CN111488751A

CN111488751A - Two-dimensional code image processing method and device, electronic equipment and storage medium

Info

Publication number: CN111488751A
Application number: CN201910087678.0A
Authority: CN
Inventors: 潘磊; 金亮; 江湘舟
Original assignee: Beijing Qisheng Technology Co Ltd
Current assignee: Beijing Qisheng Technology Co Ltd
Priority date: 2019-01-29
Filing date: 2019-01-29
Publication date: 2020-08-04

Abstract

The application provides a two-dimensional code image processing method, a two-dimensional code image processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined, wherein the positioning points are used for indicating the identification direction of the two-dimensional code; acquiring a plurality of areas to be identified formed by positioning points to be determined according to a preset positioning point combination rule and the positioning points to be determined; calculating confidence coefficients of a plurality of regions to be identified according to a preset shape matching rule; and determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized. The method includes the steps of scanning an image to be recognized to obtain a plurality of locating points to be determined, obtaining a plurality of areas to be recognized through a preset locating point combination rule in a two-dimensional code image, calculating confidence coefficients of the areas to be recognized according to a preset shape matching rule, determining a two-dimensional code to be recognized according to the calculated confidence coefficients of the areas to be recognized, and improving the two-dimensional code recognition efficiency and accuracy.

Description

Two-dimensional code image processing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of two-dimensional code recognition processing technologies, and in particular, to a two-dimensional code image processing method and apparatus, an electronic device, and a storage medium.

Background

With the rapid development of mobile terminals, various two-dimensional code applications are coming, for example, real estate projects, home goods, automobiles, scenic spot touring projects, physical stores and the like, merchants can use two-dimensional codes for any propaganda medium, users can obtain various services pushed by the merchants on mobile phones by scanning the codes through mobile phone software, and the life of the users is more convenient due to the application of the two-dimensional codes.

Generally, when a user scans a two-dimensional code, due to some external factors, for example: when a plurality of two-dimensional codes exist in the image to be identified at the same time, a user may acquire information of more than one two-dimensional code during scanning. For example, partial information (e.g., anchor point) of another two-dimensional code and interference information of some other similar anchor points may be collected. Therefore, the user cannot accurately acquire the relevant information of the two-dimensional code to be identified, and the experience of the user is reduced to a certain extent.

How to accurately distinguish the plurality of recognized two-dimensional codes and determine the two-dimensional codes to be recognized does not have an effective solution at present.

Disclosure of Invention

In view of this, an embodiment of the present application aims to provide a two-dimensional code image processing method and apparatus, an electronic device, and a storage medium, so as to solve the problem in the prior art that a two-dimensional code to be recognized in an image to be recognized cannot be accurately determined, and achieve an effect of improving user experience.

In a first aspect, an embodiment of the present application provides a two-dimensional code image processing method, where the method includes:

identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined, wherein the positioning points are used for indicating the identification direction of the two-dimensional code; acquiring a plurality of areas to be identified formed by positioning points to be determined according to a preset positioning point combination rule and the positioning points to be determined; calculating confidence coefficients of a plurality of regions to be identified according to a preset shape matching rule; and determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized.

Optionally, identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined includes:

and identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined which meet a preset shape rule in the image to be identified.

Optionally, obtaining a plurality of regions to be identified composed of the anchor points to be determined according to a preset anchor point combination rule and a plurality of anchor points to be determined, including:

and combining the positioning points into a plurality of areas to be identified according to a preset positioning point combination rule and the distribution of the positioning points to be determined.

Optionally, combining the multiple positioning points into multiple areas to be identified according to a preset positioning point combination rule and distribution of the multiple positioning points to be determined, including:

acquiring a plurality of groups of positioning points to be determined, which can construct a preset graph, according to the distribution of the positioning points to be determined and the number of preset positioning points; and constructing each group of positioning points to be determined into a region to be identified.

Optionally, calculating confidence degrees of the multiple regions to be recognized according to a preset shape matching rule, including:

calculating the similarity between the area to be identified and the target shape by adopting a preset shape matching rule; and calculating the confidence degrees of the multiple regions to be recognized according to the similarity between the regions to be recognized and the target shape.

Optionally, calculating the similarity between the region to be recognized and the target shape by using a preset shape matching rule, including:

acquiring characteristic information of a target shape and characteristic information to be matched corresponding to the characteristic information of the target shape and the area to be identified; and calculating the similarity between the characteristic information to be matched and the characteristic information of the target shape to be used as the similarity between the area to be identified and the target shape.

Optionally, if the target shape is an isosceles right triangle and the area to be identified is a triangle; calculating the similarity between the feature information to be matched and the feature information of the target shape, wherein the similarity comprises the following steps:

calculating a first similarity between the side length information of the region to be identified and the side length characteristics of the isosceles right triangle; calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle; and acquiring the similarity between the feature information to be matched and the feature information of the target shape according to the first similarity and the second similarity.

Optionally, determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized includes:

determining a region to be recognized with the highest confidence coefficient according to the confidence coefficients of the regions to be recognized; and acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

Optionally, determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized, further including:

according to the confidence degrees of a plurality of areas to be identified, eliminating interference points in a plurality of positioning points to be determined, and obtaining residual positioning points; and determining at least 1 two-dimension code to be identified according to the residual positioning points.

