellow bottom surplus, black matrix wrongly written or mispronounced character, white gravoply, with black engraved characters or The Scarlet Letter, now if judged car plate color
Mistake, the correctness of successive character segmentation can be directly affected, and then influence final Car license recognition rate.Therefore, car plate color class
It is the essential part of License Plate Character Segmentation that type, which judges, has important influence for the accuracy rate of whole recognition result.
At present, conventional car plate color determination methods mainly have following a few classes:
(1) the car plate color determination methods based on coloured image, such method own by counting in license plate area first
R, G, B color component information of pixel, according to the difference degree between each component information, and then judge the color class of car plate
Type.Such method has and judges effect well for color clearly car plate, but when car plate occur stain, colour fading or by
Serious erroneous judgement occurs in the colour cast caused by different light, such method, and when there is gray scale car plate, this method is directly lost
Effect.
(2) the car plate color determination methods based on gray level image, such method car plate color it is type simplified be two classes:Secretly
The bright word in bottom and dark word of putting one's cards on the table;The binary image of car plate is obtained first, foreground target point proportion is then counted, with reference to vertical
The features such as projection, comprehensive descision car plate color.The advantages of such method is applied widely, for the car plate of uniform gray level, is sentenced
Disconnected effect is fine, colour fading and colour cast simultaneously for car plate, has certain robustness, but for including strong jamming and stain
Car plate, due to being influenceed by binary image quality, erroneous judgement occurs in this method.
The content of the invention
It is an object of the invention to provide a kind of car plate color determination methods based on connected region information, using ticket
Vertical edge obtains character connected region, and then judges car plate color type, and judged result is more accurate, for car plate colour cast with
Stain etc. disturbs, and has stronger robustness.
The technical scheme is that:
A kind of car plate color determination methods based on connected region information, comprise the following steps:
(1) license plate image is subjected to size normalized;
(2) the significant character region in the license plate image Jing Guo size normalized is obtained;
(3) license plate image behind acquisition significant character region is subjected to contrast enhancing;
(4) vertical edge detective operators are utilized, obtain the two-value vertical edge figure of the license plate image by contrast enhancing;
(5) the two-value vertical edge figure based on license plate image, the optimal width of character stroke is obtained;
(6) license plate image after the optimal width to obtaining character stroke carries out morphology operations, obtains the prospect of car plate
Connected region image and background connected region image;
(7) prospect connected region image is optimized;
(8) gray average corresponding to gray average corresponding to prospect connected region and background connected region is counted;
(9) based on gray average corresponding to gray average corresponding to prospect connected region and background connected region, car is judged
Board color type.
In step (3), the license plate image behind the region by acquisition significant character carries out contrast enhancing, specific to use
Below equation is realized:
Wherein, f (x, y) represents the gray value of artwork, and g (x, y) represents the gray value of enhancing image, tminFor artwork gray scale
Minimum value adds 10, tmax10 are subtracted for artwork gray scale maximum.
In step (4), described utilizes vertical edge detective operators, obtains two of the license plate image by contrast enhancing
It is worth vertical edge figure;Specifically include following steps:
(41) edge detection operator formula is based on, obtains the vertical edge characteristic pattern of the license plate image by contrast enhancing;
Described edge detection operator formula is:
(42) maximum kind spacing algorithm is utilized, obtains the two-value vertical edge figure of the license plate image by contrast enhancing.
In step (5), the two-value vertical edge figure based on license plate image, the optimal width of character stroke is obtained;
Specifically include following steps:
(51) the pending current line of two-value vertical edge figure is entered;
(52) whole trip points are found from left to right;
(53) the distance between current transition point and previous trip point, the latter trip point are calculated respectively, and will be less than
The distance of certain threshold value is put into stroke width list;
(54) judge current transition point whether be the row last trip point;If so, then perform step (55);If
It is no, then into next trip point, return and perform step (53);
(55) judge current line whether be image last column;If so, then perform step (57);If it is not, then perform step
Suddenly (56);
(56) enter the next line of two-value vertical edge figure, return and perform step (51)-(54);
(57) stroke width list is based on, builds stroke width histogram;
(58) character stroke width n of the width as the license plate image corresponding to maximal dimension is selected.
