CN112580383B

CN112580383B - Two-dimensional code identification method and device, electronic equipment and storage medium

Info

Publication number: CN112580383B
Application number: CN202011590063.9A
Authority: CN
Inventors: 孙萍; 李玉笛; 支洪平
Original assignee: Iflytek Suzhou Technology Co Ltd
Current assignee: Iflytek Suzhou Technology Co Ltd
Priority date: 2020-12-29
Filing date: 2020-12-29
Publication date: 2023-08-29
Anticipated expiration: 2040-12-29
Also published as: CN112580383A

Abstract

The invention provides a two-dimensional code identification method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: dividing a two-dimensional code array diagram to be identified to obtain a plurality of two-dimensional codes; based on the adjacent enhancement mode, identifying the current two-dimensional code to obtain an identification result of the current two-dimensional code; the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes of the current two-dimensional code in the two-dimensional code array diagram. The method, the device, the electronic equipment and the storage medium provided by the invention realize batch identification of all the two-dimensional codes in the two-dimensional code array diagram, reduce the identification time in the process of batch identification of the two-dimensional codes, reduce the complexity of an identification algorithm and improve the efficiency of batch identification of the two-dimensional codes.

Description

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

Technical Field

The invention relates to the technical field of image recognition, in particular to a two-dimensional code recognition method, a two-dimensional code recognition device, electronic equipment and a storage medium.

Background

In the fields of biology, medical research and the like, a large amount of pharmaceutical reagents or biological samples are often required to be analyzed and processed. These reagents and samples are typically stored in reagent tubes. The two-dimensional code carrying the identification information is imprinted on the top or the bottom of the reagent tube, and the two-dimensional code is identified by utilizing an image processing and identification technology, so that the automatic management of sample information can be realized.

In the prior art, one or a few two-dimensional codes are usually scanned and identified. The existing two-dimensional code identification method cannot realize batch identification of the two-dimensional codes, and is low in identification success rate.

Disclosure of Invention

The invention provides a two-dimensional code identification method, a device, electronic equipment and a storage medium, which are used for solving the problems that batch identification of two-dimensional codes cannot be realized and the identification success rate is low in the prior art.

The invention provides a two-dimensional code identification method, which comprises the following steps:

dividing a two-dimensional code array diagram to be identified to obtain a plurality of two-dimensional codes;

based on the adjacent enhancement mode, identifying the current two-dimensional code to obtain an identification result of the current two-dimensional code;

the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes of the current two-dimensional code in the two-dimensional code array diagram.

According to the two-dimensional code identification method provided by the invention, the method for identifying the current two-dimensional code based on the adjacent enhancement mode, to obtain the identification result of the current two-dimensional code, comprises the following steps:

taking an image enhancement result of the current two-dimensional code in the adjacent enhancement mode as a graph to be identified;

Carrying out two-dimensional code recognition on the graph to be recognized;

if the identification is successful, taking a result obtained by identifying the two-dimensional code as an identification result of the current two-dimensional code, otherwise taking an image enhancement result of the current two-dimensional code in other image enhancement modes as a graph to be identified;

the rest image enhancement modes are image enhancement modes except the adjacent enhancement modes.

According to the two-dimensional code identification method provided by the invention, the current two-dimensional code is identified based on the adjacent enhancement mode, the identification result of the current two-dimensional code is obtained, and then the method further comprises the following steps:

based on the identification results of each two-dimensional code in at least two-dimensional code array diagrams, determining the known two-dimensional code successfully identified in each two-dimensional code array diagram; the at least two-dimensional code array diagrams are acquired from the same two-dimensional code array;

aligning each two-dimensional code array diagram based on the position of the known two-dimensional code in each two-dimensional code array diagram;

and merging the identification results of the two-dimensional codes in the aligned two-dimensional code array graphs to obtain the identification results of the two-dimensional codes in the two-dimensional code arrays.

According to the two-dimensional code identification method provided by the invention, the method for aligning each two-dimensional code array diagram based on the position of the known two-dimensional code in each two-dimensional code array diagram comprises the following steps:

Using any two-dimensional code array diagram as a reference image, and determining the distance between the known two-dimensional code in the reference image and a reference origin;

determining the distance between the known two-dimensional code and each angle point in the rest two-dimensional code array diagrams;

if the distance between the known two-dimensional code and any one of the corner points is equal to the distance between the known two-dimensional code and the reference origin, taking the any one of the corner points as the reference origin of the rest two-dimensional code array diagrams;

and aligning each two-dimensional code array map based on the reference origin of the reference image and the reference origins of the rest two-dimensional code array maps.

According to the two-dimensional code identification method provided by the invention, the two-dimensional code array diagram to be identified is segmented to obtain a plurality of two-dimensional codes, and the two-dimensional code identification method comprises the following steps:

filling the unclosed holes in the binarized images of the two-dimensional code array map after corrosion operation based on the shape characteristics of the two-dimensional codes, and performing expansion operation on the filled binarized images to obtain candidate communication areas of each two-dimensional code;

and dividing the two-dimensional code array map based on the candidate connected region of each two-dimensional code to obtain a plurality of two-dimensional codes.

According to the two-dimensional code identification method provided by the invention, the two-dimensional code array diagram is divided based on the candidate communication area of each two-dimensional code to obtain a plurality of two-dimensional codes, and the two-dimensional code identification method comprises the following steps:

detecting candidate communication areas of each two-dimensional code to obtain a target area corresponding to each two-dimensional code;

and dividing the two-dimensional code array map based on the target area corresponding to each two-dimensional code to obtain a plurality of two-dimensional codes.

According to the two-dimensional code identification method provided by the invention, the two-dimensional code array diagram is divided based on the target area corresponding to each two-dimensional code to obtain a plurality of two-dimensional codes, and the two-dimensional code identification method comprises the following steps:

performing pixel traversal on a target area corresponding to each two-dimensional code in the two-dimensional code array diagram, and determining boundary coordinates of each two-dimensional code;

determining the size of the area of each two-dimensional code and the interval between the two-dimensional codes based on the boundary coordinates of each two-dimensional code;

and dividing the two-dimensional code array map based on the area size of each two-dimensional code and the interval between the two-dimensional codes to obtain a plurality of two-dimensional codes.

The invention also provides a two-dimensional code recognition device, which comprises

The segmentation unit is used for segmenting the two-dimensional code array diagram to be identified to obtain a plurality of two-dimensional codes;

The identification unit is used for identifying the current two-dimensional code based on the adjacent enhancement mode to obtain an identification result of the current two-dimensional code;

The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of any two-dimensional code identification method are realized when the processor executes the program.

The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the two-dimensional code recognition method as described in any one of the above.

According to the two-dimensional code identification method, the device, the electronic equipment and the storage medium, the current two-dimensional code is identified by adopting the image enhancement mode, the identification success rate of the two-dimensional code is improved under the conditions of non-ideal ambient light and low imaging quality, the current two-dimensional code is identified according to the image enhancement mode used for successfully identifying the adjacent two-dimensional code in the two-dimensional code array diagram, the identification result of the current two-dimensional code is obtained, batch identification of all the two-dimensional codes in the two-dimensional code array diagram is realized, the identification of a plurality of image enhancement results corresponding to the current two-dimensional code one by one is avoided, the identification time in the batch identification process of the two-dimensional code is shortened, the complexity of an identification algorithm is reduced, and the batch identification efficiency of the two-dimensional code is improved.

Drawings

In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a two-dimensional code identification method provided by the invention;

fig. 2 is a schematic flow chart of an embodiment of step 120 in the two-dimensional code identification method provided by the present invention;

FIG. 3 is a flowchart of an algorithm for identifying two-dimensional codes by adopting an adjacent enhancement mode;

fig. 4 is a flow chart of a two-dimensional code array diagram fusion recognition method provided by the invention;

fig. 5 is a schematic flow chart of an embodiment of step 140 in the two-dimensional code identification method provided by the present invention;

FIG. 6 is a schematic flow chart of a two-dimensional code alignment method provided by the invention;

fig. 7 is a schematic flow chart of an embodiment of step 110 in the two-dimensional code identification method provided by the present invention;

fig. 8 is a schematic flow chart of an embodiment of step 112 in the two-dimensional code identification method provided by the present invention;

Fig. 9 is a flowchart illustrating an embodiment of step 1122 in the two-dimensional code identification method provided by the present invention;

fig. 10 is a flow chart of a two-dimensional code batch identification method of a medical reagent tube provided by the invention;

FIG. 11 is a schematic diagram of a two-dimensional code recognition device according to the present invention;

fig. 12 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The two-dimensional Code is a common information carrier, has multiple categories of Data Matrix, QR Code, maxi Code, PDF417, code49 and the like, forms '0' and '1' bit streams of an internal logic foundation of a computer through the arrangement and combination of deep color and light color Code elements, realizes the coding and storage of Data text symbol information, and has the characteristics of high coding density, large information capacity, strong fault tolerance and the like. For example, a Data Matrix two-dimensional code may encode 30 digits over an area of only 25mm 2.

The two-dimensional code identification method in the prior art is suitable for scenes with relatively sparse two-dimensional code distribution, ideal illumination conditions and high imaging quality. For scenes with small two-dimensional code size, dense arrangement, complex environmental illumination and low imaging quality, the existing two-dimensional code identification method cannot identify or the identification efficiency and accuracy cannot reach the expected effect.

Fig. 1 is a schematic flow chart of a two-dimensional code identification method provided by the invention, as shown in fig. 1, the method includes:

and 110, dividing the two-dimensional code array diagram to be identified to obtain a plurality of two-dimensional codes.

Specifically, the two-dimensional code array map is an image obtained by collecting a plurality of two-dimensional codes arranged according to a certain rule. For example, the plurality of two-dimensional codes are arranged linearly, circumferentially or longitudinally and longitudinally, so that a corresponding two-dimensional code array map can be obtained. For example, in the medical field, a pharmaceutical reagent is generally stored in a reagent tube with a two-dimensional code label, the reagent tube is stored in a freezing box in batches, the freezing box mainly comprises a transparent plastic top cover and an opaque plastic bearing bottom, a supporting body adopts a grid-type clamping groove design, the reagent tube is ensured to be placed regularly and not easy to incline and fall off, a plurality of specifications and color designs are generally available, and the common design is 100 holes of 10 x 10, 50 holes of 5 x 10 and the like. And acquiring an image of the freezing box, so that an image containing the two-dimensional code array can be obtained, and processing the image, so that a two-dimensional code array image can be obtained.

And identifying the two-dimensional code array diagram, namely identifying the data information corresponding to each two-dimensional code in the two-dimensional code array diagram. Before identification, the two-dimensional code array diagram can be divided, so that a plurality of two-dimensional codes in the two-dimensional code array diagram are obtained.

Step 120, based on the adjacent enhancement mode, identifying the current two-dimensional code to obtain the identification result of the current two-dimensional code; the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes in the two-dimensional code array diagram.

Specifically, the identification result of the two-dimensional code is data information contained in the two-dimensional code. Image enhancement is to selectively highlight or suppress part of features in an image by adding information to the original image or performing data transformation. The image enhancement mode can be contrast enhancement, brightness compression and the like.

For example, histogram equalization may be employed to achieve contrast enhancement. Histogram equalization is a method in the field of image processing that uses image histograms to adjust the contrast of an image. A logarithmic (log) image enhancement may be employed to achieve brightness enhancement. The digital image enhancement can expand the low gray value part of the image, display more details of the low gray value part, compress the high gray value part of the image, and reduce the details of the high gray value part, thereby achieving the purposes of improving the brightness of the image and emphasizing the low gray value part of the image. Gamma (gamma) image enhancement may be employed to achieve brightness compression. The gamma image enhancement is mainly used for correcting images, and correcting images with over-high gray level or over-low gray level to realize brightness compression and enhance contrast. The acquisition environment illumination is complicated, so that the problems of poor image uniformity, local highlight coverage and the like of the two-dimensional code array image can exist, and meanwhile, the imaging quality of the equipment is low, so that the problems of geometric deformation, local imaging blurring and the like of the two-dimensional code array image can exist. The problem causes the phenomenon that the current two-dimensional code cannot be identified when being identified. The method can adopt an image enhancement mode to obtain a plurality of image enhancement results of the current two-dimensional code, and the recognition result of the current two-dimensional code is obtained after recognition. When the two-dimensional code array diagram has a large-area illumination abnormal condition, each two-dimensional code can be tried to be identified for many times to obtain a result, and the identification efficiency is seriously low.

Considering that the current two-dimensional code and the adjacent two-dimensional code have similar illumination characteristics, for example, each two-dimensional code in the illumination dark area can be successfully identified by an image enhancement mode of brightness improvement, and each two-dimensional code in the illumination dark area can be successfully identified by an image enhancement mode of brightness compression.

That is, in the same two-dimensional code array map, if an adjacent two-dimensional code can be successfully identified by using a certain image enhancement method, the current two-dimensional code is also likely to be successfully identified by using the image enhancement method compared with other image enhancement methods. Therefore, the image enhancement mode used for successfully identifying the adjacent two-dimensional code can be marked as an adjacent enhancement mode and used for identifying the current two-dimensional code.

And the adjacent enhancement mode is adopted to identify the current two-dimensional code, so that the identification result of the current two-dimensional code is obtained, a plurality of image enhancement results corresponding to the current two-dimensional code can be prevented from being identified one by one, and the frequency of attempting identification is reduced. For example, the current two-dimensional code and the adjacent two-dimensional code are in the illumination dark area, the adjacent two-dimensional code is successfully identified through the image enhancement mode of brightness enhancement, and at the moment, the adjacent enhancement mode is brightness enhancement. When the current two-dimensional code is identified, the current two-dimensional code can be identified in a neighboring enhancement mode directly, and if the identification result of the current two-dimensional code can be obtained, the image enhancement and identification of the current two-dimensional code are not needed in modes such as contrast enhancement and brightness compression.

According to the two-dimensional code identification method provided by the embodiment of the invention, the current two-dimensional code is identified by adopting the image enhancement mode, so that the identification success rate of the two-dimensional code is improved under the conditions of non-ideal ambient light and low imaging quality, the current two-dimensional code is identified according to the image enhancement mode used for successfully identifying the adjacent two-dimensional codes in the two-dimensional code array diagram, the identification result of the current two-dimensional code is obtained, the batch identification of all the two-dimensional codes in the two-dimensional code array diagram is realized, the identification of a plurality of image enhancement results corresponding to the current two-dimensional code one by one is avoided, the identification time in the batch identification of the two-dimensional code process is shortened, the complexity of an identification algorithm is reduced, and the batch identification efficiency of the two-dimensional codes is improved.

Based on the above embodiment, fig. 2 is a schematic flow chart of an embodiment of step 120 in the two-dimensional code identification method provided by the present invention, and as shown in fig. 2, step 120 includes:

step 121, taking an image enhancement result of the current two-dimensional code in an adjacent enhancement mode as a graph to be identified;

step 122, performing two-dimensional code recognition on the graph to be recognized;

step 123, if the identification is successful, the two-dimensional code identification result is used as the identification result of the current two-dimensional code, otherwise, the image enhancement result of the current two-dimensional code in the other image enhancement modes is used as the image to be identified; the rest of the image enhancement modes are image enhancement modes other than the adjacent enhancement modes.

Specifically, when the current two-dimensional code is identified, an image enhancement result of the current two-dimensional code in an adjacent enhancement mode is used as a graph to be identified for identification.

For example, when the adjacent enhancement mode is brightness enhancement, it indicates that the image enhancement mode used for successfully identifying the adjacent two-dimensional codes in the two-dimensional code array diagram is brightness enhancement. And for the current two-dimensional code, the image enhancement result with the increased brightness can be directly used as the image to be identified for identification. If the identification is successful, the two-dimensional code identification result is used as the current two-dimensional code identification result, otherwise, the image enhancement result of the current two-dimensional code in the other image enhancement modes is used as the image to be identified, and the identification is continued. The remaining image enhancement modes may be selected to be modes other than brightness enhancement, such as contrast enhancement, brightness compression, and the like.

Fig. 3 is a flowchart of an algorithm for identifying two-dimensional codes by adopting an adjacent enhancement mode, and as shown in fig. 3, a plurality of two-dimensional codes are obtained after dividing a two-dimensional code array diagram, i is a label of the two-dimensional code, and the plurality of two-dimensional codes are stored in a code_image_list. When the ith two-dimensional code is identified, N image enhancement modes are adopted for image enhancement on the two-dimensional code, N image enhancement results are obtained, and N is a positive integer. Each image enhancement result corresponds to an image enhancement mode. j is the image enhancement mode of the two-dimensional code. current_j is the neighboring enhancement mode. N is the identification sequence number of N image enhancement results of the two-dimensional code i. The code_image_list is a two-dimensional code storage file, and the code_image_list is a two-dimensional code identification result storage file.

If i=0, the two-dimensional code i is the 1 st two-dimensional code in the identification process, and no adjacent two-dimensional code is identified before, j=0 can be set, and the identification of the N image enhancement results is started one by one.

If i is not 0, before the two-dimensional code i is identified, if there is an adjacent two-dimensional code with successful identification, j=current_j may be set, that is, the two-dimensional code i is identified according to the current_j of the adjacent enhancement mode, and if the identification is successful, the identification result is saved in the code_info_list.

If the identification fails, the identification serial number N of the two-dimensional code i is adjusted, and the rest image enhancement modes are identified one by one according to the sequence, namely, n=n+1, j= (j+1)% N is set. If the recognition of the other image enhancement mode is successful, the recognition result is saved in the code_info_list, and at the moment, current_j=j is set to indicate that the other image enhancement mode j which is successful in recognition is set as an adjacent enhancement mode.

In particular, if the adjacent enhancement mode and the rest of the image enhancement modes are failed to be identified, the rest of the image enhancement modes which are attempted to be identified last time can be saved as the adjacent enhancement modes, and the identification result can be set as unidentified.

According to the method, all the two-dimensional codes in the code_image_list are identified, and the identification results of all the two-dimensional codes are stored to the code_info_list.

According to the two-dimensional code identification method provided by the embodiment of the invention, the image enhancement result of the current two-dimensional code in the adjacent enhancement mode is used as the image to be identified, the two-dimensional code identification is carried out on the image to be identified, the identification result of the current two-dimensional code is obtained, the identification of a plurality of image enhancement results corresponding to the current two-dimensional code one by one is avoided, the identification time in the process of identifying the two-dimensional codes in batches is reduced, the complexity of an identification algorithm is reduced, and the efficiency of identifying the two-dimensional codes in batches is improved.

Based on any one of the above embodiments, fig. 4 is a schematic flow chart of the two-dimensional code array map fusion recognition method provided by the present invention, as shown in fig. 4, after step 120, further includes:

step 130, determining known two-dimensional codes successfully identified in at least two-dimensional code array graphs based on the identification results of each two-dimensional code in the at least two-dimensional code array graphs; the at least two-dimensional code array diagrams are acquired from the same two-dimensional code array;

step 140, aligning each two-dimensional code array diagram based on the position of the known two-dimensional code in each two-dimensional code array diagram;

and step 150, merging the identification results of the two-dimensional codes in the aligned two-dimensional code array graphs to obtain the identification results of the two-dimensional codes in the two-dimensional code arrays.

Specifically, the two-dimensional code array is in a form that a plurality of two-dimensional codes are arranged according to a certain rule, so that the position relation among the two-dimensional codes, for example, the placement form of each reagent tube in the freezing box, the position relation among the reagent tubes and the position relation among the two-dimensional codes at the top of each reagent tube are represented.

The uneven illumination causes are liable to cause poor image quality of the two-dimensional code array pattern, for example, partial high light reflection causes a part of the two-dimensional code to be hidden. In addition, due to reasons of image acquisition equipment, such as insufficient resolution of a camera, image edges are blurred, and image occlusion or fouling caused by the reasons is difficult to repair by an image enhancement method. Therefore, a plurality of two-dimensional code array graphs acquired by the same two-dimensional code array can be compositely overlapped with the identification results of the two-dimensional codes in the two-dimensional code array graphs, and the identification success rate of the two-dimensional codes is improved.

For example, considering that the influence of distortion blurring or specular reflection and the like is generally local, by adjusting the position and angle of the freezing box, the hidden part in the last imaging can be adjusted to a clearly visible area, for example, when specular noise exists, the image is rotated, transformed and transferred to the influence position of the noise, or when imaging, the corner area of the edge of the freezing box with blurring is placed in the center of a lens of the acquisition device as much as possible for imaging. Although some two-dimensional codes are unidentifiable in a single two-dimensional code array diagram, the part is possibly identifiable in other two-dimensional code array diagrams, and the whole identification result of the two-dimensional codes on the freezing box can be obtained by mutually supplementing by recording the identification results of a plurality of two-dimensional code array diagrams and superposing the results.

After the identification results of the two-dimensional codes in the two-dimensional code array diagrams are obtained, the known two-dimensional codes which are successfully identified in each two-dimensional code array diagram can be determined. When the known two-dimensional code is selected, the selection of the known two-dimensional code in the center of the two-dimensional code array diagram is avoided as much as possible. Preferentially, a known two-dimensional code close to four corner points of the two-dimensional code array diagram is selected. The number of the known two-dimensional codes may be one or more, which is not particularly limited in the embodiment of the present invention.

After the known two-dimensional codes and the positions of the known two-dimensional codes are determined, aligning each two-dimensional code array diagram according to the positions of the known two-dimensional codes in each two-dimensional code array diagram. And fusing the identification results of the aligned two-dimensional code array graphs to obtain the identification results of the two-dimensional codes in the two-dimensional code array.