In a second aspect, an embodiment of the present application provides a two-dimensional code image processing apparatus, including: the device comprises an identification module, an acquisition module, a calculation module and a determination module;

the identification module is used for identifying the acquired image to be identified and acquiring a plurality of positioning points to be determined, and the positioning points are used for indicating the identification direction of the two-dimensional code; the acquisition module is used for acquiring a plurality of areas to be identified formed by positioning points to be determined according to a preset positioning point combination rule and the positioning points to be determined; the calculation module is used for calculating the confidence degrees of the multiple regions to be recognized according to a preset shape matching rule; and the determining module is used for determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized.

Optionally, the identification module is specifically configured to identify the acquired image to be identified, and acquire a plurality of positioning points to be determined that satisfy a preset shape rule in the image to be identified.

Optionally, the obtaining module is specifically configured to combine the multiple positioning points into multiple areas to be identified according to a preset positioning point combination rule and distribution of the multiple positioning points to be determined.

Optionally, the obtaining module is specifically configured to obtain a plurality of groups of to-be-determined positioning points, which can construct a preset graph, according to distribution of the plurality of to-be-determined positioning points and the number of preset positioning points; and constructing each group of positioning points to be determined into a region to be identified.

Optionally, the calculation module is specifically configured to calculate a similarity between the region to be identified and the target shape by using a preset shape matching rule; and calculating the confidence degrees of the multiple regions to be recognized according to the similarity between the regions to be recognized and the target shape.

Optionally, the calculation module is specifically configured to obtain feature information of the target shape and feature information to be matched, where the region to be identified corresponds to the feature information of the target shape; and calculating the similarity between the characteristic information to be matched and the characteristic information of the target shape to be used as the similarity between the area to be identified and the target shape.

Optionally, if the target shape is an isosceles right triangle and the area to be identified is a triangle; the calculation module is specifically used for calculating a first similarity between the side length information of the region to be identified and the side length characteristics of the isosceles right triangle; calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle; and acquiring the similarity between the feature information to be matched and the feature information of the target shape according to the first similarity and the second similarity.

Optionally, the determining module is specifically configured to determine, according to the confidence degrees of the multiple regions to be recognized, a region to be recognized with the highest confidence degree; and acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

Optionally, the determining module is specifically configured to remove interference points in the multiple locating points to be determined according to the confidence degrees of the multiple regions to be identified, and obtain remaining locating points; and determining at least 1 two-dimension code to be identified according to the residual positioning points.

In a third aspect, an embodiment of the present application provides an electronic device, including: the two-dimensional code image processing method comprises a processor, a storage medium and a bus, wherein the storage medium stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the storage medium are communicated through the bus, and the processor executes the machine readable instructions to execute the steps of the two-dimensional code image processing method provided by the first aspect or the second aspect.

In a fourth aspect, the present application provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the two-dimensional code image processing method according to the first aspect or the second aspect.

According to the two-dimensional code image processing method provided by the embodiment of the application, a plurality of locating points to be determined are obtained by scanning an image to be identified, a plurality of areas to be identified are obtained by a preset locating point combination rule in the two-dimensional code image, confidence coefficients of the areas to be identified are calculated according to a preset shape matching rule, the two-dimensional code to be identified is determined according to the confidence coefficients of the areas to be identified, the efficiency and the accuracy of two-dimensional code identification and distinguishing are improved, user experience is better, meanwhile, interference points in the obtained locating points to be determined can be eliminated, and the complexity of two-dimensional code processing is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 shows a schematic flow chart of a two-dimensional code image processing method provided by an embodiment of the present application;

fig. 2 is a schematic flow chart of another two-dimensional code image processing method provided in the embodiment of the present application;

fig. 3 is a schematic flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application;

fig. 4 is a schematic flow chart of another two-dimensional code image processing method provided in the embodiment of the present application;

fig. 5 is a schematic flow chart illustrating another two-dimensional code image processing method provided in the embodiment of the present application;

fig. 6 is a schematic flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application;

fig. 7 is a schematic flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application;

fig. 8 shows a schematic diagram of distribution of two-dimensional code positioning points provided in the embodiment of the present application;

fig. 9 is a schematic structural diagram of a two-dimensional code image processing device according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of another two-dimensional code image processing device according to an embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

In the actual life working process, under the condition that two-dimensional codes need to be scanned, due to the fact that the information of a plurality of two-dimensional codes can be collected in a code scanning frame due to the operation problem of a user or the placement problem of the two-dimensional codes, terminal equipment is difficult to distinguish, and the two-dimensional code image processing method is provided for similar scenes.

Fig. 1 shows a schematic flow chart of a two-dimensional code image processing method provided in an embodiment of the present application, where an execution main body of the embodiment may be a terminal, a computer, a server, and the like, and as shown in fig. 1, the two-dimensional code image processing method provided in the present application includes:

s101, identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined.

The locating point is used for indicating the identification direction of the two-dimensional code.

Firstly, the image to be recognized where the two-dimensional code to be recognized is located can be acquired according to actual conditions, for example, the image to be recognized is acquired through a shooting function of a terminal or a special code scanning device. The image to be recognized may be an image that only includes the two-dimensional code to be recognized, or may be an image that includes the two-dimensional code to be recognized and other information unrelated to the two-dimensional code. In addition, the image to be recognized may include at least two-dimensional code images to be recognized of similar types, or may include a plurality of two-dimensional code images to be recognized of similar types, or the like. For example: the image to be recognized may be formed by only closely arranging a plurality of two-dimensional codes to be recognized, or may include a partial blank area, or may include information such as characters and signs.

Optionally, the acquired image to be identified may be identified by two-dimensional code scanning software in the user terminal application program, or may be identified by a specific two-dimensional code scanning tool.

Generally, whether the two-dimensional code can be accurately scanned and identified can be determined according to the distribution of the positioning points included in the two-dimensional code. The positioning points in the two-dimensional code can be used for helping the machine to better understand whether a certain target is the two-dimensional code or not, and meanwhile, the machine can be guided to completely identify the two-dimensional code along the distribution condition of the positioning points.

It should be noted that, in general, a preset number of anchor points, for example, 3 or 4, may be included in one rectangular two-dimensional code. Optionally, by identifying the image to be identified, a plurality of locating points to be determined may be obtained, where the plurality of locating points to be determined may be a plurality of locating points in one two-dimensional code, or may also be a plurality of locating points in a plurality of two-dimensional codes to be identified included in the image to be identified. For example: the obtained anchor points to be determined may include three, or may include four, five or more, which is not limited herein.

Optionally, the shape of the two-dimensional code in this embodiment is not limited to a rectangle, and may also be a square, a circle, and the like, the number of the positioning points correspondingly included in the two-dimensional codes with different shapes may also be different, for some special circular two-dimensional codes, the number of the positioning points corresponding to the two-dimensional codes may also be one, three, five, and the like, and the number of the positioning points in a specific one of the two-dimensional codes is not limited thereto.

S102, acquiring a plurality of to-be-identified areas formed by the to-be-determined positioning points according to a preset positioning point combination rule and the plurality of to-be-determined positioning points.

Optionally, the two-dimensional codes with different shapes may have different corresponding anchor point combination rules, for example: in the rectangular two-dimensional code, the shape formed by the positioning points can meet the requirements of an isosceles triangle or an isosceles right triangle and the like, in the circular two-dimensional code, the shape formed by the positioning points can meet the requirements of a circle or an isosceles triangle and the like, and specifically, the positioning point combination rule can be set according to the design rule of the two-dimensional code.

Optionally, assuming that the shape formed by the anchor points is a triangle, the preset anchor point combination rule may be: and the side length and the included angle both meet the triangle of the preset condition. For example: if the shape of the equipotential point composition is an isosceles triangle, the preset anchor point combination rule may be: triangles with included angles between 55 and 65 and approximately equal side lengths.

According to the set positioning point combination rule, the obtained positioning points to be determined can be combined to obtain a plurality of combination results meeting the requirements, wherein the area where each combination is located can be regarded as representing an area to be identified.

S103, calculating confidence degrees of the multiple regions to be recognized according to a preset shape matching rule.

In the above-mentioned multiple obtained positioning point combinations, the multiple positioning points in each positioning point combination may be positioning points in one two-dimensional code, or may only satisfy a preset positioning point combination rule, but belong to multiple positioning points in two-dimensional codes. For a combination containing a plurality of positioning points in a plurality of two-dimensional codes, complete two-dimensional code information cannot be obtained through scanning.

Optionally, the shape matching rule may be determined according to the shape formed by the positioning points in the two-dimensional code to be recognized. For example: the positioning points in the two-dimensional code to be identified can form an isosceles triangle or a circle, and the like, so that the sizes of the corresponding isosceles triangles of different two-dimensional codes are different, or the sizes of the circles are different, and the preset shape matching rules are different for different two-dimensional codes.

Optionally, in the multiple regions to be recognized formed by the anchor points, the shape formed by the anchor points is matched with a preset shape matching rule, and the matching degree is calculated, wherein the closer the shape is, the higher the corresponding matching result is, the higher the probability that the corresponding region to be recognized is, that is, the higher the confidence coefficient is.

And S104, determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized.

Optionally, according to the confidence degree calculation result, the confidence degrees may be sorted according to size, and a positioning point combination with the highest confidence degree is determined, where the corresponding to-be-identified region is the to-be-identified two-dimensional code. The higher the confidence coefficient is, the higher the possibility that a plurality of positioning points in the area to be identified belong to the same two-dimensional code is.

In addition, a confidence judgment threshold value can be set, a plurality of positioning points of the to-be-recognized area with the calculated confidence coefficient smaller than the threshold value are deleted to eliminate interference points and narrow the determination range of the to-be-recognized two-dimensional code, then the to-be-recognized area meeting the confidence coefficient requirement is recognized, and the to-be-recognized two-dimensional code corresponding to the plurality of positioning points in the to-be-recognized area with high confidence coefficient is determined.

According to the two-dimensional code image processing method provided by the embodiment of the application, the multiple regions to be recognized are obtained through the preset positioning point combination rule in the two-dimensional code image, the confidence degrees of the multiple regions to be recognized are calculated according to the preset shape matching rule, the two-dimensional code to be recognized is determined according to the confidence degrees of the multiple regions to be recognized, the two-dimensional code recognition and distinguishing efficiency and accuracy are improved, and the user experience degree is better.

Further, the identifying the acquired image to be identified and obtaining a plurality of positioning points to be determined includes: and identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined which meet a preset shape rule in the image to be identified.

It should be noted that the two-dimensional code may include various types of feature points, for example: location points and information points, etc. Generally, the anchor point includes a plurality of anchor points, each anchor point has the same shape, the shapes of the anchor points are the same, and the anchor points and the information points may have the same or different shapes. After identifying the acquired image to be identified, feature points of various shapes may be obtained, for example: the feature points may be squares, circles, irregular shapes, etc., and feature points that do not satisfy the shape rules may be deleted according to the preset shape rules to reduce the amount of calculation and improve the accuracy of calculation.

Further, according to a preset positioning point combination rule and a plurality of positioning points to be determined, obtaining a plurality of areas to be identified formed by the positioning points to be determined, including:

Optionally, the preset anchor point combination rule is already described in the above embodiments, and is not described herein again.

It should be noted that there may be a plurality of distribution situations for the obtained plurality of anchor points to be determined. For example: the plurality of points are distributed on a horizontal line, or the plurality of points are arranged in a disordered way, so that the plurality of positioning points may not meet the preset positioning point combination rule, and the plurality of positioning points cannot be combined. Optionally, according to the preset positioning point combination rule, the distribution conditions of the plurality of positioning points to be determined are combined at the same time, and the plurality of positioning points are combined to obtain a plurality of combinations, where each combination can represent one region to be identified.

Fig. 2 is a schematic flow chart of another two-dimensional code image processing method provided in an embodiment of the present application, and as shown in fig. 2, further, according to a preset positioning point combination rule and a distribution of a plurality of positioning points to be determined, combining the plurality of positioning points into a plurality of regions to be identified includes:

s201, obtaining a plurality of groups of positioning points to be determined, which can construct a preset graph, according to the distribution of the positioning points to be determined and the number of preset positioning points.

Optionally, the preset positioning point combination rules corresponding to the two-dimensional codes with different shapes may be different, and the number of the positioning points corresponding to the different positioning point combination rules may be different, for example: if the anchor point combination rule is: the positioning points are triangular, and the number of the corresponding positioning points can be three; if the anchor point combination rule is: the positioning points are circular, and the number of the corresponding positioning points can be one, three or more, and the like.

And combining the positioning points to be determined according to a preset positioning point combination rule and the number requirement of preset positioning points corresponding to the positioning point rule to construct a plurality of positioning point combinations meeting the requirement.

It should be noted that, when combining a plurality of positioning points to be determined, each positioning point may be combined with a plurality of other positioning points only once to construct a graph satisfying the requirement, or may be combined with a plurality of other positioning points many times, that is, each positioning point may be included in a plurality of positioning point combinations.

S202, constructing each group of positioning points to be determined into an area to be identified.

It should be noted that, a plurality of positioning point combinations meeting the requirements may be determined, each positioning point combination may form a two-dimensional code to be identified, or each positioning point combination may determine a range of the two-dimensional code to be identified, that is, a region to be identified may be constructed according to each group of positioning points to be determined meeting the requirements of the positioning point combinations.

Fig. 3 is a schematic flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application, and as shown in fig. 3, further, the calculating confidence degrees of a plurality of regions to be recognized according to a preset shape matching rule includes:

s301, calculating the similarity between the area to be identified and the target shape by adopting a preset shape matching rule.

It should be noted that the positioning point combination shapes corresponding to different types of two-dimensional codes are different, and a target shape corresponding to a to-be-determined two-dimensional code can be stored in a server background database in advance according to the to-be-determined two-dimensional code of a to-be-identified region, and when the to-be-identified region is obtained, the server calls the corresponding target shape according to a preset identifier or label and matches the corresponding positioning point combination shape forming the to-be-identified region.

Optionally, a difference threshold may be set, differences between the features of each part of the region to be recognized and the features of each part corresponding to the target shape are calculated, if the difference is smaller than the preset difference threshold, the region to be recognized corresponding to the difference is considered to be similar to the target shape, meanwhile, the similarity of the region to be recognized corresponding to the difference obtained through calculation may be obtained, and the regions to be recognized, for which the remaining differences are larger than the preset difference threshold, may be selected and sieved.

S302, according to the similarity between the areas to be recognized and the target shape, calculating the confidence degrees of the areas to be recognized.

Optionally, the similarity obtained through the above calculation may have a size difference, and the closer the region to be recognized is to the target shape, the higher the similarity is, and the higher the confidence of the corresponding region to be recognized is.

It should be noted that the confidence level may be regarded as a determination basis for determining whether the region to be recognized is the target region, and may also be referred to as a confidence level, where the greater the confidence level is, the more reliable the region is, and the greater the possibility that the region can be regarded as the target region is.