In step (6), the license plate image after the optimal width to obtaining character stroke carries out morphology operations, obtains
The prospect connected region image and background connected region image of pick-up board;Specifically include following steps:
(61) structural element template type (3) is based on, two-value vertical edge figure is carried outSecondary morphological dilations computing,
Obtain image image_dilate;Described structural element template type (3) is:
(62) structural element template type (4) is based on, 2 closing operation of mathematical morphology are carried out to image image_dilate, obtained
Image image_close;Described structural element template type (4) is:
(63) inverse processing is carried out to image image_close, obtains background connected region image image_bg;
(64) structural element template type (3) is based on, image_close is carried outSecondary morphological erosion computing, is obtained
Prospect connected region image image_obj.
In step (7), described optimization prospect connected region image;Specifically include following steps:
(71) image image_obj currently pending row is entered;
(72) below equation is utilized, finds whole left trip points i.e. left hand edge point;
Wherein, g (x, y) is image intensity value;
(73) based on current transition point, foreground point all in the n-1 neighborhoods of right side is retained;
(74) judge current transition point whether be the row last trip point;If so, then perform step (75);If
It is no, then into next trip point, return and perform step (73);
(75) judge current line whether the last column for being image image_obj;If so, then output optimizes foreground area figure
Picture;If it is not, then perform step (76);
(76) enter image image_obj next line, return and perform step (71)-(75);
After being finished, according to step (71)-(76), right hand edge point and corresponding foreground area retention point, superposition are found
Based on left hand edge reservation region and based on right hand edge reservation region, final optimization foreground area is obtained.
It is described based on grey corresponding to gray average corresponding to prospect connected region and background connected region in step (9)
Average is spent, judges car plate color type;Specifically realized using below equation:
Wherein,Gray average corresponding to expression prospect connected region,Represent gray scale corresponding to background connected region
Average, class=1 represent that car plate belongs to the bright word type in dark bottom, and class=0 represents that car plate belongs to dark word type of putting one's cards on the table.
The present invention obtains the character connected region of car plate using vertical edge and morphology operations, and is sentenced based on connected region
The gray scale difference value of disconnected foreground and background, and then judge car plate color type, judged result is more accurate, and for car plate colour cast with
Stain etc. disturbs, and has stronger robustness.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is to obtain the optimal character duration flow chart of car plate;
Fig. 3 is optimization prospect connected region flow chart;
Fig. 4 is to choose significant character area schematic;
Fig. 5 is size normalized image;
Fig. 6 is to choose significant character area image;
Fig. 7 is image enhaucament figure;
Fig. 8 is two-value vertical edge figure;
Fig. 9 is background connected region image;
Figure 10 is prospect connected region image;
Figure 11 is the background connected region image of optimization.
Embodiment
Below in conjunction with the accompanying drawings the present invention is further illustrated with specific embodiment.
As shown in figure 1, the specific implementation step of the present invention is as follows:
S1, size normalization is carried out to license plate image, eliminate influence caused by different sizes, effect is as shown in Figure 5.
S2, significant character region is chosen, eliminate the interference in the regions such as car plate frame, specific practice is as shown in figure 4, selection figure
The 0.6w*0.4h regions of inconocenter, effect are as shown in Figure 6.
S3, using formula (1), contrast enhancing, effect such as Fig. 7 are carried out to license plate image;
Wherein, f (x, y) represents the gray value of artwork, and g (x, y) represents the gray value of enhancing image, tminFor artwork gray scale
Minimum value adds 10, tmax10 are subtracted for artwork gray scale maximum.
S4, using vertical edge detective operators, obtain the two-value vertical edge figure of license plate image, effect is as shown in figure 8, tool
Body step is as follows:
S41, based on edge detection operator formula (2), obtain vertical edge characteristic pattern;
S42, based on maximum kind spacing algorithm, obtain two-value vertical edge figure.
S5, as shown in Fig. 2 obtain stroke optimal width n, comprise the following steps that:
S51, into currently pending row;
S52, all trip points are found from left to right;
S53, current transition point and the distance between previous trip point and the latter trip point are calculated respectively, select smaller
Distance be put into stroke width list;
S54, judge current transition point whether last trip point of the row;If so, then perform S55;If it is not, then
Into next trip point, return and perform step S53;
S55, judge that current line is last column of image;If so, then perform step S57;If it is not, then perform step
S56;
S56, into next line, continue executing with step S51 to step S54;
S57, structure stroke width histogram;
Stroke width n of the width as the license plate image corresponding to S58, selection maximal dimension.
