CN104200188B - Method and system for rapidly positioning position detection patterns of QR code - Google Patents
Method and system for rapidly positioning position detection patterns of QR code Download PDFInfo
- Publication number
- CN104200188B CN104200188B CN201410422618.7A CN201410422618A CN104200188B CN 104200188 B CN104200188 B CN 104200188B CN 201410422618 A CN201410422618 A CN 201410422618A CN 104200188 B CN104200188 B CN 104200188B
- Authority
- CN
- China
- Prior art keywords
- pixel
- sample area
- value
- code
- position sensing
- 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 Analysis (AREA)
Abstract
The invention provides a method and a system for rapidly positioning the position detection patterns of a QR code. The method comprises the following steps of: reading the original image of the QR code; carrying out binarization processing to obtain a binarized image; horizontally scanning the binarized image in the same direction line by line according to a set scanning resolution to obtain a plurality of candidate points; clustering all the obtained candidate points by a clustering algorithm to obtain three clusters, the clustering central position coordinates of each cluster being the central coordinates of the positioned position detection pattern; positioning to three position detection patterns in the original image of the QR code. The method and the system have the advantages of being fast in positioning speed, low in calculation resource consumption, and high in positioning result accuracy.
Description
Technical field
The invention belongs to image in 2 D code processing technology field is and in particular to a kind of quick QR code position that positions detects figure
Method and system.
Background technology
QR (Quick Response, fast reaction) code is one kind of two-dimensional bar code, is 1994 by Japanese Denso-
Wave company invents, and compared with other two-dimensional bar codes, speed is fast, packing density big, take up room little advantage, extensively to have recognition
General it is applied to the various fields such as authentication, safety anti-fake, ecommerce.
As shown in figure 1, being the structural representation of QR code, it is by multiple black squares units and multiple white square
The quadrate array of unit composition, main inclusion coding region and functional areas two parts, wherein, functional areas include position sensing figure
Shape, positioning figure and correction graph etc..With reference to Fig. 1, QR code image has three identical position sensing figures, including:Position
Detect figure a, position sensing figure b and position sensing figure c, be located at the upper left corner, the upper right corner and the lower-left of QR code image respectively
Angle, by position sensing figure it may be determined that the position of QR code and direction.Therefore, it is accurately positioned position sensing figure and belong to QR code
The basic steps of decoding, directly affect QR code decoding speed and decoding precision etc..
In prior art, during position sensing figure in positioning QR code image, it is complicated that generally existing location algorithm
Problem, thus leads to the problem that position sensing figure locating speed is slow, resource consumption is big.
Content of the invention
The defect existing for prior art, the present invention provide a kind of method that quick positioning QR code position detects figure and
System, in order to solve the above problems.
The technical solution used in the present invention is as follows:
The present invention provides a kind of method that quick positioning QR code position detects figure, comprises the following steps:
S1, reads the QR code original image needing position location to detect figure;Wherein, described QR code original image includes QR
Code target area and background area;
S2, carries out binary conversion treatment to described QR code original image, is only had black pixel point and white pixel point
Binary image;
S3, sets up rectangular coordinate system in the plane that described binary image is located;
Set scanning resolution, under set scanning resolution, if described binary picture seems by the picture of n row n row
The matrix of vegetarian refreshments composition, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j≤n;
According to set scanning resolution, binary image described in horizontal sweep in the same direction line by line, for arbitrary kth
OK, all using following scan mode:
S3.1, makes j=1;
S3.2, reads and records CkjThe chromatic value of pixel;
S3.3, judges whether j is equal to n, if equal to, then the one's own profession end of scan, go to S3.5;If it is not, then continuing
Resume studies and take and record Ck(j+1)The chromatic value of pixel, then judges Ck(j+1)The chromatic value of pixel whether with CkjThe color of pixel
Angle value is identical, if identical, executes S3.4;If it is not the same, then recording Ck(j+1)Pixel is in the rectangular coordinate system set up
On position coordinate value, then execute S3.4;
S3.4, makes j=j+1, then goes to S3.3;
S3.5, if during scanning row k, record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x are integer;
X pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Horizontal range between pixel,
L2Represent P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxHorizontal range between pixel;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 numerical value sequence
Row, wherein, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Picture
The position coordinate value of vegetarian refreshments and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinateses of candidate point
Value;
S4, after completing the horizontal sweep in the same direction to n row, is obtained multiple candidate points;Using clustering algorithm to obtaining
All candidate points clustered, three classes are obtained, the position that cluster centre position's coordinate of each class as navigates to
Detect the centre coordinate of figure;Thus navigate to three position sensing figures in described QR code original image.
Preferably, judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 numerical value
Sequence, refers to:
Set error permissible value as F%, if La-2=x1;X1-x1*F%≤La-1≤ x1+x1*F%;3(x1-x1*
F%)≤La≤ 3 (x1+x1*F%);
X1-x1*F%≤La+1≤ x1+x1*F%;X1-x1*F%≤La+2≤ x1+x1*F%;It is then La-2:La-1:La:
La+1:La+2≈1:1:3:1:1.
Preferably, described clustering algorithm is K mean cluster algorithm.
Preferably, after three position sensing figures in navigating to described QR code original image, also include:
S5, the described position sensing figure that any one is navigated to, the QR code image that this position sensing figure is located
Including target area and homochromy background area;
Mark off the 1st sample area above described position sensing figure top edge, under described position sensing figure
The lower section at edge marks off the 2nd sample area, marks off the 3rd sample area in the left of described position sensing figure left hand edge,
Mark off the 4th sample area in the right of described position sensing figure right hand edge;Wherein, described 1st sample area, the described 2nd
Sample area, described 3rd sample area and described 4th sample area are the subregion in described QR code image;
S6, for any one the i-th sample area, wherein, i=1,2,3 or 4, it is performed both by following operation:
Gather the chromatic value of each of described i-th sample area pixel, then statistics belongs to the picture of identical chromatic value
Vegetarian refreshments number, with chromatic value as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate;
Thus obtain 1st rectangular histogram corresponding with the 1st sample area, 2nd rectangular histogram corresponding with the 2nd sample area, with
Corresponding 3rd rectangular histogram of 3rd sample area, 4th rectangular histogram corresponding with the 4th sample area;
S7, is carried out to described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th rectangular histogram respectively
Filter and differentiate, then judge in described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th Nogata
In figure, if there are two rectangular histograms is the rectangular histogram assuming single-peak response, if it is present show that detected position is visited
Mapping shape is the conclusion of correct detection;Otherwise, then draw the conclusion that detected position sensing figure is error detection.
