CN104268498B - A kind of recognition methods of Quick Response Code and terminal - Google Patents
A kind of recognition methods of Quick Response Code and terminal Download PDFInfo
- Publication number
- CN104268498B CN104268498B CN201410514458.9A CN201410514458A CN104268498B CN 104268498 B CN104268498 B CN 104268498B CN 201410514458 A CN201410514458 A CN 201410514458A CN 104268498 B CN104268498 B CN 104268498B
- Authority
- CN
- China
- Prior art keywords
- quick response
- response code
- fip
- recognized
- images
- 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
Embodiments of the invention provide recognition methods and the terminal of a kind of Quick Response Code, are related to electronic technology field, it is allowed to which terminal carries out the identification of one or more Quick Response Codes under conditions of more loosely, improves detection discrimination of the Quick Response Code in complex scene.The program includes:Collection includes the images to be recognized of Quick Response Code;The FIP in the images to be recognized is extracted using preset grader, the grader is used to recognize FIP according to the Feature Descriptor of images to be recognized;Four summits of the Quick Response Code are determined according to the FIP, to determine the position of the Quick Response Code in the images to be recognized, the Quick Response Code in position in order to recognize the Quick Response Code.
Description
Technical field
The present invention relates to recognition methods and the terminal of electronic technology field, more particularly to a kind of Quick Response Code.
Background technology
Quick Response Code (Two-dimensional code), be with specific geometric figure according to certain rules in the two-dimensional direction
The chequered with black and white figure of distribution, its geometrical body corresponding with binary system using several represents word numerical information,
By terminal automatically identifying and reading to realize that information is automatically processed.Compared with one-dimension code, Quick Response Code is a kind of than one-dimension code higher level
Barcode standard, Quick Response Code both horizontally and vertically can storage information, and Quick Response Code can store Chinese character, numeral and picture
Etc. information, therefore the application field of Quick Response Code is much broader.
QR (Quick Response) code is a kind of Quick Response Code being widely used at present, and it has, and recognition speed is fast, data
The advantage that density is big, occupy little space, can effectively represent Chinese character, Japanese kanji.Include three in each QR code
FIP (finder pattern, position sensing figure), and be located at respectively on three summits of square, as the pros of " returning " word
Pattern, this 3 FIP are to make the pattern of positioning for the decoding software of terminal.In the prior art, terminal is obtained by view-finder
After images to be recognized, the FIP searched in the images according to the distinctive black and white saltus step rule of Quick Response Code in images to be recognized, when looking for
It located the positions of QR codes after to three FIP, and then read by the decoding software of terminal the data in the position of the QR codes
Information.
However, in the identification process of above-mentioned Quick Response Code, it is desirable to which the holder of terminal is when scanning Quick Response Code by view-finder
Images to be recognized is directed at, and requires not including the other guide beyond Quick Response Code in the images to be recognized, once in identification two
Terminal can not meet above-mentioned requirements (i.e. in complex scene) during dimension code, just can not correctly recognize in above-mentioned images to be recognized
FIP, and then cause positioning and the recognition failures of Quick Response Code.
The content of the invention
Embodiments of the invention provide recognition methods and the terminal of a kind of Quick Response Code, it is allowed to which terminal is in looser condition
The lower identification for carrying out one or more Quick Response Codes, improves detection discrimination of the Quick Response Code in complex scene.
To reach above-mentioned purpose, embodiments of the invention are adopted the following technical scheme that:
In a first aspect, embodiments of the invention provide a kind of recognition methods of Quick Response Code, including:
Collection includes the images to be recognized of Quick Response Code;
The position sensing figure FIP in the images to be recognized is extracted using preset grader, the grader is used for
FIP is recognized according to the Feature Descriptor of images to be recognized;
Four summits of the Quick Response Code are determined according to the FIP, to determine the Quick Response Code in the images to be recognized
Position, and the Quick Response Code of deformation is corrected, the Quick Response Code in position in order to recognize the Quick Response Code.
It is described to use preset grader with reference in a first aspect, in the first possible implementation of first aspect
The FIP in the images to be recognized is extracted, including:
Extract the Feature Descriptor in the images to be recognized;
According to the Feature Descriptor, the FIP in the images to be recognized is extracted using preset FIP graders.
It is described that institute is determined according to the FIP with reference in a first aspect, in second of possible implementation of first aspect
Four summits of Quick Response Code are stated, including:
According to the black and white saltus step rule of Quick Response Code, carried out respectively horizontally and vertically centered on the FIP
Detection, to filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;
FIP after filtering is divided into by FIP groups according to the geometry site of triangle, to determine each FIP groups
The position on four summits of indicated Quick Response Code, each FIP groups include three FIP.
With reference to second of possible implementation of foregoing first aspect, in the third possible realization of first aspect
In mode, the position on four summits for determining the Quick Response Code indicated by each FIP groups, including:
The angle point of three FIP in the FIP groups is detected, the angle point set of FIP groups is formed;
According to the geometry site of angle point in the angle point set and the angle point set, the FIP is determined respectively
Four summits of the Quick Response Code indicated by group.
With reference in a first aspect, in the 4th kind of possible implementation of first aspect, it is described determine it is described to be identified
After the position of Quick Response Code in image, in addition to:
Closed according to the position on four summits of the Quick Response Code behind the four of the Quick Response Code summits and preset correction
System, calculates the perspective matrix coefficient of the Quick Response Code;
According to the perspective matrix coefficient, by matrixing and linear interpolation method to two in the position of the Quick Response Code
Dimension code is corrected, to determine the gray level image of the Quick Response Code after correction, in order to the gray level image according to the Quick Response Code
Recognize the Quick Response Code.
With reference to the 4th kind of possible implementation of foregoing first aspect, in the 5th kind of possible realization of first aspect
In mode, determined described after correction after the gray level image of the Quick Response Code, in addition to:
If the gray level image of the Quick Response Code does not meet the parameter and standard of data message in identification Quick Response Code, mistake after correction
Filter the gray level image of the Quick Response Code after the correction.
With reference in a first aspect, in the 6th kind of possible implementation of first aspect, Quick Response Code is included in the collection
Images to be recognized before, in addition to:
The FIP that Quick Response Code is extracted in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample;
The Feature Descriptor of the positive sample and the negative sample is extracted, the Feature Descriptor is at least levied including Lis Hartel
Or histogram of gradients feature;
The Feature Descriptor of the positive sample and the negative sample is trained using sorting algorithm, the classification is generated
Device.
Second aspect, embodiments of the invention provide a kind of terminal, including:
Collecting unit, for gathering the images to be recognized for including Quick Response Code;
Extraction unit, is visited for being extracted the position in the images to be recognized in the collecting unit using preset grader
Mapping shape FIP, the grader is used to recognize FIP according to the Feature Descriptor of images to be recognized;
Recognition unit, four summits of the Quick Response Code is determined for the FIP in the extraction unit, to determine
The position of the Quick Response Code in images to be recognized is stated, the Quick Response Code in position in order to recognize the Quick Response Code.
With reference to second aspect, in the first possible implementation of second aspect,
The extraction unit, specifically for extracting the Feature Descriptor in the images to be recognized;Retouched according to the feature
Son is stated, the FIP in the images to be recognized is extracted using preset FIP graders.
With reference to second aspect, in second of possible implementation of second aspect,
The recognition unit, specifically for the black and white saltus step rule according to Quick Response Code, is carried out respectively centered on the FIP
Detection horizontally and vertically, to filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;According to triangle
Geometry site the FIP after filtering is divided into FIP groups, to determine four of the Quick Response Code indicated by each FIP groups
The position on individual summit, each FIP groups include three FIP.
With reference to second of possible implementation of foregoing second aspect, in the third possible realization of second aspect
In mode,
The recognition unit, the angle point specifically for detecting three FIP in the FIP groups, forms the angle point of FIP groups
Set;According to the geometry site of angle point in the angle point set and the angle point set, the FIP groups are determined respectively
Four summits of indicated Quick Response Code.
With reference to second aspect, in the 4th kind of possible implementation of second aspect, it is single that the terminal also includes correction
Member, wherein,
The correction unit, for the Quick Response Code behind four summits according to the Quick Response Code and preset correction
The position relationship on four summits, calculates the perspective matrix coefficient of the Quick Response Code;According to the perspective matrix coefficient, pass through matrix
Conversion and linear interpolation method are corrected to the Quick Response Code in the position of the Quick Response Code, to determine the Quick Response Code after correction
Gray level image, in order to recognize the Quick Response Code according to the gray level image of the Quick Response Code.
With reference to the 4th kind of possible implementation of foregoing second aspect, in the 5th kind of possible realization of second aspect
In mode, the terminal also includes filter element, wherein,
The filter element, if the gray level image of the Quick Response Code does not meet data letter in identification Quick Response Code after for correcting
The parameter and standard of breath, then filter the gray level image of the Quick Response Code after the correction.
With reference to second aspect, in the 6th kind of possible implementation of second aspect,
The extraction unit, the FIP for being additionally operable to extract Quick Response Code in preset picture library is positive sample, not comprising Quick Response Code
Image be negative sample;The Feature Descriptor of the positive sample and the negative sample is extracted, the Feature Descriptor at least includes
Lis Hartel is levied or histogram of gradients feature;The Feature Descriptor of the positive sample and the negative sample is carried out using sorting algorithm
Training, generates the grader.
Embodiments of the invention provide recognition methods and the terminal of a kind of Quick Response Code, and classification is used based on target detection principle
Device extracts FIP to the images to be recognized collected, carries out the Primary Location to Quick Response Code, and then determine two dimension according to the FIP
Four summits of code, with the position for the Quick Response Code being accurately positioned in the images to be recognized, the target detection used due to this programme
Principle can more easily extract images to be recognized and extract FIP, it is not necessary to as the collection of the images to be recognized of existing Quick Response Code
In journey like that, must be requested that the Quick Response Code in view-finder accounts for main body and the background of Quick Response Code is simple, and terminal could pass through Quick Response Code
Black and white saltus step rule identify FIP, so the present invention can allow terminal collection under conditions of more loose to contain one
Or the images to be recognized of multiple Quick Response Codes, further, since the present invention is after FIP is extracted, the position of Quick Response Code is carried out according to FIP
Being accurately positioned for two-step method, further increases detection discrimination of the Quick Response Code in complex scene.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic diagram one of the recognition methods of Quick Response Code provided in an embodiment of the present invention;
The schematic diagram that Fig. 2 is FIP in Quick Response Code;
Fig. 3 is a kind of schematic diagram two of the recognition methods of Quick Response Code provided in an embodiment of the present invention;
Fig. 4 is the schematic diagram of calculating Quick Response Code vertex position in the present invention;
Fig. 5 is a kind of hardware schematic of terminal provided in an embodiment of the present invention;
Fig. 6 is a kind of structural representation one of terminal provided in an embodiment of the present invention;
Fig. 7 is a kind of structural representation two of terminal provided in an embodiment of the present invention;
Fig. 8 is a kind of structural representation three of terminal provided in an embodiment of the present invention.
Embodiment
In describing below, in order to illustrate rather than in order to limit, it is proposed that such as particular system structure, interface, technology it
The detail of class, the present invention is understood so as to thorough.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known device, circuit and
The detailed description of method, in case unnecessary details hinders description of the invention.
Terminal, can be that wireless terminal can also be catv terminal, wireless terminal can refer to provide a user voice and/
Or the equipment of data connectivity, portable equipment with wireless connecting function or other for being connected to radio modem
Processing equipment.
Embodiment one
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, as shown in figure 1, including:
101st, terminal collection includes the images to be recognized of Quick Response Code;
102nd, terminal extracts the FIP in images to be recognized using preset grader, and the grader, which is used for basis, to be waited to know
The Feature Descriptor identification FIP of other image;
103rd, terminal determines four summits of Quick Response Code according to FIP, to determine the position of the Quick Response Code in images to be recognized,
The Quick Response Code in position in order to recognize the Quick Response Code.
Specifically, in a step 101, when user is needed by terminal recognition Quick Response Code, but using and carrying camera
The terminal collection of function includes the images to be recognized of Quick Response Code.
Wherein, Quick Response Code is also known as two-dimensional bar code, and it is according to certain rules in plane (two-dimensional square with specific geometric figure
To) on the chequered with black and white figure that is distributed, can be in information such as limited space memory storage word, image, fingerprint, signatures.Two dimension
Code coding dexterously make use of composition computer-internal logical foundations " 0 ", " 1 " bit stream concept, using several with
Binary system corresponding geometrical body represents word numerical information, by the identification of terminal to realize that information is automatically processed.
Quick Response Code is a kind of barcode standard than one-dimension code higher level.One-dimension code can only (be usually level in a direction
Direction) on expressing information, and Quick Response Code is both horizontally and vertically can storage information.One-dimension code can only be by numeral and letter
Composition, and Quick Response Code can store the information such as Chinese character, numeral and picture, therefore the application field of Quick Response Code is much broader.In the modern times
In business activity, the achievable application of Quick Response Code is quite varied, such as:Product false proof/trace to the source, advertisement pushing, web site url, data
Download, commodity transaction, positioning/navigation, electronic certificate, vehicle management, information transmission, business card exchange, wifi are shared etc..
However, in the prior art, user first has to scan treating containing Quick Response Code during stating function in realization
Recognize image, 3 FIP that terminal is searched in images to be recognized according to the distinctive black and white saltus step rule of Quick Response Code, and then completion pair
The positioning and identification of whole Quick Response Code.In this course, in order to be able to accurately to Quick Response Code positioning and identification, it is desirable to which user is sweeping
View-finder is accurately aligned to the images to be recognized when retouching Quick Response Code, and requires that the images to be recognized occupies the main body of view-finder,
And it is required that the conditions such as perspective, twist distortion by a relatively large margin can not occurs when scanning Quick Response Code, once it is two-dimentional in identification
Terminal can not meet above-mentioned condition during code, the FIP of terminal just in images to be recognized described in None- identified, or mistakenly identify
Similar to FIP pseudo- FIP, and then cause positioning and the recognition failures of Quick Response Code.
In a step 102, after terminal collects the images to be recognized comprising Quick Response Code, terminal can be according to be identified
Image, the FIP in images to be recognized is extracted using preset grader, wherein, the grader is used for according to images to be recognized
Feature Descriptor identification FIP.
In Quick Response Code, by taking QR codes as an example, wherein 3 in 4 corners of QR codes, it is printed on less picture and " is returning " word just
Square pattern, i.e. FIP (Finder pattern), as shown in Figure 2.This 3 FIP are to aid in the pattern of decoding software positioning, meet
The geometry site of certain triangle, for example, 3 FIP of each QR code are located on three summits of QR codes respectively, structure
Into isosceles right triangle.
In addition, grader (Classifier) is a kind of computer program, its design object is by learning automatically
Afterwards, data can be assigned into known class automatically, in the present invention, the grader of terminal preset is used for the spy according to images to be recognized
Levy description son identification FIP.
Specifically, before terminal gathers the images to be recognized comprising Quick Response Code, terminal can also be in preset picture library
The FIP for extracting Quick Response Code is positive sample, and the image not comprising Quick Response Code is negative sample;And then terminal extracts the positive sample and institute
The Feature Descriptor of negative sample is stated, the Feature Descriptor at least levies (i.e. Haar features) including Lis Hartel or histogram of gradients is special
Levy;Finally, the Feature Descriptor of the positive sample and the negative sample is trained using sorting algorithm, generates the classification
Device, optionally, specifically can be trained using AdaBoost sorting algorithms to the Feature Descriptor, generate the classification
Device.
Therefore, generate after the grader, in a step 102, terminal can be extracted in the images to be recognized first
Feature Descriptor (Lis Hartel is levied or histogram of gradients feature);And then terminal uses preset FIP according to the Feature Descriptor
Grader extracts the FIP in the images to be recognized.
In step 103, after terminal extracts the FIP in the images to be recognized, institute can be determined according to the FIP
Four summits of Quick Response Code are stated, to determine the position of the Quick Response Code in the images to be recognized.
Specifically, after terminal extracts the FIP in the images to be recognized, to the Quick Response Code in the images to be recognized
Position carried out Primary Location, however, the FIP extracted is probably due to the factor such as shooting condition, computing capability of grader
Limitation produce similar to FIP pseudo- FIP, accordingly, it would be desirable to be filtered to the FIP extracted, i.e., to described to be identified
The position of Quick Response Code in image is accurately positioned.Now, terminal can according to the black and white saltus step rule of Quick Response Code, respectively with
Detection horizontally and vertically is carried out centered on each FIP extracted respectively, with filter be unsatisfactory in the FIP it is black
The pseudo- FIP of white saltus step rule;The FIP after filtering is divided into FIP groups further according to the geometry site of triangle, to determine
The position on four summits of the Quick Response Code indicated by each FIP groups, each FIP groups include three FIP.
Further, it is determined that Quick Response Code indicated by each FIP groups four summits position when, terminal can be first
The angle point of three FIP in the FIP groups is detected, the angle point set of FIP groups is formed;Further according to the angle point set and institute
The geometry site of angle point in angle point set is stated, four summits of the Quick Response Code indicated by the FIP groups are determined respectively, most
The position of the Quick Response Code in the images to be recognized is determined eventually.
Accordingly, in step 103, terminal, can also be directly according to multiple FIP position according to the multiple FIP extracted
Put four summits for determining corresponding multiple Quick Response Codes, so determine with four vertex correspondences of multiple Quick Response Codes multiple two
The region of dimension code is identified, during the region of terminal recognition Quick Response Code, if the gray level image in the region of Quick Response Code
The parameter and standard of data message in identification Quick Response Code is not met, then filters the region of the Quick Response Code, continues to recognize next two
Tie up the region of code.
For example, terminal is according to 5 FIP extracted, and then according to the geometry site of right angled triangle by described 5
FIP is divided into the first FIP groups and the 2nd FIP groups, and each FIP groups correspond to the right angle trigonometry type that 3 FIP are constituted.This
When, terminal can determine the position on four summits of the Quick Response Code indicated by the first FIP groups, i.e. the first two-dimension code area, with
And the position on four summits of the 2nd Quick Response Code indicated by FIP groups, i.e. the second two-dimension code area, terminal can be respectively to upper
State two two-dimension code areas to be identified, if the black and white that the gray level image in the first two-dimension code area does not meet identification Quick Response Code is jumped
Become rule, then filter out the first two-dimension code area, continue to recognize next two-dimension code area.
Yet further, after terminal determines the position of the Quick Response Code in the images to be recognized, further to described
Quick Response Code in the position of Quick Response Code in images to be recognized is corrected, in order to recognize that the data in the Quick Response Code are believed
Breath.
Specifically, terminal can be according to four of the Quick Response Code after four summits of the Quick Response Code and preset correction
The position relationship on individual summit, calculates the perspective matrix coefficient of the Quick Response Code;Further according to the perspective matrix coefficient, pass through matrix
Conversion and linear interpolation method are corrected to the Quick Response Code in the position of the Quick Response Code, to determine the Quick Response Code after correction
Gray level image.If in addition, the gray level image of the Quick Response Code does not meet the parameter mark of data message in identification Quick Response Code after correction
Standard, then filter the gray level image of the Quick Response Code after the correction, and the gray level image for finally obtaining correct Quick Response Code carries out data
The identification of information.
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, based on target detection principle using grader to adopting
The images to be recognized collected extracts FIP, carries out the Primary Location to Quick Response Code, and then determine the four of Quick Response Code according to the FIP
Individual summit, with the position for the Quick Response Code being accurately positioned in the images to be recognized, because the target detection principle that this programme is used can
With more easily extract images to be recognized extract FIP, it is not necessary to as the images to be recognized of existing Quick Response Code gatherer process in that
Sample, must be requested that the background that the Quick Response Code in view-finder accounts for main body and Quick Response Code is simple, terminal could be by the black and white of Quick Response Code
Saltus step rule identifies FIP, so the present invention can allow terminal to be gathered under conditions of more loosely containing one or more
The images to be recognized of Quick Response Code, further, since the present invention is after FIP is extracted, two-step method is carried out according to FIP to the position of Quick Response Code
Be accurately positioned, further increase detection discrimination of the Quick Response Code in complex scene.
