CN104268498A - Two-dimension code recognition method and terminal - Google Patents
Two-dimension code recognition method and terminal Download PDFInfo
- Publication number
- CN104268498A CN104268498A CN201410514458.9A CN201410514458A CN104268498A CN 104268498 A CN104268498 A CN 104268498A CN 201410514458 A CN201410514458 A CN 201410514458A CN 104268498 A CN104268498 A CN 104268498A
- Authority
- CN
- China
- Prior art keywords
- quick response
- response code
- fip
- image
- identified
- 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.)
- Granted
Links
Abstract
The embodiment of the invention provides a two-dimension code recognition method and terminal and relates to the field of electronic techniques. According to the two-dimension code recognition method and terminal, the terminal is allowed to carry out recognition of one or more two-dimension codes under a looser condition, and the detection and recognition rate of the two-dimension codes in a complex scene is increased. The method comprises the steps of collecting an image, containing a two-dimension code, to be recognized; extracting FIP in the image to be recognized by using a preset classifier, wherein the classifier is used for recognizing the FIP according to the character descriptors of the image to be recognized; determining the four vertexes of the two-dimension code according to the FIP so as to determine the position of the two-dimension code in the image to be recognized, and recognizing the two-dimension code in the position of the two-dimension code.
Description
Technical field
The present invention relates to electronic technology field, particularly relate to a kind of recognition methods and terminal of Quick Response Code.
Background technology
Quick Response Code (Two-dimensional code), it is the chequered with black and white figure distributed in the two-dimensional direction according to certain rules with specific geometric figure, the geometrical body that it uses several corresponding with scale-of-two, to represent word numerical information, is processed to realize information automatically by terminal automatically identifying and reading.Compared with one-dimension code, Quick Response Code is a kind of barcode standard more senior than one-dimension code, and Quick Response Code can store information in horizontal and vertical direction, and Quick Response Code can store the information such as Chinese character, numeral and picture, and therefore the application of Quick Response Code wants much wide.
QR (Quick Response) code is a kind of Quick Response Code of current widespread use, and it has, and recognition speed is fast, packing density large, take up room little advantage, can effectively represent Chinese character, Japanese kanji.Include three FIP (finder pattern, position sensing figure) in each QR code, and lay respectively on foursquare three summits, as the square pattern of " returning " word, these 3 FIP are patterns of the decoding software work location for terminal.In the prior art, after terminal obtains image to be identified by view-finder, the FIP in image to be identified is searched in the images according to Quick Response Code distinctive black and white saltus step rule, after finding three FIP, namely located the position of QR code, and then read the data message in the position of this QR code by the decoding software of terminal.
But, in the identifying of above-mentioned Quick Response Code, require that view-finder is aimed at image to be identified when scanning Quick Response Code by the holder of terminal, and require the other guide do not comprised in this image to be identified beyond Quick Response Code, above-mentioned requirements (namely in complex scene) can not be met once in identification Quick Response Code terminal, just the FIP in the above-mentioned image to be identified of identification that cannot be correct, and then cause location and the recognition failures of Quick Response Code.
Summary of the invention
Embodiments of the invention provide a kind of recognition methods and terminal of Quick Response Code, allow terminal under looser condition, carry out the identification of one or more Quick Response Code, improve the detection discrimination of Quick Response Code in complex scene.
For achieving the above object, embodiments of the invention adopt following technical scheme:
First aspect, embodiments of the invention provide a kind of recognition methods of Quick Response Code, comprising:
Gather the image to be identified comprising Quick Response Code;
Use the position sensing figure FIP in the preset described image to be identified of sorter extraction, described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
Determine four summits of described Quick Response Code according to described FIP, to determine the position of the Quick Response Code in described image to be identified, and the Quick Response Code of distortion is corrected, so that identify the Quick Response Code in the position of described Quick Response Code.
In conjunction with first aspect, in the first possible implementation of first aspect, the FIP in the described image to be identified of sorter extraction that described use is preset, comprising:
Extract the Feature Descriptor in described image to be identified;
According to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
In conjunction with first aspect, in the implementation that the second of first aspect is possible, described four summits determining described Quick Response Code according to described FIP, comprising:
According to the black and white saltus step rule of Quick Response Code, centered by described FIP, carry out the detection of horizontal direction and vertical direction respectively, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule;
According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
In conjunction with the implementation that the second of aforesaid first aspect is possible, in the third possible implementation of first aspect, the described position determining four summits of the Quick Response Code indicated by each FIP group, comprising:
Detect the angle point of three FIP in described FIP group, form the angle point set of FIP group;
According to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively.
In conjunction with first aspect, in the 4th kind of possible implementation of first aspect, described determine the position of the Quick Response Code in described image to be identified after, also comprise:
According to the position relationship on four summits of the described Quick Response Code behind four summits of described Quick Response Code and preset correction, calculate the perspective matrix coefficient of described Quick Response Code;
According to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
In conjunction with the 4th kind of possible implementation of aforesaid first aspect, in the 5th kind of possible implementation of first aspect, described determine correct after described Quick Response Code gray level image after, also comprise:
If the gray level image of described Quick Response Code does not meet the parameter and standard identifying data message in Quick Response Code after correcting, then filter the gray level image of the Quick Response Code after described correction.
In conjunction with first aspect, in the 6th kind of possible implementation of first aspect, comprise the image to be identified of Quick Response Code in described collection before, also comprise:
The FIP extracting Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample;
Extract the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature;
Use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter.
Second aspect, embodiments of the invention provide a kind of terminal, comprising:
Collecting unit, for gathering the image to be identified comprising Quick Response Code;
Extraction unit, the position sensing figure FIP in the image to be identified extracting in described collecting unit for using preset sorter, described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
Recognition unit, for determining four summits of described Quick Response Code according to the FIP in described extraction unit, to determine the position of the Quick Response Code in described image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code.