In the specific conversion process, the value of the similarity may also be directly used as the confidence, or a mapping relationship between the similarity and the confidence may be established, which is not specifically limited in the present application.

Fig. 4 shows a schematic flow chart of another two-dimensional code image processing method provided in an embodiment of the present application, and further, as shown in fig. 4, the calculating the similarity between the region to be recognized and the target shape by using a preset shape matching rule includes:

s401, obtaining characteristic information of the target shape and characteristic information to be matched corresponding to the characteristic information of the target shape and the area to be identified.

Alternatively, the different shapes may have different corresponding characteristic information. For example: assuming that the target shape is a right triangle, the corresponding feature information may include: the size of the included angle; assuming that the target shape is an isosceles triangle, the corresponding feature information may include: the length of any two side lengths; and when the target shape is a circle, the corresponding characteristic information may include: the length of the radius of the circle, etc.

In this way, feature information of the target shape can be extracted from the preset target shape, for example: if the target shape is an isosceles triangle, the side lengths of three sides of the triangle can be extracted, and correspondingly, the feature information corresponding to the target shape is extracted from the positioning point combination corresponding to the region to be identified, namely the side length information of three sides in the graph formed by the positioning points is extracted. The corresponding characteristic information is adopted for matching, the matching accuracy is relatively high, and the meaning is not great when the corresponding characteristic information is used for matching.

S402, calculating the similarity between the feature information to be matched and the feature information of the target shape to serve as the similarity between the region to be identified and the target shape.

Optionally, if the target shape is an isosceles triangle, the side lengths of the two waists are 5CM, and the corresponding two equal included angle degrees are 50 °, the difference between the length of each side and the target length 5CM may be determined one by one in the extracted side length information corresponding to the region to be identified, and according to the difference between the two sides and the side length information corresponding to the region to be identified, the size of a certain two sides is closer, the two sides may be considered to correspond to the waist length, and further, the difference between the included angle corresponding to the waist length and the target included angle of 50 ° is calculated, and the proximity of the difference is determined.

In summary, the extracted feature information of the region to be recognized and the feature information of the target shape are compared, the sum of the similarity of each feature information is calculated, and the sum of the similarity can be used as the similarity between the region to be recognized and the target shape.

Fig. 5 is a schematic flow chart of another two-dimensional code image processing method provided in the embodiment of the present application, where a specific example is given in the embodiment, if the target shape is an isosceles right triangle and the area to be identified is a triangle.

As shown in fig. 5, calculating the similarity between the feature information to be matched and the feature information of the target shape includes:

s501, calculating first similarity between the side length information of the region to be identified and the side length characteristics of the isosceles right triangle.

Optionally, in the isosceles right triangle, the side lengths D of the two right-angle sides are the same, and the included angle between the two right-angle sides is 90 °, and the length information A, B, C corresponding to the three sides and the three included angles a, b, and c corresponding to the three sides are obtained from the triangle corresponding to the area to be identified. The lengths A, B, C of the three sides acquired by the to-be-identified area can be compared with the lengths D of the right-angle sides of the isosceles right triangle respectively, if the sizes of A and B are close to each other and the difference between the A and B and C is larger, the A and B can be considered to correspond to two waists of the target isosceles right triangle, furthermore, the A, the B and the side length D of the right-angle side can be compared, if the difference is smaller, the A and B are determined to be the right-angle sides, and meanwhile, the first similarity between the side length characteristics is calculated according to the difference.

S502, calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle.

Optionally, by comparing the side length features, it can be determined that the region to be identified is an isosceles triangle, so further determination needs to be performed according to an angle of an included angle in the triangle.

Optionally, the acquired included angles a, b, and c may be respectively determined, the degree of proximity to 90 ° is determined, the closer to 90 °, the higher the similarity to the right angle, and the second similarity between the included angle features may be obtained through calculation.

S503, according to the first similarity and the second similarity, obtaining the similarity between the feature information to be matched and the feature information of the target shape.

It should be noted that the first similarity and the second similarity obtained by the above calculation may be integrated to obtain a total similarity between the feature information to be matched and the feature information of the target shape. Assuming that the determination is performed only according to the first similarity, the determination result may be that: the isosceles right triangle, but may also be an isosceles obtuse triangle, so it is also necessary to determine whether the region to be identified has a right angle according to the characteristic information of the included angle, thereby determining the similarity between the region to be identified and the target shape.

Optionally, the calculation sequence of the steps S501 and S502 is not limited to the sequence in this embodiment, and S502 may be calculated first and then S501 may be calculated, and may be flexibly selected according to the actual situation.

Fig. 6 is a flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application, and further, as shown in fig. 6, determining a two-dimensional code to be recognized according to confidence levels of a plurality of regions to be recognized includes:

s601, determining the region to be recognized with the highest confidence coefficient according to the confidence coefficients of the regions to be recognized.

Optionally, the confidence of each to-be-recognized region may be obtained through the above calculation, and the plurality of confidences may be arranged according to a size order to determine the to-be-recognized region with the highest confidence.

And S602, acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

Optionally, after the region to be recognized with the highest confidence coefficient is determined, the locating point information corresponding to the region to be recognized may be correspondingly obtained, that is, the locating points in the region to be recognized with the highest confidence coefficient are considered to belong to the same two-dimensional code, and the two-dimensional code is recognized according to the several locating points. The positioning point is explained in the foregoing, and the positioning point can indicate the identification direction of the two-dimensional code, so as to guide the machine to identify the two-dimensional code according to the distribution condition of the positioning portion, and obtain complete two-dimensional code information.

In this embodiment, according to the information of the plurality of positioning points corresponding to the to-be-identified region with the highest obtained confidence, the to-be-identified two-dimensional code can be obtained by scanning according to a certain preset rule according to the distribution arrangement mode of the plurality of positioning points.

It should be noted that the locating point may help determine the contour boundary of the two-dimensional code, which cannot represent the two-dimensional code itself, and may be regarded as an index for searching for a complete two-dimensional code, and the target two-dimensional code may be obtained according to the index.

Fig. 7 is a schematic flowchart illustrating a further two-dimensional code image processing method provided in an embodiment of the present application; fig. 8 shows a schematic distribution diagram of two-dimensional code anchor points provided in the embodiment of the present application, please refer to fig. 7 and fig. 8.

Further, determining the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized, and further comprising:

s701, eliminating interference points in the positioning points to be determined according to the confidence degrees of the areas to be identified, and obtaining the residual positioning points.

It should be noted that, in the above steps S601 and S602, the region to be recognized with the highest confidence coefficient may be directly considered to correspond to the two-dimensional code to be recognized, so that the determination efficiency of the two-dimensional code may be higher.

In this embodiment, a plurality of two-dimensional codes to be recognized may also be determined in a screening manner from the calculated confidence degrees of the plurality of regions to be recognized.

It should be noted that the region to be recognized with the confidence level that is not the highest cannot represent that there is no two-dimensional code to be recognized, and it may be affected by some interference points, thereby reducing the confidence level.

As shown in fig. 8, it is assumed that an image to be recognized includes three two-dimensional codes to be recognized, and nine positioning points and possibly one smaller interference point may be obtained by recognizing the image. Usually, the shape or size of the interference point is obviously different from the positioning point, and the interference point with too small shape not meeting the preset positioning point shape rule can be deleted according to the preset positioning point shape rule to determine 9 positioning points to be determined. According to the preset position point combination rule and the preset position point number, such as a triangle rule, the preset position point number is 3, the 9 positioning points are combined, any 3 positioning points can form a combination satisfying the triangle rule, thus a plurality of positioning point combinations can be obtained, wherein 3 positioning points in some positioning point combinations are all contained in a two-dimensional code to be identified, and 3 positioning points in some positioning point combinations can be contained in two-dimensional codes to be identified, even three two-dimensional codes to be identified, therefore, a target shape can be set according to the shape matching rule, the shape formed by the positioning point combinations is matched with the target shape, the similarity is calculated, and the positioning point combinations with the similarity lower than the threshold value are deleted according to the set similarity threshold value, so that the rest positioning point combinations are similar to the target shape, may correspond to the two-dimensional code to be recognized. Next, the confidence of the region to be recognized determined by the combination of the remaining anchor points may be calculated according to the shape matching rule.

As shown in fig. 8, the positioning points 1, 2, and 3 form a region to be recognized, and similarly, the positioning points 2, 3, and 4 also form a region to be recognized, and since the two regions to be recognized have similar shapes, the confidence levels corresponding to the two regions to be recognized need to be obtained according to the matching degree between the two regions and the target shape. The target shape is set according to the two-dimensional code to be determined, the two-dimensional code to be determined is assumed to be E, the regions to be recognized formed by the positioning points 1, 2 and 3 are all included in one two-dimensional code, the regions to be recognized formed by the positioning points 2, 3 and 4 belong to two-dimensional codes, the confidence coefficient of the regions to be recognized is lower than that of the regions to be recognized, and the positioning points in the regions to be recognized can be eliminated. However, since the anchor points 2 and 3 in the reserved region to be recognized are included in the region to be recognized, if the anchor points are deleted directly according to the rule with low confidence, many important anchor points are deleted by mistake, so that the anchor points belonging to the region to be recognized and the region with low confidence and not belonging to the same region as the region with high confidence can be deleted as the interference points. Namely, the anchor point 4 is deleted; similarly, when the to-be-identified region composed of the positioning points 1, 2, and 3 and the to-be-identified region composed of the positioning points 3, 7, and 8 delete the interference point through the confidence, the positioning points 7 and 8 are deleted as the interference points.

Similarly, when the two-dimensional code to be determined is F, the locating point 3 is deleted as an interference point when the to-be-identified region composed of the locating points 3, 4, and 6 and the to-be-identified region composed of the locating points 4, 5, and 6 delete the interference point through the confidence. Optionally, according to different two-dimensional codes to be determined, the above-mentioned situations that the positioning point to be determined is an interference point are also different. The judgment is carried out according to the actual situation.

S702, determining at least 1 two-dimension code to be identified according to the residual positioning points.

After the interference point deleting operation is carried out, according to the number of the remaining positioning points, one two-dimensional code to be identified can be determined, and a plurality of two-dimensional codes to be identified can also be determined. Assuming that the number of the remaining anchor points is 3, one two-dimensional code to be identified can be determined, and the number of the remaining anchor points is 6, two-dimensional codes to be identified can be determined.

It should be noted that, in the present application, a rectangular two-dimensional code is taken as an example for description, and the rectangular two-dimensional code includes three positioning points, and the combined shape of the three positioning points is an isosceles right triangle.

Optionally, the method is not limited to be applied to processing of rectangular two-dimensional codes, and may also be a circular two-dimensional code, and the number of the positioning points and the combined shape thereof correspondingly included may also be flexibly set, and the application is not particularly limited.

Fig. 9 is a schematic structural diagram of a two-dimensional code image processing apparatus according to an embodiment of the present application, and as shown in fig. 9, the two-dimensional code image processing apparatus includes: an identification module 801, an acquisition module 802, a calculation module 803 and a determination module 804;

the identification module 801 is used for identifying the acquired image to be identified and acquiring a plurality of locating points to be determined, wherein the locating points are used for indicating the identification direction of the two-dimensional code; an obtaining module 802, configured to obtain multiple regions to be identified, which are formed by the positioning points to be determined, according to a preset positioning point combination rule and the multiple positioning points to be determined; a calculating module 803, configured to calculate confidence levels of the multiple regions to be identified according to a preset shape matching rule; the determining module 804 is configured to determine the two-dimensional code to be recognized according to the confidence degrees of the multiple regions to be recognized.

Optionally, the identifying module 801 is specifically configured to identify the acquired image to be identified, and acquire a plurality of positioning points to be determined, which meet a preset shape rule, in the image to be identified.

Optionally, the obtaining module 802 is specifically configured to combine a plurality of positioning points into a plurality of areas to be identified according to a preset positioning point combination rule and distribution of the plurality of positioning points to be determined.

Optionally, the obtaining module 802 is specifically configured to obtain multiple groups of positioning points to be determined, which can construct a preset graph, according to the distribution of the multiple positioning points to be determined and the number of preset positioning points; and constructing each group of positioning points to be determined into a region to be identified.

Optionally, the calculating module 803 is specifically configured to calculate a similarity between the region to be identified and the target shape by using a preset shape matching rule; and calculating the confidence degrees of the multiple regions to be recognized according to the similarity between the regions to be recognized and the target shape.

Optionally, the calculating module 803 is specifically configured to obtain feature information of the target shape and feature information to be matched corresponding to the feature information of the target shape and the region to be identified; and calculating the similarity between the characteristic information to be matched and the characteristic information of the target shape to be used as the similarity between the area to be identified and the target shape.

Optionally, if the target shape is an isosceles right triangle and the area to be identified is a triangle; the calculating module 803 is specifically configured to calculate a first similarity between the side length information of the region to be identified and the side length feature of the isosceles right triangle; calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle; and acquiring the similarity between the feature information to be matched and the feature information of the target shape according to the first similarity and the second similarity.

Optionally, the determining module 804 is specifically configured to determine, according to the confidence degrees of the multiple regions to be recognized, a region to be recognized with the highest confidence degree; and acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

Optionally, the determining module 804 is specifically configured to remove an interference point in the multiple locating points to be determined according to the confidence degrees of the multiple regions to be identified, and obtain a remaining locating point; and determining at least 1 two-dimension code to be identified according to the residual positioning points.

The apparatus may be configured to execute the method provided by the method embodiment, and the specific implementation manner and the technical effect are similar and will not be described herein again.

Fig. 10 is a schematic structural diagram of another two-dimensional code image processing apparatus provided in an embodiment of the present application, and as shown in fig. 10, the apparatus includes: a processor 901 and a memory 902, wherein: the memory 902 is used for storing programs, and the processor 901 calls the programs stored in the memory 902 to execute the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.

The apparatus may be integrated in a device such as a terminal or a server, and is not limited in this application.

Optionally, the invention also provides a program product, for example a computer-readable storage medium, comprising a program which, when being executed by a processor, is adapted to carry out the above-mentioned method embodiments.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A two-dimensional code image processing method is characterized by comprising the following steps:

identifying the acquired image to be identified, and acquiring a plurality of positioning points to be determined, wherein the positioning points are used for indicating the identification direction of the two-dimensional code;

acquiring a plurality of areas to be identified formed by the positioning points to be determined according to a preset positioning point combination rule and the positioning points to be determined;

calculating the confidence degrees of the multiple regions to be recognized according to a preset shape matching rule;

and determining the two-dimensional code to be recognized according to the confidence degrees of the plurality of regions to be recognized.

2. The method according to claim 1, wherein the identifying the acquired image to be identified and obtaining a plurality of anchor points to be determined comprises:

the method comprises the steps of identifying an acquired image to be identified, and acquiring a plurality of positioning points to be determined which meet a preset shape rule in the image to be identified.

3. The method according to claim 1, wherein said obtaining a plurality of regions to be identified, which are formed by the anchor points to be determined, according to a preset anchor point combination rule and the anchor points to be determined comprises:

and combining the positioning points into the areas to be identified according to a preset positioning point combination rule and the distribution of the positioning points to be determined.

4. The method according to claim 3, wherein the combining the plurality of positioning points into the plurality of regions to be identified according to a preset positioning point combination rule and a distribution of the plurality of positioning points to be determined comprises:

acquiring a plurality of groups of positioning points to be determined, which can construct a preset graph, according to the distribution of the positioning points to be determined and the number of preset positioning points;

and constructing each group of positioning points to be determined into one area to be identified.

5. The method according to claim 4, wherein the calculating the confidence degrees of the plurality of regions to be identified according to a preset shape matching rule comprises:

calculating the similarity between the area to be identified and the target shape by adopting a preset shape matching rule;

and calculating the confidence degrees of the multiple regions to be recognized according to the similarity between the regions to be recognized and the target shape.

6. The method according to claim 5, wherein the calculating the similarity between the region to be recognized and the target shape by using a preset shape matching rule comprises:

acquiring the characteristic information of the target shape and the characteristic information to be matched corresponding to the characteristic information of the target shape and the area to be identified;

and calculating the similarity between the characteristic information to be matched and the characteristic information of the target shape as the similarity between the area to be identified and the target shape.

7. The method according to claim 6, wherein if the target shape is an isosceles right triangle and the area to be identified is a triangle;

the calculating the similarity between the feature information to be matched and the feature information of the target shape includes:

calculating a first similarity between the side length information of the region to be identified and the side length characteristics of the isosceles right triangle;

calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle;

and acquiring the similarity between the feature information to be matched and the feature information of the target shape according to the first similarity and the second similarity.

8. The method according to claim 1, wherein the determining the two-dimensional code to be recognized according to the confidence degrees of the plurality of regions to be recognized comprises:

determining the region to be recognized with the highest confidence coefficient according to the confidence coefficients of the regions to be recognized;

and acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

9. The method according to claim 1, wherein the determining a two-dimensional code to be recognized according to the confidence degrees of the plurality of regions to be recognized further comprises:

according to the confidence degrees of the areas to be identified, eliminating interference points in the positioning points to be determined, and acquiring residual positioning points;

and determining at least 1 two-dimension code to be identified according to the residual positioning points.

10. A two-dimensional code image processing apparatus characterized by comprising: the device comprises an identification module, an acquisition module, a calculation module and a determination module;

the identification module is used for identifying the acquired image to be identified and acquiring a plurality of positioning points to be determined, wherein the positioning points are used for indicating the identification direction of the two-dimensional code;

the acquisition module is used for acquiring a plurality of areas to be identified formed by the positioning points to be determined according to a preset positioning point combination rule and the positioning points to be determined;

the calculation module is used for calculating the confidence degrees of the multiple regions to be identified according to a preset shape matching rule;

and the determining module is used for determining the two-dimensional code to be recognized according to the confidence degrees of the plurality of regions to be recognized.

11. The device according to claim 10, wherein the identification module is specifically configured to identify the acquired image to be identified, and obtain a plurality of positioning points to be determined in the image to be identified, where the positioning points meet a preset shape rule.

12. The apparatus according to claim 10, wherein the obtaining module is specifically configured to combine the multiple positioning points into the multiple regions to be identified according to a preset positioning point combination rule and a distribution of the multiple positioning points to be determined.

13. The apparatus according to claim 12, wherein the obtaining module is specifically configured to obtain a plurality of groups of to-be-determined positioning points that can construct a preset graph according to distribution of the plurality of to-be-determined positioning points and a preset number of positioning points; and constructing each group of positioning points to be determined into one area to be identified.

14. The apparatus according to claim 13, wherein the calculating module is specifically configured to calculate a similarity between the region to be recognized and a target shape by using a preset shape matching rule; and calculating the confidence degrees of the multiple regions to be recognized according to the similarity between the regions to be recognized and the target shape.

15. The apparatus according to claim 14, wherein the computing module is specifically configured to obtain feature information of the target shape and feature information to be matched, where the region to be identified corresponds to the feature information of the target shape; and calculating the similarity between the characteristic information to be matched and the characteristic information of the target shape as the similarity between the area to be identified and the target shape.

16. The apparatus according to claim 15, wherein if the target shape is an isosceles right triangle, the area to be identified is a triangle; the calculation module is specifically used for calculating a first similarity between the side length information of the area to be identified and the side length characteristics of the isosceles right triangle; calculating a second similarity between the included angle information of the area to be identified and the included angle characteristics of the isosceles right triangle; and acquiring the similarity between the feature information to be matched and the feature information of the target shape according to the first similarity and the second similarity.

17. The apparatus according to claim 10, wherein the determining module is specifically configured to determine, according to the confidence degrees of the plurality of regions to be recognized, a region to be recognized with a highest confidence degree; and acquiring the two-dimensional code to be recognized according to the region to be recognized with the highest confidence coefficient.

18. The apparatus according to claim 10, wherein the determining module is specifically configured to, according to the confidence degrees of the plurality of regions to be identified, eliminate interference points in a plurality of positioning points to be determined, and obtain remaining positioning points; and determining at least 1 two-dimension code to be identified according to the residual positioning points.

19. An electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when an electronic device runs, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the two-dimensional code image processing method according to any one of claims 1 to 9.

20. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the two-dimensional code image processing method according to any one of claims 1 to 9.