S6, morphology operations are carried out, obtain the foreground and background connected region of car plate respectively, comprise the following steps that:
S61, based on structural element template type (3), two-value vertical edge figure is carried outSecondary morphological dilations computing,
Image now is denoted as image_dilate;
S62, based on structural element template type (4), 2 closing operation of mathematical morphology, figure now are carried out to image_dilate
As being denoted as image_close;
S63, inverse processing is carried out to image_close, obtain background connected region image image_bg, effect such as Fig. 9
It is shown;
S64, based on structural element template type (3), image_close is carried outSecondary morphological erosion computing, now
Image be prospect connected region image image_obj, effect such as Figure 10.
S7, as shown in figure 3, optimization prospect connected region image, effect such as Figure 11, comprise the following steps that:
S71, into the currently pending rows of image_obj;
S72, using formula (5), find all left trip points i.e. left hand edge point;
Wherein, g (x, y) is image intensity value.
S73, based on current transition point, retain all foreground point in the n-1 neighborhoods of right side;
S74, judge current transition point whether last trip point of the row;If so, then perform step S75;If it is not,
Then enter next trip point, return and perform step S73;
S75, judge that current line is last column of image;If so, then output optimizes foreground region image;If it is not,
Then perform step S76;
S76, into next line, continue executing with step S71 to step S75;
After being finished, according to step S71 to step S76, right hand edge point and corresponding foreground area retention point are found, is folded
Add based on left hand edge reservation region and based on right hand edge reservation region, obtain final optimization foreground area.
Gray average corresponding to S8, statistics foreground areaWith background area corresponding to gray average
S9, using formula (6), judge car plate color type.In the present embodiment, foreground area average is 147.5, background area
Domain average is 210.64, therefore car plate belongs to dark word type of putting one's cards on the table, and car plate actual type is yellow bottom surplus.
Wherein, class=1 represents that car plate belongs to the bright word type in dark bottom, and class=0 represents that car plate belongs to dark word class of putting one's cards on the table
Type.
Embodiment described above is only that the preferred embodiment of the present invention is described, not to the model of the present invention
Enclose and be defined, on the premise of design spirit of the present invention is not departed from, technical side of the those of ordinary skill in the art to the present invention
The various modifications and improvement that case is made, it all should fall into the protection domain of claims of the present invention determination.
Claims (7)
1. a kind of car plate color determination methods based on connected region information, it is characterised in that comprise the following steps:
(1) license plate image is subjected to size normalized;
(2) the significant character region in the license plate image Jing Guo size normalized is obtained;
(3) license plate image behind acquisition significant character region is subjected to contrast enhancing;
(4) vertical edge detective operators are utilized, obtain the two-value vertical edge figure of the license plate image by contrast enhancing;
(5) the two-value vertical edge figure based on license plate image, the optimal width of character stroke is obtained;
(6) license plate image after the optimal width to obtaining character stroke carries out morphology operations, obtains the prospect connection of car plate
Area image and background connected region image;
(7) prospect connected region image is optimized;
(8) gray average corresponding to gray average corresponding to prospect connected region and background connected region is counted;
(9) based on gray average corresponding to gray average corresponding to prospect connected region and background connected region, car plate face is judged
Color type.
A kind of 2. car plate color determination methods based on connected region information according to claim 1, it is characterised in that:Step
Suddenly in (3), the license plate image behind the region by acquisition significant character carries out contrast enhancing, specifically real using below equation
It is existing:
Wherein, f (x, y) represents the gray value of artwork, and g (x, y) represents the gray value of enhancing image, tminIt is minimum for artwork gray scale
Value adds 10, tmax10 are subtracted for artwork gray scale maximum.
A kind of 3. car plate color determination methods based on connected region information according to claim 1, it is characterised in that:Step
Suddenly in (4), described utilizes vertical edge detective operators, obtains the two-value vertical edge of the license plate image by contrast enhancing
Figure;Specifically include following steps:
(41) edge detection operator formula is based on, obtains the vertical edge characteristic pattern of the license plate image by contrast enhancing;It is described
Edge detection operator formula be:
(42) maximum kind spacing algorithm is utilized, obtains the two-value vertical edge figure of the license plate image by contrast enhancing.
A kind of 4. car plate color determination methods based on connected region information according to claim 1, it is characterised in that:Step
Suddenly in (5), the two-value vertical edge figure based on license plate image, the optimal width of character stroke is obtained;Specifically include with
Lower step:
(51) the pending current line of two-value vertical edge figure is entered;
(52) whole trip points are found from left to right;
(53) the distance between current transition point and previous trip point, the latter trip point are calculated respectively, and will be less than certain
The distance of threshold value is put into stroke width list;
(54) judge current transition point whether be the row last trip point;If so, then perform step (55);If it is not, then
Into next trip point, return and perform step (53);
(55) judge current line whether be image last column;If so, then perform step (57);If it is not, then perform step
(56);
(56) enter the next line of two-value vertical edge figure, return and perform step (51)-(54);
(57) stroke width list is based on, builds stroke width histogram;
(58) character stroke width n of the width as the license plate image corresponding to maximal dimension is selected.
A kind of 5. car plate color determination methods based on connected region information according to claim 4, it is characterised in that:Step
Suddenly in (6), the license plate image after the optimal width to obtaining character stroke carries out morphology operations, before obtaining car plate
Scape connected region image and background connected region image;Specifically include following steps:
(61) structural element template type (3) is based on, two-value vertical edge figure is carried outSecondary morphological dilations computing, obtains figure
As image_dilate;Described structural element template type (3) is:
Wherein, n represents character stroke width;
(62) structural element template type (4) is based on, 2 closing operation of mathematical morphology are carried out to image image_dilate, obtain image
image_close;Described structural element template type (4) is:
(63) inverse processing is carried out to image image_close, obtains background connected region image image_bg;
(64) structural element template type (3) is based on, image_close is carried outSecondary morphological erosion computing, obtains prospect
Connected region image image_obj;Wherein, n represents character stroke width.
A kind of 6. car plate color determination methods based on connected region information according to claim 5, it is characterised in that:Step
Suddenly in (7), described optimization prospect connected region image;Specifically include following steps:
(71) image image_obj currently pending row is entered;
(72) below equation is utilized, finds whole left trip points i.e. left hand edge point;
Wherein, g (x, y) is image intensity value;
(73) based on current transition point, foreground point all in the n-1 neighborhoods of right side is retained;Wherein, n represents character stroke
Width;
(74) judge current transition point whether be the row last trip point;If so, then perform step (75);If it is not, then
Into next trip point, return and perform step (73);
(75) judge current line whether the last column for being image image_obj;If so, then output optimizes foreground region image;
If it is not, then perform step (76);
(76) enter image image_obj next line, return and perform step (71)-(75);
After being finished, according to step (71)-(76), find right hand edge point and corresponding foreground area retention point, superposition are based on
Left hand edge reservation region and based on right hand edge reservation region, obtains final optimization foreground area.
A kind of 7. car plate color determination methods based on connected region information according to claim 1, it is characterised in that:
It is described based on gray average corresponding to gray average corresponding to prospect connected region and background connected region in step (9), sentence
Disconnected car plate color type;Specifically realized using below equation:
Wherein,Gray average corresponding to expression prospect connected region,Gray average corresponding to background connected region is represented,
Class=1 represents that car plate belongs to the bright word type in dark bottom, and class=0 represents that car plate belongs to dark word type of putting one's cards on the table.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510013056.5A CN104573656B (en) | 2015-01-09 | 2015-01-09 | A kind of car plate color determination methods based on connected region information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510013056.5A CN104573656B (en) | 2015-01-09 | 2015-01-09 | A kind of car plate color determination methods based on connected region information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104573656A CN104573656A (en) | 2015-04-29 |
CN104573656B true CN104573656B (en) | 2018-02-02 |
Family
ID=53089678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510013056.5A Active CN104573656B (en) | 2015-01-09 | 2015-01-09 | A kind of car plate color determination methods based on connected region information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104573656B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104966107A (en) * | 2015-07-10 | 2015-10-07 | 安徽清新互联信息科技有限公司 | Credit card card-number identification method based on machine learning |
CN108205675B (en) * | 2016-12-20 | 2020-06-19 | 浙江宇视科技有限公司 | License plate image processing method and device |
CN107844761B (en) * | 2017-10-25 | 2021-08-10 | 海信集团有限公司 | Traffic sign detection method and device |
CN111860539B (en) * | 2020-07-20 | 2024-05-10 | 济南博观智能科技有限公司 | License plate color recognition method, device and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101408942A (en) * | 2008-04-17 | 2009-04-15 | 浙江师范大学 | Method for locating license plate under a complicated background |
CN101872416A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Vehicle license plate recognition method and system of road image |
CN102214290A (en) * | 2010-04-12 | 2011-10-12 | 无锡科利德斯科技有限公司 | License plate positioning method and license plate positioning template training method |
CN102254152A (en) * | 2011-06-17 | 2011-11-23 | 东南大学 | License plate location method based on color change points and color density |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040234105A1 (en) * | 2003-05-19 | 2004-11-25 | Quen-Zong Wu | Method of automatic vehicle licence plate recognition by color discrimination and reorganization |
-
2015
- 2015-01-09 CN CN201510013056.5A patent/CN104573656B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101408942A (en) * | 2008-04-17 | 2009-04-15 | 浙江师范大学 | Method for locating license plate under a complicated background |
CN102214290A (en) * | 2010-04-12 | 2011-10-12 | 无锡科利德斯科技有限公司 | License plate positioning method and license plate positioning template training method |
CN101872416A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Vehicle license plate recognition method and system of road image |
CN102254152A (en) * | 2011-06-17 | 2011-11-23 | 东南大学 | License plate location method based on color change points and color density |
Non-Patent Citations (2)
Title |
---|
一种基于笔画特征的车牌前景背景分割新方法;丛露微等;《电子测试》;20110531(第5期);97-99 * |
基于车牌特征颜色相似度的定位方法;吴德会等;《公路交通科技》;20050131;第22卷(第1期);135-139 * |
Also Published As
Publication number | Publication date |
---|---|
CN104573656A (en) | 2015-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107273896A (en) | A kind of car plate detection recognition methods based on image recognition | |
CN104573656B (en) | A kind of car plate color determination methods based on connected region information | |
CN106650553A (en) | License plate recognition method and system | |
CN106096601A (en) | The method and system of character types in a kind of automatic detection bill | |
CN106096610B (en) | A kind of file and picture binary coding method based on support vector machines | |
CN103413147B (en) | A kind of licence plate recognition method and system | |
CN103310211B (en) | A kind ofly fill in mark recognition method based on image procossing | |
CN103824091B (en) | A kind of licence plate recognition method for intelligent transportation system | |
CN107729899A (en) | A kind of number-plate number recognition methods and device | |
CN110348451A (en) | Case number (CN) automatic collection and recognition methods in railway container cargo handling process | |
CN106599896A (en) | Character segmentation method, character segmentation device, element detection method, and element detection device | |
CN101599125A (en) | The binarization method that the complex background hypograph is handled | |
CN107832762A (en) | A kind of License Plate based on multi-feature fusion and recognition methods | |
CN105069900A (en) | Method and device for processing banknote information | |
CN106951869A (en) | A kind of live body verification method and equipment | |
Shaikh et al. | A novel approach for automatic number plate recognition | |
CN112016563B (en) | Method for identifying authenticity of circular seal | |
CN104156703B (en) | License plate locating method and system based on color texture | |
CN107220664A (en) | A kind of oil bottle vanning counting method based on structuring random forest | |
CN107659799A (en) | Camera device, image processing method and storage medium | |
CN109191429A (en) | A kind of 3D printing nozzle detection method based on machine vision | |
CN106920318A (en) | The discrimination method and device of a kind of bank note | |
CN107481257A (en) | The image background minimizing technology of Fusion of Color and local ternary parallel pattern feature | |
CN104281850A (en) | Character area identification method and device | |
CN107742357A (en) | A kind of recognition methods of paper money number and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |