A method, server, storage medium and system for locating arbitrary barcodes based on gray-level co-occurrence matrix

Abstract

The present invention provides a method, server, storage medium and system for locating any barcode based on a gray-level co-occurrence matrix, comprising the following steps: obtaining an original image containing a barcode to be located, determining texture features of different regions in the original image; pre-extracting texture feature ranges of various code systems; determining the region containing any barcode in the original image according to the texture feature ranges of various code systems; determining the edge image of the barcode region, determining the four vertices of the edge image, and locating the barcode. The present invention has the following beneficial effects: 1) It is applicable to the positioning of multiple code systems, is not limited to the type of barcode, and can determine the type of barcode while locating; 2) It can locate multiple barcodes at the same time; 3) It can be applicable to complex backgrounds, such as uneven lighting or text backgrounds; 4) The texture feature ranges of various code systems can be completed by training in advance, which can shorten the calculation time and reduce the complexity of the algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of visual image processing, and in particular to a positioning method, server, storage medium and system for an arbitrary barcode based on a gray-level co-occurrence matrix. Background Art

[0002] In recent years, with the rapid development of mobile technology and the deepening of industrial automation, barcodes have been widely used in industrial processing and manufacturing, logistics, transportation, library management, food and drug production and supervision, and mobile payment due to their large information storage capacity, good robustness, and low cost. Currently, the more commonly used barcodes are one-dimensional codes and two-dimensional codes, and there are many types of barcodes (code systems). When performing barcode recognition, the host computer first pre-processes the image taken by the camera, then locates its edges, then performs binarization processing, and finally decodes it to extract the contained information.

[0003] Existing barcode positioning technologies are often targeted at a single code system and are often not suitable for positioning in complex backgrounds. Taking DM code as an example, existing two-dimensional code DM recognition technologies include: scanning method, Hough transform, corner point method positioning and other methods. The Hough transform search method is time-consuming, requires a lot of computer memory, and has low accuracy in complex backgrounds. The corner point method is simple and fast, but it is only applicable to scenarios with a clean background and intact barcodes. Therefore, the above methods have low positioning efficiency in complex backgrounds, and even fail to locate. However, in industrial sites, the two-dimensional code images taken by the camera have complex backgrounds and the industrial assembly line has high real-time requirements, which cannot meet actual needs. Summary of the invention

[0004] In view of the shortcomings of the prior art described above, an object of the present invention is to provide a method, server, storage medium and system for locating any barcode based on a gray level co-occurrence matrix, so as to solve the problem of low positioning accuracy of barcodes with complex backgrounds in the prior art.

[0005] An embodiment of the present invention provides a method for locating an arbitrary barcode based on a gray level co-occurrence matrix, comprising the following steps: obtaining an original image containing a barcode to be located, and determining texture features of different regions in the original image; pre-extracting texture feature ranges of various code systems; determining a region in the original image containing an arbitrary barcode based on the texture feature ranges of various code systems; determining an edge image of the barcode region, and determining four vertices of the edge image to achieve positioning of the barcode.

[0006] An embodiment of the present invention provides a positioning system for arbitrary barcodes based on a gray-level co-occurrence matrix, comprising: a learning and training module for pre-extracting the texture feature ranges of various code systems; an acquisition module for acquiring texture features in different regions of an original image of a barcode to be positioned; a recognition module for determining the region of the original image containing an arbitrary barcode based on the texture feature ranges of various code systems; and a processing module for determining an edge image of a barcode region and determining four vertices of the edge image to achieve barcode positioning.

[0007] An embodiment of the present invention provides a server, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the positioning method of any barcode based on the gray-level co-occurrence matrix as described above.

[0008] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the positioning method of any barcode based on the gray-level co-occurrence matrix as described above is implemented.

[0009] Compared with the prior art, the main differences and effects of the embodiments of the present invention are: 1) It is applicable to the positioning of various code systems, is not limited to the type of barcode, and can determine the type of barcode while positioning; 2) It can locate multiple barcodes at the same time; 3) It can be applicable to complex backgrounds, such as uneven lighting or text background; 4) The texture feature range of various code systems can be completed through advance training, which can shorten the calculation time and reduce the complexity of the algorithm.