According to the two-dimensional code identification method provided by the embodiment of the invention, the plurality of two-dimensional code array graphs are aligned according to the positions of the known two-dimensional codes successfully identified in the plurality of two-dimensional code array graphs, and the identification results of the two-dimensional code array graphs are fused, so that the identification success rate of the two-dimensional codes under the conditions of non-ideal ambient illumination and low imaging quality is improved.

Based on any of the above embodiments, fig. 5 is a schematic flow chart of an implementation of step 140 in the two-dimensional code identification method provided by the present invention, and as shown in fig. 5, step 140 includes:

Step 141, using any two-dimensional code array diagram as a reference image, and determining the distance between the known two-dimensional code in the reference image and a reference origin;

step 142, determining the distance between the known two-dimensional code and each corner in the rest two-dimensional code array diagrams;

step 143, if the distance between the known two-dimensional code and any corner is equal to the distance between the known two-dimensional code and the reference origin, the corner is used as the reference origin of the rest two-dimensional code array diagrams;

and step 144, aligning each two-dimensional code array diagram based on the reference origin of the reference image and the reference origins of the rest two-dimensional code array diagrams.

Specifically, each two-dimensional code array map is acquired by the same two-dimensional code array, so long as the reference origin of each two-dimensional code array map can be determined, each two-dimensional code array map can be aligned, and two-dimensional codes at the same position of each aligned two-dimensional code array map are used as the same two-dimensional code.

Any two-dimensional code array diagram can be used as a reference image in at least two-dimensional code array diagrams. For the reference image, the upper left corner of the reference image may be selected as the reference origin. The position of the known two-dimensional code is marked in the reference image, and the distance between the known two-dimensional code and the reference origin is determined. For the rest two-dimensional code array diagrams, the reference origin point of the rest two-dimensional code array diagrams needs to be determined, so that the distance between the known two-dimensional code and each angle point in the rest two-dimensional code array diagrams can be calculated to determine.

In the following, two-dimensional code array patterns are aligned for example, in which two-dimensional codes are distributed in rows and columns. Fig. 6 is a schematic flow chart of the two-dimensional code alignment method provided by the present invention, as shown in fig. 6, in the reference image, the line number and the column number of the reference origin O may be represented as (0, 0). The row number m and the column number n of the two-dimensional code a distribution are known, and are denoted as (m, n). The distance l between the known two-dimensional code a in the reference image and the reference origin O can be expressed as:

in the remaining two-dimensional code array diagrams, row numbers p and column numbers q distributed by the two-dimensional code a are known, and are denoted by (p, q). The distances between the known two-dimensional code A and the four corner points of the left upper corner, the right upper corner, the left lower corner and the right lower corner of the rest two-dimensional code array diagram are respectively calculated as follows:

wherein l1 is the distance between the known two-dimensional code A and the upper left corner, l2 is the distance between the known two-dimensional code A and the upper right corner, l3 is the distance between the known two-dimensional code A and the lower left corner, l4 is the distance between the known two-dimensional code A and the lower right corner, M is the number of two-dimensional codes in each row in the rest of two-dimensional code array diagrams, and N is the number of two-dimensional codes in each column in the rest of two-dimensional code array diagrams.

Because the two-dimensional code array map is acquired by the same two-dimensional code array, one of the four distances l1, l2, l3 and l4 is necessarily equal to the distance l from the known two-dimensional code A to the reference origin in the reference image, and the corresponding corner point is the reference origin of the rest two-dimensional code array maps.

After the reference origins of the rest two-dimensional code array diagrams are determined, the two-dimensional code array diagrams can be aligned, namely, row and column numbers of the two-dimensional codes in the recognition results of the rest two-dimensional code array diagrams are updated.

For the rest two-dimensional code array diagrams, if the reference origin is the upper left corner, the row and column numbers of the two-dimensional codes are kept unchanged; if the reference origin is the upper right corner, updating the row number of each two-dimensional code to be (p ', q') = (N-q, p); if the reference origin is the lower left corner, updating the row number of each two-dimensional code to be (p ', q') = (q, M-p); if the reference origin is the lower right corner, the rank number of each two-dimensional code is updated to (p ', q') = (M-q, N-p).

According to the two-dimensional code identification method provided by the embodiment of the invention, the reference origin of the rest two-dimensional code array graphs is determined by calculating the distance between the known two-dimensional code and the reference origin in the reference image and the distance between the known two-dimensional code and each corner point in the rest two-dimensional code array graphs, so that each two-dimensional code array graph is aligned, the calculation method is simple and easy to implement, the identification time in the process of identifying the two-dimensional codes in batches is reduced, the complexity of an identification algorithm is reduced, and the efficiency of identifying the two-dimensional codes in batches is improved.

Based on any of the above embodiments, fig. 7 is a schematic flow chart of an embodiment of step 110 in the two-dimensional code identification method provided by the present invention, and as shown in fig. 7, step 110 includes:

step 111, filling the holes which are not closed after corrosion operation in the binary image of the two-dimensional code array diagram based on the shape characteristics of the two-dimensional code, and performing expansion operation on the filled binary image to obtain candidate communication areas of each two-dimensional code;

and step 112, dividing the two-dimensional code array map based on the candidate connected region of each two-dimensional code to obtain a plurality of two-dimensional codes.

Specifically, because the two-dimensional code is small in size and has the influence of highlight masking and noise, when the line segments and the corner points in the two-dimensional code are detected by using a corner point or Hough straight line detection algorithm and the like, the detection accuracy is low, and even the detection is possibly impossible. In addition, the acquired two-dimensional code array diagram may further contain background features, the two-dimensional code array diagram is dense in arrangement, if a feature clustering method is adopted for carrying out region positioning and region segmentation on the two-dimensional codes, adjacent two-dimensional codes and the background are easy to interfere with each other to cause error clustering combination, so that the two-dimensional code region positioning is inaccurate, the two-dimensional codes obtained after segmentation may contain interference such as the background, or the two-dimensional codes obtained after segmentation may be incomplete.

The two-dimensional code array diagram can be binarized, so that the data volume in the image is greatly reduced, and the outline of the two-dimensional code is highlighted. And then, carrying out segmentation extraction of the two-dimensional code candidate connected regions based on the thought of the connected region mark. The candidate connected region is an image region formed by pixel points belonging to the same two-dimensional code in the binary image.

In order to obtain candidate connected regions, it is generally necessary to perform erosion and expansion morphological operations, where the erosion operation can shrink the image boundary, eliminate small and nonsensical objects, and the expansion operation causes the object boundary to expand outwards, so as to fill some voids in the object region and eliminate small particle noise contained in the object region, which can be specifically expressed as:

wherein x and y are coordinates of pixel points in the binary image, A is an input image, and B is a structural element. The structural elements can be set to be rectangular, cross-shaped, elliptic and other shapes, the two-dimensional code is generally rectangular, and accordingly, the structural elements are set to be rectangular.

In the binary image, the two-dimensional code is generally in the form of a white background and a black code. The expansion and corrosion are for white areas, the expansion operation causes the two-dimensional code black cells to shrink, and the corrosion operation causes the black cells to expand. In the prior art, corrosion operation is performed on the binary image to communicate black code elements separated from the inside of the two-dimensional code, and then expansion operation is performed to eliminate background interference on the boundary of the two-dimensional code, so that a candidate communication area where the two-dimensional code is located is separated.