In conjunction with second aspect, in the first possible implementation of second aspect,
Described extraction unit, specifically for extracting the Feature Descriptor in described image to be identified; According to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
In conjunction with second aspect, in the implementation that the second of second aspect is possible,
Described recognition unit, specifically for the black and white saltus step rule according to Quick Response Code, carries out the detection of horizontal direction and vertical direction respectively centered by described FIP, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule; According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
In conjunction with the implementation that the second of aforesaid second aspect is possible, in the third possible implementation of second aspect,
Described recognition unit, specifically for detecting the angle point of three FIP in described FIP group, forms the angle point set of FIP group; According to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively.
In conjunction with second aspect, in the 4th kind of possible implementation of second aspect, described terminal also comprises correcting unit, wherein,
Described correcting unit, for the position relationship on four summits according to the described Quick Response Code behind four summits of described Quick Response Code and preset correction, calculates the perspective matrix coefficient of described Quick Response Code; According to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
In conjunction with the 4th kind of possible implementation of aforesaid second aspect, in the 5th kind of possible implementation of second aspect, described terminal also comprises filter element, wherein,
Described filter element, if do not meet for the gray level image correcting rear described Quick Response Code the parameter and standard identifying data message in Quick Response Code, then filters the gray level image of the Quick Response Code after described correction.
In conjunction with second aspect, in the 6th kind of possible implementation of second aspect,
Described extraction unit, be also positive sample for extracting the FIP of Quick Response Code in preset picture library, the image not comprising Quick Response Code is negative sample; Extract the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature; Use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter.
Embodiments of the invention provide a kind of recognition methods and terminal of Quick Response Code, based target Cleaning Principle uses sorter to the image zooming-out FIP to be identified collected, carry out the Primary Location to Quick Response Code, and then four summits of Quick Response Code are determined according to described FIP, accurately to locate the position of the Quick Response Code in this image to be identified, the target detection principle adopted due to this programme can extract image zooming-out FIP to be identified more easily, need not as in the gatherer process of the image to be identified of existing Quick Response Code, the Quick Response Code in view-finder is necessarily required to account for main body and the background of Quick Response Code is simple, terminal just identifies FIP by the black and white saltus step rule of Quick Response Code, so the present invention can allow terminal to gather the image to be identified containing one or more Quick Response Code under looser condition, in addition, because the present invention is after extraction FIP, according to FIP, the position of Quick Response Code is carried out to the accurate location of two-step approach, further increase the detection discrimination of Quick Response Code in complex scene.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The schematic diagram one of the recognition methods of a kind of Quick Response Code that Fig. 1 provides for the embodiment of the present invention;
Fig. 2 is the schematic diagram of FIP in Quick Response Code;
The schematic diagram two of the recognition methods of a kind of Quick Response Code that Fig. 3 provides for the embodiment of the present invention;
Fig. 4 is the schematic diagram calculating Quick Response Code vertex position in the present invention;
The hardware schematic diagram of a kind of terminal that Fig. 5 provides for the embodiment of the present invention;
The structural representation one of a kind of terminal that Fig. 6 provides for the embodiment of the present invention;
The structural representation two of a kind of terminal that Fig. 7 provides for the embodiment of the present invention;
The structural representation three of a kind of terminal that Fig. 8 provides for the embodiment of the present invention.
Embodiment
In below describing, in order to illustrate instead of in order to limit, propose the detail of such as particular system structure, interface, technology and so on, thoroughly to understand the present invention.But, it will be clear to one skilled in the art that and also can realize the present invention in other embodiment not having these details.In other situation, omit the detailed description to well-known device, circuit and method, in order to avoid unnecessary details hinders description of the invention.
Terminal can be wireless terminal also can be catv terminal, and wireless terminal can be point to the equipment that user provides voice and/or data connectivity, has the portable equipment of wireless connecting function or is connected to other treatment facilities of radio modem.
Embodiment one
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, as shown in Figure 1, comprising:
101, terminal collection comprises the image to be identified of Quick Response Code;
102, terminal uses preset sorter to extract FIP in image to be identified, and described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
103, terminal determines four summits of Quick Response Code according to FIP, to determine the position of the Quick Response Code in image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code.
Concrete, in a step 101, when user needs by terminal recognition Quick Response Code, but use the terminal collection with camera function to comprise the image to be identified of Quick Response Code.
Wherein, Quick Response Code is also known as two-dimensional bar code, and it is the chequered with black and white figure with the distribution in plane (two-dimensional directional) according to certain rules of specific geometric figure, can store the information such as word, image, fingerprint, signature in limited space.The coding of Quick Response Code make use of the concept of " 0 ", " 1 " bit stream forming computer-internal logical foundations dexterously, the geometrical body using several corresponding with scale-of-two, to represent word numerical information, is processed to realize information automatically by the identification of terminal.
Quick Response Code is a kind of barcode standard more senior than one-dimension code.One-dimension code can only go up expressing information a direction (being generally horizontal direction), and Quick Response Code can store information in horizontal and vertical direction.One-dimension code can only be made up of numeral and letter, and Quick Response Code can store the information such as Chinese character, numeral and picture, and therefore the application of Quick Response Code wants much wide.In modern commerce activity, the attainable application of Quick Response Code is very extensive, as: product false proof/trace to the source, advertisement pushing, web site url, data download, commodity transaction, location/navigation, electronic certificate, vehicle management, information transmission, business card interchange, wifi share.
But, in the prior art, user states in the process of function the image to be identified that first will scan containing Quick Response Code in realization, and terminal searches for 3 FIP in image to be identified according to Quick Response Code distinctive black and white saltus step rule, and then the location completed whole Quick Response Code and identification.In this course, in order to accurately locate Quick Response Code and identify, require that view-finder is aimed at this image to be identified when scanning Quick Response Code by user accurately, and require that this image to be identified occupies the main body of view-finder, and require the condition such as perspective, twist distortion that can not occur when scanning Quick Response Code by a relatively large margin, above-mentioned condition can not be met once in identification Quick Response Code terminal, the FIP of terminal just in image to be identified described in None-identified, or identify the pseudo-FIP being similar to FIP mistakenly, and then cause location and the recognition failures of Quick Response Code.
In a step 102, after terminal collects the image to be identified comprising Quick Response Code, terminal can according to image to be identified, uses preset sorter to extract FIP in image to be identified, wherein, described sorter is used for the Feature Descriptor identification FIP according to image to be identified.
In Quick Response Code, for QR code, at wherein 3 of 4 corners of QR code, be printed on the square pattern that less picture " returns " word, i.e. FIP (Finder pattern), as shown in Figure 2.These 3 FIP are the patterns helping decoding software location, and meet certain leg-of-mutton geometry site, such as, 3 FIP of each QR code lay respectively on three summits of QR code, form isosceles right triangle.
In addition, sorter (Classifier) is a kind of computer program, and its design object is after by automatic learning, automatically data can be assigned to known class, in the present invention, the sorter of terminal preset is used for the Feature Descriptor identification FIP according to image to be identified.
Concrete, comprise the image to be identified of Quick Response Code in terminal collection before, the FIP that terminal can also extract Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample; And then terminal extracts the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies (i.e. Haar feature) or histogram of gradients feature; Finally, use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter, optionally, AdaBoost sorting algorithm specifically can be adopted to train described Feature Descriptor, generate described sorter.
Therefore, after generating described sorter, in a step 102, first terminal can extract the Feature Descriptor (Lis Hartel is levied or histogram of gradients feature) in described image to be identified; And then terminal is according to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
In step 103, when after the FIP that terminal is extracted in described image to be identified, four summits of described Quick Response Code can be determined according to described FIP, to determine the position of the Quick Response Code in described image to be identified.
Concrete, when after the FIP that terminal is extracted in described image to be identified, Primary Location has been carried out to the position of the Quick Response Code in described image to be identified, but, the FIP extracted may because the restriction of the factors such as the computing power of shooting condition, sorter produces the pseudo-FIP being similar to FIP, therefore, needing the FIP to having extracted to filter, namely the position of the Quick Response Code in described image to be identified accurately being located.Now, terminal according to the black and white saltus step rule of Quick Response Code, can carry out the detection of horizontal direction and vertical direction respectively, respectively to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule centered by each FIP extracted; According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group again, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
Further, when determining the position on four summits of the Quick Response Code indicated by each FIP group, terminal first can detect the angle point of three FIP in described FIP group, forms the angle point set of FIP group; Again according to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively, finally determine the position of the Quick Response Code in described image to be identified.
Accordingly, in step 103, terminal is according to the multiple FIP extracted, four summits of corresponding multiple Quick Response Code directly can also be determined according to the position of multiple FIP, and then determine and to identify with the region of multiple Quick Response Codes of four of multiple Quick Response Code vertex correspondence, in the process in the region of terminal recognition Quick Response Code, if the gray level image in the region of Quick Response Code does not meet the parameter and standard identifying data message in Quick Response Code, then filter the region of described Quick Response Code, continue the region identifying next Quick Response Code.
Such as, described 5 FIP according to extract 5 FIP, and then are divided into a FIP group and the 2nd FIP group according to the geometry site of right-angle triangle by terminal, and each FIP group corresponds to the right angle trigonometry type that 3 FIP are formed.Now, terminal can determine the position on four summits of the Quick Response Code indicated by a FIP group, i.e. the first two-dimension code area, and the 2nd position on four summits of Quick Response Code indicated by FIP group, i.e. the second two-dimension code area, terminal can identify above-mentioned two two-dimension code area respectively, if the gray level image in the first two-dimension code area does not meet the black and white saltus step rule identifying Quick Response Code, then the first two-dimension code area is filtered out, continue to identify next two-dimension code area.
Again further, after terminal determines the position of the Quick Response Code in described image to be identified, further the Quick Response Code in the position of the Quick Response Code in described image to be identified is corrected, so that identify the data message in described Quick Response Code.
Concrete, terminal according to the position relationship on four summits of the described Quick Response Code after four of a described Quick Response Code summit and preset correction, can calculate the perspective matrix coefficient of described Quick Response Code; Again according to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, to determine the gray level image correcting rear described Quick Response Code.In addition, if the gray level image of described Quick Response Code does not meet the parameter and standard identifying data message in Quick Response Code after correcting, then filter the gray level image of the Quick Response Code after described correction, the final gray level image obtaining correct Quick Response Code carries out the identification of data message.
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, based target Cleaning Principle uses sorter to the image zooming-out FIP to be identified collected, carry out the Primary Location to Quick Response Code, and then four summits of Quick Response Code are determined according to described FIP, accurately to locate the position of the Quick Response Code in this image to be identified, the target detection principle adopted due to this programme can extract image zooming-out FIP to be identified more easily, need not as in the gatherer process of the image to be identified of existing Quick Response Code, the Quick Response Code in view-finder is necessarily required to account for main body and the background of Quick Response Code is simple, terminal just identifies FIP by the black and white saltus step rule of Quick Response Code, so the present invention can allow terminal to gather the image to be identified containing one or more Quick Response Code under looser condition, in addition, because the present invention is after extraction FIP, according to FIP, the position of Quick Response Code is carried out to the accurate location of two-step approach, further increase the detection discrimination of 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, comprising:
201, terminal extracts the FIP of Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample;
202, terminal extracts the Feature Descriptor of positive sample and negative sample, and described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature;
203, the Feature Descriptor that terminal uses sorting algorithm to align sample and negative sample is trained, and generates sorter;
204, terminal collection comprises the image to be identified of Quick Response Code;
205, terminal uses preset sorter to extract FIP in image to be identified, and described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
206, terminal determines four summits of Quick Response Code according to FIP, to determine the position of the Quick Response Code in image to be identified;
207, the Quick Response Code that terminal is treated in the position of the Quick Response Code in recognition image corrects, so that identify the data message in Quick Response Code.
In step 201, when user is before collection comprises the image to be identified of Quick Response Code, terminal needs preset corresponding sorter, to realize the extraction of FIP in Quick Response Code.Concrete, the FIP that first terminal will extract Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample.
Concrete, the part individuality of actual observation or investigation in research is called sample (sample), in order to generate the sorter for identifying FIP, terminal or computing machine using all images in picture library as sample, and using the FIP of Quick Response Code as being positive sample, be negative sample by the image not comprising Quick Response Code.
In step 202., after establishing positive sample and negative sample, terminal extracts the Feature Descriptor of described positive sample and negative sample, and described Feature Descriptor is for describing the characteristic attribute of sample, exemplary, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature.
Wherein, histogram of gradients feature (HOG) feature be a kind of regional area descriptor it carry out constitutive characteristic by the gradient orientation histogram calculated on regional area, it can describe the edge of object well, and insensitive to the skew of illumination variation and a small amount of.
Lis Hartel is levied, and also referred to as Haar feature, Haar feature can be divided three classes: edge feature, linear feature, central feature and diagonal line feature, be together to form feature templates.Adularescent and black two kinds of rectangles in feature templates, and the eigenwert defining this template be white rectangle pixel and deduct black rectangle pixel and, Haar eigenwert reflects the grey scale change situation of image.
In step 203, the Feature Descriptor that terminal uses sorting algorithm to align sample and negative sample is trained, and generates sorter.
It should be noted that, by performing the sorter that step 201 generates to 203 terminals obtained, also can by the positive sample in the picture library of the corresponding computing machine of computer acquisition and negative sample, and then the Feature Descriptor using sorting algorithm to align sample and negative sample carries out training generation, after sorter described in Practical computer teaching, described sorter can be transferred to terminal, so that terminal uses described sorter to extract FIP in image to be identified.
Exemplary, AdaBoost sorting algorithm can be selected to train described Feature Descriptor, generate described sorter.Wherein, Adaboost is a kind of iterative algorithm, its core concept trains different sorters (Weak Classifier) for same training set, then these weak classifier set got up, and forms a stronger final sorter (strong classifier).Adaboost algorithm itself realizes by changing Data distribution8, and whether it is correct according to the classification of sample each among each training set, and the accuracy rate of the general classification of last time, determines the weights of each sample.Give sub classification device by the new data set revising weights to train, finally will the sorter obtained be trained finally to merge, as last Decision Classfication device at every turn.Use adaboost sorter can get rid of some unnecessary training data features, and training emphasis is placed on above crucial training data.
In step 204, when after the sorter that terminal establishes for extracting FIP, user uses the terminal collection with camera function to comprise the image to be identified of Quick Response Code.
Especially, because this programme adopts target detection principle the position of Quick Response Code to be carried out to the accurate location of two-step approach, can allow terminal under looser condition, gather the image to be identified containing Quick Response Code, need not as in the gatherer process of the image to be identified of existing Quick Response Code, necessarily require the Quick Response Code in view-finder to account for main body and the background of Quick Response Code is simple.
In step 205, after terminal collects the image to be identified comprising Quick Response Code, terminal can according to image to be identified, uses preset sorter to extract FIP in image to be identified, wherein, described sorter is used for the Feature Descriptor identification FIP according to image to be identified.
Concrete, first terminal can extract the Feature Descriptor (Lis Hartel is levied or histogram of gradients feature) in described image to be identified; And then terminal is according to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
Can find out, searched for the FIP in image to be identified by Quick Response Code distinctive black and white saltus step rule in prior art, use the sorter of generation to extract FIP in image to be identified in the present invention, the picture requirement treating recognition image can be reduced, improve the discrimination of FIP.
In step 206, when after the FIP that terminal is extracted in described image to be identified, four summits of described Quick Response Code can be determined according to described FIP, to determine the position of the Quick Response Code in described image to be identified.
Step 204 completes the Primary Location of the position to the Quick Response Code in described image to be identified to 205, namely determines quantity and the position of the FIP in described image to be identified.But, the FIP extracted may because the restriction of the factors such as the computing power of shooting condition, sorter produces the pseudo-FIP being similar to FIP, therefore, needing the FIP to having extracted to filter, namely the position of the Quick Response Code in described image to be identified accurately being located.
Concrete, terminal according to the black and white saltus step rule of Quick Response Code, can carry out the detection of horizontal direction and vertical direction respectively, respectively to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule centered by each FIP extracted; According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group again, exemplary, as shown in Figure 4, the 3rd limit is greater than according to triangle both sides sum, the difference on both sides is less than the geometry site on the 3rd limit, end-filtration does not meet the FIP of above-mentioned geometry site, obtains a FIP group, the FIP group namely formed by 1,2,3.
With reference to figure 4, in a FIP group, terminal can adopt Harris Corner Detection Algorithm to detect all angle points of three FIP in Fig. 4, forms the angle point set of a FIP group; And then, terminal obtains three summits P1, P2, P3 and two angle points C1, C2 of position as shown in Figure 4 in the angle point set of a FIP group according to the geometry site of angle point, finally, the 4th summit P4 of Quick Response Code is obtained by the intersection point calculating P1 and C1 place straight line and P2 and C2 place straight line, so far, P1, P2, P3, P4 are four summits of Quick Response Code, thus determine the position of the Quick Response Code in described image to be identified.