[0010] As a further improvement, after acquiring the original image containing the barcode to be located and before determining the texture features of different regions in the original image, the method includes: performing noise reduction processing on the original image.

[0011] The above scheme performs noise reduction processing on the original image containing any barcode to be located. The noise reduction processing can reduce the noise in the original image, making it easier to determine the texture features of the original image, thereby improving the positioning accuracy of the barcode.

[0012] As a further improvement, the texture feature parameters of different regions in the original image include: Energy, Entropy, Contrast and Correlation.

[0013] As a further improvement, the energy, entropy, contrast and correlation are calculated according to the following formulas:

[0014]

[0015] Contrast=Σ ij (ij) 2 P ij ;

[0016] Among them, (i, j) is the gray value corresponding to any point in the original image, P ij is the probability of the corresponding (i, j) combination appearing, μ x =∑ i，j i*P(i, j), μ y =∑ i，j j*P(i, j),σ x =∑ i，j (i-μ x ) 2 *P(i, j), σ y =∑ i，j (j-μ y ) 2 *P(i,j).

[0017] As a further improvement, the pre-extraction of texture feature ranges of various code systems includes: acquiring texture feature ranges of different code systems based on a series of various types of barcode images without background.

[0018] As a further improvement, the method of obtaining the texture feature range of different code systems based on a series of various types of barcode images without background includes: obtaining a series of various types of barcode images without complex backgrounds, and calculating the texture features of the barcode area in each image; for images with the same code system, respectively counting the average value and variance of the four texture feature parameters of the barcode image, and using them to determine the texture feature range of the code system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Shown is a flow chart of a method for locating an arbitrary barcode based on a gray level co-occurrence matrix according to a first embodiment of the present invention;

[0020] Figure 2 Shown is a flow chart of a method for locating an arbitrary barcode based on a gray level co-occurrence matrix according to a second embodiment of the present invention;

[0021] Figure 3 Shown is a schematic diagram of a positioning system for an arbitrary barcode based on a gray level co-occurrence matrix according to a third embodiment of the present invention;

[0022] Figure 4 Shown is a schematic diagram of an electronic device in a fourth embodiment of the present invention;

[0023] Figure 5Shown is a schematic diagram of positioning the real L edge of the DM barcode according to the present invention;

[0024] Figure 6 Shown is a schematic diagram of positioning the virtual L edge of the DM barcode according to the present invention;

[0025] Figure 7 Shown is a schematic diagram of positioning the virtual L edge of the DM barcode according to the present invention. DETAILED DESCRIPTION

[0026] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0027] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0028] The first embodiment of the present invention relates to a method for locating an arbitrary barcode based on a gray level co-occurrence matrix.

[0029] The inventor of the present application found that the barcode area has very obvious texture features, that is, there are a large number of black and white pixels that change regularly and alternately, so the barcode area has different texture feature distributions. With the help of texture feature information, the barcode area can be distinguished from the non-barcode area. On the other hand, because different types (code systems) of barcodes have different texture distributions, texture features are also helpful in distinguishing different barcode code systems. Based on this feature, the inventor of the present application proposes a positioning method for arbitrary barcodes based on a gray level co-occurrence matrix.

[0030] Process such as Figure 1 As shown, the details are as follows:

[0031] Step 101, obtaining an original image containing a barcode to be located.

[0032] Specifically, an original image containing any barcode to be located is usually uploaded by a camera. The original image contains not only the barcode to be located, but also a large number of relatively complex background images.

[0033] Step 102: Determine texture features of different regions in the original image.

[0034] Specifically, the original image is divided into M*N modules, and the co-occurrence matrix and the statistical value of the texture feature parameters of each module are calculated. When calculating the co-occurrence matrix of a module, take any point (x, y) and another point (x+a, y+b) deviating from it in the module, and set the gray value of the point pair to (i, j). If the number of gray levels is k, then the current gray combination (i, j) has k 2 possibilities, count the number of times each (i, j) combination appears in the entire image, and arrange its values ​​into a square matrix, and finally normalize the square matrix. At this time, the square matrix is ​​called the grayscale joint probability matrix, also called the co-occurrence matrix, and its corresponding matrix element P i，j It can be understood as the probability of the corresponding (i, j) combination. Since the dimension of the gray level co-occurrence matrix is ​​large, it is only used to count the information in the original image. The invention selects texture feature energy, entropy, contrast and correlation to represent the gray distribution information of the image:

[0035]

[0036] Contrast=Σ ij (ij) 2 P ij ;

[0037] where μ x =∑ i,j i*P(i,j),μ y =∑ i,j j*P(i,j),σ x =∑ i,j (i-μ x ) 1 *P(i,j),σ y =∑ i,j (j-μ y ) 2 *P(i,j).

[0038] Step 103: pre-extracting the texture feature ranges of various code systems.

[0039] Specifically, the texture feature ranges of various code systems are calculated based on various types of barcode images without background, and the calculated texture feature ranges of various code systems are stored in a memory. When it is necessary to locate various code systems with complex backgrounds, the texture feature ranges of various code systems are extracted.

[0040] Step 104, determining the area in the original image containing any barcode according to the texture feature ranges of various code systems.

[0041] In practical applications, the texture features of different regions of the original image are screened based on the texture features of various code systems. If the deviation between the texture feature value of the current region and the texture feature of a certain barcode obtained in step 103 is within ε, it can be considered that the current region contains the barcode of that type, and the type of the barcode is determined. That is:

[0042] Energy∈[Energy th (1-ε),Energy th (1+ε)];

[0043] Entropy∈[Entropy th (1-ε), Entropy th (1+ε)];

[0044] Contrast∈[Contrast th (1-ε),Contrast th (1+ε)];

[0045] Correlation∈[Correlation th (1-ε),Correlation th (1+ε)].

[0046] Step 105: determine the edge image of the barcode area.

[0047] Specifically, the barcode area is detected using an edge detection algorithm, such as Canny detection. Since Canny edge detection can retain as many edge images as possible while suppressing the minimum gradient, the edge image of the entire barcode can be extracted, and then the four vertices of the edge image are obtained to achieve the positioning of the barcode.

[0048] The following takes the DM barcode as an example to describe the specific positioning process.

[0049] Step 106, determining the four vertices of the edge image to achieve the positioning of the barcode.

[0050] Specifically, the edge image of the area containing any barcode is subjected to straight line segment detection, such as the Hough straight line algorithm. Of course, in order to ensure the real-time performance of the algorithm, the straight line segment detection algorithm can also be selected as the LSD algorithm or the EDLines algorithm or the Canny Lines algorithm, which are faster than the traditional Hough algorithm.

[0051] In practical applications, based on the detected straight line segments, two groups of straight line segments are found. These two groups of straight line segments must meet the following conditions: 1. The length of the straight line segment is greater than 20 pixels; 2. The angle between the two groups of straight line segments is between [85°, 95°], and the endpoints of the two straight line segments are recorded. In addition, for the convenience of description, Figure 5 As shown, the two groups of straight line segments are named L1 and L2, then L1 and L2 are the solid line L edges of the DM code, the endpoints of L1 are (P1, P2), and the endpoints of L2 are (P3, P4). The intersection of these two straight line segments is calculated, and the intersection is point B; Figure 6 and Figure 7 As shown, the distances from the two endpoints P1 and P2 of the L1 straight line segment to point B are calculated respectively, and the endpoint with the longest distance is selected from P1 and P2 as point A, and the distance AB is recorded as len(AB). Similarly, the distances from the two endpoints P3 and P4 of the L2 straight line segment to point B are calculated respectively, and the endpoint with the longest distance is selected as point C, and the distance BC is recorded as len(BC). The value of |len(BC)-len(AB)| is calculated, and Δ=|len(BC)-len(AB)| is made, and then (x A -τ,y A -τ) is the starting coordinate of the scan, and the scan is performed in a direction parallel to BC. The width and height of the scan area are len(BC)+2τ and |len(BC)-len(AB)|+2τ respectively. Figure 6 In the process of scanning line by line along the BC direction, the edge calculation is performed on the gray value on the scan line, and the number of edges in each line is recorded. The maximum number of edges obtained is recorded, and the scan line is the dotted edge in this direction. Similarly, along the direction parallel to AB, with the starting point coordinate (x C +τ,y C +τ), the width and height of the scanning area are Δ+2τ and len(AB)+2τ respectively. Figure 7 In the figure, len(HI) = |len(BC)-len(AB)|+2τ, len(IJ) = len(AB)+2τ, when scanning row by row along the AB direction, edge calculation is performed on the grayscale value on the scanned row, the number of edges in each row is recorded, and the column with the maximum number of edges is marked as another dotted edge. Then, two dotted edges are calculated, and the intersection point is D, thereby determining the inverted L-shaped edge composed of two dotted edges, and finally realizing the positioning process of the DM code.

[0052] Compared with the prior art, the main differences and effects of the embodiments of the present invention are: 1) It is applicable to the positioning of various code systems, is not limited to the type of barcode, and can determine the type of barcode while positioning; 2) It can locate multiple barcodes at the same time; 3) It can be applicable to complex backgrounds, such as uneven lighting or text background; 4) The texture feature range of various code systems can be completed through advance training, which can shorten the calculation time and reduce the complexity of the algorithm.

[0053] The second embodiment of the present invention relates to a method for locating an arbitrary barcode based on a gray-level co-occurrence matrix. The second embodiment is a detailed discussion of the first embodiment. The main detailed discussion is that in the first embodiment, no noise reduction processing is performed on the original image containing the arbitrary barcode to be located, and no detailed discussion is given on the process of obtaining the texture features of the arbitrary barcode. In the second embodiment of the present invention, the process of noise reduction processing on the original image containing the arbitrary barcode to be located and the process of obtaining the texture features of the arbitrary barcode are discussed in detail.

[0054] For this implementation, please refer to Figure 2 , including the following steps, are described as follows:

[0055] Step 201 is similar to step 101 in the first embodiment and will not be described in detail herein.

[0056] Step 202: Perform noise reduction processing on the original image.

[0057] Specifically, the original image is preprocessed, such as Gaussian filtering and mean filtering, so that the noise in the image can be reduced.

[0058] Step 203 is similar to step 102 in the first embodiment and will not be described in detail herein.

[0059] Step 204, obtaining a series of barcode images of various types without complex backgrounds.

[0060] Specifically, the multiple barcode images without background refer to images containing only barcodes, and these images can be uploaded by a camera or generated by a barcode generator.

[0061] Step 205, calculating the texture features of the barcode area in each image.

[0062] Specifically, the texture features of each barcode image are calculated according to the four calculation formulas of the texture features of the original image in the first embodiment.

[0063] Step 206: for images of the same code system, the average values ​​and variances of the four texture feature parameters of the barcode image are respectively counted, and used to determine the texture feature range of the code system.

[0064] In practical applications, the texture feature ranges of different code systems are obtained based on a series of barcode images of various types without background. First, a series of barcode images of various types without complex backgrounds are obtained, and the texture features of the barcode area in each image are calculated; for images of the same code system, the average and variance of the four texture feature parameters of energy, entropy, contrast and correlation are respectively counted, and they are set as the texture feature threshold Energy of the code system. th ,Entropy th ,Contrast th ,Correlation th .

[0065] Steps 207 to 209 are similar to steps 104 to 106 in the first embodiment, and are not described in detail herein.

[0066] It can be seen that the embodiment of the present invention performs noise reduction processing on the original image containing the barcode to be located. The noise reduction processing can reduce the noise in the original image and improve the positioning accuracy of the barcode. On the other hand, when pre-extracting the texture features of the same code system, by calculating the texture features of each barcode image and then calculating the statistical information of the texture features in multiple images, the positioning time can be saved, the positioning efficiency can be improved, and the applicability of the method to multiple code systems can be expanded. .

