CN111311497B - A barcode image angle correction method and device - Google Patents

Abstract

The application discloses a bar code image angle correction method and device, which are used for carrying out gray level and binarization processing on an obtained bar code image to be corrected to obtain a first binary image; performing contour retrieval on a white foreground region in the first binary image based on a contour retrieval algorithm to obtain a first contour; performing black filling on the white foreground region with the area smaller than the preset threshold value, and performing contour searching again to obtain a second contour; calculating a center of a second contour of the white foreground region based on the second contour; performing straight line fitting on the obtained central point based on Hough transformation, and outputting an included angle; the correction angle is calculated based on the included angle, and then the bar code image to be corrected is rotated to obtain the bar code image after correction, so that the technical problems that the existing bar code correction method can only correct the one-dimensional bar code by a small angle, the correction effect is poor under the condition that the angle of the bar code is serious, and the recognition result of the bar code is poor are solved.

Description

A barcode image angle correction method and device

Technical Field

The present application relates to the field of image processing technology, and in particular to a barcode image angle correction method and device.

Background Art

A barcode is a symbol formed by arranging black lines and spaces of different thicknesses according to certain coding rules. Barcodes are widely used in daily life, such as commodities and express delivery orders. Current one-dimensional barcodes can usually be used to store information such as numbers and letters. Since one-dimensional barcodes only express information in a single direction, existing machine vision technology has requirements for the placement angle of the barcode when recognizing one-dimensional barcodes. Usually, the angle of the barcode needs to be adjusted to facilitate barcode recognition. Existing barcode correction methods can only perform small angle correction on one-dimensional barcodes. When the barcode angle is severely tilted, the correction effect is poor, resulting in poor barcode recognition results.

Summary of the invention

The present application provides a barcode image angle correction method and device, which are used to solve the technical problem that the existing barcode correction method can only perform small angle correction on one-dimensional barcodes, and the correction effect is poor when the barcode angle is severely tilted, resulting in poor barcode recognition results.

In view of this, the first aspect of the present application provides a barcode image angle correction method, comprising:

grayscale the acquired barcode image to be corrected;

Binarizing the grayscaled barcode image to be corrected to obtain a first binary image;

Performing contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area;

Filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixel points within the first contour of the white foreground area;

Performing contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area;

Calculating the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points;

Perform straight line fitting on the center point based on Hough transform and output the angle;

A correction angle is calculated based on the included angle, and the barcode image to be corrected is rotated based on the correction angle to obtain a corrected barcode image.

Preferably, the step of binarizing the grayscaled barcode image to be corrected to obtain a first binary image further comprises:

The barcode image to be corrected is subjected to denoising after the grayscale processing.

Preferably, the step of filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image comprises:

The white foreground area whose area is smaller than the preset threshold is filled with black according to the flood filling algorithm to obtain a second binary image.

Preferably, the calculating the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points includes:

Obtaining four boundary points of the second contour based on the second contour of the white foreground area, wherein the four boundary points are the top, bottom, leftmost and rightmost points;

A circumscribed rectangle of the second contour is obtained based on the four boundary points, a center of the circumscribed rectangle is calculated based on the circumscribed rectangle, and the center of the circumscribed rectangle is used as the center of the second contour to obtain a plurality of center points.

Preferably, the grayscale processing of the acquired barcode image to be corrected further comprises:

The barcode image to be corrected is obtained.

The second aspect of the present application provides a barcode image angle correction device, comprising:

A grayscale processing module, used for grayscale processing of the acquired barcode image to be corrected;

A binarization processing module, used for binarizing the barcode image to be corrected after the grayscale processing to obtain a first binary image;

A first contour retrieval module, configured to perform contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area;

A filling module, used for filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixel points within the first contour of the white foreground area;

A second contour retrieval module, configured to perform contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area;

A calculation module, used for calculating the center of the second outline of the white foreground area based on the second outline of the white foreground area to obtain a plurality of center points;

A straight line fitting module, used for performing straight line fitting on the center point based on Hough transform and outputting an angle;

The correction module is used to calculate a correction angle based on the included angle, and rotate the barcode image to be corrected based on the correction angle to obtain a corrected barcode image.

