WO2019132093A1 - Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant - Google Patents

Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant Download PDF

Info

Publication number
WO2019132093A1
WO2019132093A1 PCT/KR2018/000317 KR2018000317W WO2019132093A1 WO 2019132093 A1 WO2019132093 A1 WO 2019132093A1 KR 2018000317 W KR2018000317 W KR 2018000317W WO 2019132093 A1 WO2019132093 A1 WO 2019132093A1
Authority
WO
WIPO (PCT)
Prior art keywords
rectangle
barcode
points
extracting
bar code
Prior art date
Application number
PCT/KR2018/000317
Other languages
English (en)
Korean (ko)
Inventor
홍하나
장재호
정동환
Original Assignee
한화테크윈주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한화테크윈주식회사 filed Critical 한화테크윈주식회사
Publication of WO2019132093A1 publication Critical patent/WO2019132093A1/fr

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404Methods for optical code recognition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/28Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Definitions

  • Embodiments of the present invention relate to a bar code reading system.
  • the barcode is a label that displays the information of the item, and it is widely used today because it can store information reliably and read it quickly. Generally, it is necessary to arrange a photographing apparatus adjacent to a bar code to recognize the bar code.
  • Embodiments of the present invention provide an apparatus and method for detecting a bar code that can detect a bar code without distinguishing the 1D / 2D bar code.
  • a barcode detecting apparatus includes a candidate detecting unit for extracting a first rectangle corresponding to a barcode element candidate based on contour information of an input image; And a verifying unit for verifying whether the first rectangle corresponds to the bar code element based on the position of the center point of the first rectangle.
  • the verifying unit comprises: a clustering unit for extracting clusters that are sets of first rectangles having center points whose mutual distances are within a predetermined distance among the center points of the extracted first rectangles; And a filter that excludes first rectangles of different sizes from among the rectangles included in the cluster.
  • the filter may exclude a first rectangle that is outside a certain range from the median or average value of the lengths of one side of the first rectangles included in the cluster.
  • the verification unit may include: a map generation unit generating an area map indicating first rectangles included in the cluster passing through the filter as an area; And a barcode determining unit for extracting a second rectangle surrounding the combination of the areas.
  • the candidate detection unit may include: a binarization unit for binarizing the input image; An outline extracting unit for extracting an outline from the binarized image; And an element extracting unit for generating a polygon connecting representative points among the points constituting the contour and extracting a first rectangle including the polygon.
  • the representative points may be points excluding points within a certain distance from a line connecting any two points among the points constituting the contour.
  • the candidate detecting unit may further include a classifier for classifying the first rectangle into a one-dimensional bar code or a two-dimensional bar code according to a length condition.
  • the length condition may include a ratio of length to width of the first rectangle.
  • the first rectangle having a length ratio of 1: 1 of the horizontal and vertical lengths may be classified into a two-dimensional bar code, and the other first rectangle may be classified into a one-dimensional bar code.
  • the verifying unit may further include a barcode determining unit that extracts, from the input image, a region corresponding to the second rectangle by a barcode.
  • a method of detecting a barcode includes extracting a first rectangle corresponding to a barcode element candidate based on contour information of an input image; And verifying whether the first rectangle corresponds to the bar code element based on the position of the center point of the first rectangle.
  • the step of verifying the barcode comprises the steps of extracting clusters which are a set of first rectangles having center points whose mutual distances among the center points of the extracted first rectangles are within a predetermined distance; And a filtering step of excluding a first rectangle having a different size from among the rectangles included in the cluster.
  • the filtering may include excluding a first rectangle that is out of a certain range from an intermediate value or an average value of the lengths of one side of the first rectangles included in the cluster.
  • the barcode verification step may include: generating an area map in which first quadrangles included in the cluster are displayed as areas after the filtering step; And extracting a second rectangle surrounding the combination of regions.
  • the first rectangle extracting step may include: binarizing the input image; Extracting an outline from the binarized binary image; And generating a polygon connecting representative points among the points constituting the contour, and extracting a first rectangle including the polygon.
  • the representative points may be points excluding points within a certain distance from a line connecting any two points among the points constituting the contour.
  • the method may further include classifying the first rectangle into a one-dimensional bar code or a two-dimensional bar code according to a length condition.
  • the length condition may include a ratio of length to width of the first rectangle.
  • the step of classifying the barcode may include classifying the first rectangle having a length ratio of the length to the length of the first rectangle to a two-dimensional barcode and classifying the other first rectangle into a one-dimensional barcode.
  • the method may further include extracting a region corresponding to the second rectangle from the input image with a barcode.
  • the barcode detection method can find the barcode without distinguishing the 1D / 2D barcode.
  • FIG. 1 is a diagram schematically illustrating a barcode reading system 1 according to an embodiment of the present invention.
  • 2A and 2B are examples of bar codes detected according to an embodiment of the present invention.
  • FIG. 3 is a block diagram schematically showing a barcode detecting apparatus 100 according to an embodiment of the present invention.
  • FIG 4 is an illustration of an outline reconstruction method according to an embodiment of the present invention.
  • 5 is a view for explaining barcode element extraction according to an embodiment of the present invention.
  • FIGS. 6 and 7 are diagrams for explaining one-dimensional bar code detection according to an embodiment of the present invention.
  • FIG. 8 is a view for explaining detection of a two-dimensional bar code according to an embodiment of the present invention.
  • 9 to 11 are flowcharts schematically illustrating a barcode detection method according to an embodiment of the present invention.
  • FIG. 12 shows an example in which a bar code reading system according to an embodiment of the present invention is applied.
  • a barcode detecting apparatus includes a candidate detecting unit for extracting a first rectangle corresponding to a barcode element candidate based on contour information of an input image; And a verifying unit for verifying whether the first rectangle corresponds to the bar code element based on the position of the center point of the first rectangle.
  • the functions of the various elements shown in the drawings may be provided by use of dedicated hardware as well as hardware capable of executing software in connection with appropriate software.
  • the functions may be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared.
  • the use of terms that are presented in terms of processor, control, or similar concepts should not be interpreted exclusively as hardware capable of executing software, and may include, without limitation, digital signal processor (DSP) (ROM), random access memory (RAM), and non-volatile memory. Other hardware may also be included.
  • DSP digital signal processor
  • RAM random access memory
  • non-volatile memory Other hardware may also be included.
  • FIG. 1 is a diagram schematically illustrating a barcode reading system 1 according to an embodiment of the present invention.
  • the barcode reading system 1 may include a barcode detecting device 100 and a barcode decoding device 200.
  • the barcode detecting apparatus 100 can detect a barcode from an input image.
  • the barcode may include a 1D barcode 10 (see FIG. 2A) and a 2D barcode 20 (see FIG. 2B).
  • the one-dimensional bar code 10 is a code or sign system that expresses information in an array pattern of a bar A and a space B.
  • the bars and spaces of the one-dimensional bar code are rectangles each having a width (width, W) and a length (height, H).
  • the two-dimensional bar code 20 is a code or code system for displaying information by arranging a black square C and a white square D in a mosaic manner.
  • the black square C and the white square D of the two-dimensional bar code have the same width (width, W) and length (height, H).
  • the barcode detection apparatus 100 extracts barcode black and white elements, i.e., a black element (for example, a black rectangle or a black square) and a white element (for example, a white rectangle or a white square)
  • a black element for example, a black rectangle or a black square
  • a white element for example, a white rectangle or a white square
  • the barcode detection apparatus 100 can detect at least one barcode by extracting a rectangle corresponding to a black-and-white element (hereinafter, referred to as a "barcode element") of the barcode based on the outline information in the input image.
  • the barcode detection apparatus 100 can extract the barcode from the input image by verifying the extracted rectangle.
  • the extracted bar code may be output to the bar code decoding apparatus 200 after being angle-corrected using the rotation angle in the input image.
  • the barcode decoding apparatus 200 can decode the barcode to interpret the information contained in the barcode.
