CN117952135A

CN117952135A - Bar code identification device

Info

Publication number: CN117952135A
Application number: CN202410011560.0A
Authority: CN
Inventors: 魏江涛; 贺超; 王冬生; 张立静; 周小芹
Original assignee: Shenzhen Yingda Machine Vision Technology Co ltd
Current assignee: Shenzhen Yingda Machine Vision Technology Co ltd
Priority date: 2019-05-09
Filing date: 2019-05-09
Publication date: 2024-04-30
Also published as: CN110245536A; CN110245536B

Abstract

The invention discloses a bar code recognition device, comprising: the acquisition module is used for acquiring the gray level image of the bar code; the positioning module is used for positioning the gray level image and extracting a bar code image in the gray level image; the binarization module is used for binarizing the bar code image to obtain a binarized image of the bar code; the projection module is used for projecting the binarized image along the horizontal direction and the vertical direction respectively to obtain horizontal-direction projection and vertical-direction projection of the binarized image; the feature extraction module is used for extracting features of the horizontal projection and the vertical projection respectively to obtain projection features; and the determining module is used for determining the type of the bar code according to the projection characteristics.

Description

Bar code identification device

The divisional application is a divisional application of a Chinese patent application with the application date of 2019, 5 month and 9 days, the application number of 201910382518.9 and the name of a bar code identification method.

Technical Field

The invention relates to the field of image recognition, in particular to a bar code recognition device.

Background

The field of bar code recognition mainly divides bar code recognition into four parts of bar code acquisition, image preprocessing, bar code positioning and bar code recognition. The bar code is usually collected by the cooperation of a lens and an image sensor; the image preprocessing generally adopts digital image processing technology to perform optimization processing such as denoising and deblurring, and a great deal of prior art is used for reference in the aspect; the bar code positioning is to extract the bar code from the image by utilizing the unique structural characteristics of the bar code; the bar code identification is to interpret the digital information carried by the bar code according to the coding rules of different code systems.

The traditional bar code identification method needs to compare the acquired bar codes with bar codes of various different code systems in a decoding library until the decoding is successful, and the decoding method generally needs to traverse one-dimensional codes or two-dimensional codes of various code systems and has low efficiency.

In view of the above problems, it has been proposed in the industry to distinguish one-dimensional codes from two-dimensional codes according to geometric features of barcode regions, such as aspect ratios. The method only utilizes the characteristics that the one-dimensional code area tends to be rectangular and the two-dimensional code area tends to be square, and the distinguishing method is simple and easy to distinguish in error, so that the recognition rate is reduced.

Thus, the industry has proposed a technique for detecting a straight line: on the binary image after edge detection (only limited foreground area), searching pixels on a certain straight line segment along a certain direction, and when the number of pixels reaches a certain threshold 50, finding a straight line. And continuing to search straight lines along the same direction, and when the number of the detected straight lines reaches a certain threshold 7, considering the image as a one-dimensional bar code, or else, judging the image as a two-dimensional bar code. Unfortunately, this detection method does not take into account the widely used stacked two-dimensional code such as PDF417 code, and when detecting along the longitudinal direction of PDF417 code, more than 7 lines are detected to determine PDF417 code as a one-dimensional bar code, and errors occur, which results in incapability of decoding; the novel mixed code can be misjudged into a one-dimensional bar code by the detection method, and errors occur, so that decoding cannot be performed, the whole decoding efficiency is low, and the linear detection technology has a large limitation.

Disclosure of Invention

Aiming at the problems faced by the background technology, the invention aims to provide a method for identifying a bar code according to the characteristics of horizontal projection and vertical projection of a binary image of the bar code.

In order to achieve the above purpose, the invention adopts the following technical means:

First aspect: the invention provides a bar code recognition method, which is applied to a recognition device of a bar code type recognition system, and comprises the following steps:

acquiring a gray image of the bar code;

Positioning the gray level image and extracting a bar code image in the gray level image;

Binarizing the bar code image to obtain a binarized image of the bar code;

Projecting the binarized image along the horizontal direction and the vertical direction respectively to obtain horizontal projection and vertical projection of the binarized image;

Respectively carrying out feature extraction on the horizontal direction projection and the vertical direction projection to obtain projection features;

and determining the type of the bar code according to the projection characteristics.

Optionally, feature extraction is performed on the horizontal direction projection and the vertical direction projection respectively, so as to obtain projection features, including:

Performing linear scanning on the horizontal projection along the horizontal direction;

Counting the number X of black stripes or white stripes which pass through the scanning line simultaneously;

performing linear scanning on the vertical projection along the vertical direction;

Counting the number Y of black stripes or white stripes which pass through the scanning line simultaneously;

and taking the number X of the black stripes or the white stripes and the number Y of the black stripes or the white stripes as the projection characteristics.

Optionally, the determining the type of the barcode according to the projection feature includes:

Analyzing the quantitative relation between the X and the Y;

Comparing the maximum value Xmax of the X with the maximum value Ymax of the Y;

Calculating the ratio of a larger value to a smaller value between the maximum value Xmax and the maximum value Ymax to obtain a characteristic value N;

And comparing the characteristic value N with a first preset threshold value to determine the type of the bar code.

Optionally, comparing the feature value N with a first preset threshold to determine a barcode to identify a type of barcode, including:

if the characteristic value N is larger than the first preset threshold value, determining that the bar code is a one-dimensional code;

And if the characteristic value N is smaller than the first preset threshold value, determining that the bar code is a two-dimensional code.

Optionally, the first preset threshold is greater than or equal to 2 and less than or equal to 7.

Optionally, the first preset threshold is 7, and if the feature value N is between 1 and 2, the barcode is determined to be a matrix two-dimensional barcode; if the characteristic value N is between 2 and 7, determining that the bar code is a stacked two-dimensional code.

Optionally, if the bar code is determined to be a two-dimensional code, if the minimum value Xmin of X or the minimum value Ymin of Y is less than or equal to 2, determining that the bar code is a matrix two-dimensional code; and if the minimum value Xmin or the minimum value Ymin is greater than 2, determining that the bar code is a stacked two-dimensional code.

Optionally, the feature extraction for the horizontal direction projection and the vertical direction projection respectively includes:

detecting the similarity between the horizontal projection and the binarized image to obtain horizontal similarity;

Detecting the similarity between the vertical projection and the binarized image to obtain vertical similarity;

And taking the horizontal similarity and the vertical similarity as the projection characteristics.

Optionally, the degree of coincidence between the horizontal projection and the binary image is the horizontal similarity, the degree of coincidence between the vertical projection and the binary image is the vertical similarity, and determining the type of the bar code according to the projection characteristics includes:

If the horizontal similarity or the vertical similarity reaches a second preset threshold, determining that the bar code is a one-dimensional code;

And if the horizontal similarity or the vertical similarity does not reach the second preset threshold, determining that the bar code is a two-dimensional code.

Optionally, the degree of coincidence between the horizontal projection and the black block of the binary image is the horizontal similarity, the degree of coincidence between the vertical projection and the black block of the binary image is the vertical similarity, and determining the type of the bar code according to the projection characteristics includes:

Second aspect: the invention provides a bar code recognition device, which comprises:

The acquisition module is used for acquiring the gray level image of the bar code;

the positioning module is used for positioning the gray level image and extracting a bar code image in the gray level image;

The binarization module is used for binarizing the bar code image to obtain a binarized image of the bar code;

The projection module is used for projecting the binarized image along the horizontal direction and the vertical direction respectively to obtain horizontal-direction projection and vertical-direction projection of the binarized image;

The feature extraction module is used for extracting features of the horizontal projection and the vertical projection respectively to obtain projection features;

And the determining module is used for determining the type of the bar code according to the projection characteristics.

Optionally, the feature extraction module includes:

the first scanning unit is used for carrying out linear scanning on the horizontal projection along the horizontal direction;

A first statistics unit for counting the number X of black stripes or white stripes which the scanning line passes through simultaneously;

The second scanning unit is used for carrying out linear scanning on the vertical projection along the vertical direction;

The second statistics unit is used for counting the number Y of black stripes or white stripes which are penetrated by the scanning straight line at the same time;

And the feature determining unit is used for taking the number X of the black stripes or the white stripes and the number Y of the black stripes or the white stripes as the projection features.

Optionally, the determining module includes:

An analysis unit for analyzing the quantitative relationship between the X and the Y;

A first comparing unit, configured to compare the maximum value Xmax of X with the maximum value Ymax of Y;

The calculating unit is used for calculating the ratio of a larger value to a smaller value between the maximum value Xmax and the maximum value Ymax to obtain a characteristic value N;

and the second comparison unit is used for comparing the characteristic value N with a first preset threshold value to determine the type of the bar code.

Optionally, the second comparing unit includes:

The first determining subunit is configured to determine that the barcode is a one-dimensional code if the feature value N is greater than the first preset threshold;

and the second determining subunit is used for determining that the bar code is a two-dimensional code if the characteristic value N is smaller than the first preset threshold value.

Optionally, the first preset threshold is 7, and the second comparing unit includes:

The third determining subunit is configured to determine that the barcode is a matrix two-dimensional barcode if the feature value N is between 1 and 2;

and the fourth determination subunit is configured to determine that the barcode is a stacked two-dimensional barcode if the feature value N is between 2 and 7.

Optionally, if the barcode is a two-dimensional barcode, the determining module includes:

A fifth determining subunit, configured to determine that the barcode is a matrix two-dimensional barcode if the minimum value Xmin of X or the minimum value Ymin of Y is less than or equal to 2;

And the sixth determining subunit is configured to determine that the barcode is a stacked two-dimensional barcode if the minimum value Xmin or the minimum value Ymin is greater than 2.

Optionally, the feature extraction module includes:

The first detection unit is used for detecting the similarity between the horizontal projection and the binarized image to obtain horizontal similarity;

And the second detection unit is used for detecting the similarity between the vertical projection and the binarized image to obtain vertical similarity.

And a third determining unit configured to take the horizontal similarity and the vertical similarity as the projection features.

Optionally, the degree of coincidence between the horizontal projection and the binary image is the horizontal similarity, and the degree of coincidence between the vertical projection and the binary image is the vertical similarity, and the determining module includes:

a fourth determining unit, configured to determine that the barcode is a one-dimensional code if the horizontal similarity or the vertical similarity reaches a second preset threshold;

And a fifth determining unit, configured to determine that the barcode is a two-dimensional barcode if the horizontal similarity or the vertical similarity does not reach the second preset threshold.

Optionally, the degree of coincidence between the horizontal projection and the black block of the binary image is the horizontal similarity, the degree of coincidence between the vertical projection and the black block of the binary image is the vertical similarity, and the determining module includes:

A sixth determining unit, configured to determine that the barcode is a one-dimensional code if the horizontal similarity or the vertical similarity reaches a second preset threshold;

And a seventh determining unit, configured to determine that the barcode is a two-dimensional barcode if the horizontal similarity or the vertical similarity does not reach the second preset threshold.

Third aspect: a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the barcode recognition method of the first aspect when executing the computer program.

Fourth aspect: a computer readable storage medium storing a computer program which when executed by a processor implements the barcode recognition method of the first aspect.

Compared with the prior art, the invention has the following beneficial effects:

And respectively carrying out feature extraction on the horizontal direction projection and the vertical direction projection which are respectively established along two edges which are perpendicular to each other of the binarized image of the bar code, and identifying the bar code as a one-dimensional code or a two-dimensional code according to the features of the horizontal direction projection and the vertical direction projection of the one-dimensional code and the two-dimensional code. The one-dimensional code is formed by arranging black bars and white bars at intervals in one direction, so that the binary image of the one-dimensional code is obviously collapsed when projected in one of the horizontal direction or the vertical direction; the two-dimensional code is formed by hashing black blocks and white blocks in a coding area, and the algorithm determines that the black blocks are approximately and uniformly distributed in the whole coding area, so that the binary image of the two-dimensional code is obviously collapsed when projected in the horizontal direction and the vertical direction, and the characteristics of obvious similarity of the horizontal projection and the vertical projection of the two-dimensional code are also generated; the distinguishing features which are obviously different from the horizontal direction projection and the vertical direction projection of the one-dimensional code and the horizontal direction projection and the vertical direction projection of the two-dimensional code are caused, and based on the distinguishing features, the identification device can quickly and accurately distinguish the one-dimensional code from the two-dimensional code, so that the decoding is performed according to the coding mode of the one-dimensional code after the one-dimensional code is identified, and the decoding is performed according to the coding mode of the two-dimensional code after the two-dimensional code is identified, and the decoding efficiency can be effectively improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a bar code identification method according to an embodiment of the invention;