Preferably, it also includes:

The denoising module is used to perform denoising on the barcode image to be corrected after the grayscale processing.

Preferably, the filling module is specifically used for:

The white foreground area whose area is smaller than the preset threshold is filled with black according to the flood filling algorithm to obtain a second binary image.

Preferably, the calculation module is specifically used for:

Obtaining four boundary points of the second contour based on the second contour of the white foreground area, wherein the four boundary points are the top, bottom, leftmost and rightmost points;

A circumscribed rectangle of the second contour is obtained based on the four boundary points, a center of the circumscribed rectangle is calculated based on the circumscribed rectangle, and the center of the circumscribed rectangle is used as the center of the second contour to obtain a plurality of center points.

Preferably, it also includes:

The image acquisition module is used to acquire the barcode image to be corrected.

It can be seen from the above technical solutions that this application has the following advantages:

The present application provides a barcode image angle correction method, comprising: graying an acquired barcode image to be corrected; binarizing the grayed barcode image to be corrected to obtain a first binary image; performing contour retrieval on a white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area; black filling a white foreground area whose area is smaller than a preset threshold to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixel points in the first contour of the white foreground area; performing contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area; calculating the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points; performing straight line fitting on the center points based on Hough transform to output an angle; obtaining a correction angle based on the angle calculation, and rotating the barcode image to be corrected based on the correction angle to obtain a corrected barcode image.

The barcode image angle correction method in the present application performs grayscale and binarization processing on the acquired barcode image to be corrected to obtain a first binary image; considering that other white foreground areas outside the barcode will affect the detection of the direction straight line of the barcode, especially the dense small-area white foreground area, the white foreground in the first binary image is subjected to contour retrieval, and then the white foreground area with an area smaller than a preset threshold is filled with black to obtain a second binary image, thereby achieving the effect of deleting the small-area white foreground area and improving the detection accuracy of the direction straight line of the barcode; based on the contour retrieval algorithm, the white foreground area in the second binary image is subjected to contour retrieval, and the center of the second contour of the white foreground area is calculated based on the second contour of the white foreground area to obtain a plurality of center points, and then the center points are subjected to straight line fitting by using Hough transform to obtain the direction straight line and the angle of the barcode, and the correction angle can be calculated by the angle, and then the barcode image is corrected, thereby solving the technical problem that the existing barcode correction method can only perform small-angle correction on one-dimensional barcodes, and the correction effect is poor when the barcode angle is severely tilted, resulting in poor barcode recognition results.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic flow chart of a barcode image angle correction method provided in an embodiment of the present application;

FIG2 is another schematic flow chart of a barcode image angle correction method provided in an embodiment of the present application;

FIG3 is a schematic structural diagram of a barcode image angle correction device provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of parameters in a polar coordinate system provided in an embodiment of the present application.

DETAILED DESCRIPTION

In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

For ease of understanding, please refer to FIG. 1 , which shows an embodiment of a barcode image angle correction method provided by the present application, including:

Step 101: grayscale the acquired barcode image to be corrected.

It should be noted that the acquired barcode image to be corrected is grayed to facilitate subsequent binarization processing.

Step 102: Binarize the grayscaled barcode image to be corrected to obtain a first binary image.

Step 103: Perform contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area.

Step 104 , fill the white foreground region whose area is smaller than the preset threshold with black to obtain a second binary image, wherein the area of the white foreground region is calculated based on the number of pixels within the first contour of the white foreground region.

It should be noted that there are a large number of white foregrounds in the first binary image obtained. In addition to the barcode, other white foreground areas will affect the detection of the directional straight line of the barcode, especially the dense small-area white foreground areas. These small-area white foreground areas not only affect the efficiency of program operation, but also easily lead to straight line detection errors. Therefore, it is necessary to reduce the small-area white foreground areas. In the embodiment of the present application, the white foreground area in the first binary image is subjected to contour retrieval by a contour retrieval algorithm to obtain a first contour of the white foreground area. After obtaining the first contour, the area of the white foreground area corresponding to each first contour can be obtained by calculating the number of pixels in each first contour, and the white foreground area with an area less than a preset threshold is filled with black to obtain a second binary image, thereby achieving the purpose of deleting the small-area white foreground area, thereby improving the detection accuracy of the directional straight line of the barcode. Among them, the contour retrieval of the white foreground area in the first binary image based on the contour retrieval algorithm belongs to the prior art, and the specific process of contour retrieval based on the contour retrieval algorithm will not be repeated here.