  • FIG. 3 is a block diagram schematically showing a barcode detecting apparatus 100 according to an embodiment of the present invention.
  • the apparatus 100 for detecting a barcode may include a candidate detector 110, a verifier 130, and a compensator 150.
  • the candidate detection unit 110 can detect an area corresponding to the black and white element of the bar code from the input image.
  • the candidate detection unit 110 may include a binarization unit 112, an outline extraction unit 114, an element extraction unit 116, and a classification unit 118.
  • the binarization unit 112 may binarize the input image to generate a monochrome binary image. Since the barcode is composed of monochrome data, binarization is performed for barcode extraction.
  • the binarization method is not particularly limited, and various known methods can be used.
  • the Otsu algorithm can be used as a binarization method.
  • the Otsu algorithm performs binarization by minimizing the intra-class variance between two classes or maximizing the inter-class variance when classifying the pixels of an image into two classes based on the threshold value.
  • the barcode is black and white data on the edge of the histogram, so there is an advantage that it can be more clearly divided when Otsu algorithm classifies it than to binarize it with a certain value.
  • the contour extracting unit 114 can extract a contour from the binary image.
  • the method of extracting the contour is not particularly limited, and various known methods can be used.
  • the outline information may include information of lines and / or points constituting the outline.
  • the element extracting unit 116 can extract a rectangle corresponding to the candidate of the bar code element from the outline.
  • the element extracting unit 116 may extract a rectangle using some points (representative points) among the points constituting the outline. That is, the element extracting unit 116 can minimize the barcode detection information by using the minimum line information and point information.
  • the representative point may be a selected one of adjacent points (points at similar positions).
  • the element extracting unit 116 can reconstruct contours by generating lines connecting representative points. In one embodiment, the element extraction unit 116 may reconstruct the contour using the Ramer-Douglas-Peucker algorithm.
  • the reconstructed outline is a polygon.
  • the element extracting unit 116 may generate a first rectangle including (surrounds) a polygon.
  • the first rectangle may be a candidate for a bar code element.
  • FIG 4 is an illustration of an outline reconstruction method according to an embodiment of the present invention.
  • Figs. 4 (b) to 4 (f) show a method of reconstructing a part of the "all" outline shown in (a).
  • the element extracting unit 116 generates new lines connecting only representative points from a plurality of points n1 to np forming an outline as shown in (b), and reconstructs outlines by connecting new lines, can do.
  • a line L1 connecting the two points n1 and np is generated as shown in (c), and a point nh where the distance x from the line L1 is equal to or larger than the threshold value And generates lines (L2, L3) connecting the two new points (n1 and nh and nh and np).
  • points (nj) with a distance x from the line L3 exceeding the threshold value are extracted as shown in (e), and lines L4 and L6 connecting the new two points (nh and nj and nj and np) L5.
  • points (nk) with a distance x from the line L5 exceeding the threshold value are extracted as shown in (f), and lines L6 and L7 connecting the new two points (nj and nk and nk and np) L7). That is, five representative points (n1, nh, nj, nk, np) out of 10 points of n1 to np constituting the contour in (b) are selected and a new contour Can be configured.
  • the classifying unit 118 may classify the first rectangle into a one-dimensional bar code or a two-dimensional bar code according to the length and / or the ratio of the first rectangle.
  • the classifying unit 118 classifies the first rectangle having the ratio of the first rectangle, that is, the ratio of the length / length to the length of the first rectangle, to the two-dimensional barcode, and the first rectangle to the one-dimensional barcode.
  • the classifying unit 118 may selectively perform filtering excluding the first rectangle whose length of the long side is less than or equal to the threshold value among the first rectangles classified by the one-dimensional bar code.
  • the verification unit 130 may perform verification of the first rectangles classified into the barcode.
  • the verification unit 130 may include a clustering unit 132, a filter 134, a map generation unit 136, and a barcode determination unit 138.
  • the clustering unit 132 may find the center point of the first rectangle and may cluster the first rectangles based on the position of the center point.
  • the clustering unit 132 may cluster the first squares in which the center point is located within a certain distance between the center points.
  • a cluster which is a set of clustered first rectangles can be determined as a single barcode.