Preferably, in S5, described 1st sample area, described 2nd sample area, described 3rd sample area and the described 4th
Sample area is the identical region of shape.
Preferably, described 1st sample area, described 2nd sample area, described 3rd sample area and described 4th sample region
Domain is rectangle, rectangle or triangle.
Preferably, in S5, precision is excluded according to error detection and the side length determination of described position sensing figure is following
Parameter value:
Described 1st sample area is apart from the length apart from L1, described 1st sample area of described position sensing figure top edge
Angle value and width value;
Described 2nd sample area is apart from the length apart from L2, described 2nd sample area of described position sensing figure lower limb
Angle value and width value;
Described 3rd sample area is apart from the length apart from L3, described 3rd sample area of described position sensing figure left hand edge
Angle value and width value;
Described 4th sample area is apart from the length apart from L4, described 4th sample area of described position sensing figure right hand edge
Angle value and width value.
Preferably, in S6, rectangular histogram corresponding with described i-th sample area is prepared by the following:
Gather the chromatic value of each of described i-th sample area pixel, then pressing preset algorithm will be adjacent some
Individual chromatic value is included into same colourity interval, thus obtains multiple colourities interval;Then statistics belongs to the interval pixel of identical colourity
Point number, with colourity interval as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate.
Preferably, before gathering the chromatic value of each of described i-th sample area pixel, also include:
The QR code image that described position sensing figure is located carries out color enhancement process.
The present invention also provides a kind of quick positioning QR code position to detect the system of figure, including:
Read module, for reading the QR code original image needing position location to detect figure;Wherein, described QR code is original
Image includes QR code target area and background area;
Binary conversion treatment module, the QR code original image for being read to described read module is carried out at binaryzation
Reason, is only had black pixel point and the binary image of white pixel point;
Parameter setting module, for setting scanning resolution, under set scanning resolution, if described binary picture
Seem the matrix being made up of the pixel of n row n row, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j
≤n;
Scan module, for according to the scanning resolution set by described parameter setting module, horizontal sweep in the same direction line by line
Described binary image;Specifically, for arbitrary row k, its total n pixel forms, and scan mode is:
S-a, reads and records the chromatic value of the 1st pixel first;
S-b, then, reads and records the chromatic value of the 2nd pixel backward, judges that the chromatic value of the 2nd pixel is
No and previous pixel chromatic value is identical, if identical, executes S-c;If it is not the same, then recording the 2nd pixel
The position coordinate value fastened in rectangular coordinate, then executes S-c;
S-c, reads and records the chromatic value of the 3rd pixel backward, judge the chromatic value of the 3rd pixel whether with front
The chromatic value of one pixel is identical, if identical, executes S-d;If it is not the same, then recording the 3rd pixel at right angle
Position coordinate value in coordinate system, then executes S-d;
S-d, the rest may be inferred, until reading the chromatic value of nth pixel point, judges that the chromatic value of nth pixel point is
No and previous pixel chromatic value is identical, if identical, executes S-e;If it is not the same, then recording nth pixel point
The position coordinate value fastened in rectangular coordinate, then executes S-e;
S-e, by putting in order from left to right, if record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x
For integer;X pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Water between pixel
Flat distance, L2Represent P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxWater between pixel
Flat distance;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 numerical value sequence
Row, wherein, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Picture
The position coordinate value of vegetarian refreshments and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinateses of candidate point
Value;
After completing the horizontal sweep in the same direction to n row, multiple candidate points are obtained;
Cluster module, all candidate points for being scanned to described scan module cluster;
Locating module, navigates to three cluster centre position's coordinates that described cluster module is clustered, this cluster centre
The centre coordinate of three position sensing figures that position coordinateses as navigate to;Navigate to three in described QR code original image
Individual position sensing figure.
Beneficial effects of the present invention are as follows:
The quick positioning QR code position that the present invention provides detects the method and system of figure, has that locating speed is fast, calculates
The advantage that resource consumption is few, positioning result accuracy is high.
Brief description
Fig. 1 is the structural representation of existing QR code;
A kind of specific example figure of the QR code original image that Fig. 2 provides for the present invention;
Fig. 3 is when whether the position sensing figure W1 that judgement navigates to is correct, and a kind of concrete of each sample area divides
Schematic diagram;
Fig. 4 is the schematic diagram after omitting black pixel point in QR code in Fig. 3;
Fig. 5 is to judge whether the position sensing figure W2 navigating to is correct constantly, and the division of each sample area is specifically shown
It is intended to;
Fig. 6 is the schematic diagram after omitting black pixel point in QR code in Fig. 5;
Fig. 7 is when whether the position sensing figure W3 that judgement navigates to is correct, and the another kind of concrete of each sample area is drawn
Divide schematic diagram;
Fig. 8 is the schematic diagram after omitting black pixel point in QR code in Fig. 7;
Fig. 9 detects the schematic flow sheet of the method for figure for the quick positioning QR code position that the present invention provides;
Figure 10 detects the structural representation of the system of figure for the quick positioning QR code position that the present invention provides.
Specific embodiment
Below in conjunction with accompanying drawing, the present invention is described in detail:
The present invention provides a kind of method that quick positioning QR code position detects figure, as shown in figure 9, comprising the following steps:
S1, reads the QR code original image needing position location to detect figure;Wherein, described QR code original image includes QR
Code target area and background area;
As shown in Fig. 2 being a kind of specific example figure of QR code original image, wherein, in Fig. 2, label 1 is target area, position
Region outside in target area is background area, i.e. label 2 in Fig. 2.In background area, it is understood that there may be some interference
Pattern.