Step 105 : Perform contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area.

Step 106: Calculate the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points.

It should be noted that, because the bars of the barcode are all equal-height bars and are aligned in the same direction, the straight line connecting the center points of these bars is the direction straight line of the barcode. Therefore, it is necessary to calculate the center of the second contour of the white foreground area to obtain the center point of each barcode bar.

Step 107: Perform straight line fitting on the center point based on Hough transform and output the angle.

It should be noted that after obtaining several center points, a straight line detection algorithm can be used to detect the straight line and return the straight line with the best fit. In the embodiment of the present application, Hough transform is preferably used to fit the center point to the straight line. Hough transform is a shape detection algorithm in image processing, which can handle both discontinuous points and continuous points. The principle of Hough transform is to transform the image function expression from Euclidean distance to parameter space, so as to realize the fitting detection of the shape. In the rectangular coordinate system, the straight line can be expressed as y=ax+b, and in the polar coordinate system, the straight line can be expressed as ρ=x cosθ+y sinθ, where ρ is the vertical distance from the origin to the straight line, and θ is the angle between the vertical line of the straight line and the horizontal axis in the clockwise direction, as shown in Figure 4. When ρ is greater than 0, the straight line is below the origin; when ρ is greater than 0, the straight line is above the origin. Regardless of whether the straight line is above or below the origin, the angle θ is less than 180°. Therefore, (ρ; θ) can be used to represent any straight line. Hough transform is used to fit the center point to a straight line. Specifically, first, a two-dimensional array is created as an accumulator. The rows and columns of the array represent ρ and θ respectively. The values in the array are initialized by setting them to 0, and the x and y values of the center point are substituted into the polar coordinate equation of the line. Then, the θ values are traversed according to the precision, with the interval being the precision value. The corresponding ρ value is substituted into the equation to obtain a plurality of value pairs (ρ; θ). These value pairs are compared with the accumulator. If the corresponding position can be found in the accumulator, the value at the corresponding position is incremented by 1. Then, the second center point is taken, and the aforementioned steps are repeated and the value in the accumulator is updated until all the center points are taken. When all operations are completed, there is a maximum value in the accumulator, and the value pair (ρ; θ) corresponding to the maximum value is output to obtain the angle θ.

Step 108: obtain a correction angle based on the included angle calculation, and rotate the barcode image to be corrected based on the correction angle to obtain a corrected barcode image.

It should be noted that the correction angle can be obtained by subtracting the included angle θ from 90°, and the barcode image to be corrected is rotated based on the correction angle to obtain the corrected barcode image.

The barcode image angle correction method in the embodiment of the present application performs grayscale and binarization processing on the acquired barcode image to be corrected to obtain a first binary image; considering that other white foreground areas outside the barcode will affect the detection of the direction straight line of the barcode, especially the dense small-area white foreground area, the white foreground in the first binary image is subjected to contour retrieval, and then the white foreground area with an area smaller than a preset threshold is filled with black to obtain a second binary image, thereby achieving the effect of deleting the small-area white foreground area and improving the detection accuracy of the direction straight line of the barcode; the white foreground area in the second binary image is subjected to contour retrieval based on the contour retrieval algorithm, and the center of the second contour of the white foreground area is calculated based on the second contour of the white foreground area to obtain a plurality of center points, and then the center points are subjected to straight line fitting using Hough transform to obtain the direction straight line and the angle of the barcode, and the correction angle can be calculated through the angle, and then the barcode image is corrected, thereby solving the technical problem that the existing barcode correction method can only perform small-angle correction on one-dimensional barcodes, and the correction effect is poor when the barcode angle is severely tilted, resulting in poor barcode recognition results.

For ease of understanding, please refer to FIG. 2 , another embodiment of a barcode image angle correction method provided by the present application includes:

Step 201: Obtain a barcode image to be corrected.

It should be noted that the barcode image to be corrected can be obtained through a camera, and the barcode image to be corrected is a color image.

Step 202: grayscale the acquired barcode image to be corrected.

It should be noted that the obtained barcode image to be corrected is grayed to facilitate the subsequent binarization process. In the embodiment of the present application, the weighted average method is preferably used for graying, that is:

f(x,y)=0.30R(x,y)+0.59G(x,y)+0.11B(x,y);

Among them, R, G, and B are the three channels of the color image, and f is the grayscale image after grayscale processing.

Step 203: De-noise the grayscaled barcode image.

It should be noted that since noise has an adverse effect on subsequent binarization processing, in the embodiment of the present application, the barcode image to be corrected after grayscale processing is denoised, and the image can be smoothed by a filtering algorithm to achieve the denoising effect. Commonly used filtering algorithms include mean filtering, median filtering, and Gaussian filtering. In the embodiment of the present application, median filtering is preferably used. The image is traversed by a sliding window, and the pixel values of the middle point of the sliding window and its surrounding neighboring pixel points are arranged in ascending or descending order, and then the sorted middle value is taken as the pixel value of the center point of the window.

Step 204: Binarize the barcode image to be corrected after the denoising process to obtain a first binary image.

It should be noted that, in the embodiment of the present application, a global binarization method is used to perform binarization processing on the denoised barcode image to be corrected, and the segmentation threshold of the foreground target and the background in the barcode image to be corrected is defined as T, the size of the image is M×N, the number of pixels belonging to the foreground accounts for the proportion of all pixels in the whole image is ω ₀ , and the corresponding average grayscale is μ ₀ , the number of background pixels accounts for all pixels in the whole image is ω ₁ , and the corresponding average grayscale is μ ₁ , the total average grayscale of the image is μ, and the inter-class variance is g. It is defined that the number of pixels in the image whose grayscale value is less than the threshold T is recorded as N ₀ , and the number of pixels whose corresponding grayscale value is greater than the threshold T is recorded as N ₁ . At this time, the definition is as follows:

μ＝ω ₀ ×μ ₀ +ω ₁ ×μ ₁ ;

g＝ω ₀ (μ ₀ -μ) ² +ω ₁ (μ ₁ -μ) ² ;

T = argmax(g);

The T corresponding to the maximum value of g is the required threshold value. The denoised barcode image to be corrected is binarized according to the obtained threshold value T to obtain a first binary image.

Step 205 : Perform contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area.

Step 206 , fill the white foreground area whose area is smaller than the preset threshold with black according to the flood filling algorithm to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixels in the first contour of the white foreground area.

It should be noted that there are a large number of white foregrounds in the first binary image obtained. Other white foreground areas except the barcode will affect the detection of the directional straight line of the barcode, especially the dense small-area white foreground areas. These small-area white foreground areas not only affect the efficiency of program operation, but also easily lead to straight line detection errors. Therefore, it is necessary to reduce the small-area white foreground areas. In the embodiment of the present application, the white foreground area in the first binary image is subjected to contour retrieval by a contour retrieval algorithm, so as to obtain the first contour of the white foreground area. After obtaining the first contour, the area of the white foreground area corresponding to each first contour can be obtained by calculating the number of pixels in each first contour. According to the flood filling algorithm, the white foreground area with an area less than a preset threshold is filled with black, so as to achieve the purpose of deleting the small-area white foreground area, thereby improving the detection accuracy of the directional straight line of the barcode. Among them, the preset threshold in the embodiment of the present application is set to 30, and the black filling based on the flood filling algorithm belongs to the prior art, and the specific process of the black filling by the flood filling algorithm is not repeated here.

Step 207: Perform contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area.

Step 208: Calculate the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points.

It should be noted that, because the bars of the barcode are all equal-height bars, aligned in the same direction, the straight line formed by the center points of these bars is the direction straight line of the barcode. Therefore, it is necessary to calculate the center of the second contour of the white foreground area to obtain the center point of each barcode bar. The specific steps are:

Based on the second contour of the white foreground area, four boundary points of the second contour are obtained, where the four boundary points are the top, bottom, leftmost and rightmost points;

The circumscribed rectangle of the second contour is obtained based on the four boundary points, and the center of the circumscribed rectangle is calculated based on the circumscribed rectangle. The center of the circumscribed rectangle is used as the center of the second contour to obtain several center points. The positions of non-center points can be filled with black to obtain a center point image, wherein the coordinates of the center point of the circumscribed rectangle can be obtained by taking half of the length and width of the circumscribed rectangle.

Step 209: Perform straight line fitting on the center point based on Hough transform and output the angle.

It should be noted that after obtaining several center points, a straight line detection algorithm can be used to detect the straight line and return the straight line with the best fit. In the embodiment of the present application, Hough transform is preferably used to fit the center point to the straight line. Hough transform is a shape detection algorithm in image processing, which can handle both discontinuous points and continuous points. The principle of Hough transform is to transform the image function expression from Euclidean distance to parameter space, so as to realize the fitting detection of the shape. In the rectangular coordinate system, the straight line can be expressed as y=ax+b, and in the polar coordinate system, the straight line can be expressed as ρ=x cosθ+y sinθ, where ρ is the vertical distance from the origin to the straight line, and θ is the angle between the vertical line of the straight line and the horizontal axis in the clockwise direction, as shown in Figure 4. When ρ is greater than 0, the straight line is below the origin; when ρ is greater than 0, the straight line is above the origin. Regardless of whether the straight line is above or below the origin, the angle θ is less than 180°. Therefore, (ρ; θ) can be used to represent any straight line. Hough transform is used to fit the center point to a straight line. Specifically, first, a two-dimensional array is created as an accumulator. The rows and columns of the array represent ρ and θ respectively. The values in the array are initialized by setting them to 0, and the x and y values of the center point are substituted into the polar coordinate equation of the line. Then, the θ values are traversed according to the precision, with the interval being the precision value. The corresponding ρ value is substituted into the equation to obtain a plurality of value pairs (ρ; θ). These value pairs are compared with the accumulator. If the corresponding position can be found in the accumulator, the value at the corresponding position is incremented by 1. Then, the second center point is taken, and the aforementioned steps are repeated and the value in the accumulator is updated until all the center points are taken. When all operations are completed, there is a maximum value in the accumulator, and the value pair (ρ; θ) corresponding to the maximum value is output to obtain the angle θ.

Step 210: obtain a correction angle based on the included angle calculation, and rotate the barcode image to be corrected based on the correction angle to obtain a corrected barcode image.

It should be noted that the correction angle can be obtained by subtracting the included angle θ from 90°, and the barcode image to be corrected is rotated based on the correction angle to obtain the corrected barcode image.

For ease of understanding, please refer to FIG. 3 , which shows an embodiment of a barcode image angle correction device provided by the present application, including:

The grayscale processing module 301 is used to perform grayscale processing on the acquired barcode image to be corrected.

The binarization processing module 302 is used to perform binarization processing on the barcode image to be corrected after the grayscale processing to obtain a first binary image.

The first contour retrieval module 303 is used to perform contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area.

The filling module 304 is used to fill the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixels in the first contour of the white foreground area.

The second contour retrieval module 305 is used to perform contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area.

The calculation module 306 is used to calculate the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points.

The straight line fitting module 307 is used to perform straight line fitting on the central point based on Hough transform and output the angle.

The correction module 308 is used to obtain a correction angle based on the included angle calculation, and to rotate the barcode image to be corrected based on the correction angle to obtain a corrected barcode image.

Furthermore, it also includes:

The denoising module 309 is used to perform denoising on the barcode image to be corrected after the grayscale processing.

Furthermore, the filling module 304 is specifically used for:

The white foreground area whose area is smaller than the preset threshold is filled with black according to the flood filling algorithm to obtain a second binary image.

Furthermore, the calculation module 306 is specifically used for:

Based on the second contour of the white foreground area, four boundary points of the second contour are obtained, where the four boundary points are the top, bottom, leftmost and rightmost points;

A circumscribed rectangle of the second contour is obtained based on the four boundary points, a center of the circumscribed rectangle is calculated based on the circumscribed rectangle, and the center of the circumscribed rectangle is used as the center of the second contour to obtain a plurality of center points.

Furthermore, it also includes:

The image acquisition module 310 is used to acquire the barcode image to be corrected.

In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (8)

1. A barcode image angle correction method, comprising: grayscale the acquired barcode image to be corrected; Binarizing the grayscaled barcode image to be corrected to obtain a first binary image; Performing contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area; Filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixel points within the first contour of the white foreground area; Performing contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area; Calculating the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points; Perform straight line fitting on the center point based on Hough transform and output the angle; Calculating a correction angle based on the included angle, and rotating the barcode image to be corrected based on the correction angle to obtain a corrected barcode image; The step of calculating the center of the second contour of the white foreground area based on the second contour of the white foreground area to obtain a plurality of center points includes: Obtaining four boundary points of the second contour based on the second contour of the white foreground area, wherein the four boundary points are the top, bottom, leftmost and rightmost points; A circumscribed rectangle of the second contour is obtained based on the four boundary points, a center of the circumscribed rectangle is calculated based on the circumscribed rectangle, and the center of the circumscribed rectangle is used as the center of the second contour to obtain a plurality of center points. 2. The barcode image angle correction method according to claim 1, characterized in that the barcode image to be corrected after the grayscale processing is binarized to obtain a first binary image, and before that, the method further comprises: The barcode image to be corrected is subjected to denoising after the grayscale processing. 3. The barcode image angle correction method according to claim 1, characterized in that the step of filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image comprises: The white foreground area whose area is smaller than the preset threshold is filled with black according to the flood filling algorithm to obtain a second binary image. 4. The barcode image angle correction method according to claim 1, characterized in that the grayscale processing of the acquired barcode image to be corrected is performed before the grayscale processing further comprises: The barcode image to be corrected is obtained. 5. A barcode image angle correction device, comprising: A grayscale processing module, used for grayscale processing of the acquired barcode image to be corrected; A binarization processing module, used for binarizing the barcode image to be corrected after the grayscale processing to obtain a first binary image; A first contour retrieval module, configured to perform contour retrieval on the white foreground area in the first binary image based on a contour retrieval algorithm to obtain a first contour of the white foreground area; A filling module, used for filling the white foreground area whose area is smaller than a preset threshold with black to obtain a second binary image, wherein the area of the white foreground area is calculated based on the number of pixel points within the first contour of the white foreground area; A second contour retrieval module, configured to perform contour retrieval on the white foreground area in the second binary image based on a contour retrieval algorithm to obtain a second contour of the white foreground area; A calculation module, used for calculating the center of the second outline of the white foreground area based on the second outline of the white foreground area to obtain a plurality of center points; A straight line fitting module, used for performing straight line fitting on the center point based on Hough transform and outputting an angle; A correction module, used for calculating a correction angle based on the included angle, and rotating the barcode image to be corrected based on the correction angle to obtain a corrected barcode image; The calculation module is specifically used for: Obtaining four boundary points of the second contour based on the second contour of the white foreground area, wherein the four boundary points are the top, bottom, leftmost and rightmost points; A circumscribed rectangle of the second contour is obtained based on the four boundary points, a center of the circumscribed rectangle is calculated based on the circumscribed rectangle, and the center of the circumscribed rectangle is used as the center of the second contour to obtain a plurality of center points. 6. The barcode image angle correction device according to claim 5, further comprising: The denoising module is used to perform denoising on the barcode image to be corrected after the grayscale processing. 7. The barcode image angle correction device according to claim 5, characterized in that the filling module is specifically used for: The white foreground area whose area is smaller than the preset threshold is filled with black according to the flood filling algorithm to obtain a second binary image. 8. The barcode image angle correction device according to claim 5, further comprising: The image acquisition module is used to acquire the barcode image to be corrected.

Images