Embodiment two
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, as shown in figure 3, including:
201st, the FIP that terminal extracts Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative
Sample;
202nd, terminal extracts the Feature Descriptor of positive sample and negative sample, and the Feature Descriptor is at least levied including Lis Hartel
Or histogram of gradients feature;
203rd, terminal is trained using sorting algorithm to the Feature Descriptor of positive sample and negative sample, generates grader;
204th, terminal collection includes the images to be recognized of Quick Response Code;
205th, terminal extracts the FIP in images to be recognized using preset grader, and the grader, which is used for basis, to be waited to know
The Feature Descriptor identification FIP of other image;
206th, terminal determines four summits of Quick Response Code according to FIP, to determine the position of the Quick Response Code in images to be recognized;
207th, the Quick Response Code in the position of the Quick Response Code in terminal-pair images to be recognized is corrected, in order to recognize two dimension
Data message in code.
In step 201, when user is before images to be recognized of the collection comprising Quick Response Code, terminal needs preset corresponding
Grader, to realize the extraction of FIP in Quick Response Code.Specifically, terminal first has to extract the FIP of Quick Response Code in preset picture library
For positive sample, the image not comprising Quick Response Code is negative sample.
Specifically, actual observation or a part of individual of investigation are referred to as sample (sample) in research, it is used for generate
Recognize FIP grader, terminal or computer using all images in picture library as sample, and using the FIP of Quick Response Code as
Positive sample, is negative sample by the image not comprising Quick Response Code.
In step 202., after positive sample and negative sample is established, terminal extracts the spy of the positive sample and negative sample
Description is levied, the Feature Descriptor is used for the characteristic attribute for describing sample, and exemplary, the Feature Descriptor at least includes
Lis Hartel is levied or histogram of gradients feature.
Wherein, histogram of gradients feature (HOG) be characterized in a kind of regional area descriptor it by calculating on regional area
Gradient orientation histogram carry out constitutive characteristic, it can describe the edge of object well, and to illumination variation and a small amount of inclined
Move insensitive.
Lis Hartel is levied, also referred to as Haar features, and Haar features can be divided into three classes:Edge feature, linear character, center are special
Seek peace diagonal feature, be together to form feature templates.There are white and two kinds of rectangles of black in feature templates, and define the template
Characteristic value for white rectangle pixel and subtract black rectangle pixel and, Haar characteristic values reflect the grey scale change feelings of image
Condition.
In step 203, terminal is trained using sorting algorithm to the Feature Descriptor of positive sample and negative sample, generation
Grader.
It should be noted that by performing the grader that step 201 is generated to 203 terminals obtained, can also be by calculating
Machine gathers positive sample and negative sample in the picture library of corresponding computer, and then using sorting algorithm to positive sample and negative sample
Feature Descriptor is trained generation, and computer generates after the grader, can transmit the grader to terminal, so as to
The FIP in images to be recognized is extracted using the grader in terminal.
Exemplary, AdaBoost sorting algorithms can be selected to be trained the Feature Descriptor, described point of generation
Class device.Wherein, Adaboost is a kind of iterative algorithm, and its core concept is that different graders are trained for same training set
(Weak Classifier), then gets up these weak classifier sets, constitutes a stronger final classification device (strong classifier).
Adaboost algorithm realized by change data distribution in itself, and it is according to the classification of each sample among each training set
It is whether correct, and the general classification of last time accuracy rate, to determine the weights of each sample.The new data of weights will be changed
Collection is given sub-classification device and is trained, and will finally train obtained grader finally to merge every time, is determined as last
Plan grader.Some unnecessary training data features can be excluded using adaboost graders, and training emphasis is placed on
Above crucial training data.
In step 204, after terminal establishes the grader for extracting FIP, user can be using with camera
The terminal collection of function includes the images to be recognized of Quick Response Code.
Especially, because this programme uses target detection principle to carry out being accurately positioned for two-step method to the position of Quick Response Code,
Terminal can be allowed to gather the images to be recognized containing Quick Response Code under conditions of more loosely, it is not necessary to as existing Quick Response Code
In the gatherer process of images to be recognized like that, must be requested that the Quick Response Code in view-finder accounts for main body and the background of Quick Response Code is simple.
In step 205, after terminal collects the images to be recognized comprising Quick Response Code, terminal can be according to be identified
Image, the FIP in images to be recognized is extracted using preset grader, wherein, the grader is used for according to images to be recognized
Feature Descriptor identification FIP.
Specifically, the terminal Feature Descriptor that can extract first in the images to be recognized (levy or gradient is straight by Lis Hartel
Square figure feature);And then terminal is extracted in the images to be recognized according to the Feature Descriptor using preset FIP graders
FIP.
As can be seen that compared in the prior art by the distinctive black and white saltus step rule search images to be recognized of Quick Response Code
FIP, the present invention in using generation grader extract images to be recognized in FIP, the picture to images to be recognized can be reduced
Face is required, improves FIP discrimination.
In step 206, after terminal extracts the FIP in the images to be recognized, institute can be determined according to the FIP
Four summits of Quick Response Code are stated, to determine the position of the Quick Response Code in the images to be recognized.
Step 204 completes the Primary Location of the position to the Quick Response Code in the images to be recognized to 205, that is, determines
The quantity of FIP in the images to be recognized and position.However, the FIP extracted is probably due to shooting condition, the meter of grader
The limitation of the factors such as calculation ability produces the pseudo- FIP similar to FIP, accordingly, it would be desirable to be filtered to the FIP extracted, i.e.,
The position of Quick Response Code in the images to be recognized is accurately positioned.
Specifically, terminal can be according to the black and white saltus step rule of Quick Response Code, respectively centered on each FIP extracted point
Detection horizontally and vertically is not carried out, to filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;Root again
The FIP after filtering is divided into FIP groups according to the geometry site of triangle, it is exemplary, as shown in figure 4, according to triangle
Shape both sides sum is more than the 3rd side, and the difference on both sides is less than the geometry site on the 3rd side, and end-filtration is unsatisfactory for above-mentioned geometry
The FIP of position relationship, obtains a FIP group, i.e., the first FIP groups constituted by 1,2,3.