S2, carries out binary conversion treatment to described QR code original image, is only had black pixel point and white pixel point
Binary image;That is, binary image only has two kinds of chromatic values, respectively black and white.
S3, sets up rectangular coordinate system in the plane that described binary image is located;
Rectangular coordinate system can be set up using any point in the plane of binary image place as zero, by building
Vertical rectangular coordinate system, the position coordinate value of each candidate point when being mainly used in representing follow-up cluster, in the present invention, for convenience of description,
Adopt with the summit in the binary image lower left corner for zero o, zero o level direction to the right is x-axis, zero
O vertically upward direction is the mode of y-axis, and the rectangular coordinate system with reference to Fig. 2 sets up mode.
Set scanning resolution, under set scanning resolution, if described binary picture seems by the picture of n row n row
The matrix of vegetarian refreshments composition, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j≤n;Wherein, resolution
Setting value determined according to concrete positioning precision.
According to set scanning resolution, binary image described in horizontal sweep in the same direction line by line, it should be noted that this
Skilled person is appreciated that line by line horizontal sweep in the same direction, can be both every a line of horizontal sweep from left to right;Can also be certainly
The every a line of the left horizontal sweep of dextrad;Or, based on same scanning theory it is also possible to vertically scan by column each from top to bottom
Row are it is also possible to vertically scan by column every string from bottom to top;Or, first rotation process, Ran Houzai are carried out to binary image
Scanning also may be used.Concrete scan mode is very flexible, all scanning theory based on the present invention, that is,:By colourity value changes record picture
Vegetarian refreshments position coordinate value it is contemplated that deformation all within the scope of the present invention.
For arbitrary row k, all using following scan mode:
S3.1, makes j=1;
S3.2, reads and records CkjThe chromatic value of pixel;
S3.3, judges whether j is equal to n, if equal to, then the one's own profession end of scan, go to S3.5;If it is not, then continuing
Resume studies and take and record Ck(j+1)The chromatic value of pixel, then judges Ck(j+1)The chromatic value of pixel whether with CkjThe color of pixel
Angle value is identical, if identical, executes S3.4;If it is not the same, then recording Ck(j+1)Pixel is in the rectangular coordinate system set up
On position coordinate value, then execute S3.4;
S3.4, makes j=j+1, then goes to S3.3;
In practical application, for some binary image, n generally equal to more than 1000, for introducing scanning theory, simplify
Illustrate, introduce a kind of the simplified mode taking n=10 as a example:In 1-3 row, the color of each pixel is referring to table 1:
Table 1
In vain | In vain | Black | Black | In vain | In vain | In vain | In vain | In vain | In vain |
In vain | Black | In vain | Black | Black | Black | In vain | Black | In vain | In vain |
In vain | Black | In vain | Black | Black | Black | In vain | Black | In vain | Black |
(1) scan table 1 the 1st row
When scan table 11 row, read the chromatic value of the 1st pixel first, for white;
Then read the chromatic value of the 2nd pixel backward, for white, equal with the chromatic value of previous pixel;
Then continue to read the chromatic value of the 3rd pixel backward, be black, the chromatic value not phase with previous pixel
With therefore, the position coordinate value of the 3rd pixel of record, for (3,10);
Then read the chromatic value of the 4th pixel backward, be black, equal with the chromatic value of previous pixel;
Then continue to read the chromatic value of the 5th pixel backward, for white, the chromatic value not phase with previous pixel
With therefore, the position coordinate value of the 5th pixel of record, for (5,10);
Then read the chromatic value of the 6th pixel backward, for white, equal with the chromatic value of previous pixel, according to
This analogizes, until reading the chromatic value of the 10th pixel, for white, equal with the chromatic value of previous pixel.
Therefore, by scanning the 1st row, record the coordinate figure of two pixels altogether, respectively:(3,10) and (5,10);
Wherein, the vertical coordinate that y-axis coordinate 10 represents the 1st row is 10.
(2) scan table 1 the 2nd row
Based on same principle, when scanning the 2nd row, record the coordinate figure of 6 pixels altogether, respectively:(2,9), (3,
9), (4,9), (7,9), (8,9) and (9,9).
(3) scan table 1 the 3rd row
When scanning the 3rd row, record the coordinate figure of 7 pixels altogether, respectively:(2,8), (3,8), (4,8), (7,8),
(8,8), (9,8) and (10,8).
S3.5, if during scanning row k, record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x are integer;
X pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Horizontal range between pixel,
L2Represent P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxHorizontal range between pixel;
Still with above-mentioned table 1 for row, during scanning 1 row, x=2, P1For the 3rd pixel, P2For the 5th pixel;Then L1
=5-3=2;
With above-mentioned scanning the 2nd behavior example, x=6, P1For the 2nd pixel, P2For the 3rd pixel, P3For the 4th pixel
Point, P4For the 7th pixel, P5For the 8th pixel, P6For the 9th pixel;
L-value is the distance between two neighboring pixel, therefore, L1=3-2=1;L2=4-3=1;L3=7-4=3;L4
=8-7=1;L5=9-8=1;
With above-mentioned scanning the 3rd behavior example, x=7, P1For the 2nd pixel, P2For the 3rd pixel, P3For the 4th pixel
Point, P4For the 7th pixel, P5For the 8th pixel, P6For the 9th pixel;P7For the 10th pixel;
L1=3-2=1;L2=4-3=1;L3=7-4=3;L4=8-7=1;L5=9-8=1;L6=10-9=1;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 numerical value sequence
Row, wherein, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Picture
The position coordinate value of vegetarian refreshments and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinateses of candidate point
Value;
In this step, La-2:La-1:La:La+1:La+2≈1:1:3:1:1 refers to:
Set error permissible value as F%, for example, 15%, if La-2=x1;X1-x1*F%≤La-1≤ x1+x1*F%;3
(x1-x1*F%)≤La≤ 3 (x1+x1*F%);X1-x1*F%≤La+1≤ x1+x1*F%;X1-x1*F%≤La+2≤x1+
X1*F%;It is then La-2:La-1:La:La+1:La+2≈1:1:3:1:1.