In step 207, after terminal determines the position of the Quick Response Code in described image to be identified, further the Quick Response Code in the position of the Quick Response Code in described image to be identified is corrected, so that identify the data message in described Quick Response Code.
Concrete, terminal according to the position relationship on four summits of the described Quick Response Code after four of a described Quick Response Code summit and preset correction, can calculate the perspective matrix coefficient of described Quick Response Code; Again according to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, to determine the gray level image correcting rear described Quick Response Code.
Exemplary, with reference to figure 4, in terminal, preset position P11, P22, P33, the P44 on four summits of the described Quick Response Code after correction, according to four summits P1, P2, P3, P4 of the Quick Response Code determined, set up solving equations perspective matrix coefficient; Suppose that the coordinate of any point Z pixel in position P11, P22, P33, the P44 on four summits of the described Quick Response Code after correcting is (x, y), so terminal is according to this perspective matrix coefficient, to (x, y) carry out perspective matrix conversion obtain correcting coordinate Z1 corresponding with Z in the determined Quick Response Code of front P1, P2, P3, P4 (x ', y '), again to (x ', y ') calculate (x with linear interpolation method, y) gray-scale value, so, just can obtain the gray level image of the Quick Response Code after correcting, carry out the identification of data message.
Embodiments of the invention provide a kind of recognition methods of Quick Response Code, based target Cleaning Principle uses sorter to the image zooming-out FIP to be identified collected, carry out the Primary Location to Quick Response Code, and then four summits of Quick Response Code are determined according to described FIP, accurately to locate the position of the Quick Response Code in this image to be identified, the target detection principle adopted due to this programme can extract image zooming-out FIP to be identified more easily, need not as in the gatherer process of the image to be identified of existing Quick Response Code, the Quick Response Code in view-finder is necessarily required to account for main body and the background of Quick Response Code is simple, terminal just identifies FIP by the black and white saltus step rule of Quick Response Code, so the present invention can allow terminal to gather the image to be identified containing one or more Quick Response Code under looser condition, in addition, because the present invention is after extraction FIP, according to FIP, the position of Quick Response Code is carried out to the accurate location of two-step approach, further increase the detection discrimination of Quick Response Code in complex scene.
Embodiment three
As shown in Figure 5, for embodiments of the invention provide a kind of hardware schematic diagram of terminal.
Described terminal is the terminal device with camera, can be wireless terminal also can be catv terminal, such as mobile phone terminal, IPAD etc., and the present embodiment illustrates using mobile phone terminal as terminal:
As Fig. 5, institute's mobile phone terminal comprises processor 01, transceiver 02, storer 03 and bus 04.
Wherein, processor 01, transceiver 02 are connected by bus communication with storer 03.
Processor 01 is the control center of described mobile phone terminal, and processor 01 is by processing the data that transceiver 02 receives, and the software called in storer 03 or program, perform the various functions of described mobile phone terminal.
Transceiver 02, can be used for receiving and sending messages or gathering in the process of image, the reception of signal and data and transmission, and transceiver 02 processes to processor 01 after receiving the information of mobile phone terminal transmission; In addition, transceiver 02 can also by radio communication and network and other devices communicatings.
Storer 03, can be used for storing software program, and processor 01 is stored in the software program of storer 03 by running, thus performs various function application and the data processing of described mobile phone terminal.
In embodiments of the present invention, the collection of described transceiver 02 comprises the image to be identified of Quick Response Code and is sent to processor 01; Described processor 01 calls the FIP in the described image to be identified of sorter extraction preset in described storer 03, and described sorter is used for the Feature Descriptor identification FIP according to image to be identified; Described processor 01 determines four summits of described Quick Response Code according to described FIP, to determine the position of the Quick Response Code in described image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code.
Further, processor 01 described in step calls the FIP in the described image to be identified of sorter extraction preset in described storer 03, can specifically comprise: described processor 01 extracts the Feature Descriptor in described image to be identified; And according to described Feature Descriptor, call the FIP in the described image to be identified of FIP sorter extraction preset in described storer 03.
Further, processor 01 described in step determines four summits of described Quick Response Code according to described FIP, can specifically comprise: described processor 01 is according to the black and white saltus step rule of Quick Response Code, the detection of horizontal direction and vertical direction is carried out respectively, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule centered by described FIP; FIP after filtration is divided into FIP group according to leg-of-mutton geometry site by described processor 01, and to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
Further, step determines the position on four summits of the Quick Response Code indicated by each FIP group, can specifically comprise: described processor 01 detects the angle point of three FIP in described FIP group, forms the angle point set of FIP group; Processor 01, according to the geometry site of angle point in described angle point set and described angle point set, determines four summits of the Quick Response Code indicated by described FIP group respectively.
Further, after the position of the Quick Response Code in described image to be identified determined by processor 01 described in step, can also comprise: processor 01, according to the position relationship on four summits of the described Quick Response Code after four of described Quick Response Code summits and preset correction, calculates the perspective matrix coefficient of described Quick Response Code; Processor 01 is according to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
Further, after step determines the gray level image of the rear described Quick Response Code of correction, can also comprise: if the gray level image of described Quick Response Code does not meet the parameter and standard identifying data message in Quick Response Code after correcting, described processor 01 filters the gray level image of the Quick Response Code after described correction.
Further, before transceiver described in step 02 collection comprises the image to be identified of Quick Response Code, can also comprise: the FIP that described processor 01 extracts Quick Response Code by transceiver 02 in preset picture library is positive sample, the image not comprising Quick Response Code is negative sample; Described processor 01 extracts the Feature Descriptor of described positive sample and described negative sample, and described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature; Described processor 01 uses the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, and generates described sorter.