[0067] The third embodiment of the present invention relates to a positioning system for arbitrary barcodes based on a gray level co-occurrence matrix, see Figure 3 ,include:

[0068] Learning and training module, used to pre-extract the texture feature range of various code systems;

[0069] An acquisition module is used to acquire texture features of different areas in the original image of the barcode to be located;

[0070] A recognition module, used to determine the area containing any barcode in the original image according to the texture feature range of various code systems;

[0071] The processing module is used to determine the edge image of the barcode area, determine the four vertices of the edge image, and realize the positioning of the barcode.

[0072] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0073] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0074] The fourth embodiment of the present invention relates to a server, see Figure 4 ,include:

[0075] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method for locating an arbitrary barcode based on a gray-level co-occurrence matrix.

[0076] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0077] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0078] A fifth embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0079] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0080] In summary, the present invention first calculates the texture features of different areas in the original image, then extracts the texture feature ranges of different code systems based on various types of barcode images without background, and screens the texture features of the original image to determine the barcode area in the original image, and then the barcode area can be extracted from the original image with a relatively complex background, so as to locate the barcode with a relatively complex background. In addition, the positioning direction is not limited to the type of barcode, the positioning efficiency is relatively high, and the texture features of barcodes with different code systems can be obtained in advance through learning and training, which can shorten the positioning time. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0081] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for locating an arbitrary barcode based on a gray level co-occurrence matrix, characterized in that: The following steps are involved: Obtain the original image containing the barcode to be located; Determining texture features of different regions in the original image; Obtain a series of barcode images of various types without complex backgrounds; calculate the texture features of the barcode area in each image; For images with the same code system, respectively calculating the average values ​​and variances of the four texture feature parameters of the barcode image, and using the average values ​​and variances to determine the texture feature range of the code system; Determine the area of ​​the original image containing any barcode according to the texture feature range of various code systems; Determine the edge image of the barcode area; Determine the four vertices of the edge image to locate the barcode.

2. The method for locating an arbitrary barcode based on a gray level co-occurrence matrix according to claim 1, characterized in that: After acquiring the original image containing the barcode to be located and before determining the texture features of different areas in the original image, the method includes: Perform noise reduction on the original image.

3. The method for locating an arbitrary barcode based on a gray level co-occurrence matrix according to claim 1, characterized in that: The texture feature parameters of different regions in the original image include: Energy, Entropy, Contrast and Correlation.

4. The method for locating an arbitrary barcode based on a gray level co-occurrence matrix according to claim 3, characterized in that: Energy, entropy, contrast and correlation are calculated according to the following formulas: Entrioy=-∑ ij P ij LogP ij ; Contrast=∑ ij (i-j) 2 P ij ; Among them, (i, j) is the gray value corresponding to any point in the original image, P ij is the probability of the corresponding (i, j) combination appearing, μ x =∑ i,j i*p(i,j),μ y =∑ i,j j*P(i,j),σ x =∑ i,j (i-μ i ) 2 *P(i,j),σ y =∑ i,j (j-μ y ) 2 *P(i,j).

5. A positioning system for any barcode based on gray level co-occurrence matrix, characterized by: include: Learning and training module, used to pre-extract the texture feature range of various code systems; The acquisition module is used to acquire a series of barcode images of various types without complex backgrounds; and calculate the texture features of the barcode area in each image; For images with the same code system, respectively calculating the average values ​​and variances of the four texture feature parameters of the barcode image, and using the average values ​​and variances to determine the texture feature range of the code system; A recognition module, used to determine the area containing any barcode in the original image according to the texture feature range of various code systems; The processing module is used to determine the edge image of the barcode area, determine the four vertices of the edge image, and realize the positioning of the barcode.

6. A server, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for locating an arbitrary barcode based on a gray level co-occurrence matrix as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for locating an arbitrary barcode based on a gray level co-occurrence matrix as described in any one of claims 1 to 4 is implemented.

Images