Still taking table 1 as a example, for the 1st row being scanned, only one of which L-value, therefore, do not exist and meet La-2:La-1:
La:La+1:La+2≈1:1:3:1:1 sequence of values;
For the 2nd row being scanned, L1:L2:L3:L4:L5=1:1:3:1:1, therefore, obtain the 2nd row P2And P4Pixel
The coordinate figure of point, respectively (3,9), (7,9), its meansigma methods is (5,9), and coordinate (5,9) is the position coordinate value of candidate point.
For the 3rd row being scanned, L1:L2:L3:L4:L5=1:1:3:1:1, therefore, obtain the 3rd row P2And P4Pixel
The coordinate figure of point, respectively (3,8), (7,8), its meansigma methods is (5,8), and the position that coordinate (5,8) is another candidate point is sat
Scale value.
S4, after completing the horizontal sweep in the same direction to n row, is obtained multiple candidate points;Using clustering algorithm to obtaining
All candidate points clustered, three classes are obtained, the position that cluster centre position's coordinate of each class as navigates to
Detect the centre coordinate of figure;Thus navigate to three position sensing figures in described QR code original image.
In this step, the clustering algorithm being adopted is various clustering algorithms of the prior art, and for example, K mean cluster is calculated
Method etc., the present invention is not intended to limit to this.
It should be noted that during due to practical application, pixel number n of every a line is often more than 1000, therefore, can examine
Measure large number of candidate point, therefore, because a QR code figure comprises three position test pattern, therefore, calculated using cluster
Method can obtain three cluster centres, and each cluster centre corresponds to one and puts the centre coordinate detecting figure.
As can be seen here, the method that the quick positioning QR code position that the present invention provides detects figure, have capacity of resisting disturbance high,
The advantage that accuracy of identification is big and locating speed is fast;The center of three position sensing figures can quickly be navigated to.
After three position sensing figures in navigating to described QR code original image, for being further ensured that the present invention's
Positioning result accuracy, also includes the whether correct step of position sensing figure that following judgement is navigated to, including:
S5, the described position sensing figure that any one is navigated to, the QR code image that this position sensing figure is located
Including target area and homochromy background area;As shown in figure 3, label 7 is the outward flange of homochromy background area;Target area is
The region being located for QR code code word.
Mark off the 1st sample area above described position sensing figure top edge, under described position sensing figure
The lower section at edge marks off the 2nd sample area, marks off the 3rd sample area in the left of described position sensing figure left hand edge,
Mark off the 4th sample area in the right of described position sensing figure right hand edge;Wherein, described 1st sample area, the described 2nd
Sample area, described 3rd sample area and described 4th sample area are the subregion in described QR code image;Due to the 1st
Sample area is the subregion in QR code image that is to say, that the 1st sample area is to the 4th sample region to the 4th sample area
Domain or be located at target area, or it is located at homochromy background area, or the intersection being located at homochromy background area and target area
Region.Only under the premise of this, could subsequently be based on rectangular histogram peak number using the present invention and judge whether error detection.Concrete principle
Introduce follow-up.
Wherein, for ensureing the accuracy of testing result, the 1st sample area, the 2nd sample area, the 3rd sample area and the 4th
Sample area is the identical region of shape, identical with the area that ensures each sample area;Its shape can be length
Square, rectangle or triangle etc..
In addition, following parameter value is determined according to the side length of error detection exclusion precision and position sensing figure:
Described 1st sample area is apart from the length apart from L1, described 1st sample area of described position sensing figure top edge
Angle value and width value;Described 2nd sample area is apart from described position sensing figure lower limb apart from L2, described 2nd sample region
The length value in domain and width value;Described 3rd sample area apart from described position sensing figure left hand edge apart from L3, the described 3rd
The length value of sample area and width value;Described 4th sample area is apart from described position sensing figure right hand edge apart from L4, institute
State length value and the width value of the 4th sample area.
The concrete division embodiment of three kind sample area is described below:
The first:
As shown in figure 3, being a kind of tool of each sample area when whether the position sensing figure W1 that judgement navigates to is correct
Body divides schematic diagram;Wherein, 3-1 represents the 1st sample area;4-1 represents the 4th sample area,;5-1 represents the 2nd sample area;
6-1 represents the 3rd sample area;As seen from Figure 3, the 1st sample area is rectangle to the 4th sample area, its be positioned
To a certain edge of position sensing figure be completely superposed.Black in the sample area edge being divided by Fig. 3 and QR code
There is coincidence in pixel, therefore, the location and shape of each sample area being divided by clear sign, as shown in figure 4, be to scheme
Schematic diagram after black pixel point omits in QR code in 3;
Second:
As shown in figure 5, being to judge whether the position sensing figure W2 navigating to is correct constantly, the division of each sample area
Specific example.Wherein, 3-2 represents the 1st sample area;4-2 represents the 4th sample area,;5-2 represents the 2nd sample area;6-2 generation
Table the 3rd sample area;As shown in fig. 6, being the schematic diagram after omitting black pixel point in QR code in Fig. 5;In Fig. 5-Fig. 6, institute
The sample area edge dividing is overlapped with the black pixel point presence in QR code.
The third:
As shown in fig. 7, being the another kind of each sample area when whether the position sensing figure W3 that judgement navigates to is correct
Concrete division schematic diagram;Wherein, 3-3 represents the 1st sample area;4-3 represents the 4th sample area,;5-3 represents the 2nd sample region
Domain;6-3 represents the 3rd sample area;As shown in figure 8, being the schematic diagram after omitting black pixel point in QR code in Fig. 7;Fig. 7-
In Fig. 8, the sample area edge being divided is misaligned with the black pixel point in QR code, there is certain interval.