Embodiments of the invention provide a kind of terminal, based target Cleaning Principle uses sorter to the image zooming-out FIP to be identified collected, carry out the Primary Location to Quick Response Code, and then four summits of Quick Response Code are determined according to described FIP, accurately to locate the position of the Quick Response Code in this image to be identified, the target detection principle adopted due to this programme can extract image zooming-out FIP to be identified more easily, need not as in the gatherer process of the image to be identified of existing Quick Response Code, the Quick Response Code in view-finder is necessarily required to account for main body and the background of Quick Response Code is simple, terminal just identifies FIP by the black and white saltus step rule of Quick Response Code, so the present invention can allow terminal to gather the image to be identified containing one or more Quick Response Code under looser condition, in addition, because the present invention is after extraction FIP, according to FIP, the position of Quick Response Code is carried out to the accurate location of two-step approach, further increase the detection discrimination of Quick Response Code in complex scene.
Embodiment four
Embodiments of the invention provide a kind of terminal, as shown in Figure 6, comprising:
Collecting unit 11, for gathering the image to be identified comprising Quick Response Code;
Extraction unit 12, the position sensing figure FIP in the image to be identified extracting in described collecting unit 11 for using preset sorter, described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
Recognition unit 13, for determining four summits of described Quick Response Code according to the FIP in described extraction unit 12, to determine the position of the Quick Response Code in described image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code.
Further, described extraction unit 12, specifically for extracting the Feature Descriptor in described image to be identified; According to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
Further, described recognition unit 13, specifically for the black and white saltus step rule according to Quick Response Code, carries out the detection of horizontal direction and vertical direction respectively centered by described FIP, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule; According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
Further, described recognition unit 13, specifically for detecting the angle point of three FIP in described FIP group, forms the angle point set of FIP group; According to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively.
Further, as shown in Figure 7, described terminal also comprises correcting unit 14, wherein,
Described correcting unit 14, for the position relationship on four summits according to the described Quick Response Code behind four summits of the Quick Response Code in described recognition unit 13 and preset correction, calculates the perspective matrix coefficient of described Quick Response Code; According to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
Further, as shown in Figure 8, described terminal also comprises filter element 15, wherein,
Described filter element 15, if do not meet for the gray level image correcting rear described Quick Response Code the parameter and standard identifying data message in Quick Response Code, then filters the gray level image of the Quick Response Code after described correction.
Further, described extraction unit 12, be also positive sample for extracting the FIP of Quick Response Code in preset picture library, the image not comprising Quick Response Code is negative sample; Extract the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature; Use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter.
Embodiments of the invention provide a kind of terminal, based target Cleaning Principle uses sorter to the image zooming-out FIP to be identified collected, carry out the Primary Location to Quick Response Code, and then four summits of Quick Response Code are determined according to described FIP, accurately to locate the position of the Quick Response Code in this image to be identified, the target detection principle adopted due to this programme can extract image zooming-out FIP to be identified more easily, need not as in the gatherer process of the image to be identified of existing Quick Response Code, the Quick Response Code in view-finder is necessarily required to account for main body and the background of Quick Response Code is simple, terminal just identifies FIP by the black and white saltus step rule of Quick Response Code, so the present invention can allow terminal to gather the image to be identified containing one or more Quick Response Code under looser condition, in addition, because the present invention is after extraction FIP, according to FIP, the position of Quick Response Code is carried out to the accurate location of two-step approach, further increase the detection discrimination of Quick Response Code in complex scene.
Those skilled in the art can be well understood to, for convenience and simplicity of description, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by device is divided into different functional modules, to complete all or part of function described above.The system of foregoing description, the specific works process of device and unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiments that the application provides, should be understood that, disclosed system, apparatus and method, can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described module or unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form of SFU software functional unit also can be adopted to realize.
If described integrated unit using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words or all or part of of this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) or processor (processor) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (14)
1. a recognition methods for Quick Response Code, is characterized in that, comprising:
Gather the image to be identified comprising Quick Response Code;
Use the position sensing figure FIP in the preset described image to be identified of sorter extraction, described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
Four summits of described Quick Response Code are determined, to determine the position of the Quick Response Code in described image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code according to described FIP.
2. method according to claim 1, is characterized in that, the FIP in the described image to be identified of sorter extraction that described use is preset, comprising:
Extract the Feature Descriptor in described image to be identified;
According to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
3. method according to claim 1, is characterized in that, described four summits determining described Quick Response Code according to described FIP, comprising:
According to the black and white saltus step rule of Quick Response Code, centered by described FIP, carry out the detection of horizontal direction and vertical direction respectively, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule;
According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
4. method according to claim 3, is characterized in that, the described position determining four summits of the Quick Response Code indicated by each FIP group, comprising:
Detect the angle point of three FIP in described FIP group, form the angle point set of FIP group;
According to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively.
5. method according to claim 1, is characterized in that, described determine the position of the Quick Response Code in described image to be identified after, also comprise:
According to the position relationship on four summits of the described Quick Response Code behind four summits of described Quick Response Code and preset correction, calculate the perspective matrix coefficient of described Quick Response Code;
According to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
6. method according to claim 5, is characterized in that, described determine correct after described Quick Response Code gray level image after, also comprise:
If the gray level image of described Quick Response Code does not meet the parameter and standard identifying data message in Quick Response Code after correcting, then filter the gray level image of the Quick Response Code after described correction.
7. method according to claim 1, is characterized in that, before comprising the image to be identified of Quick Response Code, also comprises in described collection:
The FIP extracting Quick Response Code in preset picture library is positive sample, and the image not comprising Quick Response Code is negative sample;
Extract the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature;
Use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter.
8. a terminal, is characterized in that, comprising:
Collecting unit, for gathering the image to be identified comprising Quick Response Code;
Extraction unit, the position sensing figure FIP in the image to be identified extracting in described collecting unit for using preset sorter, described sorter is used for the Feature Descriptor identification FIP according to image to be identified;
Recognition unit, for determining four summits of described Quick Response Code according to the FIP in described extraction unit, to determine the position of the Quick Response Code in described image to be identified, so that identify the Quick Response Code in the position of described Quick Response Code.
