CN115713556A

CN115713556A - Two-dimensional code positioning method and device and computer readable storage medium

Info

Publication number: CN115713556A
Application number: CN202211445004.1A
Authority: CN
Inventors: 刘洪亮; 张广优
Original assignee: Evoc Hi Tech Holdings Group Ltd
Current assignee: Evoc Hi Tech Holdings Group Ltd
Priority date: 2022-11-18
Filing date: 2022-11-18
Publication date: 2023-02-24

Abstract

The embodiment of the application relates to the technical field of two-dimensional code positioning, and discloses a two-dimensional code positioning method, a two-dimensional code positioning device and a computer readable storage medium.

Description

Two-dimensional code positioning method and device and computer readable storage medium

Technical Field

The embodiment of the invention relates to the technical field of two-dimension code positioning, in particular to a two-dimension code positioning method and device and a computer readable storage medium.

Background

At present, with the progress of production and living of people and the continuous improvement of living standard, the two-dimensional code is often used for payment when shopping is carried out, the payment can be conveniently and quickly completed by scanning and identifying the two-dimensional code of a merchant through equipment such as a mobile phone, and great convenience is brought to the life of people. Also can come lifting efficiency through the two-dimensional code in many other aspects of production and life, for example when checking the goods, people can look over the details of appointed goods rapidly through the two-dimensional code on the equipment scanning goods, have saved a lot of times, have also improved the accuracy of work. The premise that the two-dimensional code is convenient and quick to use is that an effective two-dimensional code positioning method is needed to position a recognizable Region (ROI) of the two-dimensional code, and the two-dimensional code can be recognized by equipment according to the positioned recognizable region, so that information contained in the two-dimensional code can be effectively acquired.

The existing two-dimension code positioning method is often complex in positioning process, the positioning effect needs to be improved, and the increasing efficiency and effect requirements of people cannot be met, so that the research and development of the two-dimension code positioning method which is high in positioning accuracy and simple and effective in positioning process is particularly important.

Disclosure of Invention

In view of the above problems, embodiments of the present invention provide a two-dimensional code positioning method, which is used to solve the problems in the prior art.

According to an aspect of an embodiment of the present invention, there is provided a two-dimensional code positioning method, including:

preprocessing an input image to obtain a preprocessed image;

performing linear detection on the preprocessed image to obtain a linear line to be screened;

screening straight lines to be screened according to screening conditions to obtain target straight lines aiming at the frame position of the ROI of the two-dimensional code, wherein the screening conditions comprise that the included angle of the two straight lines to be screened is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or the distance between the end point of one straight line to be screened of the two straight lines to be screened and the nearest end point of the other straight line to be screened is less than or equal to the length of the shortest straight line to be screened of the two straight lines to be screened, and/or the length of the longest straight line to be screened of the two straight lines to be screened is greater than or equal to the minimum size of the two-dimensional code;

obtaining a positioning point in the preprocessed image according to the target straight line;

and determining the ROI area of the input image according to the positioning points.

In an optional manner, the preprocessing the input image to obtain a preprocessed image further includes:

carrying out reduction processing on an input image to obtain a reduced image;

and carrying out fuzzy processing on the reduced image to obtain a preprocessed image.

In an optional manner, the performing line detection on the preprocessed image to obtain a line set, further includes:

and performing straight line detection on the preprocessed image through an LSD algorithm, acquiring the angle and the coordinate of each straight line and generating the straight line to be screened.

In an alternative form, the screening conditions further include:

and 5 times of the length of the shortest straight line to be screened in the two straight lines to be screened is greater than or equal to the length of the other straight line to be screened.

In an optional manner, the obtaining the anchor point in the preprocessed image according to the target straight line further includes:

calculating the first edge intensity of the preprocessed image, and calculating to obtain a first edge image of the preprocessed image according to the first edge intensity;

carrying out binarization processing on the first edge image to obtain a first processed image;

and obtaining a first positioning point in the first processed image according to the positioning straight line.

and expanding the first positioning point by n units to obtain a second positioning point, wherein n is set according to the size of the input image.

In an alternative mode, the obtaining the ROI region in the input image according to the anchor point further includes:

mapping the second positioning point to the input image to obtain a positioning area;

carrying out fuzzy processing on the positioning area to obtain a smooth area;

calculating second edge intensity of the smooth area, and calculating a second edge image of the smooth area according to the second edge intensity;

carrying out binarization processing on the second edge image to obtain a second processed image;

obtaining a third positioning point in the second processing image according to the second positioning point;

and mapping the third positioning point to the input image to obtain the ROI area.

extending a plurality of target straight lines;

and acquiring the intersection points of the plurality of target straight lines as positioning points.

According to another aspect of the embodiments of the present invention, there is provided a two-dimensional code positioning apparatus, including:

the preprocessing module is used for preprocessing an input image to obtain a preprocessed image;

the detection module is used for carrying out linear detection on the preprocessed image to obtain a linear line to be screened;

the screening module is used for screening the straight lines to be screened according to screening conditions to obtain target straight lines aiming at the frame position of the ROI of the two-dimensional code, wherein the screening conditions comprise that the included angle of the two straight lines to be screened is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or the distance between the end point of one straight line to be screened of the two straight lines to be screened and the nearest end point of the other straight line to be screened is less than or equal to the length of the shortest straight line to be screened of the two straight lines to be screened, and/or the length of the longest straight line to be screened of the two straight lines to be screened is greater than or equal to the minimum size of the two-dimensional code;

the first calculation module is used for obtaining positioning points in the preprocessed image according to the target straight line;

and the second calculation module is used for determining the ROI area of the input image according to the positioning points.

the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one program, and the program enables the processor to execute the operation of the two-dimensional code positioning method.