  • the clustering unit 132 may find the center points of the first rectangles classified by the one-dimensional bar code, and may calculate the distance between the center points of the first rectangles.
  • the clustering unit 132 may cluster the first rectangles having a distance between the center points within a predetermined distance based on the position of the center point. That is, each of the center points of the first rectangles included in the cluster may be located within a certain distance from the center point of at least one other first rectangle included in the same cluster.
  • the clustering unit 132 may find the center points of the first rectangles classified into the two-dimensional bar code, and calculate the distance between the center points of the first rectangles.
  • the clustering unit 132 may cluster the first rectangles having a distance between the center points within a predetermined distance based on the position of the center point. That is, each of the center points of the first rectangles included in the cluster may be located within a certain distance from the center point of at least one other first rectangle included in the same cluster.
  • the filter 134 may perform filtering excluding the first rectangle of different size among the first rectangles assigned to the cluster.
  • the filter 134 may exclude the first rectangle whose length of the long side of each of the first rectangles included in the cluster of the one-dimensional bar code is out of a certain range from the reference value.
  • the reference value may be an intermediate value or an average value of the lengths of long sides of the first squares included in the cluster.
  • the filter 134 may exclude a first rectangle in which the length of one side of each of the first rectangles included in the cluster of the two-dimensional bar code is out of a certain range from the reference value.
  • the reference value may be an intermediate value or an average value of the lengths of one side of the first rectangles included in the cluster.
  • the map generating unit 136 may generate an area map in which the first rectangles passed by the filter 134 are displayed as areas.
  • the map generating unit 136 may display the area corresponding to the first rectangle in white and the other background in black. Accordingly, a large area in which a plurality of small areas are synthesized can be generated in the area map.
  • the barcode determining unit 138 may generate a second rectangle surrounding a large area of the area map.
  • the barcode determining unit 138 may extract an area corresponding to the second rectangle in the input image as a final barcode.
  • the compensation unit 150 may calculate the rotation angle of the bar code and warp the input image using the rotation angle.
  • the compensator 150 may extract a plurality of barcode images from the input image and warp each barcode image using the rotation angle of each barcode.
  • the barcode detecting apparatus 100 may output the warped barcode image or the input image to the barcode decoding apparatus 200.
  • 5 is a view for explaining barcode element extraction according to an embodiment of the present invention.
  • the binarization unit 112 may generate a binary image 52 by binarizing the input image 50.
  • the contour extracting unit 114 can extract the contour 54 from the binary image 52.
  • the element extracting unit 116 may extract the first rectangle 56 surrounding the generated polygon by reconstructing the outline 54 from the input image 50.
  • the first rectangle 56 may have various sizes depending on the shape of the polygon. Accordingly, a plurality of first rectangles 56 having different sizes in the input image 50 can be extracted as candidates of the barcode elements.
  • FIGS. 6 and 7 are diagrams for explaining one-dimensional bar code detection according to an embodiment of the present invention.
  • the clustering unit 132 extracts a center point 63 of each of the first rectangles 61 classified into a one-dimensional bar code, and calculates a distance between the center points based on the position of the center point within a predetermined distance Clusters the first squares.
  • the filter 134 calculates the length of the long sides of each of the first squares included in the cluster 65 and excludes the first square out of the predetermined range from the median or average value of the lengths of the long sides.
  • the map generating unit 136 generates an area map in which the first rectangle passing through the filter 134 is indicated by the area 67.
  • the barcode determining unit 138 can extract the second rectangle 69 surrounding the area where the plurality of areas 67 are synthesized. An area corresponding to the second rectangle 69 in the input image can be extracted as a one-dimensional barcode.
  • FIG. 7 shows a case where a first rectangle 71 'of different sizes among a plurality of first rectangles 71 included in the cluster 75 clustered on the basis of the position of the center point 73 is excluded by the filter 134 Fig.
  • the first rectangles 71 passing through the filter in the region map 75 are represented by the region 77 and the second rectangle 79 surrounding the region where the plurality of regions 77 are synthesized can be generated .
  • FIG. 8 is a view for explaining detection of a two-dimensional bar code according to an embodiment of the present invention.
  • the clustering unit 132 extracts a center point 83 of each of the first rectangles 81 classified into a two-dimensional bar code, and calculates a distance between the center points of the first rectangles 81, Clusters of the first rectangles in the first direction and in the second direction perpendicular to the first direction are clustered.
  • the filter 134 calculates the length of one side of the first rectangles included in the cluster 85 and excludes the first rectangle 81 'out of the predetermined range from the median or average value of the lengths of the sides.
  • the map generating unit 136 generates an area map in which the first rectangle passed through the filter 134 is indicated by the area 87. [
  • the barcode determining unit 138 can extract the second rectangle 89 surrounding the area where the plurality of areas 87 are synthesized. An area corresponding to the second rectangle 89 in the input image can be extracted as a two-dimensional barcode.
  • FIGS. 9 to 11 are flowcharts schematically illustrating a barcode detection method according to an embodiment of the present invention.
  • the barcode detecting method shown in Figs. 9 to 11 can be performed by the barcode detecting apparatus 100 described above.
  • a detailed description of the contents overlapping with those described above will be omitted.
  • the barcode detection apparatus 100 can detect a barcode candidate from the input image (S81).
  • the barcode detection apparatus 100 can binarize the input image (S811).
  • the binarization method is not particularly limited.
  • the barcode detection apparatus 100 can extract the contour from the binary image (S813).
  • the outline extraction method is not particularly limited.
  • the barcode detection apparatus 100 may reconstruct the outline to extract the first rectangle corresponding to the candidate of the barcode element (S815).
  • the barcode detection apparatus 100 can generate a polygon by connecting only the representative points among the points constituting the contour and reconstruct the outline, and extract the first rectangle surrounding the polygon.
  • the barcode detection apparatus 100 can select representative points by excluding points within a critical distance from a line connecting any two points.
  • the extracted first rectangle may be a barcode element candidate.
  • the barcode detection apparatus 100 may classify the extracted first rectangles into a one-dimensional barcode or a two-dimensional barcode based on the length (S817).
  • the barcode detection apparatus 100 may classify the first rectangle into a one-dimensional barcode or a two-dimensional barcode according to the length and / or the ratio of the first rectangle.
  • the first rectangle having the ratio of the first rectangle that is, the ratio of the length / length to the length of the first rectangle may be classified into the two-dimensional barcode, and the other first rectangle may be classified into the one- .
  • the barcode detection apparatus 100 may exclude a first rectangle having a length longer than a threshold value among first rectangles classified into a one-dimensional barcode.
  • the barcode detection apparatus 100 may detect the one-dimensional barcode or the two-dimensional barcode by verifying the first rectangles (S83).
  • the barcode detection apparatus 100 may spatially cluster the first squares based on the center point of the first square (S831).
  • the barcode detecting apparatus 100 can find the center points of the first rectangles classified by the one-dimensional barcode and clusters the first rectangles having the distance between the center points within a predetermined distance based on the position of the center points.
  • the barcode detecting apparatus 100 can find the center points of the first rectangles classified by the two-dimensional barcode and clusters the first rectangles whose distance between the center points is within a predetermined distance based on the position of the center points.
  • the barcode detection apparatus 100 may apply filters to the first rectangles assigned to the cluster to select only the first rectangles having similar sizes except for the first rectangles having different sizes (S833).
  • the barcode detection apparatus 100 may exclude a first rectangle in which the length of the long side of the first rectangles allocated to the cluster of the first bar code is out of a predetermined range from the reference value.
  • the reference value may be an intermediate value or an average value of the lengths of long sides of the first squares allocated to the cluster.
  • the barcode detection apparatus 100 may exclude a first rectangle whose length of one side of the first rectangles allocated to the cluster of the two-dimensional barcode is out of a certain range from the reference value.
  • the reference value may be a median or an average value of the lengths of one side of the first rectangles assigned to the cluster.
  • the barcode detection apparatus 100 may generate an area map in which the first rectangle having passed through the filter is displayed as an area (S835).
  • the area map the area of the first rectangle on the black background may be displayed in white.
  • the barcode detection apparatus 100 may extract a second rectangle surrounding the combination of regions and extract an area corresponding to the second rectangle from the input image with a barcode (S837).
  • the barcode detection device 10 can process the input image or the barcode image by using the rotation angle of the second rectangle.
  • FIG. 12 shows an example in which a bar code reading system according to an embodiment of the present invention is applied.
  • a system may include a barcode reading system 1 and a photographing apparatus 2.
  • FIG. 12 a system according to an embodiment may include a barcode reading system 1 and a photographing apparatus 2.
  • the image photographing apparatus 2 can photograph the object 40 on the transfer tray 30.
  • the image capturing apparatus 2 may be a camera attached to one side (head, hand, or the like) of the robot capable of linear movement in the X-axis and Y-axis directions and linear movement and rotation in the Z-axis direction (load direction).
  • the image capturing apparatus 2 can take an object 40 such as a part loaded on one side of the conveyance tray 30 moving at a constant speed.
  • the bar code reading system 1 can receive the image acquired by the image capturing apparatus 2, detect the object 40 from the image, and detect and read the bar code from the object image from which the object 40 is extracted.
  • the configuration and operation of the barcode reading system 1 have been described with reference to Figs. 1 to 11, and therefore, the description thereof will be omitted.
  • the robot can recognize an object placed on the transfer tray at random. If the barcode is attached to the object, additional work information can be assigned to each object. Therefore, utilization of the barcode information helps to diversify the work sequence of the robot. Further, it is possible to find and recognize the barcode area attached to the object based on the image photographed at the time of object recognition, without needing to photograph only the barcode separately.
  • the embodiments of the present invention can detect and recognize a barcode from an image including a barcode obtained using a camera in addition to the robot shown in Fig. For example, when the embodiment of the present invention is applied to a mobile terminal, all the barcodes included in the product can be confirmed at one time after the whole product is taken without enlarging and photographing only the barcode portion of the product.
  • the conventional barcode detection algorithm Since the conventional barcode detection algorithm is mainly based on edge information in the image, it extracts linear information using sobel or canny edge detection or extracts linear information using a hough transform to detect a barcode.
  • these methods are limited to the image in which the barcode is horizontally photographed, and often operate only when the size of the barcode is large in the image.
  • the conventional barcode detection algorithm operates only when an object is shot in a specific direction from a close proximity, and thus its use is limited.
  • Embodiments of the present invention utilize the bar shape of the bar code to extract a rectangular bar code bar. That is, in the embodiments of the present invention, by extracting the shape of data constituting the bar code, the bar code can be found without distinguishing the 1D / 2D bar code regardless of the size and / or rotation of the bar code.
  • the barcode detection and verification method of the barcode reading system according to the present invention can be implemented as a computer-readable code on a computer-readable recording medium.
  • a computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like.
  • the computer-readable recording medium may be distributed over network-connected computer systems so that computer readable codes can be stored and executed in a distributed manner.
  • functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers of the technical field to which the present invention belongs.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Electromagnetism (AREA)
  • Toxicology (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention, selon certains modes de réalisation, concerne un dispositif et un procédé de détection de code à barres. Un dispositif de détection de code à barres selon un mode de réalisation de la présente invention comprend : une unité de détection de candidat servant à extraire un premier carré correspondant à un élément de code à barres candidat, sur la base d'informations de contour d'une image d'entrée ; et une unité de vérification servant à vérifier si le premier carré correspond à un élément de code à barres, sur la base de la position d'un point central du premier carré.
PCT/KR2018/000317 2017-12-28 2018-01-08 Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant WO2019132093A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170182641A KR20190080275A (ko) 2017-12-28 2017-12-28 바코드 검출 장치 및 이를 이용한 바코드 검출 방법
KR10-2017-0182641 2017-12-28

Publications (1)

Publication Number Publication Date
WO2019132093A1 true WO2019132093A1 (fr) 2019-07-04

Family

ID=67067773

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2018/000317 WO2019132093A1 (fr) 2017-12-28 2018-01-08 Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant

Country Status (2)

Country Link
KR (1) KR20190080275A (fr)
WO (1) WO2019132093A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117408659A (zh) * 2023-10-27 2024-01-16 北京利通盛达科技有限公司 一种erp企业管理系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102371446B1 (ko) * 2020-05-14 2022-03-07 한국과학기술연구원 유럽연구소 우편물에 인쇄된 배송지 주소를 인식하는 방법 및 장치
KR102666036B1 (ko) 2021-05-26 2024-05-14 주식회사 에잇바이트 바코드 생성 장치 및 방법, 및 바코드 검증 장치 및 방법
KR102343439B1 (ko) * 2021-06-24 2021-12-27 주식회사 포스로직 바코드 영역 검출 방법 및 이러한 방법을 수행하는 장치

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050051029A (ko) * 2003-11-26 2005-06-01 (주)아이미디어아이앤씨 코드이미지 검출 방법 및 장치
KR100498763B1 (ko) * 2002-12-24 2005-07-01 한국전자통신연구원 바코드 고속 관심 영역 위치 판독 시스템 및 제어 방법
KR20140103021A (ko) * 2013-02-15 2014-08-25 삼성전자주식회사 객체 인식이 가능한 전자 장치
KR101623689B1 (ko) * 2015-06-08 2016-05-24 한경대학교 산학협력단 바코드 식별 장치 및 방법
KR101807566B1 (ko) * 2016-06-17 2017-12-11 인천대학교 산학협력단 바코드 검출 방법 및 장치

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100498763B1 (ko) * 2002-12-24 2005-07-01 한국전자통신연구원 바코드 고속 관심 영역 위치 판독 시스템 및 제어 방법
KR20050051029A (ko) * 2003-11-26 2005-06-01 (주)아이미디어아이앤씨 코드이미지 검출 방법 및 장치
KR20140103021A (ko) * 2013-02-15 2014-08-25 삼성전자주식회사 객체 인식이 가능한 전자 장치
KR101623689B1 (ko) * 2015-06-08 2016-05-24 한경대학교 산학협력단 바코드 식별 장치 및 방법
KR101807566B1 (ko) * 2016-06-17 2017-12-11 인천대학교 산학협력단 바코드 검출 방법 및 장치

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117408659A (zh) * 2023-10-27 2024-01-16 北京利通盛达科技有限公司 一种erp企业管理系统

Also Published As

Publication number Publication date
KR20190080275A (ko) 2019-07-08

Similar Documents

Publication Publication Date Title
WO2019132093A1 (fr) Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant
US8611662B2 (en) Text detection using multi-layer connected components with histograms
WO2019132589A1 (fr) Dispositif de traitement d'images et procédé de détection d'objets multiples
JP3124296B2 (ja) 基準マークの位置および方向の検出方法
Sharma et al. A new method for arbitrarily-oriented text detection in video
US20170287252A1 (en) Counterfeit Document Detection System and Method
WO2014051246A1 (fr) Procédé et appareil pour déduire un composite facial
WO2019225964A1 (fr) Système et procédé de détection rapide d'objets
WO2015182904A1 (fr) Appareil d'étude de zone d'intérêt et procédé de détection d'objet d'intérêt
US20200302135A1 (en) Method and apparatus for localization of one-dimensional barcodes
WO2019132592A1 (fr) Dispositif et procédé de traitement d'image
Shivakumara et al. Video text detection based on filters and edge features
EP3073444A2 (fr) Système informatisé et procédé de détermination de texture d'image
US9600737B2 (en) Image feature extraction method, image feature extraction apparatus, and recording medium storing program therefor
Sonavane et al. Survey on automatic number plate recognition (anr)
US5672886A (en) Surface inspection system for detecting various surface faults
KR20120116699A (ko) 클러스터링 기법을 이용한 이동물체 검출장치 및 방법
US10095946B2 (en) Systems and methods for strike through detection
Zayene et al. Data, protocol and algorithms for performance evaluation of text detection in arabic news video
US11501543B2 (en) System and method for automatic real-time localization of license plate of vehicle from plurality of images of the vehicle
WO2017155315A1 (fr) Procédé de classement de véhicules spécifique à la taille pour zone locale, et procédé de détection de véhicules utilisant ledit procédé
Mukarambi et al. Script identification from camera based Tri-Lingual document
Jia et al. Automatic license plate recognition: a review
JP2000105795A (ja) 全方向一次元バーコード読み取り装置
Zeng et al. Text detection in born-digital images using multiple layer images

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18893841

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18893841

Country of ref document: EP

Kind code of ref document: A1