With reference to Fig. 4, in the first FIP groups, terminal can detect in Fig. 4 three using Harris Corner Detection Algorithms
FIP all angle points, form the angle point set of the first FIP groups;And then, terminal root in the angle point set of the first FIP groups
Three summits P1, P2, P3 and two angle points C1, C2 of position as shown in Figure 4 are obtained according to the geometry site of angle point, finally,
The intersection point of straight line where by calculating P1 and C1 and P2 and C2 place straight line obtains the 4th summit P4 of Quick Response Code, so far, P1,
P2, P3, P4 be four summits of Quick Response Code, so that it is determined that the position of the Quick Response Code in the images to be recognized.
In step 207, after terminal determines the position of the Quick Response Code in the images to be recognized, further to described
Quick Response Code in the position of Quick Response Code in images to be recognized is corrected, in order to recognize that the data in the Quick Response Code are believed
Breath.
Specifically, terminal can be according to four of the Quick Response Code after four summits of the Quick Response Code and preset correction
The position relationship on individual summit, calculates the perspective matrix coefficient of the Quick Response Code;Further according to the perspective matrix coefficient, pass through matrix
Conversion and linear interpolation method are corrected to the Quick Response Code in the position of the Quick Response Code, to determine the Quick Response Code after correction
Gray level image.
It is exemplary, with reference to Fig. 4, preset in terminal four summits of the Quick Response Code after correction position P11,
P22, P33, P44, according to the four of the Quick Response Code having determined summits P1, P2, P3, P4, set up solving equations perspective matrix
Coefficient;Assuming that correction after the Quick Response Code four summits position P11, P22, P33, P44 in any point Z pixels seat
Be designated as (x, y), then terminal according to the perspective matrix coefficient, (x, y) is carried out perspective matrix conversion obtain correcting preceding P1, P2,
Coordinate Z1 corresponding with Z in Quick Response Code determined by P3, P4 (x ', y '), then to (x ', y ') obtained with linear interpolation method calculating
The gray value of (x, y), so, it is possible to the gray level image of the Quick Response Code after being corrected, carries out the identification of data message.
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, based on target detection principle using grader to adopting
The images to be recognized collected extracts FIP, carries out the Primary Location to Quick Response Code, and then determine the four of Quick Response Code according to the FIP
Individual summit, with the position for the Quick Response Code being accurately positioned in the images to be recognized, because the target detection principle that this programme is used can
With more easily extract images to be recognized extract FIP, it is not necessary to as the images to be recognized of existing Quick Response Code gatherer process in that
Sample, must be requested that the background that the Quick Response Code in view-finder accounts for main body and Quick Response Code is simple, terminal could be by the black and white of Quick Response Code
Saltus step rule identifies FIP, so the present invention can allow terminal to be gathered under conditions of more loosely containing one or more
The images to be recognized of Quick Response Code, further, since the present invention is after FIP is extracted, two-step method is carried out according to FIP to the position of Quick Response Code
Be accurately positioned, further increase detection discrimination of the Quick Response Code in complex scene.
Embodiment three
As shown in figure 5, providing a kind of hardware schematic of terminal for embodiments of the invention.
The terminal is the terminal device with camera, can be that wireless terminal can also be catv terminal, such as hand
Machine terminal, IPAD etc., the present embodiment is illustrated using mobile phone terminal as terminal:
Such as Fig. 5, institute's mobile phone terminal includes processor 01, transceiver 02, memory 03 and bus 04.
Wherein, processor 01, transceiver 02 and memory 03 are connected by bus communication.
Processor 01, is the control centre of the mobile phone terminal, and processor 01 passes through the data that are received to transceiver 02
Handled, and call the software or program in memory 03, perform the various functions of the mobile phone terminal.
Transceiver 02, during receiving and sending messages or gathering image, the reception and transmission of signal and data, transmitting-receiving
Device 02 is received after the information that mobile phone terminal is sent, and is handled to processor 01;In addition, transceiver 02 can also by radio communication with
Network and other equipment communication.
Memory 03, available for storage software program, processor 01 is stored in the software program of memory 03 by operation,
So as to perform various function application and the data processing of the mobile phone terminal.
In embodiments of the present invention, the transceiver 02 gathers the images to be recognized comprising Quick Response Code and sent to processor
01;The processor 01 calls grader preset in the memory 03 to extract the FIP in the images to be recognized, described point
Class device is used to recognize FIP according to the Feature Descriptor of images to be recognized;The processor 01 determines the two dimension according to the FIP
Four summits of code, to determine the position of the Quick Response Code in the images to be recognized, in order to recognize the position of the Quick Response Code
Interior Quick Response Code.
Further, processor 01 described in step calls grader extraction preset in the memory 03 described to be identified
FIP in image, can be specifically included:The processor 01 extracts the Feature Descriptor in the images to be recognized;And according to
The Feature Descriptor, calls FIP graders preset in the memory 03 to extract the FIP in the images to be recognized.
Further, processor 01 described in step determines four summits of the Quick Response Code according to the FIP, can be specific
Including:The processor 01 is carried out horizontal direction and hung down respectively according to the black and white saltus step rule of Quick Response Code centered on the FIP
Nogata to detection, to filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;The processor 01 is according to triangle
Geometry site the FIP after filtering is divided into FIP groups, to determine four of the Quick Response Code indicated by each FIP groups
The position on individual summit, each FIP groups include three FIP.
Further, step determines the position on four summits of the Quick Response Code indicated by each FIP groups, can specifically wrap
Include:The processor 01 detects the angle point of three FIP in the FIP groups, forms the angle point set of FIP groups;Processor 01
According to the geometry site of angle point in the angle point set and the angle point set, determine that the FIP groups are signified respectively
Four summits of the Quick Response Code shown.
Further, after processor 01 described in step determines the position of the Quick Response Code in the images to be recognized, may be used also
With including:Processor 01 is according to four summits of the Quick Response Code after four summits of the Quick Response Code and preset correction
Position relationship, calculates the perspective matrix coefficient of the Quick Response Code;Processor 01 is become according to the perspective matrix coefficient by matrix
Change and the Quick Response Code in the position of the Quick Response Code is corrected with linear interpolation method, to determine the ash of the Quick Response Code after correction
Image is spent, in order to recognize the Quick Response Code according to the gray level image of the Quick Response Code.
Further, after the gray level image of the Quick Response Code after step determines to correct, it can also include:If after correction
The gray level image of the Quick Response Code does not meet the parameter and standard of data message in identification Quick Response Code, and the processor 01 then filters institute
State the gray level image of the Quick Response Code after correction.
Further, before transceiver described in step 02 gathers the images to be recognized comprising Quick Response Code, it can also include:
The FIP that the processor 01 extracts Quick Response Code by transceiver 02 in preset picture library is positive sample, not comprising Quick Response Code
Image is negative sample;The processor 01 extracts the Feature Descriptor of the positive sample and the negative sample, the feature description
Son is at least levied or histogram of gradients feature including Lis Hartel;The processor 01 is using sorting algorithm to the positive sample and described
The Feature Descriptor of negative sample is trained, and generates the grader.
Embodiments of the invention provide a kind of terminal, to be identified to what is collected using grader based on target detection principle
Image zooming-out FIP, carries out the Primary Location to Quick Response Code, and then determines four summits of Quick Response Code according to the FIP, with accurate
The position of the Quick Response Code in the images to be recognized is positioned, because the target detection principle that this programme is used can be extracted more easily
Images to be recognized extracts FIP, it is not necessary to as in the gatherer process of the images to be recognized of existing Quick Response Code, must be requested that find a view
Quick Response Code in frame accounts for main body and the background of Quick Response Code is simple, and terminal could be identified by the black and white saltus step rule of Quick Response Code
FIP, so the present invention can allow terminal collection under conditions of more loosely to be identified containing one or more Quick Response Codes
Image, further, since the present invention is after FIP is extracted, carries out being accurately positioned for two-step method to the position of Quick Response Code according to FIP, enters
One step improves detection discrimination of the Quick Response Code in complex scene.
Example IV
Embodiments of the invention provide a kind of terminal, as shown in fig. 6, including:
Collecting unit 11, for gathering the images to be recognized for including Quick Response Code;
Extraction unit 12, for extracting the position in the images to be recognized in the collecting unit 11 using preset grader
Detection figure FIP is put, the grader is used to recognize FIP according to the Feature Descriptor of images to be recognized;
Recognition unit 13, four summits of the Quick Response Code is determined for the FIP in the extraction unit 12, with true
The position of Quick Response Code in the fixed images to be recognized, the Quick Response Code in position in order to recognize the Quick Response Code.
Further, the extraction unit 12, specifically for extracting the Feature Descriptor in the images to be recognized;According to
The Feature Descriptor, the FIP in the images to be recognized is extracted using preset FIP graders.
Further, the recognition unit 13, specifically for the black and white saltus step rule according to Quick Response Code, using the FIP as
Center carries out detection horizontally and vertically respectively, to filter the puppet that black and white saltus step rule is unsatisfactory in the FIP
FIP;FIP after filtering is divided into by FIP groups according to the geometry site of triangle, to determine that each FIP groups are signified
The position on four summits of the Quick Response Code shown, each FIP groups include three FIP.
Further, the recognition unit 13, the angle point specifically for detecting three FIP in the FIP groups, is formed
The angle point set of FIP groups;It is true respectively according to the geometry site of angle point in the angle point set and the angle point set
Four summits of the Quick Response Code indicated by the fixed FIP groups.
Further, as shown in fig. 7, the terminal also includes correction unit 14, wherein,
The correction unit 14, four summits and preset correction for the Quick Response Code in the recognition unit 13
The position relationship on four summits of the Quick Response Code afterwards, calculates the perspective matrix coefficient of the Quick Response Code;According to the perspective
Matrix coefficient, is corrected by matrixing and linear interpolation method to the Quick Response Code in the position of the Quick Response Code, to determine
The gray level image of the Quick Response Code after correction, in order to recognize the Quick Response Code according to the gray level image of the Quick Response Code.
Further, as shown in figure 8, the terminal also includes filter element 15, wherein,
The filter element 15, if the gray level image of the Quick Response Code does not meet data in identification Quick Response Code after for correcting
The parameter and standard of information, then filter the gray level image of the Quick Response Code after the correction.
Further, the extraction unit 12, the FIP for being additionally operable to extract Quick Response Code in preset picture library is positive sample,
Image not comprising Quick Response Code is negative sample;The Feature Descriptor of the positive sample and the negative sample is extracted, the feature is retouched
Son is stated at least to levy including Lis Hartel or histogram of gradients feature;Using sorting algorithm to the positive sample and the spy of the negative sample
Levy description to be trained, generate the grader.
Embodiments of the invention provide a kind of terminal, to be identified to what is collected using grader based on target detection principle
Image zooming-out FIP, carries out the Primary Location to Quick Response Code, and then determines four summits of Quick Response Code according to the FIP, with accurate
The position of the Quick Response Code in the images to be recognized is positioned, because the target detection principle that this programme is used can be extracted more easily
Images to be recognized extracts FIP, it is not necessary to as in the gatherer process of the images to be recognized of existing Quick Response Code, must be requested that find a view
Quick Response Code in frame accounts for main body and the background of Quick Response Code is simple, and terminal could be identified by the black and white saltus step rule of Quick Response Code
FIP, so the present invention can allow terminal collection under conditions of more loosely to be identified containing one or more Quick Response Codes
Image, further, since the present invention is after FIP is extracted, carries out being accurately positioned for two-step method to the position of Quick Response Code according to FIP, enters
One step improves detection discrimination of the Quick Response Code in complex scene.
It is apparent to those skilled in the art that, for convenience and simplicity of description, only with above-mentioned each function
The division progress of module is for example, in practical application, as needed can distribute above-mentioned functions by different function moulds
Block is completed, i.e., the internal structure of device is divided into different functional modules, to complete all or part of work(described above
Energy.The specific work process of the system, apparatus, and unit of foregoing description, may be referred to corresponding in preceding method embodiment
Journey, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the module or
The division of unit, only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units
Or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, institute
Display or the coupling each other discussed or direct-coupling or communication connection can be by some interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially
The part contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the present invention each
The all or part of step of embodiment methods described.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD
Etc. it is various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (12)
1. a kind of recognition methods of Quick Response Code, it is characterised in that including:
Collection includes the images to be recognized of Quick Response Code;
The position sensing figure FIP in the images to be recognized is extracted using preset grader, the grader is used for basis
The Feature Descriptor identification FIP of images to be recognized;
Four summits of the Quick Response Code are determined according to the FIP, to determine the position of the Quick Response Code in the images to be recognized,
The Quick Response Code in position in order to recognize the Quick Response Code;
Wherein, four summits that the Quick Response Code is determined according to the FIP, including:
According to the black and white saltus step rule of Quick Response Code, detection horizontally and vertically is carried out respectively centered on the FIP,
To filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;
FIP after filtering is divided into by FIP groups according to the geometry site of triangle, to determine that each FIP groups are signified
The position on four summits of the Quick Response Code shown, each FIP groups include three FIP, and the geometric position of the triangle is closed
System refers to that triangle both sides sum is more than the 3rd side, and the difference on both sides is less than the 3rd side.
2. according to the method described in claim 1, it is characterised in that described to extract the figure to be identified using preset grader
FIP as in, including:
Extract the Feature Descriptor in the images to be recognized;
According to the Feature Descriptor, the FIP in the images to be recognized is extracted using preset FIP graders.
3. according to the method described in claim 1, it is characterised in that described to determine Quick Response Code indicated by each FIP groups
The position on four summits, including:
The angle point of three FIP in the FIP groups is detected, the angle point set of FIP groups is formed;
According to the geometry site of angle point in the angle point set and the angle point set, the FIP groups are determined respectively
Four summits of indicated Quick Response Code.
4. according to the method described in claim 1, it is characterised in that in the Quick Response Code determined in the images to be recognized
After position, in addition to:
According to the position relationship on four summits of the Quick Response Code behind the four of the Quick Response Code summits and preset correction, meter
Calculate the perspective matrix coefficient of the Quick Response Code;
According to the perspective matrix coefficient, by matrixing and linear interpolation method to the Quick Response Code in the position of the Quick Response Code
It is corrected, to determine the gray level image of the Quick Response Code after correction, in order to be recognized according to the gray level image of the Quick Response Code
The Quick Response Code.
5. method according to claim 4, it is characterised in that the gray level image of the Quick Response Code after the determination correction
Afterwards, in addition to:
If the gray level image of the Quick Response Code does not meet the parameter and standard of data message in identification Quick Response Code after correction, institute is filtered
State the gray level image of the Quick Response Code after correction.
6. according to the method described in claim 1, it is characterised in that the images to be recognized of the collection comprising Quick Response Code it
Before, in addition to:
The FIP that Quick Response Code is extracted in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample;
The Feature Descriptor of the positive sample and the negative sample is extracted, the Feature Descriptor is at least levied or ladder including Lis Hartel
Spend histogram feature;
The Feature Descriptor of the positive sample and the negative sample is trained using sorting algorithm, the grader is generated.
7. a kind of identification terminal of Quick Response Code, it is characterised in that including:
Collecting unit, for gathering the images to be recognized for including Quick Response Code;
Extraction unit, for extracting the position sensing figure in the images to be recognized in the collecting unit using preset grader
Shape FIP, the grader is used to recognize FIP according to the Feature Descriptor of images to be recognized;
Recognition unit, four summits of the Quick Response Code are determined for the FIP in the extraction unit, to determine described treat
Recognize the position of the Quick Response Code in image, the Quick Response Code in position in order to recognize the Quick Response Code;
Wherein, the recognition unit, specifically for the black and white saltus step rule according to Quick Response Code, is entered respectively centered on the FIP
The detection of row horizontally and vertically, to filter the pseudo- FIP that black and white saltus step rule is unsatisfactory in the FIP;According to triangle
FIP after filtering is divided into FIP groups by the geometry site of shape, to determine the Quick Response Code indicated by each FIP groups
The position on four summits, each FIP groups include three FIP, and the geometry site of the triangle refers to triangle
Both sides sum is more than the 3rd side, and the difference on both sides is less than the 3rd side.
8. the identification terminal of Quick Response Code according to claim 7, it is characterised in that
The extraction unit, specifically for extracting the Feature Descriptor in the images to be recognized;According to the Feature Descriptor,
The FIP in the images to be recognized is extracted using preset FIP graders.
9. the identification terminal of Quick Response Code according to claim 7, it is characterised in that
The recognition unit, the angle point specifically for detecting three FIP in the FIP groups, forms the angle point collection of FIP groups
Close;According to the geometry site of angle point in the angle point set and the angle point set, the institute of FIP groups is determined respectively
Four summits of the Quick Response Code of instruction.
10. the identification terminal of Quick Response Code according to claim 7, it is characterised in that the terminal also includes correction unit,
Wherein,
The correction unit, four for the Quick Response Code behind four summits according to the Quick Response Code and preset correction
The position relationship on summit, calculates the perspective matrix coefficient of the Quick Response Code;According to the perspective matrix coefficient, pass through matrixing
The Quick Response Code in the position of the Quick Response Code is corrected with linear interpolation method, to determine the gray scale of the Quick Response Code after correction
Image, in order to recognize the Quick Response Code according to the gray level image of the Quick Response Code.
11. the identification terminal of Quick Response Code according to claim 10, it is characterised in that it is single that the terminal also includes filtering
Member, wherein,
The filter element, if the gray level image of the Quick Response Code does not meet data message in identification Quick Response Code after for correcting
Parameter and standard, then filter the gray level image of the Quick Response Code after the correction.
12. the identification terminal of Quick Response Code according to claim 7, it is characterised in that
The extraction unit, the FIP for being additionally operable to extract Quick Response Code in preset picture library is positive sample, the figure not comprising Quick Response Code
As being negative sample;The Feature Descriptor of the positive sample and the negative sample is extracted, the Feature Descriptor at least includes Ha Er
Feature or histogram of gradients feature;The Feature Descriptor of the positive sample and the negative sample is instructed using sorting algorithm
Practice, generate the grader.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410514458.9A CN104268498B (en) | 2014-09-29 | 2014-09-29 | A kind of recognition methods of Quick Response Code and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410514458.9A CN104268498B (en) | 2014-09-29 | 2014-09-29 | A kind of recognition methods of Quick Response Code and terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104268498A CN104268498A (en) | 2015-01-07 |
CN104268498B true CN104268498B (en) | 2017-09-19 |
Family
ID=52160018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410514458.9A Active CN104268498B (en) | 2014-09-29 | 2014-09-29 | A kind of recognition methods of Quick Response Code and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104268498B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI854622B (en) | 2023-03-01 | 2024-09-01 | 神基科技股份有限公司 | Barcode image recogniztion method and device using the same |
Families Citing this family (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104766037A (en) * | 2015-03-20 | 2015-07-08 | 中国联合网络通信集团有限公司 | Two-dimension code recognition method and device |
CN104951726B (en) * | 2015-06-25 | 2017-12-08 | 福建联迪商用设备有限公司 | Method and device for QR Quick Response Code position sensings |
CN107194301A (en) * | 2016-03-15 | 2017-09-22 | 中兴通讯股份有限公司 | A kind of recognition methods of Quick Response Code and device |
CN106156685A (en) * | 2016-07-07 | 2016-11-23 | 立德高科(昆山)数码科技有限责任公司 | The method of multiple Quick Response Codes, device and the terminal that recognition is in the same area |
CN106897648B (en) * | 2016-07-22 | 2020-01-31 | 阿里巴巴集团控股有限公司 | Method and system for identifying position of two-dimensional code |
CN107220577A (en) * | 2017-05-12 | 2017-09-29 | 广州智慧城市发展研究院 | A kind of Quick Response Code localization method and system based on machine learning |
CN107203798B (en) * | 2017-05-24 | 2019-10-01 | 南京邮电大学 | A kind of generation and recognition methods limiting access type figure ground two dimensional code |
EP3428834B1 (en) | 2017-07-12 | 2019-06-12 | Sick AG | Optoelectronic code reader and method for reading optical codes |
CN107578250B (en) * | 2017-07-17 | 2023-06-16 | 中国农业大学 | Two-dimensional code anti-counterfeiting method and system |
CN107832652A (en) * | 2017-09-28 | 2018-03-23 | 努比亚技术有限公司 | Two-dimensional code identification method, terminal and computer-readable recording medium |
CN107818282B (en) * | 2017-09-30 | 2020-04-28 | 努比亚技术有限公司 | Two-dimensional code identification method, terminal and computer readable storage medium |
CN107798521A (en) * | 2017-11-15 | 2018-03-13 | 上海捷售智能科技有限公司 | A kind of vegetable identification and POS and method based on machine code image recognition |
CN108388822B (en) * | 2018-01-25 | 2021-03-23 | 微梦创科网络科技(中国)有限公司 | Method and device for detecting two-dimensional code image |
CN108961262B (en) * | 2018-05-17 | 2023-04-18 | 南京汇川工业视觉技术开发有限公司 | Bar code positioning method in complex scene |
CN110516494B (en) * | 2018-05-22 | 2023-10-10 | 杭州海康威视数字技术股份有限公司 | Two-dimensional code identification method, device, equipment and system |
CN109190439B (en) * | 2018-09-21 | 2021-06-08 | 南京机灵侠软件技术有限公司 | Optical splitter and port line label two-dimensional code identification method thereof |
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 |
CN109934249A (en) * | 2018-12-14 | 2019-06-25 | 网易(杭州)网络有限公司 | Data processing method, device, medium and calculating equipment |
CN109815763A (en) * | 2019-01-04 | 2019-05-28 | 广州广电研究院有限公司 | Detection method, device and the storage medium of two dimensional code |
CN109993877B (en) * | 2019-03-07 | 2021-11-02 | 北京航天泰坦科技股份有限公司 | Anti-counterfeiting invoice identification method based on position information |
CN111753578A (en) * | 2019-03-27 | 2020-10-09 | 北京外号信息技术有限公司 | Identification method of optical communication device and corresponding electronic equipment |
CN110334560B (en) * | 2019-07-16 | 2023-04-07 | 山东浪潮科学研究院有限公司 | Two-dimensional code positioning method and device |
CN110399956A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | The method, apparatus of two dimensional code, electronic equipment and medium for identification |
CN110490020B (en) * | 2019-07-31 | 2023-01-13 | 珠海市杰理科技股份有限公司 | Bar code identification method and device, computer equipment and storage medium |
CN110807342B (en) * | 2019-10-18 | 2023-08-11 | 珠海市杰理科技股份有限公司 | Bar code positioning method, bar code positioning device, computer equipment and storage medium |
CN110969043A (en) * | 2019-11-25 | 2020-04-07 | 深圳创新奇智科技有限公司 | Two-dimensional code detection system and method based on key point detection |
CN111179427A (en) * | 2019-12-24 | 2020-05-19 | 深圳市优必选科技股份有限公司 | Autonomous mobile device, control method thereof, and computer-readable storage medium |
CN111523342A (en) * | 2020-04-26 | 2020-08-11 | 成都艾视特信息技术有限公司 | Two-dimensional code detection and correction method in complex scene |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710407A (en) * | 2009-12-29 | 2010-05-19 | 江西科技师范学院 | Payment method capable of consumption payment by mobile phone on basis of two-dimension code and payment system thereof |
CN103488966A (en) * | 2013-09-04 | 2014-01-01 | 张家港保税区润桐电子技术研发有限公司 | Intelligent mobile phone capable of identifying real-name ticket information |
CN103699869A (en) * | 2013-12-30 | 2014-04-02 | 优视科技有限公司 | Method and device for recognizing two-dimension codes |
CN103914675A (en) * | 2014-03-17 | 2014-07-09 | 东华大学 | Garment QD code recognition method |
-
2014
- 2014-09-29 CN CN201410514458.9A patent/CN104268498B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710407A (en) * | 2009-12-29 | 2010-05-19 | 江西科技师范学院 | Payment method capable of consumption payment by mobile phone on basis of two-dimension code and payment system thereof |
CN103488966A (en) * | 2013-09-04 | 2014-01-01 | 张家港保税区润桐电子技术研发有限公司 | Intelligent mobile phone capable of identifying real-name ticket information |
CN103699869A (en) * | 2013-12-30 | 2014-04-02 | 优视科技有限公司 | Method and device for recognizing two-dimension codes |
CN103914675A (en) * | 2014-03-17 | 2014-07-09 | 东华大学 | Garment QD code recognition method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI854622B (en) | 2023-03-01 | 2024-09-01 | 神基科技股份有限公司 | Barcode image recogniztion method and device using the same |
Also Published As
Publication number | Publication date |
---|---|
CN104268498A (en) | 2015-01-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104268498B (en) | A kind of recognition methods of Quick Response Code and terminal | |
CN110060237B (en) | Fault detection method, device, equipment and system | |
CN103065134B (en) | A kind of fingerprint identification device and method with information | |
CN105184778B (en) | Detection method and device | |
CN112528831B (en) | Multi-target attitude estimation method, multi-target attitude estimation device and terminal equipment | |
CN107122806A (en) | A kind of nude picture detection method and device | |
CN104809452A (en) | Fingerprint identification method | |
CN104809464A (en) | Fingerprint information processing method | |
CN104809453A (en) | Authentication method based on fingerprints | |
CN111626163B (en) | Human face living body detection method and device and computer equipment | |
CN106886774A (en) | The method and apparatus for recognizing ID card information | |
CN108009536A (en) | Scan method to go over files and system | |
CN112633084B (en) | Face frame determining method and device, terminal equipment and storage medium | |
CN110796135B (en) | Target positioning method and device, computer equipment and computer storage medium | |
CN107272899B (en) | VR (virtual reality) interaction method and device based on dynamic gestures and electronic equipment | |
CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
CN111191582A (en) | Three-dimensional target detection method, detection device, terminal device and computer-readable storage medium | |
CN108090486A (en) | Image processing method and device in a kind of game of billiards | |
CN114445843A (en) | Card image character recognition method and device of fixed format | |
CN112560584A (en) | Face detection method and device, storage medium and terminal | |
CN112307944A (en) | Dish inventory information processing method, dish delivery method and related device | |
CN111382638B (en) | Image detection method, device, equipment and storage medium | |
CN113763307B (en) | Sample data acquisition method and device | |
CN113538291A (en) | Card image tilt correction method and device, computer equipment and storage medium | |
CN113191189A (en) | Face living body detection method, terminal device and computer readable storage medium |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200422 Address after: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Patentee after: HUAWEI TECHNOLOGIES Co.,Ltd. Address before: 301, A building, room 3, building 301, foreshore Road, No. 310052, Binjiang District, Zhejiang, Hangzhou Patentee before: Huawei Technologies Co.,Ltd. |
|
TR01 | Transfer of patent right |