FIG. 2 is a schematic diagram of adjusting the orientation of a barcode image;

FIG. 3 is a schematic diagram of creating a horizontal projection and a vertical projection of a one-dimensional code;

FIG. 4 is a schematic illustration of feature extraction for horizontal projection;

FIG. 5 is a schematic illustration of feature extraction for the vertical projection of FIG. 3;

FIG. 6 is a schematic diagram of establishing horizontal and vertical projections of a two-dimensional code;

FIG. 7 is a schematic diagram of feature extraction for the horizontal projection of FIG. 6;

FIG. 8 is a schematic illustration of feature extraction for the vertical projection of FIG. 6;

FIG. 9 is another schematic diagram of creating a horizontal projection and a vertical projection of a one-dimensional code;

FIG. 10 is a schematic illustration of feature extraction for the horizontal and vertical projections of FIG. 9;

FIG. 11 is another schematic diagram of creating a horizontal projection and a vertical projection of a two-dimensional code;

Fig. 12 is a schematic diagram of feature extraction for the horizontal and vertical projections of fig. 11.

FIG. 13 is a schematic diagram of a bar code recognition device according to the present invention;

FIG. 14 is a schematic diagram of a computer device according to the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.

For a better understanding of the invention with objects, structures, features, and effects, the invention will be described further with reference to the drawings and to the detailed description.

As shown in fig. 1, fig. 1 is a schematic diagram of an embodiment of a barcode recognition method according to an embodiment of the present invention, including the following steps:

S100: acquiring a gray image of the bar code;

s200: positioning the gray level image and extracting a bar code image in the gray level image;

s300: performing binarization processing on the bar code image to obtain a binarization image of the bar code;

As shown in fig. 2, for steps S100 to S300, it can be understood that when the gray image P1 is obtained, the gray image P1 is first preprocessed, for example, the gray image P1 is filtered to remove noise, and the gray image P1 is smoothed, and then the gray image P1 is further clarified by sharpening, and so on; after the gray image P1 is subjected to the preprocessing operation, the position of the bar code image P2 in the whole gray image P1 is more prominent, so that the bar code image P2 can be conveniently positioned. Specifically, the barcode image P2 may be positioned according to the features of the barcode image P2, for example, the edge of the barcode image P2 is detected by an edge detection technology, so as to determine the position of the barcode image P2, and further segment the barcode image P2 from the whole gray scale image P1; in some embodiments, image localization and image segmentation may be performed simultaneously by the same processing unit. It should be noted that the preprocessing and the barcode image P2 positioning have mature technologies as supports, for example, the preprocessing has a median filtering processing method, the edge detection can be performed by a Canny operator for edge detection, and then the image segmentation is performed by an oxford thresholding method, and these methods and other existing image positioning and image segmentation methods are not described herein. As shown in fig. 2, since the barcode image P2 is generally in an inclined state in the whole gray-scale image P1, it can be aligned by azimuth adjustment, specifically, a vertical coordinate system can be established along two mutually perpendicular edges of the barcode image P2, or the barcode image P2 is rotated so that the two vertical edges of the barcode image P2 are respectively parallel to two coordinate axes of the existing vertical coordinate system, so as to facilitate subsequent processing, and of course, azimuth adjustment can also be performed in subsequent steps.

Next, as shown in fig. 3 and 6, the located barcode image P2 is subjected to binarization processing, the background is converted into white, the black block or black bar in the barcode image P2 is converted into black, and the white block or white bar in the barcode image P2 is also converted into white. It should be noted that the black and white colors are opposite, and the black blocks or bars in the barcode image P2 are converted to white colors, and the white blocks or bars in the barcode image P2 are converted to black colors, which does not affect the subsequent processing and recognition.

S400: projecting the binarized image along the horizontal direction and the vertical direction respectively to obtain horizontal projection and vertical projection of the binarized image;

Then, as shown in fig. 3 and 6, the horizontal direction projection and the vertical direction projection of the binarized image P3 are respectively established along the horizontal direction (the direction of one edge of the binarized image P3) and the vertical direction (the direction of the other edge of the binarized image P3).