Because the two-dimension codes in the two-dimension code array diagram are densely distributed, the two-dimension codes are easy to be interfered by the background. For example, in an image acquired by the freezing box, the gap between the grid background and the edge of the two-dimensional code is small, and when the inner code element of the two-dimensional code is communicated by adopting corrosion operation, the two-dimensional code and the grid background are adhered into a whole easily, so that a candidate communication area where the two-dimensional code is located cannot be screened out accurately.

Although the color features can be used for distinguishing the two-dimensional code from the background, in the actual processing process, the background color is complex or illumination is uneven, so that stable color features cannot be extracted, and interference of the background in the two-dimensional code array diagram is difficult to reject through the color features.

The average interval between black code elements in the two-dimensional code is smaller, for example, the boundary of the Data Matrix two-dimensional code is composed of two virtual edges with L-shaped positioning real edges and black and white alternating, and the interval between boundary code elements is definitely smaller than the interval between internal holes.

The corrosion operation is preferably performed under the condition that the two-dimensional code is not adhered to the background, for example, the size of the structural element is set according to the size of the two-dimensional code, so that the two-dimensional code is not adhered to the grid background in the freezing box in the binary image corresponding to the two-dimensional code array image after the corrosion operation.

At this time, there may still be some open holes inside the two-dimensional code, which would cause the internal symbols of the two-dimensional code to be not fully closed if the expansion operation is directly performed, and the obtained candidate communication area includes holes, resulting in failure in detection of the candidate communication area.

At this time, according to the shape characteristics of the two-dimensional code, the holes which are not closed after the corrosion operation in the binarized image of the two-dimensional code array diagram can be filled.

Before the expansion operation, the outline detection can be performed on the area where the two-dimensional code is located in the binary image, and hole screening can be performed according to the shape and the area of the outline area obtained through detection.

For example, an area threshold T0 is set according to the area of the two-dimensional code, and when the area contourArea of the outline area is detected to be smaller than T0, the outline area is considered to have a hole. For another example, the area threshold T1 and the shape threshold T2 may be set according to the shape of the two-dimensional code, and when the area contourArea of the contour area is detected to be smaller than T1 and max (contourWidth) is detected to be smaller than min (contourWidth) T2, the contour area is considered to have a hole.

In the above description, the contourArea is the area of the outline area, the contourWidth is the width of the outline area, the contourHeight is the height of the outline area, and the area threshold T0, the area threshold T1 and the shape threshold T2 can be set and adjusted according to the shape characteristics of the two-dimensional code.

And taking the detected area containing the holes as a Mask (Mask), then superposing the Mask on an image obtained by corroding the binarized image of the two-dimensional code array image, filling the detected unclosed internal holes, and then performing expansion operation on the filled binarized image to eliminate edge saw teeth, so as to obtain candidate communication areas of each two-dimensional code with smooth boundaries.

According to the two-dimensional code identification method provided by the embodiment of the invention, according to the shape characteristics of the two-dimensional code, the unclosed holes of the two-dimensional code array diagram after the corrosion operation are filled, and the filled two-dimensional code array diagram is expanded to obtain the candidate communication areas of each two-dimensional code, so that the internal code elements of the candidate communication areas of each two-dimensional code are fully closed, the interference of the background in the two-dimensional code array diagram is avoided, and the accuracy of two-dimensional code segmentation is improved.

Based on any of the above embodiments, fig. 8 is a schematic flow chart of an implementation of step 112 in the two-dimensional code recognition method provided by the present invention, and as shown in fig. 8, step 112 includes:

step 1121, detecting candidate communication areas of each two-dimensional code to obtain a target area corresponding to each two-dimensional code;

In step 1122, the two-dimensional code array map is divided based on the target area corresponding to each two-dimensional code, so as to obtain a plurality of two-dimensional codes.

Specifically, the candidate connected regions of each two-dimensional code may be real two-dimensional codes, and may also be false targets formed by image noise, so that feature analysis is required to be performed on the candidate connected regions to screen out effective target regions, namely, target regions corresponding to each two-dimensional code.

The mode of feature analysis includes area analysis, shape analysis, and the like. For example, canny edge detection and contour detection can be performed on the candidate connected regions of each two-dimensional code, and the minimum bounding rectangle of each candidate connected region can be obtained. Calculating the average area of the candidate connected regions according to the detected contour regions, and expressing the average area as follows:

where avg_area is the average Area of the candidate communication areas, Σregion_area is the total Area of the candidate communication areas, n_region is the number of the candidate communication areas, region_area is the Area of any candidate communication Area, and can be calculated from the detected contour Area.

If the Area region_area of any candidate communication Region does not satisfy the following relation:

Avg_Area*α≤Region_Area≤Avg_Area*β

Wherein, alpha and beta are area floating coefficients;

the candidate connected region may be the region in which the decoy object is located and should be culled.

Further, the larger the ratio between the area of the candidate communication area and the area of its smallest circumscribed rectangle, the closer the shape of the candidate communication area is to the rectangle. Therefore, if the ratio between the Area region_area of any one of the candidate communication regions and the Area rect_area of the smallest circumscribed rectangle thereof does not satisfy the following relation:

wherein μ is a shape factor, typically no greater than 0.5;

Further, the aspect ratio of the smallest circumscribed rectangle of each of the remaining candidate communication areas is calculated. Here, since the image data is processed, the aspect ratio is replaced with the aspect ratio obtained by the image data. The aspect ratio of the minimum bounding rectangle is formulated as:

where rect_width is the width of the smallest bounding rectangle in the image and rect_height is the height of the smallest bounding rectangle in the image.

If the aspect ratio of the smallest bounding rectangle is large, the corresponding candidate connected region may be the region where the spurious target is located, and should be eliminated. For example, if the ratio is greater than 1.5, it is considered that the candidate communication area is unlikely to be a square two-dimensional code area.

And detecting the candidate communication areas of each two-dimensional code to obtain the characteristics such as the area, the shape and the like of the candidate communication areas, removing the area where the false target is located after characteristic analysis, and obtaining the target area corresponding to each two-dimensional code.

According to the two-dimensional code identification method provided by the embodiment of the invention, the candidate communication area of each two-dimensional code is detected, the target area corresponding to each two-dimensional code is obtained, the false target formed by image noise is removed, and the accuracy of two-dimensional code segmentation is improved.

Based on any of the above embodiments, fig. 9 is a schematic flow chart of an embodiment of step 1122 in the two-dimensional code identification method provided by the present invention, and as shown in fig. 9, step 1122 includes:

step 11221, performing pixel traversal on a target area corresponding to each two-dimensional code in the two-dimensional code array diagram, and determining boundary coordinates of each two-dimensional code;

step 11222, determining the area size of each two-dimensional code and the interval between the two-dimensional codes based on the boundary coordinates of each two-dimensional code;

in step 11223, the two-dimensional code array map is divided based on the area size of each two-dimensional code and the intervals between the two-dimensional codes, so as to obtain a plurality of two-dimensional codes.