As can be seen here, in the present invention, as long as the area of each sample area of guarantee is identical with shape, concrete division
Position can need flexibly to arrange according to actually detected.
S6, for any one the i-th sample area, wherein, i=1,2,3 or 4, it is performed both by following operation:
Gather the chromatic value of each of described i-th sample area pixel, then statistics belongs to the picture of identical chromatic value
Vegetarian refreshments number, with chromatic value as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate;Tool
Body implementation is:
Gather the chromatic value of each of described i-th sample area pixel, then pressing preset algorithm will be adjacent some
Individual chromatic value is included into same colourity interval, thus obtains multiple colourities interval;Then statistics belongs to the interval pixel of identical colourity
Point number, with colourity interval as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate.
For example, colourity interval is chosen as 50, as well known to those skilled in the art, co-exists in 256 chromatic values, then:By colourity
It is interval that value 1-50 is divided into the 1st colourity;Chromatic value 51-100 is divided into the 2nd colourity interval;Chromatic value 101-150 is divided into
3rd colourity is interval;Chromatic value 151-200 is divided into the 4th colourity interval;Chromatic value 201-256 is divided into the 5th colourity area
Between;Then, taking the 1st colourity interval as a example, count the pixel falling in each sample area in the range of chromatic value 1-50
Number.
In this step, for the simplicity of guarantee statistics with histogram, the QR code figure that can first position sensing figure be located
As carrying out color enhancement process, then gather the chromatic value of each of each sample area pixel again.
Thus obtain 1st rectangular histogram corresponding with the 1st sample area, 2nd rectangular histogram corresponding with the 2nd sample area, with
Corresponding 3rd rectangular histogram of 3rd sample area, 4th rectangular histogram corresponding with the 4th sample area;
S7, is carried out to described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th rectangular histogram respectively
Filter and differentiate, then judge in described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th Nogata
In figure, if there are two rectangular histograms is the rectangular histogram assuming single-peak response, if it is present show that detected position is visited
Mapping shape is the conclusion of correct detection;Otherwise, then draw the conclusion that detected position sensing figure is error detection.
For example, for Fig. 3, when whether the position sensing figure W1 that judgement navigates to is correct, obtain 3-1- the 1st in division
After sample area, 4-1- the 4th sample area, 5-1- the 2nd sample area and this four sample area of 6-1- the 3rd sample area, it is
Simplify explanation, all included as a example 100 pixels by each sample area:
For the 1st sample area, because it is fully located at homochromy background area that is to say, that the color of this 100 pixels
Angle value is identical, and therefore, in the 1st obtained rectangular histogram, only one chromatic value with homochromy background area of appearance is corresponding unimodal,
This unimodal area is 100 cellar areas.
For the 4th sample area, positioned at QR code target area, because QR code target area comprises black pixel point and white
Pixel, therefore, in the 4th obtained rectangular histogram, assumes double-peak feature, a peak is corresponding with black chtominance value, represents the 4th and adopts
The black pixel point area comprising in sample region;Another peak is corresponding with white chromaticity value, represents and comprises in the 4th sample area
White pixel point area;For example, the corresponding peak area of black chtominance value is 75 cellar areas, white chromaticity value corresponding peak face
Amass as 25 cellar areas.
For the 2nd sample area, positioned at QR code target area, similar with the 4th sample area, obtained the 2nd rectangular histogram
In, assume double-peak feature, a peak is corresponding with black chtominance value, represents the black pixel point area comprising in the 2nd sample area,
As for 20 cellar areas;Another peak is corresponding with white chromaticity value, represents the white pixel point face comprising in the 2nd sample area
Long-pending such as 80 cellar areas.
For the 3rd sample area, because it is fully located at homochromy background area, similar with the 1st sample area, therefore, institute
In the 3rd rectangular histogram obtaining, only one chromatic value with homochromy background area of appearance is corresponding unimodal, and this unimodal area is 100
Individual cellar area.
Therefore, for Fig. 3, the 1st rectangular histogram and the 3rd rectangular histogram assume single-peak response it follows that, detected position
Detection figure W1 is correct position sensing figure conclusion.
Again for example, for Fig. 5, when judging whether the position sensing figure W2 that navigates to is correct, obtain 3-2 the in division
After 1 sample area, 4-2- the 4th sample area, 5-2 the 2nd sample area and this four sample area of 6-2- the 3rd sample area, system
Count the 1st rectangular histogram that obtains all assume double-hump characteristics to the 4th rectangular histogram it follows that, the position sensing figure W2 being navigated to
Conclusion for error detection.
Again for example, for Fig. 6, when whether the position sensing figure W3 that judgement navigates to is correct, count the 1st obtaining straight
Square figure in the 4th rectangular histogram, exist two rectangular histograms assume single-peak response it follows that, the position sensing figure being navigated to
W3 is the conclusion of correct detection.
As can be seen here, the present invention, when whether the position sensing figure judging to navigate to is error detection, counts this position respectively
Put the rectangular histogram of the chromaticity statistics situation of four sample area in upper and lower, left and right detecting figure, thus obtain four rectangular histograms;
Then, judge in this four rectangular histograms, if there are two rectangular histograms and assume unimodal feature, if it is present showing to navigate to
Position sensing figure be located at some corner position of QR code image, for example, positioned at the upper left corner, the upper right corner or the lower left corner, then
Show that the position sensing figure detecting is correct conclusion;That is, for correct position sensing figure, it is necessarily deposited
In two sample area being located at color background region, and the statistic histogram being located at the sample area in color background region is inevitable
Assume unimodal feature;And for wrong position sensing figure, because it is located inside QR code target image, therefore, do not exist
The sample area in pure color background region, so, the statistic histogram obtaining necessarily does not assume unimodal feature.Conversely, then showing
The position sensing figure being navigated to is located at the non-top corner regions of QR code image, then show that the position sensing figure detecting is mistake
Conclusion by mistake;Have the advantages that error detection investigates that speed is fast, computing resource that is consuming is few.Further, since in existing QR code specification,
In the periphery of QR code target image, it is respectively provided with the color background region of a certain width, so, the error detection exclusion that the present invention provides
Process, has the advantages that applied widely.