9. terminal according to claim 8, is characterized in that,
Described extraction unit, specifically for extracting the Feature Descriptor in described image to be identified; According to described Feature Descriptor, use the FIP in the preset described image to be identified of FIP sorter extraction.
10. terminal according to claim 8, is characterized in that,
Described recognition unit, specifically for the black and white saltus step rule according to Quick Response Code, carries out the detection of horizontal direction and vertical direction respectively centered by described FIP, to filter in described FIP the pseudo-FIP not meeting black and white saltus step rule; According to leg-of-mutton geometry site, the FIP after filtration is divided into FIP group, to determine the position on four summits of the Quick Response Code indicated by each FIP group, described each FIP group comprises three FIP.
11. terminals according to claim 10, is characterized in that,
Described recognition unit, specifically for detecting the angle point of three FIP in described FIP group, forms the angle point set of FIP group; According to the geometry site of angle point in described angle point set and described angle point set, determine four summits of the Quick Response Code indicated by described FIP group respectively.
12. terminals according to claim 8, is characterized in that, described terminal also comprises correcting unit, wherein,
Described correcting unit, for the position relationship on four summits according to the described Quick Response Code behind four summits of described Quick Response Code and preset correction, calculates the perspective matrix coefficient of described Quick Response Code; According to described perspective matrix coefficient, by matrixing and linear interpolation method, the Quick Response Code in the position of described Quick Response Code is corrected, with the gray level image of described Quick Response Code after determining to correct so that according to the gray level image identification of described Quick Response Code Quick Response Code.
13. terminals according to claim 12, is characterized in that, described terminal also comprises filter element, wherein,
Described filter element, if do not meet for the gray level image correcting rear described Quick Response Code the parameter and standard identifying data message in Quick Response Code, then filters the gray level image of the Quick Response Code after described correction.
14. terminals according to claim 8, is characterized in that,
Described extraction unit, be also positive sample for extracting the FIP of Quick Response Code in preset picture library, the image not comprising Quick Response Code is negative sample; Extract the Feature Descriptor of described positive sample and described negative sample, described Feature Descriptor at least comprises Lis Hartel and levies or histogram of gradients feature; Use the Feature Descriptor of sorting algorithm to described positive sample and described negative sample to train, generate described sorter.
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 true CN104268498A (en) | 2015-01-07 |
| CN104268498B 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 (27)
| 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 |
| CN104951726A (en) * | 2015-06-25 | 2015-09-30 | 福建联迪商用设备有限公司 | Method and device for QR (quick response) two-dimension code position detection |
| 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 |
| CN106897648A (en) * | 2016-07-22 | 2017-06-27 | 阿里巴巴集团控股有限公司 | The method and its system of the two-dimentional code position of identification |
| WO2017157034A1 (en) * | 2016-03-15 | 2017-09-21 | 中兴通讯股份有限公司 | Method, device, and storage medium for identifying two-dimensional code |
| CN107203798A (en) * | 2017-05-24 | 2017-09-26 | 南京邮电大学 | A kind of generation and recognition methods for limiting access type figure ground Quick Response 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 |
| CN107578250A (en) * | 2017-07-17 | 2018-01-12 | 中国农业大学 | A kind of dimension code anti-counterfeit method and system |
| 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 |
| CN107818282A (en) * | 2017-09-30 | 2018-03-20 | 努比亚技术有限公司 | Two-dimensional code identification method, terminal and computer-readable recording medium |
| 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 |
| CN108388822A (en) * | 2018-01-25 | 2018-08-10 | 微梦创科网络科技（中国）有限公司 | A kind of method and apparatus of detection image in 2 D code |
| CN108961262A (en) * | 2018-05-17 | 2018-12-07 | 南京汇川工业视觉技术开发有限公司 | A kind of Bar code positioning method under complex scene |
| CN109190439A (en) * | 2018-09-21 | 2019-01-11 | 南京机灵侠软件技术有限公司 | A kind of image-recognizing method of optical splitter port lines and its two-dimension code label |
| CN109255271A (en) * | 2017-07-12 | 2019-01-22 | 西克股份公司 | For reading the photoelectricity code reader and method of light code |
| 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 |
| 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 |
| CN109993877A (en) * | 2019-03-07 | 2019-07-09 | 北京航天泰坦科技股份有限公司 | Anti-fake bill recognition methods based on location information |
| CN110046529A (en) * | 2018-12-11 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Two-dimensional code identification method, device and equipment |
| CN110334560A (en) * | 2019-07-16 | 2019-10-15 | 济南浪潮高新科技投资发展有限公司 | A kind of two dimensional code localization 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 |
| CN110490020A (en) * | 2019-07-31 | 2019-11-22 | 珠海市杰理科技股份有限公司 | Bar code recognition, device, computer equipment and storage medium |
| CN110516494A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视数字技术股份有限公司 | A kind of two-dimensional code identification method, device, equipment and system |
| CN110807342A (en) * | 2019-10-18 | 2020-02-18 | 珠海市杰理科技股份有限公司 | Bar code positioning method and 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 |
Family Cites Families (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 |
| CN103699869B (en) * | 2013-12-30 | 2017-02-01 | 优视科技有限公司 | Method and device for recognizing two-dimension codes |
| CN103914675B (en) * | 2014-03-17 | 2016-11-16 | 东华大学 | A kind of 2 D code of quick response matrix recognition methods of clothing |
-
2014
- 2014-09-29 CN CN201410514458.9A patent/CN104268498B/en active Active
Cited By (47)
| 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 |