Specifically, since the number of two-dimensional codes and the distribution of the two-dimensional codes in the two-dimensional code array map are difficult to determine in advance, the size of each two-dimensional code and the interval between each two-dimensional code cannot be known in advance, and a plurality of two-dimensional codes cannot be obtained by direct segmentation.

Therefore, the pixel traversal method can be adopted to determine the area size of each two-dimensional code and the interval between the two-dimensional codes, and then the two-dimensional code array diagram is segmented.

Firstly, pixel traversal is carried out on a target area corresponding to each two-dimensional code in the two-dimensional code array diagram, and boundary coordinates of each two-dimensional code are determined. The boundary coordinates include upper and lower boundary coordinates and left and right boundary coordinates.

For example, before traversing the pixels in the two-dimensional code array map, the two-dimensional code array map may be subjected to inversion and normalization operations, that is, (255-image)/255 processing, where image is the two-dimensional code array map. The purpose of the inversion and normalization operations is to reduce the computational effort. After the processing, the background in the two-dimensional code array diagram is black, and only the pixel value in the target area corresponding to the two-dimensional code is left to be 1. Projecting the processed two-dimensional code array graph in the horizontal direction and the vertical direction respectively, counting the number of non-0 pixels in each row and each column, and respectively representing the numbers as row_static and col_static by using an array.

Then four containers of top_y, bottom_y, left_x and right_x are set for storing the upper, lower, left and right boundary coordinates of each row and each column of region blocks respectively. Traversing an array row_static element by element, when the row_static [ i ] = 0 and row_static [ i+1] > 0 are met, describing the upper boundary of the row two-dimensional code area, storing the row coordinate index i into a top_y container, and when the row_static [ i ] > 0 and row_static [ i+1] = 0 are met, describing the lower boundary of the row two-dimensional code area, and storing the row coordinate index i into the bottom_y container; similarly, traversing the col_static array, when col_static [ j ] = 0 and col_static [ j+1] > 0 are satisfied, describing that the column is the left boundary of the two-dimensional code area, storing the column coordinate index j into the left_x container, when col_static [ j ] > 0 and col_static [ j+1] = 0 are satisfied, describing that the column is the right boundary of the two-dimensional code area, and storing the column coordinate index j into the right_x container. the top_y and the bottom_y have the same length, the element at the corresponding position defines the upper and lower boundary coordinates of a certain two-dimensional code area block in the two-dimensional code array diagram, the left_x and the right_x have the same length, and the element at the corresponding position defines the left and right boundary coordinates of a certain two-dimensional code area block in the two-dimensional code array diagram.

Secondly, when the two-dimensional code array diagram is divided, the row and column positions of each two-dimensional code in the two-dimensional code array diagram are required to be obtained, and the coordinate values of specific pixels are not required to be obtained. Therefore, the area size of each two-dimensional code and the interval between the two-dimensional codes can be determined according to the boundary coordinates of each two-dimensional code.

For example, the interval between the respective two-dimensional codes may be represented by a default number of rows and columns between the regions of each two-dimensional code. The default row number between the detected two-dimensional code area blocks is represented by n_absent_row and n_absent_col, wherein the default row number before the first row and after the last row is included, and the dimension sizes are len (top_y) +1 and len (left_x) +1 respectively. Calculating the average size of the detected two-dimensional code:

avg_code_lengh＝(∑(bottom_y[i]-top_y[i])+∑(right_x[j]-left_x[j]))/(len(top_y)+len(left_x))

then, calculating the interval value interval=top_y [ i ] -bottom_y [ i-1] between the upper boundary of the current row of two-dimensional codes and the lower boundary of the last row of two-dimensional codes one by one in the detected two-dimensional codes, wherein the default row number between the two rows of two-dimensional codes can be represented as n_absen_row [ i ] = (interval+avg_code_low)/avg_code_low+bias-1, the len (top_y) > i is greater than or equal to 1, the avg_code_low represents the distance between centers of two-dimensional codes in the two-dimensional code array chart, and the problem of uncertainty of the distance value caused by image scaling or size reasons can be avoided when the average size of the sigma coefficient and the two-dimensional code represents the distance value, for example, if the two-dimensional code array chart is acquired based on a freezing box, the approximated value is 2, the bias parameter is used for compensating the influence of calculating the average size avg_code_low and the sigma_high deviation is represented as 0+0 when the average size is greater than or equal to 0.

Similarly, the interval value interval=left_x [ j ] -right_x [ j-1] between the left boundary of the current column of two-dimensional codes and the right boundary of the previous column of two-dimensional codes in the detected two-dimensional codes can be calculated one by one, and the default two-dimensional code column number between the two columns is n_absent_col [ j ] = (interval+avg_code_low) avg_code_low [ sigma+bias-1 ]; the default number of rows and columns of the two-dimensional code before the initial row and the initial column can be expressed as n_absent_row [0] =top_y0 ]/avg_code_lend [ sigma+bias 0], n_absent_col [0] =left_x [0 ]/avg_code_lend [ sigma+ _bias, and _bias can be taken about 0.3 according to experience; the default number of rows and columns at the end of the same can be expressed as:

n_absent_row[-1]＝(image_height-bottom_y[-1])/avg_code_lengh*σ+_bias，n_absent_col[-1]＝(image_width-right_x[-1])/avg_code_lengh*σ+_bias。

and dividing the two-dimensional code array graph according to the area size of each two-dimensional code and the interval between the two-dimensional codes to obtain a plurality of two-dimensional codes.

For example, n_absent_row, n_absent_col is accumulated element by element, i.e

Then, the row and column number (M, N) corresponding to the detected two-dimensional code region block (Range (top_y [ i ], bottom_y [ i ]), range (left_x [ j ], right_x [ j ])) is m=n_absen_row [ i ] +i, n=n_absen_col [ j ] +j, M, N index value starts from 0, and the total row column number (M, N) of the two-dimensional code array diagram is:

M＝n_absent_row[-1]+len(top_y)

N＝n_absent_col[-1]+len(left_x)

and when the mask block has a non-0 foreground element, indicating that the area is a two-dimensional code target area, dividing a foreground part corresponding to the mask block from the two-dimensional code array image as a two-dimensional code image, calculating rotation torque according to the rotation angle of the minimum circumscribed rectangle of the mask block, performing affine transformation on the two-dimensional code image to rotate the two-dimensional code image to a positive-displacement angle as a final two-dimensional code image to be identified, and storing each two-dimensional code image to be identified and corresponding row and column number coordinates (m, n) in a code_image_list file and a code_index_list file at one time.

According to the two-dimensional code identification method provided by the embodiment of the invention, pixel traversal is performed on the target area corresponding to each two-dimensional code in the two-dimensional code array diagram, the area size of each two-dimensional code and the interval between each two-dimensional code are determined, and then the two-dimensional code array diagram is segmented, so that a plurality of two-dimensional codes are obtained, the segmentation algorithm is simple and convenient, and the two-dimensional code batch identification efficiency is improved.

Based on any one of the above embodiments, fig. 10 is a schematic flow chart of a two-dimensional code batch identification method of a medical reagent tube provided by the present invention, as shown in fig. 10, the method includes:

step one, collecting an image

In the field of medical research, pharmaceutical agents are generally stored in reagent tubes with two-dimensional code labels, the reagent tubes are stored in a frozen box in batches, and images comprising a two-dimensional code array can be obtained by image acquisition of the frozen box.