According to another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which at least one program is stored, and the program causes a two-dimensional code positioning apparatus to perform operations corresponding to the above-mentioned method.

According to the two-dimensional code positioning method, when the ROI area of the two-dimensional code is positioned, the input image can be preprocessed, the preprocessed image is obtained by preprocessing the input image, the target straight line meeting the requirement of reflecting the frame position of the ROI area of the two-dimensional code in the straight line to be screened in the preprocessed image is detected through the detection condition, the positioning point is obtained in the preprocessed image according to the target straight line, the ROI area in the input image can be obtained, and the positioning of the ROI area of the two-dimensional code is achieved.

In addition, the accuracy of two-dimensional code identification can be effectively improved, the two-dimensional code positioning method provided by the application can be suitable for two-dimensional code images under various conditions by preprocessing the input image to obtain the preprocessed image, for example, when the input image has uneven illumination, the positioning effect and the identification effect of the two-dimensional code are easily influenced, the preprocessed image is obtained by preprocessing the input image, the influence of the quality of the input image on the subsequent operation steps can be effectively reduced, the two-dimensional code with poor image conditions can also have a good positioning effect, the applicability of two-dimensional code positioning is improved, positioning points obtained through a target straight line are mapped back to the input image, namely, an accurate ROI (region of interest) area is obtained in the original image, the two-dimensional code positioning of the original image is separated from the positioning operation of the preprocessed image, the original image cannot be damaged, the positioning effect is improved, and by the method, the accuracy of two-dimensional code positioning can be improved, the parameter setting is simple, and the applicability is wide.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and in order that the technical solutions of the embodiments of the present invention can be clearly understood, the embodiments of the present invention can be implemented according to the content of the description, and the above and other objects, features, and advantages of the embodiments of the present invention can be more clearly understood, the detailed description of the present invention is provided below.

Drawings

The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 shows a schematic flow chart of a two-dimensional code positioning method provided by an embodiment of the present invention;

fig. 2 is a schematic flowchart illustrating an embodiment of a two-dimensional code positioning method according to an embodiment of the present invention;

fig. 3 is a schematic flowchart illustrating another embodiment of a two-dimensional code positioning method according to an embodiment of the present invention;

fig. 4 is a schematic flowchart illustrating a two-dimensional code positioning method according to another embodiment of the present invention;

fig. 5 is a schematic flowchart illustrating a two-dimensional code positioning method according to another embodiment of the present invention;

fig. 6 is a schematic structural diagram of a two-dimensional code positioning device according to an embodiment of the present invention;

fig. 7 shows a schematic structural diagram of a two-dimensional code positioning device according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein.

Aiming at the current common two-dimensional code positioning mode, the inventor notices that the existing two-dimensional code positioning mode usually carries out two-dimensional code positioning in a mode of opening operation on an original image, corrosion or expansion, more parameters need to be adjusted for operation, when the parameter adjustment is large, due to the characteristic of the corrosion method, the internal structure of the two-dimensional code is easily damaged, subsequent identification is influenced, when the parameter adjustment is too small, the interval between a midpoint and a point of the two-dimensional code cannot be well compensated, the straight line detection effect is poor, the positioning precision is not high, the positioning effect of the two-dimensional code with a slight or moderate bending edge is poor, when the illumination is uneven, the corresponding mode is not provided, the positioning effect is improved, and the two-dimensional code positioning precision is not high. Therefore, it is important to develop a two-dimensional code recognition method with simple recognition method, high accuracy and wide applicability.

In order to solve the problems, the inventor of the present application has designed a two-dimensional code positioning method through research, and the method includes preprocessing an input image to obtain a preprocessed image, performing line detection on the preprocessed image to obtain a line to be screened, screening the line to be screened according to screening conditions to obtain a target line, wherein the screening conditions are simple in calculation process and high in stability, positioning points are obtained in the preprocessed image according to the target line, and finally an ROI region of the input image is determined according to the positioning points, so that the risk that the original image is directly processed and the two-dimensional code structure of the original image is easily damaged is avoided, and the precision and the applicability of two-dimensional code positioning are improved.

Fig. 1 shows a flowchart of a two-dimensional code positioning method provided in an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:

step 110: and preprocessing the input image to obtain a preprocessed image.

In this step, the input image refers to an image including a two-dimensional code acquired by a sensor, the input image may be acquired synchronously by a user holding a camera in a shooting process, or an image pre-stored in an input storage device may be used as the input image, a source and an acquisition means of the input image may be flexibly selected according to actual needs, and only the input image capable of being processed by a processor needs to be acquired, which is not particularly limited in the embodiment of the present application.