| CN104951726A (en) * | 2015-06-25 | 2015-09-30 | 福建联迪商用设备有限公司 | Method and device for QR (quick response) two-dimension code position detection |
| WO2017157034A1 (en) * | 2016-03-15 | 2017-09-21 | 中兴通讯股份有限公司 | Method, device, and storage medium for identifying two-dimensional code |
| 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 |
| US10685201B2 (en) | 2016-07-22 | 2020-06-16 | Alibaba Group Holding Limited | Method and system for recognizing location information in two-dimensional code |
| TWI683257B (en) * | 2016-07-22 | 2020-01-21 | 香港商阿里巴巴集團服務有限公司 | Method and system for identifying position of two-dimensional code |
| 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 |
| CN106897648A (en) * | 2016-07-22 | 2017-06-27 | 阿里巴巴集团控股有限公司 | The method and its system of the two-dimentional code position of identification |
| EP3489856A4 (en) * | 2016-07-22 | 2020-03-04 | Alibaba Group Holding Limited | Method and system for recognizing location information in two-dimensional code |
| CN111291584A (en) * | 2016-07-22 | 2020-06-16 | 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 |
| CN107203798A (en) * | 2017-05-24 | 2017-09-26 | 南京邮电大学 | A kind of generation and recognition methods for limiting access type figure ground Quick Response Code |
| CN109255271A (en) * | 2017-07-12 | 2019-01-22 | 西克股份公司 | For reading the photoelectricity code reader and method of light code |
| US11176454B2 (en) | 2017-07-12 | 2021-11-16 | Sick Ag | Optoelectronic code reader and method for reading optical codes |
| CN109255271B (en) * | 2017-07-12 | 2022-01-21 | 西克股份公司 | Electro-optical 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 |
| CN107578250A (en) * | 2017-07-17 | 2018-01-12 | 中国农业大学 | A kind of dimension code anti-counterfeit 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 |
| CN107818282A (en) * | 2017-09-30 | 2018-03-20 | 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 |
| CN108388822A (en) * | 2018-01-25 | 2018-08-10 | 微梦创科网络科技（中国）有限公司 | A kind of method and apparatus of detection image in 2 D code |
| 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 |
| CN108961262A (en) * | 2018-05-17 | 2018-12-07 | 南京汇川工业视觉技术开发有限公司 | A kind of Bar code positioning method under 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 |
| CN110516494A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视数字技术股份有限公司 | A kind of two-dimensional code identification method, device, equipment and system |
| CN109190439A (en) * | 2018-09-21 | 2019-01-11 | 南京机灵侠软件技术有限公司 | A kind of image-recognizing method of optical splitter port lines and its two-dimension code label |
| 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 |
| TWI726422B (en) * | 2018-12-11 | 2021-05-01 | 開曼群島商創新先進技術有限公司 | Two-dimensional code recognition method, device and equipment |
| CN110046529A (en) * | 2018-12-11 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Two-dimensional code identification method, device and equipment |
| WO2020119301A1 (en) * | 2018-12-11 | 2020-06-18 | 阿里巴巴集团控股有限公司 | Two-dimensional code identification method, apparatus, and device |
| 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 |
| CN109993877A (en) * | 2019-03-07 | 2019-07-09 | 北京航天泰坦科技股份有限公司 | Anti-fake bill recognition methods based on location information |
| CN110334560A (en) * | 2019-07-16 | 2019-10-15 | 济南浪潮高新科技投资发展有限公司 | A kind of two dimensional code localization method and device |
| 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 |
| 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 |
| CN110490020A (en) * | 2019-07-31 | 2019-11-22 | 珠海市杰理科技股份有限公司 | Bar code recognition, device, computer equipment and storage medium |
| 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 |
| CN110807342A (en) * | 2019-10-18 | 2020-02-18 | 珠海市杰理科技股份有限公司 | Bar code positioning 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104268498B (en) | 2017-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104268498A (en) | Two-dimension code recognition method and terminal | |
| CN110427905B (en) | Pedestrian tracking method, device and terminal | |
| CN112528831B (en) | Multi-target attitude estimation method, multi-target attitude estimation device and terminal equipment | |
| KR20140091762A (en) | Text detection using multi-layer connected components with histograms | |
| CN107862234A (en) | A kind of recognition methods of color bar code, electronic equipment and storage medium | |
| CN113657274B (en) | Table generation method and device, electronic equipment and storage medium | |
| CN104574401A (en) | Image registration method based on parallel line matching | |
| CN106203539A (en) | The method and apparatus identifying container number | |
| CN108986137B (en) | Human body tracking method, device and equipment | |
| CN112633084A (en) | Face frame determination method and device, terminal equipment and storage medium | |
| CN104063701B (en) | Fast electric television stations TV station symbol recognition system and its implementation based on SURF words trees and template matches | |
| CN104966109A (en) | Medical laboratory report image classification method and apparatus | |
| WO2022121025A1 (en) | Certificate category increase and decrease detection method and apparatus, readable storage medium, and terminal | |
| CN104077557A (en) | Method and device for acquiring card information | |
| CN112364807A (en) | Image recognition method and device, terminal equipment and computer readable storage medium | |
| CN112686122A (en) | Human body and shadow detection method, device, electronic device and storage medium | |
| CN111652878A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| CN114972947B (en) | Depth scene text detection method and device based on fuzzy semantic modeling | |
| CN110428264A (en) | Fake method, device, equipment and medium are tested in identification based on dot matrix screen antifalsification label | |
| CN112348112B (en) | Training method and training device for image recognition model and terminal equipment | |
| CN114495132A (en) | Character recognition method, device, equipment and storage medium | |
| CN115273177A (en) | Method, device and equipment for recognizing face types of heterogeneous faces and storage medium | |
| CN111639573B (en) | ORB algorithm-based gesture recognition method, storage medium and electronic equipment | |
| CN113378837A (en) | License plate shielding identification method and device, electronic equipment and storage medium | |
| Yang et al. | Intelligent digitization of substation one-line diagrams based on computer vision |
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 |