The image acquisition equipment comprises a high-speed scanner, a mobile terminal and the like. In the field of medical research, high-speed imaging instruments are generally used for image acquisition. The high-speed image shooting instrument adopts an imaging mode from top to bottom, is quite easy to be interfered by the illumination of the environment in all directions at the top and around in the process of imaging an object below the lens, and the partial two-dimensional code is not clear or visible due to the fact that the plastic freezing storage box is quite easy to generate partial high reflection. In addition, because the high-speed photographing instrument lens support is limited in height and can only be used for short-distance imaging, barrel-shaped distortion is easy to occur in imaging under a wide-angle view field due to the influence of physical characteristics of lenses and lens group structures, and the phenomenon of edge blurring is caused due to high center sharpness and low edge sharpness.

Step two, preprocessing the image and positioning and extracting the freezing storage box area

The method is influenced by imaging environment and imaging equipment quality, the problems of color cast, geometric distortion, insufficient contrast and the like of an image can exist, a gray world method and other white balance algorithms are adopted to correct the color cast of the image, a camera Matrix and a distortion coefficient distCoeffs of the camera are obtained through calibrating the camera to correct the distortion of the image, and a histogram equalization image enhancement algorithm is adopted to improve the contrast of the image. Because the freezing box in the image is larger in area and has a regular rectangular shape compared with other background sundry objects, the rectangular freezing box area can be simply positioned from the image based on the contour area and the shape characteristics.

Specifically, an image can be converted into a gray level image and binarized, then canny edge detection and contour extraction are performed, the area of each contour area contourArea and the corresponding minimum circumscribed rectangular area rectArea are calculated, when the contourArea/rectArea >0.9 is met, the contour is described to be attached to a rectangular shape, the contour is reserved, and the area max (rectArea) with the largest area is taken as a target area of the freezing storage box. Then, a rotation matrix rotation_mat is calculated according to the rotation angle rotation_angle of the minimum circumscribed rectangle, affine transformation is carried out, an image corresponding to the target area of the freezing storage box is rotated to a forward position, and the image is rotated to the forward position so as to facilitate the subsequent positioning of each two-dimensional code position. The rotation angle rotation_angle of the minimum circumscribed rectangle means a rotation angle corresponding to when the x-axis rotates counterclockwise to the nearest side, satisfying 0 < |rotation_angle| < =90 degrees.

In order to rotate the cryopreservation cassette to the closest flat state as much as possible, when |rotation_angle| < 45 degrees, rotation_angle_t= |rotation_angle| (-1), when |rotation_angle| > 45 degrees, rotation_angle_t=90- |rotation_angle|, rotation_angle_t is positive indicating counterclockwise rotation. After determining the rotation angle, a rotation matrix may be calculated: rotation_mat=getrotation matrix2D (rotation_angle_t, scale), wherein rotation_mat is the center Point of the rotation image, and it is only necessary to take rotation_mat=point (width/2, height/2), scale is the scale, and 1 is only necessary.

The acquired rotation matrix is expressed asTwo-dimensional vector is +.>Affine transformation is +.>

After the frozen box area is obtained, binarization processing is needed to separate the foreground and background parts of the two-dimensional code. Considering that the brightness of different areas in the target image of the cryopreservation box is greatly different under the influence of uneven illumination, if the global threshold method is adopted for binarization, it is difficult to separate the two-dimensional codes and the background in a plurality of different brightness areas simultaneously by using a single threshold, so that the processing is mainly carried out by adopting the local threshold method. Local thresholding divides an image into multiple local blocks _m×n . Here, m and n represent the number of horizontal partial blocks and the number of vertical partial blocks in the image, respectively. Preferably, m=4, n=4.

And calculating the brightness weighted average value in each local area, for example, using a Gaussian distribution function to distribute weights, calculating the weighted average value, and then binarizing each local block according to the corresponding average value, so that different image areas can be binarized by adopting different thresholds according to different self-adaption of brightness, and the two-dimensional code foreground part can be effectively extracted.

The method mainly considers that the brightness of different areas in the image is greatly different under the influence of uneven illumination, if the image is binarized by adopting an OTSU (on-the-fly) Otsu (on-the-fly) method and other global threshold methods, the foreground and the background in a plurality of different brightness areas are difficult to separate simultaneously by using a single threshold, and when the local area value method is adopted, the two-dimensional code details in each local area can be effectively reserved by adopting different thresholds according to the brightness difference in each local adjacent area. The local value method can be expressed as ADAPTIVE threshold (src, dst,255, ADAPTIVE method, threshold type, block_size, C), wherein src is a target image of the cryopreservation box, dst is a processed binarization map, ADAPTIVE method is an algorithm adopted for calculating the threshold value in each neighborhood, adaptive_threshold_mean_c or daptive_threshold_gauss_sum_c can be selected, and the like, the average value in the neighborhood and the GAUSSIAN average value are respectively subtracted by an offset value adjustment amount C to be used as a neighborhood threshold value, the size of a neighborhood block is controlled by the block_size parameter, and threshold type is used as a threshold value type.

Step three, connected domain marking

Based on the shape characteristics of the two-dimensional codes on the reagent tube, filling the unclosed holes after the corrosion operation of the binarized images of the target images of the freezing storage box, and performing the expansion operation of the filled binarized images to obtain the communication area of each two-dimensional code.

And fourthly, carrying out feature analysis on the connected areas, screening out the possibly real two-dimensional codes corresponding to the connected areas of each two-dimensional code of the two-dimensional code target area, and possibly, also because of false targets formed by image noise, so that the connected areas need to be subjected to feature analysis to screen out effective target areas, namely, the target areas corresponding to each two-dimensional code. The mode of feature analysis includes area analysis, shape analysis, and the like.

Fifthly, carrying out positioning segmentation on the two-dimensional code target area to obtain each two-dimensional code

And traversing pixels of a target area corresponding to each two-dimensional code in the target image of the freezing storage box, determining boundary coordinates of each two-dimensional code, and further determining the area size of each two-dimensional code and the interval between each two-dimensional code. And dividing the target image of the freezing storage box according to the area size of each two-dimensional code and the interval between the two-dimensional codes to obtain a plurality of two-dimensional codes.

Step six, identifying each two-dimensional code

In the identification process, aiming at the problem of difficult two-dimensional code identification caused by environmental illumination and imaging quality reasons, various image enhancement is carried out on each local two-dimensional code image, and the current two-dimensional code is identified according to an image enhancement mode used for successfully identifying the adjacent two-dimensional code. Meanwhile, a scheme of carrying out composite superposition on multiple recognition results is adopted, so that the two-dimensional code under noise interference can acquire the recognition information, and the overall recognition success rate is effectively improved.

Based on any one of the above embodiments, fig. 11 is a schematic structural diagram of a two-dimensional code recognition device provided by the present invention, as shown in fig. 11, the device includes:

the dividing unit 1110 is configured to divide the two-dimensional code array map to be identified to obtain a plurality of two-dimensional codes;

the identifying unit 1120 is configured to identify the current two-dimensional code based on the adjacent enhancement mode, so as to obtain an identification result of the current two-dimensional code;

the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes in the two-dimensional code array diagram.