As shown in Figure 10, the present invention also provides a kind of quick positioning QR code position to detect the system of figure, including:
Read module, for reading the QR code original image needing position location to detect figure;Wherein, described QR code is original
Image includes QR code target area and background area;
Binary conversion treatment module, the QR code original image for being read to described read module is carried out at binaryzation
Reason, is only had black pixel point and the binary image of white pixel point;
Parameter setting module, for setting scanning resolution, under set scanning resolution, if described binary picture
Seem the matrix being made up of the pixel of n row n row, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j
≤n;
Scan module, for according to the scanning resolution set by described parameter setting module, horizontal sweep in the same direction line by line
Described binary image;Specifically, for arbitrary row k, its total n pixel forms, and scan mode is:
S-a, reads and records the chromatic value of the 1st pixel first;
S-b, then, reads and records the chromatic value of the 2nd pixel backward, judges that the chromatic value of the 2nd pixel is
No and previous pixel chromatic value is identical, if identical, executes S-c;If it is not the same, then recording the 2nd pixel
The position coordinate value fastened in rectangular coordinate, then executes S-c;
S-c, reads and records the chromatic value of the 3rd pixel backward, judge the chromatic value of the 3rd pixel whether with front
The chromatic value of one pixel is identical, if identical, executes S-d;If it is not the same, then recording the 3rd pixel at right angle
Position coordinate value in coordinate system, then executes S-d;
S-d, the rest may be inferred, until reading the chromatic value of nth pixel point, judges that the chromatic value of nth pixel point is
No and previous pixel chromatic value is identical, if identical, executes S-e;If it is not the same, then recording nth pixel point
The position coordinate value fastened in rectangular coordinate, then executes S-e;
S-e, by putting in order from left to right, if record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x
For integer;X pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Water between pixel
Flat distance, L2Represent P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxWater between pixel
Flat distance;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 numerical value sequence
Row, wherein, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Picture
The position coordinate value of vegetarian refreshments and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinateses of candidate point
Value;
After completing the horizontal sweep in the same direction to n row, multiple candidate points are obtained;
Cluster module, all candidate points for being scanned to described scan module cluster;
Locating module, navigates to three cluster centre position's coordinates that described cluster module is clustered, this cluster centre
The centre coordinate of three position sensing figures that position coordinateses as navigate to;Navigate to three in described QR code original image
Individual position sensing figure.
In sum, the quick positioning QR code position that the present invention provides detects the method and system of figure, has positioning speed
The advantage that degree is fast, computing resource consumes less, positioning result accuracy is high.
The above is only the preferred embodiment of the present invention it is noted that ordinary skill people for the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
Depending on protection scope of the present invention.
Claims (10)
1. a kind of quick positioning QR code position detects the method for figure it is characterised in that comprising the following steps:
S1, reads the QR code original image needing position location to detect figure;Wherein, described QR code original image includes QR code mesh
Mark region and background area;
S2, carries out binary conversion treatment to described QR code original image, is only had the two of black pixel point and white pixel point
Value image;
S3, sets up rectangular coordinate system in the plane that described binary image is located;
Set scanning resolution, under set scanning resolution, if described binary picture seems by the pixel of n row n row
The matrix of composition, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j≤n;
According to set scanning resolution, binary image described in horizontal sweep in the same direction line by line, for arbitrary row k, all
Using following scan mode:
S3.1, makes j=1;
S3.2, reads and records CkjThe chromatic value of pixel;
S3.3, judges whether j is equal to n, if equal to, then the one's own profession end of scan, go to S3.5;If it is not, then continuing to read
Take and record Ck(j+1)The chromatic value of pixel, then judges Ck(j+1)The chromatic value of pixel whether with CkjThe chromatic value of pixel
Identical, if identical, execute S3.4;If it is not the same, then recording Ck(j+1)Pixel is fastened in the rectangular coordinate set up
Position coordinate value, then executes S3.4;
S3.4, makes j=j+1, then goes to S3.3;
S3.5, if during scanning row k, record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x are integer;By x
Pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Horizontal range between pixel, L2Represent
P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxHorizontal range between pixel;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 sequence of values, its
In, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Pixel
Position coordinate value and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinate value of candidate point;
S4, after completing the horizontal sweep in the same direction to n row, is obtained multiple candidate points;Using clustering algorithm to the institute obtaining
There is candidate point to be clustered, three classes are obtained, the position sensing that cluster centre position's coordinate of each class as navigates to
The centre coordinate of figure;Thus navigate to three position sensing figures in described QR code original image.
2. quick positioning QR code position according to claim 1 detects the method for figure it is characterised in that judging L1、L2…
Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 sequence of values, refers to:
Set error permissible value as F%, if La-2=x1;X1-x1*F%≤La-1≤ x1+x1*F%;3 (x1-x1*F%)≤La
≤ 3 (x1+x1*F%);
X1-x1*F%≤La+1≤ x1+x1*F%;X1-x1*F%≤La+2≤ x1+x1*F%;It is then La-2:La-1:La:La+1:La+2
≈1:1:3:1:1.
3. quick positioning QR code position according to claim 1 detects the method for figure it is characterised in that described cluster is calculated
Method is K mean cluster algorithm.