In this step, the preprocessing refers to preprocessing performed on the input image before formally starting the two-dimensional code recognition, so as to enable the input image to be more conveniently subjected to the two-dimensional code recognition, including but not limited to sharpening, blurring, cropping, warping, scaling, and the like, and may also be used to adjust other parameters of the input image, which is not particularly limited in this embodiment of the present application, and the preprocessed image refers to an adjusted input image obtained after performing a preprocessing operation for arbitrary parameter adjustment on the input image.

The input image is preprocessed to obtain the preprocessed image, so that the original image used for identifying the two-dimensional code can be identified more conveniently through preprocessing, and convenience is provided for subsequent operation.

Step 120: and carrying out linear detection on the preprocessed image to obtain a linear line to be screened.

In this step, the line detection is performed on the preprocessed image, and the line detection mode may be various, for example, an LSD line detection algorithm, a Hough _ line detection algorithm, an FLD line detection algorithm, an EDlines line detection algorithm, an LSWMS line detection algorithm, a CannyLines line detection algorithm, an MCMLSD line detection algorithm, or an LSM line detection algorithm is used, and the Hough _ line detection algorithm is commonly used for line detection, circle detection, ellipse detection, and the like, and is a more commonly used line detection algorithm; the LSD linear detection algorithm is a linear detection algorithm integrated in opencv, the linear detection effect of the algorithm is superior to that of the Hough algorithm, and the LSD linear detection algorithm has better detection speed; the FLD linear detection algorithm uses line characteristics to replace point characteristics for linear detection, and has better robustness; the EDlines straight line detection algorithm is a rapid line segment detector without parameters, and the detection speed is high; the LSWMS linear detection algorithm is a linear detection algorithm which performs compromise between detection precision and detection speed; the CannyLines linear detection algorithm extracts the edge mapping of the image and detects a meaningful line segment through fitting and verification, and the CannyLines linear detection algorithm has good effect in an artificial scene; the MCMLSD straight line detection algorithm is a Markov chain edge line segment detector and has a good detection effect; the LSM line detection algorithm is a line merging algorithm, and can make the merged line segment more accurate by grouping line segments and sequentially merging line segment pairs satisfying the adaptive merging criterion in each group into one line segment. According to actual needs, one or more of the above linear detection algorithms can be adopted to perform linear detection on the preprocessed image so as to obtain a linear line to be screened, or other different linear detection algorithms can be adopted, and only the linear segment in the preprocessed image can be conveniently and accurately obtained, so that the embodiment of the application is not specially limited.

The to-be-screened straight line is detected by a straight line detection algorithm, and it can be understood that if the preprocessed image contains the two-dimensional code, after the straight line detection is performed, the obtained to-be-screened straight line is multiple and contains straight line segments capable of reflecting the frame position of the ROI area of the two-dimensional code to a certain extent.

The line to be screened is obtained by performing line detection on the preprocessed image, most of line data can be obtained from the preprocessed image, and the line segments capable of reflecting the frame position of the ROI area of the two-dimensional code can be conveniently and further extracted for providing a data base.

Step 130: screening straight lines to be screened according to screening conditions to obtain target straight lines aiming at the frame position of the ROI of the two-dimensional code, wherein the screening conditions comprise that the included angle of the two straight lines to be screened is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or the distance between the end point of one straight line to be screened in the two straight lines to be screened and the nearest end point of the other straight line to be screened is less than or equal to the length of the shortest straight line to be screened in the two straight lines to be screened, and/or the length of the longest straight line to be screened in the two straight lines to be screened is greater than or equal to the minimum size of the two-dimensional code.

In this step, the purpose of screening the lines to be screened is to find out line segments, called target lines, in all the lines to be screened, where the line segments can reflect the position of the ROI border of the two-dimensional code, where the position of the ROI border of the two-dimensional code may be the L-edge position of the two-dimensional code, and the like. The line segment capable of reflecting the frame position of the two-dimensional code ROI area refers to a line segment which is completely or partially overlapped with a two-dimensional code frame line, and the essence of the line segment is that if a straight line to be screened is completely or partially overlapped with the two-dimensional code frame line, the straight line to be screened is regarded as a target straight line, parameters of the straight line to be screened can be used as parameters of the two-dimensional code frame line to participate in calculation, the mode that the straight line to be screened is completely overlapped with the two-dimensional code frame line is judged to be a screening condition, different conditions to be screened can be selected according to actual needs and characteristics of the two-dimensional code frame line, and the method is not specially limited.

In this step, if the input image includes the two-dimensional code image, the two-dimensional code image may not be a square rectangle due to a change in the shooting angle, and therefore, the included angle between the two to-be-screened straight lines is greater than or equal to 75 degrees and less than or equal to 105 degrees as one of the screening conditions, and the to-be-screened straight line capable of reflecting the frame position of the ROI area of the two-dimensional code in the to-be-screened straight line can be better screened as the target straight line.

In this step, since the line detection in step 120 may not completely identify the complete two-dimensional code frame line, and the obtained line segment may be an incoherent line segment, the length of the shortest line to be screened, which is less than or equal to the distance between the end point of one line to be screened of the two lines to be screened and the end point of the other line to be screened, is taken as one of the screening conditions, and the incoherent line to be screened, which is detected by the line detection method in step 120 and can reflect the frame position of the two-dimensional code ROI area, can be better screened as the target line.

In this step, since the length of the frame line of the two-dimensional code cannot be smaller than the minimum size of the two-dimensional code, the minimum size refers to the minimum size under the ordinary conditions in the field of application of the two-dimensional code, for example, in the industrial field, when the two-dimensional code is used for being read by an industrial bar code gun, according to the current technical level, the size of the two-dimensional code can still be guaranteed to be successfully read, under the condition that the precision of reading equipment is sufficient, the laser engraving machine is adopted for printing the two-dimensional code, the minimum size capable of being printed is 0.12x0.12mm, when the two-dimensional code is used for being scanned by a shop scanner, the size is usually not smaller than 20.3x20.3mm, therefore, the length of the longest line to be screened among two lines to be screened is greater than or equal to the minimum size of the two-dimensional code, as one of the screening conditions, the line to be screened obtained in step 120 can be better screened according to the actual situation to obtain a target line, it should be understood that the two-dimensional code is substituted into different reading equipment or different printing equipment, different screening conditions can be applied to different two-dimensional codes, and different technical limitations can be selected according to different embodiments of this field, and the minimum size can be selected according to different embodiments, and the present invention.

Through setting up the screening condition, can be more accurate screen out the target straight line that can reflect the regional frame position of two-dimensional code ROI from waiting to screen the straight line, and the screening condition judgement mode that sets up based on the conventional specification of two-dimensional code is simple effective, need not carry out more parameter operation, has promoted recognition efficiency and recognition accuracy, provides the data basis for follow-up location calculation.

Step 140: and obtaining positioning points in the preprocessed image according to the target straight line.

In this step, the target line refers to a line capable of reflecting the frame position of the ROI region of the two-dimensional code, and therefore, four corner points, i.e., positioning points, of the two-dimensional code in the preprocessed image can be calculated according to the target line.

The method for obtaining the locating point in the preprocessed image according to the target straight line specifically includes the steps of obtaining an edge image of the preprocessed image by calculating the edge intensity of the preprocessed image, carrying out binarization on the edge image to obtain a binarized image, and obtaining the intersection point of a plurality of target straight lines as the locating point.

The acquisition mode of the intersection point can be obtained by adopting a simultaneous equation set, the expressions of the two target straight lines are determined according to the straight line data obtained in the step 120, the intersection point of the two target straight lines is obtained by establishing the simultaneous equation set through the expressions, the two straight lines can be prolonged through the expressions of the two target straight lines until the intersection point is generated on the preprocessed image, and the intersection point is obtained through image recognition.

In some embodiments, in order to facilitate calculation of the edge strength of the preprocessed image and obtain an edge image with a better effect, any one target straight line may be selected before the edge strength is calculated, and the preprocessed image is wholly rotated according to the direction of the target straight line, so that at least part of the target straight line in the preprocessed image is in a horizontal or vertical state.

In some embodiments, in order to make the obtained edge image more effective, when calculating the edge intensity of the preprocessed image, the edge intensities of multiple directions on the preprocessed image may be calculated, and then the edge intensities of the multiple directions are averaged, and then the edge image is obtained by averaging the edge intensities.

In some embodiments, when the edge image is binarized, an OTSU binarization method with relatively balanced energy efficiency may be used to binarize the edge image in order to balance the effect and the time consumption.

In some embodiments, in order to mitigate the influence of the size difference between the preprocessed image and the input image on the fineness of the anchor points, after the intersection points of a plurality of target straight lines are obtained, each intersection point may be expanded outwards or contracted inwards by the same unit size to adapt to the parameter difference between the preprocessed image and the input image, the expanded or contracted unit size may be set according to the sizes of the preprocessed image and the input image for compensation, and then the expanded or contracted intersection points are used as the anchor points.

In some embodiments, a positioning point may also be obtained in the preprocessed image according to the target line by generating a training model through machine learning, and the target line is input into the model to obtain the positioning point.

In some embodiments, the positioning points may be obtained in the preprocessed image according to the target line in an image recognition manner, for example, the target line in the preprocessed image is subjected to image recognition, and the corner points corresponding to the frame positions of the ROI region of the two-dimensional code are recognized as the positioning points.

By obtaining the positioning points on the preprocessed image, the subsequent calculation can be conveniently remapped to the input image more accurately according to the positioning points on the preprocessed image, and the actual two-dimensional code area is positioned on the input image, so that a data basis is provided for the subsequent calculation.

Step 150: and determining the ROI area of the input image according to the positioning points.

In this step, the ROI region of the input image is determined according to the anchor points, specifically, the ROI region in the input image is determined by mapping the anchor points obtained in step 140 into the input image.

In some embodiments, in order to improve the accuracy of the obtained ROI region, after the anchor points are mapped back into the input image, an initial two-dimensional code region may be obtained according to positions of the anchor points in the input image, the initial two-dimensional code region is subjected to blurring and binarization processing, the anchor points are further modified in the processed binarized image, and then the modified anchor points are mapped back into the input image to obtain the ROI region.

The step of further correcting the locating point in the processed binary image means that if the locating point is obviously deviated from a corresponding position in the processed binary image, namely the intersection point of the target straight line, the position of the deviated locating point is updated to the corresponding position, and other position correction methods can be adopted to correct the position of the locating point according to actual needs, so that the locating point can more accurately reflect the end point of the two-dimensional code region.