S500: respectively carrying out feature extraction on the horizontal direction projection and the vertical direction projection to obtain projection features;

S600: and determining the type of the bar code according to the projection characteristics.

Then, as shown in fig. 4,5, 7 and 8, the binary image is projected along the horizontal direction and the vertical direction respectively to obtain a horizontal projection and a vertical projection of the binary image, and feature extraction is performed on the horizontal projection and the vertical projection respectively to obtain projection features. Since the binarized image P3 of the one-dimensional code is projected in only one of the horizontal direction or the vertical direction, significant collapse occurs; the two-dimensional code is formed by hashing black blocks and white blocks in a coding area, the coding mode determines that the black blocks are approximately and uniformly distributed in the whole coding area, so that the binary image P3 of the two-dimensional code is obviously collapsed when projected in the horizontal direction and the vertical direction, and the horizontal direction projection and the vertical direction projection of the two-dimensional code have obvious similar characteristics; the above causes significantly different distinguishing features of the horizontal direction projection and the vertical direction projection of the one-dimensional code from those of the two-dimensional code. For example, when the binary image P3 of the one-dimensional code collapses along the horizontal projection, the binary image P must collapse into one connected domain, and the vertical projection cannot collapse, and the binary image P is a plurality of connected domains; the two-dimensional code binary image P3 is collapsed when projected in the horizontal direction and the vertical direction, and the horizontal projection and the vertical projection of the two-dimensional code binary image P3 basically form a connected domain, and for a specific stacked two-dimensional code, even if the horizontal projection or the vertical projection of the two-dimensional code binary image P3 forms a plurality of connected domains, the two-dimensional code binary image P3 can be distinguished from the one-dimensional code by the specific projection characteristics after being collapsed.

Here, code128 codes and QR codes, which are typical of one-dimensional codes and two-dimensional codes, are taken as examples, and other one-dimensional codes and two-dimensional codes are similar to the codes. As shown in fig. 3, the horizontal projection and the vertical projection of the Code128 Code are horizontally folded and stacked, while the black bars of the Code128 Code are almost unchanged (theoretically unchanged) along the vertical direction; as shown in fig. 5, the horizontal projection and the vertical projection of the QR code are both significantly collapsed with respect to the pre-projection binary image P3.

And finally, according to the features of the one-dimensional code and the two-dimensional code and comparing with the extracted projection features, judging whether the bar code is the one-dimensional code or the two-dimensional code.

Analyzing the quantitative relation between the X and the Y;

Comparing the maximum value Xmax of the X with the maximum value Ymax of the Y;

Optionally, the comparing the feature value N with a first preset threshold to determine the type of the barcode includes:

Taking Code128 in fig. 3 and QR in fig. 5 as examples, feature extraction is performed by linear scanning. When the horizontal projection and the vertical projection of the Code128 Code are scanned linearly, since the black bars of the Code128 Code are collapsed together in the horizontal direction, any position of the horizontal projection of the scanning line passes through one black bar (the black bars here refer to the black bars separated by the white bars, when the scanning line passes through the black bars simultaneously, then passes through the white bars and then passes through the black bars again, the scanning line passes through two black bars simultaneously, even if the two black bars are connected at other positions, the next same), and the number X of the black bars through which the scanning line passes simultaneously is counted to be equal to one; the black bars hardly collapse along the vertical direction (theoretically, the black bars do not change), the scanning straight line passes through at least seven black bars (three initial bars and four end bars) at any position of the projection in the vertical direction, the number Y of the counted black bars is always more than seven, and the value Y at any code scanning position is basically unchanged (theoretically, the value Y is unchanged); ymax is greater than Xmax, ymax/Xmax is always greater than seven. When the horizontal projection of the QR code is subjected to linear scanning, the number X of the black bars passing through the scanning line is always increased and then decreased, and when the vertical projection of the QR code is subjected to linear scanning, the number Y of the black bars passing through the scanning line is also increased and then decreased, and the following rules are approximately satisfied: xmin=ymin=1, xmax≡ymax, then 2 > max { Xmax, ymax }/max { Xmax, ymax } > 1. Therefore, when projection feature extraction is performed on one bar code, when max { Xmax, ymax }/max { Xmax, ymax } > 7, that is, when the feature value N is greater than the first preset threshold, the bar code is judged to be a one-dimensional code, and otherwise, the bar code is judged to be a two-dimensional code.

Optionally, when the bar code is determined to be a two-dimensional code, if the minimum value Xmin of the X or the minimum value Ymin of the Y is less than or equal to 2, determining that the bar code is a matrix two-dimensional code; and if the minimum value Xmin or the minimum value Ymin is greater than 2, determining that the bar code is a stacked two-dimensional code.

Since the QR code is a matrix two-dimensional code, the following relationship is provided for a stacked two-dimensional code such as PDF 417: xmin > 2 and Ymin > 2, while 7 > max { Xmax, ymax }/max { Xmax, ymax }, therefore, after judging that the barcode is a two-dimensional barcode, further judgment can be made: when Xmin > 2 or Ymin > 2 or 7 > max { Xmax, ymax }/max { Xmax, ymax } > 2, the bar code is judged to be a stacked two-dimensional code.

Since the horizontal direction projection and the vertical direction projection of the one-dimensional code have obvious morphological differences from the horizontal direction projection and the vertical direction projection of the two-dimensional code, in other embodiments, the one-dimensional code and the two-dimensional code may be distinguished based on these distinguishing features, as shown in fig. 9, 10, 11 and 13, which are another embodiment of the identification method of the identification module 100 of the present invention, the difference from the previous embodiment is that: the similarity between the horizontal projection and the vertical projection and the binarized image P3 may be detected, and specifically, the coincidence between the horizontal projection and the vertical projection and the binarized image P3 may be detected, or the coincidence between the horizontal projection and the vertical projection and the black block of the binarized image P3 may be detected, to obtain the horizontal similarity and the vertical similarity. Taking the coincidence ratio of the horizontal projection and the vertical projection with the binarized image P3 as an example, because one of the horizontal projection and the vertical projection of the one-dimensional code is almost coincident with the binarized image P3, and neither of the horizontal projection and the vertical projection of the two-dimensional code is coincident with the binarized image P3, based on the coincidence ratio, namely, the horizontal similarity and the vertical similarity, of the one-dimensional code with the binarized image P3 is judged to be the one-dimensional code when the coincidence ratio, namely, the horizontal similarity and the vertical similarity, of the one-dimensional code reach a second preset threshold; otherwise, judging the bar code as a two-dimensional code. Further, when the overlapping area of one of the horizontal direction projection and the vertical direction projection and the black block of the binarized image P3 reaches a certain threshold value, judging that the bar code is a one-dimensional code; otherwise, judging the bar code as a two-dimensional code. Further, the threshold value is 50%, and when the overlap ratio between one of the horizontal projection and the vertical projection and the binarized image P3 reaches more than 50%, the bar code is judged to be a one-dimensional code; otherwise, judging the bar code as a two-dimensional code. Preferably, when the overlap ratio between one of the horizontal projection and the vertical projection and the binarized image P3 reaches more than 70%, the barcode is determined to be a one-dimensional code. Preferably, when the overlap ratio between one of the horizontal projection and the vertical projection and the binarized image P3 reaches more than 90%, the barcode is determined to be a one-dimensional code.

It can be seen that the embodiment of the invention provides a bar code identification method, which is to respectively set up horizontal direction projection and vertical direction projection along two mutually perpendicular edges of a binarized image P3 of a bar code, respectively perform feature extraction on the horizontal direction projection and the vertical direction projection, and identify the bar code as a one-dimensional code or a two-dimensional code according to the features of the horizontal direction projection and the vertical direction projection of the one-dimensional code and the two-dimensional code respectively. The two-dimensional code is formed by hashing black blocks and white blocks in a coding area, the coding mode determines that the black blocks are approximately uniformly distributed in the whole coding area, the two-dimensional code binary image P3 is obviously collapsed when projected in the horizontal direction and the vertical direction, and the horizontal direction projection and the vertical direction projection of the two-dimensional code have obvious similar characteristics; the distinguishing features which are obviously different from the horizontal direction projection and the vertical direction projection of the one-dimensional code and the horizontal direction projection and the vertical direction projection of the two-dimensional code are caused, based on the distinguishing features, the identification module 100 can quickly and accurately distinguish the one-dimensional code from the two-dimensional code, and the two-dimensional code is decoded according to the coding mode of the one-dimensional code after being identified as the one-dimensional code, and the two-dimensional code is decoded according to the coding mode of the two-dimensional code after being identified as the two-dimensional code, so that the identification efficiency is improved.

The above describes a barcode recognition method of the present invention, and the following describes a barcode recognition device of the embodiment of the present invention:

As shown in fig. 13, the identification device of the present invention mainly includes: an acquisition module 10, a positioning module 11, a binarization module 12, a projection module 13, a feature extraction module 14 and a determination module 15.

An acquisition module 10 for acquiring a gray image of the bar code;

the positioning module 11 is used for positioning the gray level image and extracting a bar code image in the gray level image;

a binarization module 12, configured to binarize the barcode image to obtain a binarized image of the barcode;

The projection module 13 is used for respectively projecting the binarized image along the horizontal direction and the vertical direction to obtain horizontal-direction projection and vertical-direction projection of the binarized image;

a feature extraction module 14, configured to perform feature extraction on the horizontal direction projection and the vertical direction projection, to obtain projection features;

A determining module 15, configured to determine a type of the barcode according to the projection characteristic.

Optionally, the feature extraction module 14 includes:

Optionally, the determining module includes:

a first comparing unit for comparing the maximum value Xmax of X with the maximum value Ymax of Y;

Optionally, the second comparing unit includes:

Optionally, the feature extraction module includes:

For specific limitations of the barcode recognition apparatus, reference may be made to the above limitations of the barcode recognition method, and the description thereof will not be repeated here.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 14. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for data required by the bar code identification method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to perform the steps described for a bar code identification method.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon which when executed by a processor performs the steps described for a bar code identification method.

The bar code identification method, the device, the equipment and the medium have the following beneficial effects:

And respectively carrying out feature extraction on the horizontal direction projection and the vertical direction projection which are respectively established along two edges which are perpendicular to each other of the binarization image P3 of the bar code, and identifying the bar code as a one-dimensional code or a two-dimensional code according to the features of the horizontal direction projection and the vertical direction projection of the one-dimensional code and the two-dimensional code. The two-dimensional code is formed by hashing black blocks and white blocks in a coding area, the coding mode determines that the black blocks are approximately uniformly distributed in the whole coding area, the two-dimensional code binary image P3 is obviously collapsed when projected in the horizontal direction and the vertical direction, and the horizontal direction projection and the vertical direction projection of the two-dimensional code have obvious similar characteristics; the identification device can rapidly and accurately distinguish the one-dimensional code from the two-dimensional code based on the distinguishing features, and decodes the one-dimensional code according to the encoding mode of the one-dimensional code after the one-dimensional code is identified, and decodes the two-dimensional code according to the encoding mode of the two-dimensional code after the two-dimensional code is identified, thereby improving the identification efficiency and accuracy of the bar code.

The above detailed description is merely illustrative of the preferred embodiments of the invention and is not intended to limit the scope of the invention, so that all equivalent technical changes that can be made by the present specification and illustrations are included in the scope of the invention.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; 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, and are intended to be included in the scope of the present invention.

Claims

1. A bar code identification device, comprising:

2. The bar code identification device of claim 1, wherein the feature extraction module comprises:

3. The bar code identification device of claim 2, wherein the determination module comprises:

4. A bar code identification device as claimed in claim 3, wherein the second comparison unit comprises:

5. The bar code identification device of claim 4, wherein the first predetermined threshold is greater than or equal to 2 and less than or equal to 7.

6. The bar code identification device of claim 5, wherein the first predetermined threshold is 7, and the second comparing unit comprises:

7. The bar code identification device of claim 6, wherein if the bar code is a two-dimensional bar code, the determining module comprises:

8. The bar code identification device of claim 3, wherein the feature extraction module comprises:

The second detection unit is used for detecting the similarity between the vertical projection and the binarized image to obtain vertical similarity;

9. The bar code identification device of claim 8, wherein the degree of coincidence of the horizontal projection and the binary image is the horizontal similarity, and the degree of coincidence of the vertical projection and the binary image is the vertical similarity, the determining module comprises:

10. The bar code identification device of claim 8, wherein the horizontal projection and the black block of the binary image have a degree of coincidence of the horizontal similarity and the vertical projection and the black block of the binary image have a degree of coincidence of the vertical similarity, and the determining module comprises: