KR20220083406A - Apparatus and method for extracting barcode - Google Patents

Abstract

A barcode extraction apparatus according to the present invention includes: image acquisition means for acquiring an original image including a barcode; and a Laplacian filter unit that detects an edge component in the original image through a Laplacian filtering process, and generates a Laplacian filtered image by using the edge component. According to the present invention, in detecting the edge component in the original image including the barcode, the edge component detection and the Laplacian filtering image are generated through the Laplacian filtering process, so that the barcode is detected in a shorter time than other filtering processing methods. be able to do

Description

Barcode extraction apparatus and method {APPARATUS AND METHOD FOR EXTRACTING BARCODE}

The present invention relates to an apparatus and method for extracting a barcode, which is a label that displays information on an article and the like.

As the number of single-person households increases, more and more people are using courier services. In general, parcel delivery goods are temporarily stored in a distribution warehouse and delivered to users of a delivery service. At this time, the logistics warehouse manages the parcels by attaching barcodes to the parcels and reading the barcodes attached thereto. In addition, when sorting parcels made in a distribution warehouse, it is sometimes necessary to simultaneously recognize several barcodes in order to speed up the operation. As such, in the management of parcel delivery or sorting of parcels, it is most important to accurately extract the barcode attached to the parcel in order to provide a prompt and accurate parcel delivery service.

Recently, as the technology related to artificial intelligence develops, a barcode extraction method using neural networks is being developed. However, the barcode extraction method using a neural network requires a process of learning a barcode through a neural network, so it takes a long time to learn, takes a lot of money, and has difficulties in implementation because the learning algorithm system is complicated.

Another method of extracting barcodes is the Hough Transform. Hough transformation is a method of detecting a barcode by calculating an angle of a bar code tilted from an original image including the barcode, and rotating the original image. However, when barcodes are detected by Hough transform, there is a problem in that barcode detection accuracy is significantly lowered when linear noise is included in the original image.

On the other hand, in Patent Document 1, it is determined whether a character pattern that can exist in the first barcode exists in at least one of the vicinity of both ends of the light-dark pattern string, and when it is determined that the character pattern exists, the light-dark pattern string is set to the first A method of estimating a margin position corresponding to the first barcode assuming a partial code pattern of the barcode, and determining the light and dark pattern sequence as reading data of the second barcode when no margin is detected at the margin position The barcode is being read.

Japanese Patent Publication No. 5152086 (2012.12.14)

An object of the present invention is to provide a barcode extraction device capable of filtering a background component corresponding to noise from an original image including a barcode by introducing a filtering processing technique suitable for barcode extraction, and extracting only the barcode component with high accuracy There is this.

In order to achieve the above object, a barcode extraction apparatus according to an embodiment of the present invention includes: an image acquisition means for acquiring an original image including a barcode; and a Laplacian filter unit that detects an edge component in the original image through a Laplacian filtering process, and generates a Laplacian filtered image by using the edge component.

Here, the edge component detected by the Laplacian filter unit may include an edge component in a horizontal direction and an edge component in a vertical direction.

Furthermore, the edge component detected by the Laplacian filter unit may further include an edge component in a diagonal direction.

In addition, the barcode extraction apparatus according to an embodiment of the present invention detects the horizontal edge component and the vertical edge component in the Laplacian filtered image through Sobel filtering processing, respectively, and It may further include a Sobel filter for generating a Sobel filtered image by using the edge component and the vertical edge component.

Here, the Sobel filter unit may generate the Sobel filtered image by taking an absolute value from a value obtained by subtracting the vertical edge component from the horizontal edge component.

Meanwhile, in order to achieve the above object, (a) obtaining an original image including a barcode; and (b) detecting an edge component in the original image through Laplacian filtering processing, and generating a Laplacian filtered image using the edge component.

The edge component detected in step (b) may include an edge component in a horizontal direction and an edge component in a vertical direction.

Furthermore, the edge component detected in step (b) may further include an edge component in a diagonal direction.

In addition, in the barcode extraction method according to an embodiment of the present invention, after step (b), (c) the edge component in the horizontal direction and the vertical direction in the Laplacian filtered image through Sobel filtering processing The method may further include detecting edge components, respectively, and generating a Sobel filtered image using the horizontal edge component and the vertical edge component.

In step (c), the Sobel filtered image may be generated by taking an absolute value from a value obtained by subtracting the vertical edge component from the horizontal edge component.

According to the present invention, in detecting the edge component in the original image including the barcode, the edge component detection and the Laplacian filtering image are generated through the Laplacian filtering process, so that the barcode can be detected in a shorter time than other filtering processing methods. be able to

1 is a diagram schematically showing a barcode extraction apparatus according to an embodiment of the present invention.
2 is a flowchart illustrating a barcode extraction method performed by the barcode extraction apparatus of FIG. 1 .
3 is a view exemplarily illustrating a state in which a barcode is extracted from an original image by a barcode extraction method according to an embodiment of the present invention.

Hereinafter, a barcode extraction apparatus and method according to the present invention will be described in detail with reference to the accompanying drawings. The accompanying drawings are provided by way of example only so that the technical idea of the present invention can be sufficiently conveyed to those skilled in the art, and the present invention is not limited to the drawings presented below and may be embodied in other forms. have.

1 is a diagram schematically illustrating a barcode extraction apparatus according to an embodiment of the present invention, and FIG. 2 is a flowchart illustrating a barcode extraction method performed by the barcode extraction apparatus of FIG. 1 . Hereinafter, an apparatus and method for extracting a barcode according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2 together.

As shown in FIG. 1 , the barcode extraction apparatus 1000 according to an embodiment of the present invention includes an image acquisition means 100 and a Laplacian filter unit 200 , and further includes a Sobel filter unit 300 . can do. The barcode extraction method according to an embodiment of the present invention is performed by the barcode extraction apparatus 1000, and first, the image acquiring means 100 acquiring an original image including the barcode (S100) may be performed.

The image acquisition means 100 may correspond to any means capable of acquiring an original image including a barcode, including a camera, a laser scanner, a smart phone, and the like. Here, the original image including the barcode includes the barcode to be extracted and the background around the barcode to be removed. The filter units 200 and 300 to be described below perform filtering processing to remove the background from the original image including the barcode and to extract only the barcode.

The original image including the barcode may be implemented as a combination of several pixels. Each pixel may have a pixel value corresponding to an illuminance value based on gray scale or an illuminance value based on RGB. In general, a pixel having the largest change in pixel value among pixels constituting an image is a pixel corresponding to an edge portion. Hereinafter, a pixel value of a pixel corresponding to the edge portion will be referred to as an edge component, and the filter units 200 and 300 according to the present invention detect an edge component from an original image including a barcode.

Since the image is two-dimensional, if the pixel values of the pixels constituting the image are differentiated in the horizontal and vertical directions, respectively, it can be seen how the pixel values change in the horizontal and vertical directions, respectively. Assuming that the image is on the x-y coordinate (here, x is the horizontal axis and y is the vertical axis), it is easy to know the position of the edge by obtaining the gradient in which the pixel value changes in the horizontal direction and the gradient in the vertical direction. . However, since the image is discrete data rather than continuous data, differentiation operation cannot be performed. Accordingly, the horizontal and vertical gradients are computations that calculate the difference between the pixel values of adjacent pixels, instead of the differential computation. .

When pixel values of pixels adjacent to each other in the horizontal direction are compared to obtain a gradient that changes in the horizontal direction, the portion where the pixels in the horizontal direction contact each other is parallel to the y-axis, so that the edge component in the vertical direction can be detected. On the same principle, if pixel values of pixels adjacent to each other in the vertical direction are compared to obtain the gradient that changes in the vertical direction, the portion where the pixels in the vertical direction contact each other is parallel to the x-axis, so the edge component for the horizontal direction can be detected. The filter units 200 and 300 according to the present invention detect an edge component through a method of comparing pixel values of pixels adjacent to each other as described above.

After the step S100, the Laplacian filter unit 200 detects an edge component in the original image including the barcode through Laplacian filtering processing, and generates a Laplacian filtered image using the edge component (S200) is made Here, the Laplacian filtering process performed by the Laplacian filter unit 200 may mean convolution of the Laplacian kernel matrix and the original image.

For example, the Laplacian filter unit 200 corresponds to the 3×3 size Laplacian kernel matrix with the 3×3 size pixels among the pixels of the original image obtained in step S100. Convolution can be performed (this is called '2D convolution'). An edge component is detected from the original image by the convolution performed by the Laplacian filter unit 200, and the Laplacian filter unit 200 may output a Laplacian filtered image including the edge component.

The edge component detected by the Laplacian filter unit 200 in the original image may include an edge component in a horizontal direction and an edge component in a vertical direction. A Laplacian kernel matrix generally used to detect an edge component in a horizontal direction and an edge component in a vertical direction is expressed by Equation 1 below.