The initial two-dimensional code area is subjected to fuzzy processing by adopting Gaussian fuzzy.

In some embodiments, in order to improve the definition of the binarized image, before the binarization processing is performed on the initial two-dimensional code region, the edge intensity of the initial two-dimensional code region may be calculated and an edge image is obtained, and then the binarization processing is performed on the edge image.

In addition, in step 140 and step 150, the manner of obtaining the edge image may adopt various manners, for example, calculating an average value of the edge intensities in different directions, and obtaining the edge image according to the average value, which is not particularly limited in this embodiment of the present application. The binarization method may also be implemented in various manners, which is not limited in this embodiment of the present application.

Through the combination of the

above steps

110, 120, 130, 140 and 150, according to the two-dimensional code positioning method provided by the application, when the two-dimensional code ROI region is positioned, the input image may be preprocessed, the preprocessed image may be obtained by preprocessing the input image, the target straight line satisfying the condition that the frame position of the two-dimensional code ROI region can be reflected in the straight line to be screened in the preprocessed image may be detected through the detection condition, the positioning point may be obtained in the preprocessed image according to the target straight line, the ROI region in the input image may be obtained, and the positioning of the two-dimensional code ROI region may be achieved.

The two-dimensional code positioning method provided by the embodiment of the application can effectively improve the accuracy of two-dimensional code identification, and the two-dimensional code positioning method provided by the application can be suitable for two-dimensional code images under various conditions by preprocessing the input image to obtain the preprocessed image, for example, when the input image has uneven illumination, the positioning effect and the identification effect of the two-dimensional code are easily influenced, the preprocessed image is obtained by preprocessing the input image, the influence of the quality of the input image on the subsequent operation steps can be effectively reduced, the two-dimensional code with poor image conditions can also have a good positioning effect, the applicability of two-dimensional code positioning is improved, the positioning point obtained through a target straight line is mapped back to the input image, namely, an accurate two-dimensional code ROI area is obtained in the original image, the two-dimensional code positioning of the original image is separated from the positioning operation of the preprocessed image, the original image cannot be damaged, the positioning effect is improved, and by the method, the accuracy of two-dimensional code positioning can be improved, and the applicability is simple and wide.

As shown in FIG. 2, in one embodiment of the present invention, step 110 further comprises:

step a01: carrying out reduction processing on an input image to obtain a reduced image;

step a02: and carrying out fuzzy processing on the reduced image to obtain a preprocessed image.

In step a01, the purpose of reducing the input image is to reduce the detection pressure of the straight line detection method on the curved straight line in the subsequent steps to a certain extent by reducing the input image if the input image has a straight line curve, so as to improve the detection effect, and different reduction ratios can be selected according to actual situations, which is not particularly limited in the embodiment of the present application.

In step a02, the reduced image is blurred to obtain a preprocessed image, so that if a curved straight line which may be difficult to be identified by a straight line detection method in a subsequent step still exists in the reduced image, the probability that the curved straight line is successfully identified in the subsequent step can be further improved by blurring the reduced image, and a blur kernel and a blur mode with different proportions can be selected according to actual situations, for example, gaussian blur of a 7 × 7 blur kernel is adopted.

The input image is reduced and blurred to obtain the preprocessed image, so that the curvature of lines in the input image is reduced, the success rate of recognizing curved lines in subsequent steps is higher, the success rate of a two-dimensional code positioning method is improved, and the applicability is expanded.

As shown in fig. 2, in one embodiment of the present invention, step 120 further comprises:

step b01: and performing straight line detection on the preprocessed image through an LSD algorithm, acquiring the angle and the coordinate of each straight line and generating a straight line to be screened.

In step b01, the line detection is performed on the preprocessed image through the LSD algorithm, so as to find out all lines in the preprocessed image, and since the frames of the two-dimensional code are substantially all lines, it can be understood that as long as all lines in the preprocessed image are correctly obtained, the frame lines of the two-dimensional code are inevitably included, so that a data basis is provided for the accurate positioning of the two-dimensional code ROI region in the subsequent step.

In the step b01, the step of obtaining the angle and the coordinate of each straight line and generating the straight line to be screened refers to the step of synchronously obtaining the detected coordinate and the detected angle of each straight line, wherein the angle and the detected coordinate of each straight line can be stored in a set, and the data correspond to the straight lines to be screened one by one.

In order to position the obtained straight lines in the subsequent steps and the like so as to obtain an accurate ROI (region of interest) of the two-dimensional code, the angle and the coordinate of each straight line are obtained while the straight lines are detected in the straight line detection, so that a data base is provided for subsequent calculation, and the straight lines to be screened are generated to be used for further screening the frame straight lines of the two-dimensional code subsequently.

As shown in fig. 2, in one embodiment of the present invention, the screening conditions further comprise:

Because the aspect ratio of the two-dimensional code in the common specification rarely exceeds 5 times, the frame straight line of the two-dimensional code with most conventional specifications can be successfully screened by setting the length of the shortest straight line to be screened, which is 5 times or more greater than or equal to the length of the other straight line to be screened, in the two straight lines to be screened as the screening condition.