4. quick positioning QR code position according to claim 1 detects the method for figure it is characterised in that navigating to
After stating three position sensing figures in QR code original image, also include:
S5, the described position sensing figure that any one is navigated to, the QR code image that this position sensing figure is located includes
Target area and homochromy background area;
Mark off the 1st sample area above described position sensing figure top edge, in described position sensing figure lower limb
Lower section mark off the 2nd sample area, mark off the 3rd sample area in the left of described position sensing figure left hand edge, in institute
The right stating position sensing figure right hand edge marks off the 4th sample area;Wherein, described 1st sample area, described 2nd sampling
Region, described 3rd sample area and described 4th sample area are the subregion in described QR code image;
S6, for any one the i-th m sample area, wherein, im=1,2,3 or 4, it is performed both by following operation:
Gather the chromatic value of each of described i-th m sample area pixel, then statistics belongs to the pixel of identical chromatic value
Number, with chromatic value as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate;
Thus obtain 1st rectangular histogram corresponding with the 1st sample area, 2nd rectangular histogram corresponding with the 2nd sample area, adopt with the 3rd
Corresponding 3rd rectangular histogram in sample region, 4th rectangular histogram corresponding with the 4th sample area;
S7, is filtered to described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th rectangular histogram respectively
And differentiate, then judge in described 1st rectangular histogram, described 2nd rectangular histogram, described 3rd rectangular histogram and described 4th rectangular histogram
In, if there are two rectangular histograms is the rectangular histogram assuming single-peak response, if it is present drawing detected position sensing
Figure is the conclusion of correct detection;Otherwise, then draw the conclusion that detected position sensing figure is error detection.
5. quick positioning QR code position according to claim 4 detects the method for figure it is characterised in that in S5, described
1st sample area, described 2nd sample area, described 3rd sample area and described 4th sample area are that shape is identical
Region.
6. quick positioning QR code position according to claim 5 detects the method for figure it is characterised in that the described 1st adopts
Sample region, described 2nd sample area, described 3rd sample area and described 4th sample area are rectangle or triangle.
7. quick positioning QR code position according to claim 5 detects the method for figure it is characterised in that in S5, according to
Error detection excludes precision and the side length of described position sensing figure determines following parameter value:
Described 1st sample area is apart from the length value apart from L1, described 1st sample area of described position sensing figure top edge
And width value;
Described 2nd sample area is apart from the length value apart from L2, described 2nd sample area of described position sensing figure lower limb
And width value;
Described 3rd sample area is apart from the length value apart from L3, described 3rd sample area of described position sensing figure left hand edge
And width value;
Described 4th sample area is apart from the length value apart from L4, described 4th sample area of described position sensing figure right hand edge
And width value.
8. quick positioning QR code position according to claim 5 detects the method for figure it is characterised in that in S6, with institute
State the corresponding rectangular histogram of the i-th sample area to be prepared by the following:
Gather the chromatic value of each of described i-th sample area pixel, then press preset algorithm by several adjacent colors
Angle value is included into same colourity interval, thus obtains multiple colourities interval;Then statistics belongs to identical colourity interval pixel
Number, with colourity interval as abscissa, draws rectangular histogram corresponding with this sample area with pixel number for vertical coordinate.
9. quick positioning QR code position according to claim 5 detects the method for figure it is characterised in that described in collection
Before the chromatic value of each of the i-th sample area pixel, also include:
The QR code image that described position sensing figure is located carries out color enhancement process.
10. a kind of quick positioning QR code position detects the system of figure it is characterised in that including:
Read module, for reading the QR code original image needing position location to detect figure;Wherein, described QR code original image
Including QR code target area and background area;
Binary conversion treatment module, the QR code original image for being read to described read module carries out binary conversion treatment, obtains
To the binary image only with black pixel point and white pixel point;
Parameter setting module, for setting scanning resolution, under set scanning resolution, if described binary picture seems
The matrix being made up of the pixel of n row n row, then in matrix, any one pixel is designated as Cij;Wherein, 1≤i≤n;1≤j≤n;
Scan module, for according to the scanning resolution set by described parameter setting module, line by line in the same direction described in horizontal sweep
Binary image;Specifically, for arbitrary row k, its total n pixel forms, and scan mode is:
S-a, reads and records the chromatic value of the 1st pixel first;
S-b, then, reads and records the chromatic value of the 2nd pixel backward, judge the chromatic value of the 2nd pixel whether with
The chromatic value of previous pixel is identical, if identical, executes S-c;If it is not the same, then recording the 2nd pixel straight
The position coordinate value that angular coordinate is fastened, then executes S-c;
S-c, reads and records the chromatic value of the 3rd pixel backward, judge the chromatic value of the 3rd pixel whether with previous
The chromatic value of pixel is identical, if identical, executes S-d;If it is not the same, then recording the 3rd pixel in rectangular coordinate
The position coordinate value fastened, then executes S-d;
S-d, the rest may be inferred, until reading the chromatic value of nth pixel point, judge the chromatic value of nth pixel point whether with
The chromatic value of previous pixel is identical, if identical, executes S-e;If it is not the same, then record nth pixel point is straight
The position coordinate value that angular coordinate is fastened, then executes S-e;
S-e, by putting in order from left to right, if record the position coordinate value of x pixel altogether;Wherein, 0≤x≤n, x are whole
Number;X pixel is designated as P successively by scanning sequencing1、P2…Px;If L1Represent P1And P2Level between pixel away from
From, L2Represent P2And P3Horizontal range between pixel, the rest may be inferred, Lx-1Represent Px-1And PxLevel between pixel away from
From;
Then judge L1、L2…Lx-1Among, if there is La-2:La-1:La:La+1:La+2≈1:1:3:1:1 sequence of values, its
In, 1≤a≤x-3;If it is present obtaining P respectivelya-1And Pa+1The position coordinate value of pixel, then calculates Pa-1Pixel
Position coordinate value and Pa+1The meansigma methodss of the position coordinate value of pixel, this meansigma methods is the position coordinate value of candidate point;
After completing the horizontal sweep in the same direction to n row, multiple candidate points are obtained;
Cluster module, all candidate points for being scanned to described scan module cluster;
Locating module, navigates to three cluster centre position's coordinates that described cluster module is clustered, this cluster centre position
The centre coordinate of three position sensing figures that coordinate as navigates to;Navigate to three positions in described QR code original image
Put detection figure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410422618.7A CN104200188B (en) | 2014-08-25 | 2014-08-25 | Method and system for rapidly positioning position detection patterns of QR code |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410422618.7A CN104200188B (en) | 2014-08-25 | 2014-08-25 | Method and system for rapidly positioning position detection patterns of QR code |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104200188A CN104200188A (en) | 2014-12-10 |
CN104200188B true CN104200188B (en) | 2017-02-15 |
Family
ID=52085479
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410422618.7A Active CN104200188B (en) | 2014-08-25 | 2014-08-25 | Method and system for rapidly positioning position detection patterns of QR code |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104200188B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200187B (en) * | 2014-08-25 | 2017-06-16 | 北京慧眼智行科技有限公司 | A kind of quick exclusion QR code positions detect the method and system of figure error detection |
CN105184208B (en) * | 2015-09-02 | 2017-10-31 | 福建联迪商用设备有限公司 | A kind of Quick Response Code Primary Location method and system |
CN107025455B (en) * | 2017-04-01 | 2019-12-24 | 浙江华睿科技有限公司 | Positioning method and device for quickly reflecting QR (quick response) code area |
CN109448013B (en) * | 2018-08-31 | 2021-09-10 | 广东技术师范大学 | QR code image binarization processing method with local uneven illumination |
CN110046529B (en) * | 2018-12-11 | 2020-06-09 | 阿里巴巴集团控股有限公司 | Two-dimensional code identification method, device and equipment |
JP7446643B2 (en) * | 2020-05-26 | 2024-03-11 | マプサス テクノロジー ホールディング リミテッド | Visual positioning methods, devices, equipment and readable storage media |
CN112541370B (en) * | 2020-12-16 | 2022-03-15 | 电子科技大学 | QR code position detection graph positioning method based on FPGA |
CN113095104A (en) * | 2021-05-08 | 2021-07-09 | 山东新一代信息产业技术研究院有限公司 | Defective two-dimensional code positioning method |
US11960966B2 (en) | 2022-05-16 | 2024-04-16 | Abbyy Development Inc. | Decoding of two-dimensional barcodes under unfavorable conditions |
US12008431B2 (en) | 2022-05-16 | 2024-06-11 | Abbyy Development Inc. | Decoding of linear barcodes under unfavorable conditions |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510268A (en) * | 2009-03-20 | 2009-08-19 | 南京航空航天大学 | Automatic identification method for secret related drawings |
CN103294980A (en) * | 2013-06-18 | 2013-09-11 | 四川大学 | Micro-QR (Quick Response) code recognition method based on picture processing |
CN103699865A (en) * | 2014-01-15 | 2014-04-02 | 吴东辉 | Border graphic code |
-
2014
- 2014-08-25 CN CN201410422618.7A patent/CN104200188B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510268A (en) * | 2009-03-20 | 2009-08-19 | 南京航空航天大学 | Automatic identification method for secret related drawings |
CN103294980A (en) * | 2013-06-18 | 2013-09-11 | 四川大学 | Micro-QR (Quick Response) code recognition method based on picture processing |
CN103699865A (en) * | 2014-01-15 | 2014-04-02 | 吴东辉 | Border graphic code |
Non-Patent Citations (2)
Title |
---|
K_Means聚类算法研究及图形演示的实现;蒋庆丰等;《信息技术》;20100325(第3期);第23-25页 * |
票据图像压缩和防伪的一些研究;李芳芳;《中国优秀硕士学位论文全文数据库 信息科技辑》;20130715(第7期);第4.2-4.3节 * |
Also Published As
Publication number | Publication date |
---|---|
CN104200188A (en) | 2014-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104200188B (en) | Method and system for rapidly positioning position detection patterns of QR code | |
CN102773862B (en) | Quick and accurate locating system used for indoor mobile robot and working method thereof | |
CN103207987B (en) | A kind of registration recognition methods of pointer instrument | |
CN101408937B (en) | Method and apparatus for locating character row | |
CN109993019A (en) | Two-dimensional code identification method, system and equipment and medium based on connected domain analysis | |
CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
CN106407981A (en) | License plate recognition method, device and system | |
CN105095822B (en) | A kind of Chinese letter co pattern image detection method and system | |
CN106960208A (en) | A kind of instrument liquid crystal digital automatic segmentation and the method and system of identification | |
CN103400373B (en) | The automatic recognition positioning method of camera calibration controlling filed artificial target picpointed coordinate | |
CN106599890B (en) | digital instrument recognition algorithm for substation inspection robot | |
CN105404874B (en) | A kind of vehicle window identifying system based on projection and hough straight-line detections | |
CN104990926A (en) | TR element locating and defect detecting method based on vision | |
CN108460418B (en) | Invoice classification method based on character recognition and semantic analysis | |
CN105184208A (en) | Two-dimension code preliminary positioning method and system | |
CN105988305B (en) | Wafer pre-alignment method | |
CN106097316A (en) | The substrate position identifying processing method of laser scribing means image identification system | |
CN103745221A (en) | Two-dimensional code image correction method | |
CN106485710A (en) | A kind of element mistake part detection method and device | |
CN105678737A (en) | Digital image corner point detection method based on Radon transform | |
CN114972531B (en) | Corner detection method, equipment and readable storage medium | |
CN106709952A (en) | Automatic calibration method of display screen | |
CN106529551A (en) | Intelligent recognition, counting, and detection algorithm for quasi-circle object facing packaging industry | |
CN109919154A (en) | A kind of character intelligent identification Method and identification device | |
CN103235951B (en) | A kind of Primary Location method of matrix two-dimensional barcode |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
PP01 | Preservation of patent right | ||
PP01 | Preservation of patent right |
Effective date of registration: 20180709 Granted publication date: 20170215 |
|
PD01 | Discharge of preservation of patent | ||
PD01 | Discharge of preservation of patent |
Date of cancellation: 20210709 Granted publication date: 20170215 |
|
PP01 | Preservation of patent right | ||
PP01 | Preservation of patent right |
Effective date of registration: 20220930 Granted publication date: 20170215 |