[Equation 1]

과, 수직 방향의 에지 성분을 검출하는 데 사용되는 라플라시안 커널 행렬

의 합에 해당한다.The Laplacian kernel matrix shown in Equation 1 is a Laplacian kernel matrix used to detect horizontal edge components in the original image.

and Laplacian kernel matrix used to detect edge components in the vertical direction.

corresponds to the sum of

The Laplacian filter unit 200 may perform a Laplacian filtering process for detecting an edge component in the original image by convolving the Laplacian kernel matrix as shown in Equation 1 with the original image. In the Laplacian filtering process performed by the Laplacian filter unit 200 , since it is possible to simultaneously calculate an edge component in a horizontal direction and an edge component in a vertical direction, an edge component can be detected in a shorter time than other filtering processing methods.

Additionally, the edge component detected by the Laplacian filter unit 200 from the original image may further include a diagonal edge component in addition to a horizontal edge component and a vertical edge component. A Laplacian kernel matrix generally used to detect an edge component in a horizontal direction, an edge component in a vertical direction, and an edge component in a diagonal direction is expressed by Equation (2) below.

[Equation 2]

, 수직 방향의 에지 성분을 검출하는 데 사용되는 라플라시안 커널 행렬

, 및 대각선 방향의 에지 성분을 검출하는 데 사용되는 2개의 라플라시안 커널 행렬

과

의 합에 해당한다.The Laplacian kernel matrix shown in Equation 2 is a Laplacian kernel matrix used to detect horizontal edge components in the original image.

, the Laplacian kernel matrix used to detect the edge component in the vertical direction.

, and two Laplacian kernel matrices used to detect diagonal edge components.

class

corresponds to the sum of

Since the barcode included in the original image is in the form of alternating black and white stripes in the shape of a bar, the point of inflection for pixel values is well shown. Since the Laplacian filtering process performed by the Laplacian filter unit 200 uses second-order differentiation, pixel values of pixels adjacent to each other in the diagonal direction may also be second-ordered. That is, the Laplacian filter unit 200 may perform Laplacian filtering processing for detecting edge components in the original image by convolving the Laplacian kernel matrix as shown in Equation 2 with the original image. It is possible to detect not only the edge component and the vertical edge component but also the diagonal edge component.

When the Laplacian filter unit 200 detects an edge component in a horizontal direction, an edge component in a vertical direction, and an edge component in a diagonal direction in the original image, inflection points for pixel values in the original image are easily distinguished. It is possible to detect embedded barcodes with higher accuracy. In addition, since the Laplacian filtering process performed by the Laplacian filter unit 200 can simultaneously calculate an edge component in a horizontal direction, an edge component in a vertical direction, and an edge component in a diagonal direction, the edge component is faster than other filtering processing methods can be detected in time.

However, since the Laplacian filtering process performed by the Laplacian filter unit 200 uses second-order differentiation, barcode detection of a wider area is possible compared to other filtering processing methods, but the background around the barcode corresponding to noise is also more detect a lot.

Accordingly, in the barcode extraction method according to an embodiment of the present invention, after step S200, in order to remove the background around the barcode corresponding to noise, the Sobel filter unit 300 performs Sobel filtering processing, Detecting the horizontal edge component and the vertical edge component in the Laplacian filtering image generated in step S200, respectively, and generating a Sobel filtered image using the horizontal edge component and the vertical edge component It may include a step (S300). Since the noise that was not previously removed by the filtering process of the Laplacian filter unit 200 has been removed from the Sobel filtering image generated by the Sobel filter unit 300, the barcode included in the original image can be detected with higher accuracy. be able to

The Sobel filter unit 300 serves to detect an edge component in the original image like the Laplacian filter unit 200 . However, when the Laplacian filter unit 200 uses the second differentiation, the horizontal direction edge component and the vertical direction edge component (or the horizontal direction edge component, the vertical direction edge component, and the diagonal direction edge) component), the Sobel filter unit 300 detects the horizontal edge component and the vertical edge component, respectively.

When the horizontal edge component detected by the Sobel filter unit 300 in the Laplacian filtered image is SOBEL.X, the SOBEL.X may be expressed as in Equation 3 below.

[Equation 3]

In Equation 3, BARCODE.X is a pixel value corresponding to a barcode among the edge components in the horizontal direction. Also, in Equation 3, Noise is a background component around the barcode (that is, a pixel value of a pixel corresponding to the background part of the original image), and the background component around the barcode includes a horizontal background component and a vertical background component. These may be mixed.

Also, when the vertical edge component detected by the Sobel filter unit 300 in the Laplacian filtered image is SOBEL.Y, the SOBEL.Y may be expressed as in Equation 4 below.

[Equation 4]

In Equation 4, BARCODE.Y is a pixel value corresponding to the barcode among the edge components in the vertical direction, Noise is a background component around the barcode as in Equation 3, and the background component around the barcode includes a background component in the horizontal direction. and background components in the vertical direction may be mixed.

In general, according to the method of using the Sobel filter, a total edge component is calculated by adding SOBEL.X and SOBEL.Y. However, in the present invention, the Sobel filter unit 300 performs an operation as in Equation 5 below, instead of adding SOBEL.X and SOBEL.Y.

[Equation 5]

That is, the Sobel filter unit 300 generates a Sobel filtered image by taking an absolute value from a value obtained by subtracting the vertical edge component SOBEL.Y from the horizontal edge component SOBEL.X, and generates a Sobel filtering image. can be printed out.

The reason why the Sobel filter unit 300 subtracts the vertical edge component SOBEL.Y from the horizontal edge component SOBEL.X is that the pixel value corresponding to the barcode is equal to the horizontal edge component and the vertical direction. Since only one of the edge components exists (typically, it exists in the vertical edge component), only one of BARCODE.X and BARCODE.Y is left. In addition, when the Sobel filter unit 300 subtracts the vertical edge component SOBEL.Y from the horizontal edge component SOBEL.X, the background component around the barcode corresponding to noise can be removed.

3 is a diagram exemplarily illustrating a state in which a barcode is extracted from an original image by a barcode extraction method according to an embodiment of the present invention.

More specifically, in FIG. 3 , an original image including a barcode is acquired by the image acquisition means 100 (a dotted line box in FIG. 3A ), and the original image through the Laplacian filtering process of the Laplacian filter unit 200 . A state in which a Laplacian filtered image is generated ( FIG. 3b ) is shown. Also, FIG. 3 shows a state in which a Sobel filtered image is generated from the Laplacian filtered image through the Sobel filtering process of the Sobel filter unit 300 ( FIG. 3c ).

As described above, although the present invention has been described with reference to the limited embodiments and drawings, the present invention is not limited to the above-described embodiments, and those skilled in the art to which the present invention pertains can make various modifications and variations from these descriptions. This is possible. For example, after acquiring the original image including the barcode by the image acquiring means 100 , before the Laplacian filtering process of the Laplacian filter 200 , a gray scale step of converting the original image into a grayscale image may be further added. Alternatively, after the Laplacian filtering process of the Laplacian filter unit 200 and before the Sobel filtering process of the Sobel filter unit 300, a median value filtering step of removing noise from the Laplacian filtering image through a median filter is further added. can be Alternatively, after the Sobel filtering process of the Sobel filter unit 300, a normal erosion calculation step or an expansion calculation step may be further added. The technical spirit of the present invention should be understood only by the claims, and all equivalents or equivalent modifications thereof will fall within the scope of the technical spirit of the present invention.

100: image acquisition means
200: Laplacian filter unit
300: Sobel filter unit
1000: barcode extraction device

Claims (10)

image acquisition means for acquiring an original image including a barcode; and
and a Laplacian filter unit that detects an edge component in the original image through a Laplacian filtering process and generates a Laplacian filtered image by using the edge component.
The method of claim 1,
The edge component detected by the Laplacian filter unit includes a horizontal edge component and a vertical edge component.
3. The method of claim 2,
The edge component detected by the Laplacian filter unit further comprises a diagonal edge component.
4. The method of claim 2 or 3,
The horizontal edge component and the vertical edge component are respectively detected in the Laplacian filtered image through Sobel filtering processing, and the Sobel filtered image using the horizontal edge component and the vertical edge component Barcode extraction device further comprising a; Sobel filter unit to generate a.
5. The method of claim 4,
The Sobel filter unit generates the Sobel filtering image by taking an absolute value from a value obtained by subtracting the vertical edge component from the horizontal edge component.
(a) obtaining an original image including a barcode; and
(b) detecting an edge component in the original image through a Laplacian filtering process, and generating a Laplacian filtered image by using the edge component.
7. The method of claim 6,
The edge component detected in step (b) includes a horizontal edge component and a vertical edge component.
8. The method of claim 7,
The edge component detected in step (b) further comprises an edge component in a diagonal direction.
9. The method according to claim 7 or 8,
After step (b),
(c) Detecting the horizontal edge component and the vertical edge component in the Laplacian filtered image through Sobel filtering processing, respectively, and using the horizontal edge component and the vertical edge component Barcode extraction method comprising further; generating a Sobel filtering image.
10. The method of claim 9,
In step (c), the Sobel filtering image is generated by taking an absolute value from a value obtained by subtracting the vertical edge component from the horizontal edge component.

Images