As shown in fig. 3, in one embodiment of the present invention, step 140 further comprises:

step c01: calculating the first edge intensity of the preprocessed image, and calculating to obtain a first edge image of the preprocessed image according to the first edge intensity;

step c02: carrying out binarization processing on the first edge image to obtain a first processed image;

and c03: and obtaining a first positioning point in the first processed image according to the positioning straight line.

In step c01, the first edge strength refers to the edge strength of the preprocessed image, the edge strength is substantially the amplitude of the gradient of the edge point, the most basic feature of the image is the edge, the edge refers to the set of pixels with step change in the gray level of the surrounding pixels, and the point between a pair of adjacent points with significantly different gray levels of the two pixels is called the edge point.

In step c01, further, in order to improve the effect of the first edge image, the first edge intensity of the pre-processed image is calculated, and the first edge image of the pre-processed image calculated according to the first edge intensity may be calculated by calculating edge intensities of the pre-processed image in a plurality of directions, averaging the edge intensities in the plurality of directions as the first edge intensity, for example, calculating edge intensities in four directions of-45 degrees, 0 degrees, 45 degrees and 90 degrees, averaging the edge intensities in the four directions as the first edge intensity, and calculating the first edge image of the pre-processed image according to the first edge intensity.

The edge intensities in the multiple directions are calculated, and the average value of the edge intensities in the multiple directions is calculated to obtain the first edge image of the preprocessed image, so that the edge image is clearer, and the effect that the subsequent steps are not beneficial to positioning of the two-dimensional code is not easily generated by further processing the first edge image, such as edge blurring.

In step c02, different binarization methods may be used to perform binarization processing on the first edge image, for example, an iterative threshold method, a P-partition method, a minimum error-based global threshold method, a local threshold method, and a method in which a global threshold is combined with a local threshold, where an OTSU binarization method is used in this embodiment of the present application.

The first edge image is subjected to binarization processing, so that the first edge image is changed into a black-and-white image, the influence of illumination in the input image on the positioning effect can be reduced, if the input image has an uneven illumination phenomenon, when a two-dimensional code ROI area is subsequently positioned, the positioning error or the positioning accuracy is possibly caused by the illumination reason, and the influence of the uneven illumination can be reduced through the step c 02.

In step c03, further, in order to improve the accuracy of the first positioning point, the first positioning point may be expanded outward by n pixels to adapt to the parameter difference between the preprocessed image and the input image, and the expanded pixel size n may be set according to the size of the preprocessed image and the input image, so as to perform compensation to improve the accuracy.

Through the combination of the steps c01, c02 and c03, the first positioning point is obtained in the preprocessed image after the edge strength and binarization processing, so that the positioning accuracy can be effectively improved, the influence of the shooting quality of the input image, namely the original image or environmental factors on the positioning effect is avoided, and an accurate data basis is provided for obtaining a final positioning result by subsequent mapping back to the original image.

step c04: expanding the first positioning point by n units to obtain a second positioning point, wherein n is set according to the size of the input image;

in step c04, since the ratio of the pre-processed image to the input image may be different, the first fixed point obtained in the pre-processed image does not necessarily guarantee the accuracy in the input image, so the position of the first fixed point is expanded, the unit number n of the expansion is set according to the size of the input image, and may be generally set to 1 to 10 pixels, and n is set to 5 by default in the experiment.

By expanding the first positioning point, the position of the obtained second positioning point in the input image, namely the original image, is more accurate, and the two-dimensional code ROI area in the original image can be more accurately reflected.

As shown in fig. 4, in one embodiment of the present invention, step 150 further comprises:

step d01: mapping the second positioning point to the input image to obtain a positioning area;

step d02: carrying out fuzzy processing on the positioning area to obtain a smooth area;

step d03: calculating second edge intensity of the smooth area, and calculating a second edge image of the smooth area according to the second edge intensity;

step d04: carrying out binarization processing on the second edge image to obtain a second processed image;

step d05: obtaining a third positioning point in the second processed image according to the second positioning point;

step d06: and mapping the third positioning point to the input image to obtain the ROI area.

In step d01, since the ROI region of the two-dimensional code needs to be obtained in the original image for two-dimensional code recognition, the second localization point obtained in step c04 is mapped to the input image, and the obtained localization region is the more accurate ROI region of the two-dimensional code.

In step d02, there are various ways to perform blur processing on the positioning region, such as gaussian blur, salt and pepper blur, motion blur, and the like, and different image blur methods may be used to perform blur processing on the positioning region according to actual situations, in the embodiment of the present application, gaussian blur is used to perform blur processing on the positioning region.

The smooth area is obtained by carrying out fuzzy processing on the positioning area, so that the phenomenon of discontinuity between points is not easy to occur in the positioning area, the binarization processing in the subsequent steps is convenient, and the processing effect of the subsequent steps can be improved.

In step d03, the second edge intensities of the smooth region may be calculated in various manners, for example, calculating the edge intensities in multiple directions of the smooth region, averaging the edge intensities in the multiple directions to obtain the second edge intensity, for example, calculating the edge intensities in four directions of-45 degrees, 0 degrees, 45 degrees, and 90 degrees, averaging the edge intensities in the four directions to obtain the second edge intensity, and then calculating the second edge image of the smooth region according to the second edge intensity.

The second edge image of the smooth area is obtained by calculating the second edge strength of the smooth area and calculating, so that the boundary of the image of the smooth area is clearer, the two-dimensional code can be positioned in the subsequent steps more conveniently, and a data basis is provided for the subsequent steps.

In step d04, there may be a variety of manners for performing binarization processing on the second edge image to obtain a second processed image, for example, an OSTU method is used to perform binarization processing on the second edge image, where the OSTU method is used in the embodiment of the present application.

In the step d02, the step d03 and the step d04, the positioning region obtained in the step d01 is processed to obtain a binary image of the positioning region, and then a third positioning point is obtained in the binary image of the positioning region according to the second positioning point, so that the influence of the type of the two-dimensional code on the fineness can be further reduced, and the two-dimensional code with the black background and the white background can be kept with good positioning accuracy.

In step d05, a third positioning point is obtained in the second processed image according to the second positioning point, which means that the position of the second positioning point in the second processed image is modified to be closer to four corner points of the two-dimensional code frame in the second processed image, so as to obtain the third positioning point. The position correction method for the second positioning point may adopt various manners, for example, image correction, image registration, coordinate transformation, and the like, which is not particularly limited in this embodiment of the present application.

In step d06, since the final positioning two-dimensional code needs to be positioned in the original image, that is, in the input image, so as to ensure the integrity and definition of the two-dimensional code image as much as possible, a third positioning point needs to be mapped into the input image. The third positioning point is transformed into the input image through image mapping, that is, an image method in the image is adopted to place the image or a part of the image in another image so that the image or the part of the image can be aligned with a specified region or a marker, the mapping in the embodiment of the present application may be to keep the third positioning point overlapped with the position of the original third positioning point in the input image, or keep the original ratio with the border and the center of the image, the type of the image mapping may adopt translation, rotation, scale transformation, affine transformation or perspective transformation, and only the third positioning point is required to be kept overlapped with four corner points of the two-dimensional code in the input image as far as possible, and the embodiment of the present application is not particularly limited to this.

Through the steps d01, d02, d03, d04, d05 and d06, the second positioning point is mapped back into the input image to obtain the positioning area, the positioning area is processed to obtain the smooth area, the problem that intervals exist between points in the image can be avoided, the positioning area is processed to obtain the binary image, the influence of uneven illumination in the input image on the positioning accuracy can be reduced, the positioning accuracy and the applicability of the two-dimensional code can be improved, the third positioning point is obtained in the second processed image according to the second positioning point, the newly obtained positioning point can be corrected according to the second processed image, the obtained third positioning point is more accurate, the third positioning point is mapped back into the input image to obtain the accurate positioning area in the original image, and the two-dimensional code area which can be identified finally is in the area range without any processing, and the identification accuracy of the two-dimensional code cannot be influenced.

As shown in fig. 5, in one embodiment of the present invention, step 140 further comprises:

step e01: extending a plurality of target straight lines;

step e02: and acquiring intersection points of the target straight lines as positioning points.

In step e01, because the line detection may obtain an incomplete line, that is, a non-continuous line, the target line obtained after screening may be an incomplete line segment, and according to the property of the two-dimensional code endpoint, the intersection point of the two lines of the two-dimensional code frame is inevitably an endpoint of the two-dimensional code, that is, a locating point, so that by extending the multiple target lines, the incomplete target lines can be prevented from causing no intersection point, and the problem that accurate locating points cannot be obtained through the intersection point is avoided.

In step e02, due to the property of the two-dimensional code ROI region, the end point of the two-dimensional code ROI region can be obtained more accurately by obtaining the intersection point of the target straight line as the positioning point.

Fig. 6 shows a functional block diagram of a two-dimensional code positioning apparatus 600 according to an embodiment of the present invention. As shown in fig. 6, the apparatus includes: a preprocessing module 610, a detection module 620, a screening module 630, a first calculation module 640, and a second calculation module 650.

The preprocessing module 610 is configured to preprocess an input image to obtain a preprocessed image;

the detection module 620 is configured to perform linear detection on the preprocessed image to obtain a linear line to be screened;

the screening module 630 is configured to screen the to-be-screened straight lines according to screening conditions to obtain target straight lines for the frame position of the ROI area of the two-dimensional code, where the screening conditions include that an included angle between two to-be-screened straight lines is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or a distance between an end point of one of the two to-be-screened straight lines and a nearest end point of the other to-be-screened straight line is less than or equal to a length of a shortest to-be-screened straight line of the two to-be-screened straight lines, and/or a length of a longest to-be-screened straight line of the two to-be-screened straight lines is greater than or equal to a minimum size of the two-dimensional code;

the first calculation module 640 is used for obtaining positioning points in the preprocessed image according to the target straight line;

a second calculation module 650 for determining the ROI area of the input image based on the anchor points.

In some embodiments, the pre-processing module 610 further comprises:

the zooming unit is used for carrying out zooming-out processing on the input image to obtain a zoomed-out image;

and the first blurring unit is used for blurring the reduced image to obtain a preprocessed image.

In some embodiments, the detection module 620 further comprises:

and the detection unit is used for carrying out straight line detection on the preprocessed image through an LSD algorithm, acquiring the angle and the coordinate of each straight line and generating the straight line to be screened.

In some embodiments, the first calculation module 640 further comprises:

the first calculation unit is used for calculating the first edge intensity of the preprocessed image and calculating the first edge image of the preprocessed image according to the first edge intensity;

the first processing unit is used for carrying out binarization processing on the first edge image to obtain a first processed image;

and the second calculation unit is used for obtaining a first positioning point in the first processing image according to the positioning straight line.

In some embodiments, the first calculation module 640 further comprises:

and the third calculating unit is used for expanding the first positioning point by n units to obtain a second positioning point, and n is set according to the size of the input image.

In some embodiments, the second calculation module 650 further comprises:

the fourth calculation unit is used for mapping the second positioning point to the input image to obtain a positioning area;

the second fuzzy unit is used for carrying out fuzzy processing on the positioning area to obtain a smooth area;

the fifth calculating unit is used for calculating the second edge intensity of the smooth area and obtaining a second edge image of the smooth area according to the second edge intensity;

the second processing unit is used for carrying out binarization processing on the second edge image to obtain a second processed image;

a sixth calculating unit, configured to obtain a third positioning point in the second processed image according to the second positioning point;

and the seventh calculating unit is used for mapping the third positioning points to the input image to obtain the ROI area.

In some embodiments, the first calculation module 640 further comprises:

the third processing unit is used for prolonging the target straight lines;

and the eighth calculating unit is used for acquiring the intersection points of the plurality of target straight lines as positioning points.

Fig. 7 is a schematic structural diagram of a two-dimensional code positioning device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the two-dimensional code positioning device.

As shown in fig. 7, the two-dimensional code positioning apparatus may include: a processor 702, a memory 706, a communication interface 704, and a communication bus 708.

The processor 702, memory 706 and communication interface 704 communicate with one another via a communication bus 708.

The memory 706 is utilized for storing at least one program 710, and the program 710 enables the processor 702 to perform the related steps in the above embodiments of the two-dimensional code positioning method.

The embodiment of the invention also provides a computer-readable storage medium, wherein at least one program is stored in the storage medium, and when the program runs on the two-dimensional code positioning device, the two-dimensional code positioning device can execute the two-dimensional code positioning method in any embodiment.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims

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

preprocessing an input image to obtain a preprocessed image;

performing linear detection on the preprocessed image to obtain a to-be-screened straight line;

screening the straight lines to be screened according to screening conditions to obtain target straight lines aiming at the frame position of the ROI of the two-dimensional code, wherein the screening conditions comprise that the included angle of the two straight lines to be screened is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or the distance between the end point of one straight line to be screened and the nearest end point of the other straight line to be screened is less than or equal to the length of the shortest straight line to be screened in the two straight lines to be screened, and/or the length of the longest straight line to be screened in the two straight lines to be screened is greater than or equal to the minimum size of the two-dimensional code;

obtaining positioning points in the preprocessed image according to the target straight line;

2. The two-dimensional code positioning method according to claim 1, wherein the preprocessing the input image to obtain a preprocessed image further comprises:

carrying out reduction processing on the input image to obtain a reduced image;

and carrying out fuzzy processing on the reduced image to obtain the preprocessed image.

3. The two-dimensional code positioning method according to claim 1, wherein the performing of line detection on the preprocessed image to obtain a line to be screened further comprises:

4. The two-dimensional code positioning method according to claim 1, wherein the screening condition further includes:

5. The two-dimensional code positioning method according to claim 1, wherein the obtaining of the positioning point in the preprocessed image according to the target straight line further comprises:

calculating first edge intensity of the preprocessed image, and calculating to obtain a first edge image of the preprocessed image according to the first edge intensity;

6. The two-dimensional code positioning method according to claim 5, wherein the obtaining of the positioning point in the preprocessed image according to the target straight line further comprises:

and extending the first positioning point by n units to obtain a second positioning point, wherein n is set according to the size of the input image.

7. The two-dimensional code positioning method according to claim 6, wherein the determining the ROI area of the input image according to the positioning points further comprises:

carrying out fuzzy processing on the positioning area to obtain a smooth area;

and mapping the third positioning points to the input image to obtain the ROI area.

8. The two-dimensional code positioning method according to claim 1, wherein the obtaining of the positioning point in the preprocessed image according to the target straight line further comprises:

extending a plurality of the target straight lines;

and acquiring the intersection points of the target straight lines as the positioning points.

9. The utility model provides a two-dimensional code positioner which characterized in that includes:

the screening module is used for screening the straight lines to be screened according to screening conditions to obtain target straight lines aiming at the frame position of the ROI of the two-dimensional code, wherein the screening conditions comprise that the included angle of the two straight lines to be screened is greater than or equal to 75 degrees and less than or equal to 105 degrees, and/or the distance between the end point of one straight line to be screened and the nearest end point of the other straight line to be screened is less than or equal to the length of the shortest straight line to be screened in the two straight lines to be screened, and/or the length of the longest straight line to be screened in the two straight lines to be screened is greater than or equal to the minimum size of the two-dimensional code;

10. A computer-readable storage medium, in which at least one program is stored, which, when run on a two-dimensional code positioning apparatus, causes the two-dimensional code positioning apparatus to perform the operations of the two-dimensional code positioning method according to any one of claims 1 to 8.