Specifically, the dividing unit 1110 is configured to divide the two-dimensional code array map to be identified, so as to obtain a plurality of two-dimensional codes. The identifying unit 1120 is configured to identify the current two-dimensional code according to an image enhancement mode used for successfully identifying the two-dimensional code adjacent to the current two-dimensional code in the two-dimensional code array diagram, so as to obtain an identification result of the current two-dimensional code.

According to the two-dimensional code identification device provided by the embodiment of the invention, the current two-dimensional code is identified by adopting the image enhancement mode, so that the identification success rate of the two-dimensional code is improved under the conditions of non-ideal ambient light and low imaging quality, the current two-dimensional code is identified according to the image enhancement mode used for successfully identifying the adjacent two-dimensional codes in the two-dimensional code array diagram, the identification result of the current two-dimensional code is obtained, the batch identification of all the two-dimensional codes in the two-dimensional code array diagram is realized, the identification of a plurality of image enhancement results corresponding to the current two-dimensional code one by one is avoided, the identification time in the batch identification of the two-dimensional code process is shortened, the complexity of an identification algorithm is reduced, and the batch identification efficiency of the two-dimensional codes is improved.

Based on any of the above embodiments, the identifying unit 1120 includes:

the image enhancement result of the current two-dimensional code in the adjacent enhancement mode is used as the image to be identified;

the identification subunit is used for carrying out two-dimensional code identification on the graph to be identified;

the image to be identified switching subunit is used for taking a result obtained by identifying the two-dimensional code as an identification result of the current two-dimensional code if the identification is successful, or taking an image enhancement result of the current two-dimensional code in other image enhancement modes as an image to be identified; the rest of the image enhancement modes are image enhancement modes other than the adjacent enhancement modes.

Based on any of the above embodiments, the apparatus further includes a fusion identification unit, where the fusion identification unit includes:

the known two-dimensional code determining subunit is used for determining the known two-dimensional code successfully identified in at least two-dimensional code array graphs based on the identification result of each two-dimensional code in the at least two-dimensional code array graphs; the at least two-dimensional code array diagrams are acquired from the same two-dimensional code array;

the array diagram alignment subunit is used for aligning each two-dimensional code array diagram based on the position of the known two-dimensional code in each two-dimensional code array diagram;

the array diagram fusion subunit is used for fusing the identification results of the two-dimensional codes in the aligned two-dimensional code array diagrams to obtain the identification results of the two-dimensional codes in the two-dimensional code arrays.

Based on any of the above embodiments, the array map alignment subunit includes:

the first distance determining module is used for determining the distance between the known two-dimensional code in the reference image and the reference origin by taking any two-dimensional code array image as the reference image;

the second distance determining module is used for determining the distance between the known two-dimensional code and each corner in the rest two-dimensional code array diagrams;

the reference origin determining module is used for taking any one of the angle points as the reference origin of the rest two-dimensional code array graphs if the distance between the known two-dimensional code and any one of the angle points is equal to the distance between the known two-dimensional code and the reference origin;

The array diagram alignment module is used for aligning each two-dimensional code array diagram based on the reference origin of the reference image and the reference origins of the rest two-dimensional code array diagrams.

Based on any of the above embodiments, the dividing unit 1110 includes:

the hole filling subunit is used for filling the unclosed holes in the binarized images of the two-dimensional code array graph after corrosion operation based on the shape characteristics of the two-dimensional codes, and performing expansion operation on the filled binarized images to obtain candidate communication areas of each two-dimensional code;

the array diagram dividing subunit is configured to divide the two-dimensional code array diagram based on the candidate connected region of each two-dimensional code, so as to obtain a plurality of two-dimensional codes.

Based on any of the above embodiments, the array map splitting subunit includes:

the target area determining module is used for detecting the candidate communication areas of each two-dimensional code to obtain a target area corresponding to each two-dimensional code;

the two-dimensional code determining module is used for dividing the two-dimensional code array diagram based on the target area corresponding to each two-dimensional code to obtain a plurality of two-dimensional codes.

Based on any one of the above embodiments, the two-dimensional code determining module includes:

the boundary coordinate determining submodule is used for performing pixel traversal on a target area corresponding to each two-dimensional code in the two-dimensional code array diagram and determining boundary coordinates of each two-dimensional code;

The region interval determining submodule is used for determining the region size of each two-dimensional code and the interval between the two-dimensional codes based on the boundary coordinates of each two-dimensional code;

the segmentation submodule is used for segmenting the two-dimensional code array diagram based on the area size of each two-dimensional code and the interval between the two-dimensional codes to obtain a plurality of two-dimensional codes.

Based on any of the above embodiments, fig. 12 is a schematic structural diagram of an electronic device according to the present invention, and as shown in fig. 12, the electronic device may include: processor (Processor) 1210, communication interface (Communications Interface) 1220, memory (Memory) 1230 and communication bus (Communications Bus) 1240, wherein Processor 1210, communication interface 1220, memory 1230 perform communication with each other via communication bus 1240. Processor 1210 may invoke logic commands in memory 1230 to perform the following method:

dividing a two-dimensional code array diagram to be identified to obtain a plurality of two-dimensional codes; based on the adjacent enhancement mode, identifying the current two-dimensional code to obtain an identification result of the current two-dimensional code; the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes in the two-dimensional code array diagram.

In addition, the logic commands in the memory 1230 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, comprising several commands for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the methods provided by the above embodiments, for example, comprising:

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several commands for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The two-dimensional code identification method is characterized by comprising the following steps of:

the adjacent enhancement mode is an image enhancement mode used for successfully identifying adjacent two-dimensional codes of the current two-dimensional code in the two-dimensional code array diagram;

the method for identifying the current two-dimensional code based on the adjacent enhancement mode comprises the following steps of:

Carrying out two-dimensional code recognition on the graph to be recognized;

if the identification is successful, taking a result obtained by identifying the two-dimensional code as an identification result of the current two-dimensional code, otherwise taking an image enhancement result of the current two-dimensional code in other image enhancement modes as a graph to be identified, and continuing to identify; the rest image enhancement modes are image enhancement modes except the adjacent enhancement modes.

2. The two-dimensional code identification method according to claim 1, wherein the identifying the current two-dimensional code based on the adjacent enhancement mode, obtaining an identification result of the current two-dimensional code, further comprises:

3. The two-dimensional code recognition method according to claim 2, wherein the aligning each two-dimensional code array pattern based on the position of the known two-dimensional code in each two-dimensional code array pattern includes:

4. The two-dimensional code recognition method according to any one of claims 1 to 3, wherein the dividing the two-dimensional code array map to be recognized to obtain a plurality of two-dimensional codes includes:

5. The method for identifying two-dimensional codes according to claim 4, wherein the dividing the two-dimensional code array map based on the candidate connected region of each two-dimensional code to obtain a plurality of two-dimensional codes comprises:

6. The method for identifying two-dimensional codes according to claim 5, wherein the dividing the two-dimensional code array map based on the target area corresponding to each two-dimensional code to obtain a plurality of two-dimensional codes comprises:

7. A two-dimensional code recognition device, characterized by comprising:

the identifying unit is used for:

carrying out two-dimensional code recognition on the graph to be recognized;

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the two-dimensional code recognition method according to any one of claims 1 to 6 when the computer program is executed by the processor.

9. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the two-dimensional code recognition method according to any one of claims 1 to 6.