WO2023284609A1 - 图形码识别方法、装置、计算机设备和存储介质 - Google Patents
图形码识别方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2023284609A1 WO2023284609A1 PCT/CN2022/104117 CN2022104117W WO2023284609A1 WO 2023284609 A1 WO2023284609 A1 WO 2023284609A1 CN 2022104117 W CN2022104117 W CN 2022104117W WO 2023284609 A1 WO2023284609 A1 WO 2023284609A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- tested
- edge
- graphic code
- positioning frame
- edge parts
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003860 storage Methods 0.000 title claims description 13
- 238000001514 detection method Methods 0.000 claims abstract description 102
- 238000005070 sampling Methods 0.000 claims abstract description 95
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims description 82
- 230000003044 adaptive effect Effects 0.000 claims description 30
- 230000009466 transformation Effects 0.000 claims description 16
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008439 repair process Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 12
- 239000011159 matrix material Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods 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
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods 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
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods 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
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
- G06K7/1491—Methods for optical code recognition the method including quality enhancement steps the method including a reconstruction step, e.g. stitching two pieces of bar code together to derive the full bar code
Definitions
- the present application relates to the technical field of image processing, in particular to a pattern code recognition method, device, computer equipment and storage medium.
- DM code data Matrix, DM code
- DM codes can be marked on various materials in the form of dots, such as glass, metal, resin, etc.
- a pattern code recognition method, device, computer equipment and storage medium are provided.
- the embodiment of the present application provides a method for identifying a graphic code, the method comprising:
- the positioning frame detection area Acquiring the positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- edge feature extraction is performed on a plurality of edge parts of the pattern code to be tested, and period information corresponding to each of the plurality of edge parts is obtained; the period information includes a target frequency;
- the identification information of the pattern code to be tested is generated by using the reconstruction result.
- the embodiment of the present application provides a pattern code recognition device, the device comprising:
- the positioning frame detection area acquisition module is used to obtain the positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- a fast Fourier transform processing module configured to perform edge feature extraction on multiple edge parts of the pattern code to be tested based on fast Fourier transform processing, to obtain period information corresponding to each of the multiple edge parts;
- the period information includes the target frequency;
- a barcode specification determination module configured to determine the barcode specification of the graphic code to be tested according to the preset graphic code system coding rules and the respective target frequencies corresponding to the plurality of edge parts;
- a reconstruction module configured to perform edge frequency domain sampling on a plurality of edge parts of the graphic code to be tested based on the barcode specification, to obtain a reconstruction result of the graphic code to be tested;
- the identification information generating module is used to generate the identification information of the pattern code to be tested by using the reconstruction result.
- an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores computer-readable instructions, and the processor implements the above-mentioned graphic code recognition when executing the computer-readable instructions The operation of the method.
- the embodiment of the present application provides a computer-readable storage medium, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the operation of the pattern code recognition method as described above is implemented.
- the above-mentioned pattern code recognition method, device, computer equipment and storage medium by obtaining the positioning frame detection area in the image of the pattern code to be recognized, the positioning frame detection area includes a plurality of edge parts of the pattern code to be detected, and then based on Fast Fourier Leaf transformation processing, edge feature extraction is performed on multiple edge parts of the graphic code to be tested, and the corresponding cycle information of the multiple edge parts is obtained.
- the cycle information includes the target frequency.
- the identification information of the graphic code realizes the accurate judgment of the barcode specification and period of the graphic code, and determines the barcode specification and period by applying fast Fourier transform processing, and then uses the edge frequency domain feature to carry out adaptive sampling reconstruction, which greatly improves the Decoding speed and accuracy, and compatible with different industrial scenarios.
- Fig. 1 is an application environment diagram of a pattern code recognition method according to one or more embodiments.
- Fig. 2 is a schematic flowchart of a pattern code recognition method according to one or more embodiments.
- Fig. 3a is a schematic diagram of a detection area of a positioning frame according to one or more embodiments.
- Fig. 3b is a schematic diagram of edge frequency domain sampling according to one or more embodiments.
- Fig. 3c is a schematic diagram of a graphic code recognition process according to one or more embodiments.
- Fig. 4 is a schematic flowchart of another pattern code recognition method according to one or more embodiments.
- Fig. 5 is a structural block diagram of a pattern code recognition device according to one or more embodiments.
- Fig. 6 is an internal structural diagram of a computer device according to one or more embodiments.
- a pattern code recognition method provided in an embodiment of the present application can be applied to the application environment shown in FIG. 1 .
- the terminal 102 communicates with the server 104 through the network.
- the terminal 102 can send the picture to be recognized to the server 104, so as to use the server 104 as an input picture (that is, the image of the pattern code to be recognized) for pattern code recognition processing, and then the server 104 can return the obtained identification information to the terminal 102.
- the terminal 102 can be, but not limited to, a personal computer, a notebook computer, a smart phone, a tablet computer, an Internet of Things device and a portable wearable device, and the Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart vehicle device, etc.
- Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.
- the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.
- a pattern code recognition method is provided.
- the method is applied to the server 104 for illustration. It can be understood that the method can also be applied to the terminal, or It is applied to a system including a terminal and a server, and is realized through the interaction between the terminal and the server.
- the method includes the following operations:
- Operation 201 acquiring a positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- the graphic code can be DM code (Data Matrix Code), which is a two-dimensional barcode.
- the four edges of the DM code can be composed of two long sides (such as L-shaped sides) and two positioning sides, with binary data inside;
- the graphic code image to be recognized may be a two-dimensional grayscale image, for example, a two-dimensional grayscale image of the graphic code image to be recognized may be obtained.
- the positioning frame detection area can be the internal image area of the positioning frame in the graphic code image to be recognized, and there is a graphic code to be detected in the internal image area, for example, the image of the graphic code image to be recognized can be placed in the positioning frame
- the area is used as the detection area of the positioning frame to be detected (1 in Fig. 3a).
- the graphic code image to be recognized it can be determined that there is a positioning frame of the graphic code to be detected in the graphic code image to be recognized, and then the image area in the positioning frame can be used as the detection area of the positioning frame, and the detection area of the positioning frame Multiple edge portions of the pattern code to be tested may be included.
- the barcode location can be performed based on the two-dimensional grayscale image, and the positioning frame in the two-dimensional grayscale image can be obtained, and then the two-dimensional grayscale image and the The positioning frame is used to obtain the detection area of the positioning frame in the graphic code image to be recognized.
- barcode positioning is carried out on the two-dimensional grayscale image of the graphic code image to be recognized, and one or more quadrilateral positioning frames can be obtained, and each quadrilateral positioning frame can have a corresponding position in the graphic code image to be recognized.
- Operation 202 based on fast Fourier transform processing, perform edge feature extraction on a plurality of edge parts of the pattern code to be tested, and obtain period information corresponding to each of the plurality of edge parts; the period information includes a target frequency;
- fast Fourier transform is a mathematical transformation that transforms the signal from the spatial domain to the frequency domain. It is an efficient algorithm for discrete Fourier transform (DFT), which can convert images The spatial information in is converted into frequency information.
- DFT discrete Fourier transform
- edge feature extraction can be performed on multiple edge parts of the graphic code to be tested in the detection area of the positioning frame based on fast Fourier transform processing, and then the period information corresponding to each of the multiple edge parts can be obtained,
- the period information may include a target frequency corresponding to the edge portion.
- fast Fourier transform is performed on the four edge parts of the pattern code to be tested in the detection area of the positioning frame, and the frequency response value can be obtained, and then for each edge part, the target frequency corresponding to the edge part can be selected, as shown in High response frequency f.
- Operation 203 Determine the barcode specification of the graphic code to be tested according to the preset graphic code system coding rules and the respective target frequencies corresponding to the plurality of edge parts;
- the barcode specification can be the number of data points contained in the graphic code, for example, the DM barcode specification is the number of data points contained in the two-dimensional dot matrix code, which can be 10*10 to 144*144, and the barcode specification can be determined by The edge of the two positioning sides of the DM code is obtained, so it is necessary to accurately judge the periodicity of the edge of the DM code to obtain the corresponding barcode specification.
- the corresponding target frequencies of the plurality of edge parts of the pattern code to be tested can be screened and matched, and then the barcode specification of the pattern code to be tested can be determined, so that further according to the barcode specification and periodic information for adaptive sampling reconstruction.
- the preset graphic code coding rules can be DM coding rules.
- the high response frequencies f corresponding to the four edge parts of the graphic codes to be tested can be screened and matched to determine the The barcode specification of DM code.
- Operation 204 based on the barcode specification, perform edge frequency domain sampling on multiple edge parts of the graphic code to be tested to obtain a reconstruction result of the graphic code to be tested;
- edge frequency domain sampling can be performed on each edge part according to the barcode specification, combined with the period information corresponding to each edge part of the pattern code to be tested, and then the reconstruction result of the pattern code to be tested can be obtained.
- the four edge parts can be adaptively sampled and reconstructed to obtain the repaired and reconstructed DM code to be tested.
- the corresponding reconstruction result of the pattern code to be detected can be obtained for each quadrilateral positioning frame detection area.
- Operation 205 using the reconstruction result to generate identification information of the pattern code to be tested.
- the reconstruction result can be converted into a character string according to the decoding rule of the pattern code, and then the identification information of the pattern code to be tested can be generated.
- the DM decoding rule can be applied to convert the reconstruction result into a character string, and then the identification information of the DM code to be tested can be output.
- the positioning frame detection area includes a plurality of edge parts of the graphic code to be tested, and then based on the fast Fourier transform processing, the image of the graphic code to be tested Edge feature extraction is performed on multiple edge parts to obtain the period information corresponding to each of the multiple edge parts.
- the period information includes the target frequency. According to the preset pattern coding rules and the target frequencies corresponding to the multiple edge parts, the pattern to be tested is determined.
- the barcode specification of the code and then based on the barcode specification, the edge frequency domain sampling is performed on multiple edge parts of the graphic code to be tested, and the reconstruction result of the graphic code to be tested is obtained, and the identification information of the graphic code to be tested is generated by using the reconstruction result.
- Accurately judge the barcode specification and period of the graphic code determine the barcode specification and period by applying fast Fourier transform processing, and then use the edge frequency domain feature to carry out adaptive sampling reconstruction, which greatly improves the decoding speed and accuracy, and is compatible with different industrial scenarios.
- the fast Fourier transform processing is used to perform edge feature extraction on a plurality of edge parts of the pattern code to be tested, and to obtain period information corresponding to each of the plurality of edge parts, which may include the following operations :
- fast Fourier transform processing can be performed on the four edge parts to obtain the corresponding frequency response values of the four edge parts, and then for each edge part , the target frequency can be selected from the frequency response value, such as the frequency response value f, and the period information corresponding to the edge part can be obtained.
- the signal is converted from the space domain to the frequency domain, and then the frequency response value can be obtained.
- a plurality of edge parts of the pattern code to be tested are subjected to fast Fourier transform processing to obtain respective frequency response values corresponding to the plurality of edge parts, and then for each edge part, according to the frequency response value, determine the corresponding frequency response value of the edge part.
- the cycle information can be based on the fast Fourier transform to accurately obtain the cycle information corresponding to the four edge parts of the pattern code to be tested, which improves the decoding accuracy.
- the frequency response value may include multiple values, and for each edge portion, determining the period information corresponding to the edge portion according to the frequency response value may include the following operations:
- a candidate frequency response value is determined from a plurality of frequency response values; the candidate frequency response value is a response value obtained by filtering a plurality of frequency response values according to preset barcode rules; according to From the normalized candidate frequency response values, determine a maximum frequency response value, and use the maximum frequency response value as a target frequency to obtain period information corresponding to the edge portion.
- multiple frequency response values can be screened according to the preset barcode rules to obtain candidate frequency response values, and then the normalized candidate frequency response values can be obtained Determine the maximum frequency response value, that is, the maximum frequency, as the target frequency corresponding to the edge part, and obtain the period information of the four edge parts in the detection area of the positioning frame.
- the high-frequency response values and low-frequency response values that do not conform to the DM barcode rules among the multiple frequency response values can be removed to obtain the remaining frequency response values (that is, the candidate frequency response value), and then the maximum frequency response value, that is, the maximum frequency f, can be determined from the remaining multiple frequency response values after normalization, and the period information of the detection area of the positioning frame can be obtained, wherein the period information Multiple frequency response values for the four edges and their corresponding maximum frequency f may be included.
- corresponding cycle information can be obtained for each quadrilateral positioning frame detection area.
- the candidate frequency response value is determined from the multiple frequency response values, and the candidate frequency response value is the response obtained by screening the multiple frequency response values according to the preset barcode rule value, and then determine the maximum frequency response value according to the normalized candidate frequency response value, and use the maximum frequency response value as the target frequency to obtain the period information corresponding to the edge part, and select the frequency of each edge part based on preset conditions
- the maximum frequency can accurately obtain the period information corresponding to the edge part, which provides data support for the subsequent DM code adaptive sampling reconstruction.
- performing edge frequency domain sampling on a plurality of edge parts of the graphic code to be tested to obtain a reconstruction result of the graphic code to be tested may include the following operations:
- the target sampling step of the pattern code to be tested can be determined.
- the frequency of the four edges is generally (1, 1, x, x), and x corresponds to black and white Staggered edges, that is, positioning edges; on the other hand, for the dotted code, the frequency of its four edges is generally (x, x, 2x, 2x), that is, the frequency of the L-shaped edge and the frequency of the fixed-shaped edge in the four edges have Twice the relationship.
- an appropriate sampling step size s can be obtained as the target sampling step size.
- the target sampling step can be used to perform binarized sampling processing on the detection area of the positioning frame, and then a binarized sampling result can be obtained.
- binarized sampling can be performed on the detection area of the positioning frame according to the sampling step size s, and binarized information can be obtained through local threshold binarization, as shown in the figure A in 3b is the processing result based on the target sampling step size (that is, each small square divided), and b in FIG. 3b is the binarized sampling result.
- the frequency of the L-shaped side is 14, and the frequency of the positioning side is 7.
- the barcode specification of the DM code to be tested can be determined, and then an appropriate sampling step size (that is, the target sampling step size) can be obtained.
- the adaptive binarization sampling process may be performed as follows:
- the image I after affine transformation is subjected to mean value filtering, and the central gray level of each module in the filtered image can be sampled according to the barcode specification g and the target sampling step size s, Then, a gray matrix v of size g can be obtained.
- the local gray average matrix t of the sampling point can be obtained, and then for each point in the gray matrix v , comparing the gray scale of the local gray average matrix t at the same position with that of the sampling point, the binarized matrix b can be obtained, which is the adaptive binarization sampling result.
- the edge information of the pattern code to be tested can be repaired and reconstructed, and then the reconstruction result of the pattern code to be tested can be obtained.
- the target sampling step of the graphic code to be tested is determined according to the barcode specification, and then the target sampling step is used to perform adaptive binarization sampling processing on the detection area of the positioning frame to obtain an adaptive binarization sampling result, and then Based on the self-adaptive binarization sampling result, the reconstruction result of the pattern code to be tested is obtained, and the target sampling step of the pattern code to be tested can be accurately obtained, thereby improving the decoding accuracy.
- the obtaining the reconstruction result of the pattern code to be tested based on the adaptive binarization sampling result may include the following operations:
- the edge information may be the actual edge barcode condition before the graphic code to be tested is repaired and reconstructed, for example, the edge of the barcode is stained/missing.
- the jump point calculation can be performed on the four edges of the graphic code to be tested, and then the edge information with stains/missing conditions can be repaired and reconstructed based on the DM coding rules, and the obtained The reconstruction result of the pattern code to be tested.
- corresponding reconstruction results may be obtained based on each quadrilateral positioning frame detection area.
- the jump point calculation is performed on multiple edge parts of the graphic code to be tested, and the edge information corresponding to each of the multiple edge parts is determined, and then according to the graphic coding rules, the multiple edge Part of the corresponding edge information is repaired and reconstructed, and the reconstruction result of the graphic code to be tested can be obtained.
- the image binarization and edge jump point judgment can be used to reconstruct the edge information that is stained/missing in the DM code to be tested, reducing the Compatible with the technical difficulties of different scenarios, it speeds up the overall decoding process and improves the decoding accuracy.
- the acquisition of the positioning frame detection area in the graphic code image to be recognized may include the following operations:
- the positioning frame detection information may indicate that there is a positioning frame in the graphic code image to be recognized.
- the image of the graphic code to be recognized can be obtained, and the multi-scale gradient connected domain algorithm is used to locate the barcode on the image of the graphic code to be recognized, and the barcode positioning result is obtained, that is, whether there is a positioning frame containing the graphic code to be detected. If there is no positioning box in the graphic code image, you can confirm that the barcode positioning result is empty, output an empty result, interrupt the program, and enter the recognition process of the next graphic code image to be recognized; frame, the image area in the positioning frame can be used as the detection area of the positioning frame.
- barcode positioning may be performed on the acquired pattern code image to be recognized, so as to detect the positioning frame.
- the graphic code image to be recognized through the above-mentioned embodiment, then determine the barcode positioning result corresponding to the graphic code image to be recognized, when there is positioning frame detection information in the barcode positioning result, determine the positioning frame detection area from the graphic code image to be recognized, can be in After it is determined that there is a positioning frame in the graphic code image to be recognized, the detection area of the positioning frame is obtained, which speeds up the overall decoding process and improves the decoding accuracy.
- Affine transformation processing is performed on the positioning frame detection area to convert the positioning frame detection area into a rectangular positioning frame detection area.
- affine transformation processing can be performed on the detection area of the positioning frame.
- affine transformation processing may be performed on each quadrilateral positioning frame detection area.
- the affine transformation process is performed on the detection area of the positioning frame to convert the detection area of the positioning frame into a rectangular detection area of the positioning frame, which can facilitate further edge feature extraction and binarization sampling operations.
- the process of graphic code recognition processing can be:
- barcode positioning can be performed on the input image (that is, the graphic code image to be recognized).
- the input image that is, the graphic code image to be recognized.
- an empty result is output;
- the input picture and one or more positioning frames corresponding to the input picture may be input into the edge feature extraction module.
- affine transformation processing can be performed on one or more positioning frame detection areas obtained from the input picture and one or more positioning frames corresponding to the input picture, and then one or more positioning frames after the affine transformation processing Fast Fourier transform is performed on multiple positioning frame detection areas to obtain period information corresponding to each positioning frame detection area, which is input to the adaptive sampling module.
- the edge frequency domain sampling can be performed on each positioning frame detection area, and the adaptive binarization sampling result can be obtained according to the appropriate target sampling step size, and then the jump can be performed based on the adaptive binarization sampling result Point calculation, reset the L side, to repair and reconstruct the edge information in the detection area of each positioning frame, and obtain the reconstruction result.
- the reconstruction result corresponding to the detection area of each positioning frame can be converted into a character string by applying the DM decoding rule, and then the barcode result (that is, identification information) of the DM code to be tested can be output.
- FIG. 4 a schematic flowchart of another pattern code recognition method is provided.
- the method includes the following operations:
- a detection area of a positioning frame in an image of a pattern code to be recognized is acquired; the detection area of the positioning frame includes a plurality of edge portions of the pattern code to be detected.
- an affine transformation process is performed on the positioning frame detection area to convert the positioning frame detection area into a rectangular positioning frame detection area.
- fast Fourier transform processing is performed on a plurality of edge parts of the pattern code to be tested, and frequency response values corresponding to each of the plurality of edge parts are obtained.
- period information corresponding to the edge portion is determined according to the frequency response value; the period information includes a target frequency.
- the barcode specification of the pattern code to be tested is determined according to the preset pattern code system code rule and the target frequency corresponding to each of the plurality of edge parts.
- a target sampling step of the pattern code to be tested is determined according to the barcode specification.
- the target sampling step is used to perform adaptive binarization sampling processing on the detection area of the positioning frame to obtain an adaptive binarization sampling result.
- operation 408 based on the self-adaptive binarization sampling result, perform skip point calculation on multiple edge parts of the pattern code to be tested, and determine edge information corresponding to each of the multiple edge parts.
- the edge information corresponding to each of the plurality of edge parts is repaired and reconstructed according to the pattern code system code rule, and a reconstruction result of the pattern code to be tested is obtained.
- the identification information of the pattern code to be tested is generated by using the reconstruction result.
- a kind of graphic code recognition device comprising:
- the positioning frame detection area acquisition module 501 is used to obtain the positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- the fast Fourier transform processing module 502 is used for performing edge feature extraction on a plurality of edge parts of the pattern code to be tested based on the fast Fourier transform processing, so as to obtain period information corresponding to each of the plurality of edge parts;
- the period information includes a target frequency;
- a barcode specification determining module 503, configured to determine the barcode specification of the graphic code to be tested according to the preset graphic code system coding rules and the respective target frequencies corresponding to the plurality of edge parts;
- a reconstruction module 504 configured to perform edge frequency domain sampling on a plurality of edge parts of the graphic code to be tested based on the barcode specification, to obtain a reconstruction result of the graphic code to be tested;
- the identification information generating module 505 is configured to use the reconstruction result to generate the identification information of the pattern code to be tested.
- the fast Fourier transform processing module 502 includes:
- the frequency response value obtaining sub-module is used to perform fast Fourier transform processing on a plurality of edge parts of the pattern code to be tested, and obtain respective frequency response values corresponding to the plurality of edge parts;
- the period information obtaining submodule is configured to, for each edge part, determine the period information corresponding to the edge part according to the frequency response value.
- the frequency response value includes multiple values
- the period information obtaining submodule includes:
- a frequency response value screening unit configured to determine a candidate frequency response value from a plurality of frequency response values for each edge portion; the candidate frequency response value corresponds to a plurality of frequency response values according to preset barcode rules The response value obtained by screening;
- the target frequency determining unit is configured to determine a maximum frequency response value according to the normalized candidate frequency response values, and use the maximum frequency response value as a target frequency to obtain period information corresponding to the edge portion.
- the reconstruction module 504 includes:
- a target sampling step determination submodule configured to determine the target sampling step of the graphic code to be tested according to the barcode specification
- the adaptive binarization sampling sub-module is used to use the target sampling step size to perform adaptive binarization sampling processing on the detection area of the positioning frame to obtain an adaptive binarization sampling result;
- the reconstruction result obtaining sub-module is used to obtain the reconstruction result of the pattern code to be tested based on the self-adaptive binarization sampling result.
- the rebuild results in submodules:
- An edge information determination unit configured to perform skip point calculation on a plurality of edge parts of the pattern code to be tested based on the adaptive binarization sampling result, and determine edge information corresponding to each of the plurality of edge parts;
- the restoration and reconstruction unit is configured to repair and reconstruct the edge information corresponding to each of the plurality of edge parts according to the pattern code system code rule, so as to obtain the reconstruction result of the pattern code to be tested.
- the positioning frame detection area acquisition module 501 includes:
- the image acquisition sub-module is used to acquire the graphic code image to be recognized
- a barcode positioning submodule configured to determine the barcode positioning result corresponding to the graphic code image to be recognized
- the positioning frame detection area determination sub-module is used to determine the positioning frame detection area from the image of the graphic code to be recognized when the positioning frame detection information exists in the barcode positioning result.
- the device also includes:
- An affine transformation module configured to perform affine transformation processing on the positioning frame detection area, so as to convert the positioning frame detection area into a rectangular positioning frame detection area.
- Each module in the above-mentioned pattern code recognition device can be fully or partially realized by software, hardware and combinations thereof.
- the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.
- a computer device is provided.
- the computer device may be a server, and its internal structure may be as shown in FIG. 6 .
- the computer device includes a processor, memory and a network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation 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 readable instructions and a database.
- the internal memory provides an environment for the execution of the operating system and computer readable instructions on the non-volatile storage medium.
- the database of the computer device is used to store pattern code recognition data.
- the network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer-readable instructions are executed by the processor, the pattern code recognition method can be realized.
- FIG. 6 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer equipment to which the solution of this application is applied.
- the specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.
- a computer device including a memory and a processor, wherein computer-readable instructions are stored in the memory, and the processor implements the following operations when executing the computer-readable instructions:
- the positioning frame detection area Acquiring the positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- edge feature extraction is performed on a plurality of edge parts of the pattern code to be tested, and period information corresponding to each of the plurality of edge parts is obtained; the period information includes a target frequency;
- the identification information of the pattern code to be tested is generated by using the reconstruction result.
- the processor executes the computer-readable instructions
- the operation of the pattern code recognition method in the above-mentioned other embodiments is also implemented.
- a computer-readable storage medium on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the following operations are implemented:
- the positioning frame detection area Acquiring the positioning frame detection area in the graphic code image to be recognized; the positioning frame detection area includes a plurality of edge parts of the graphic code to be detected;
- edge feature extraction is performed on a plurality of edge parts of the pattern code to be tested, and period information corresponding to each of the plurality of edge parts is obtained; the period information includes a target frequency;
- the identification information of the pattern code to be tested is generated by using the reconstruction result.
- the operation of the pattern code recognition method in the above-mentioned other embodiments is also implemented.
- Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory or optical memory, etc.
- Volatile memory can include Random Access Memory (RAM) or external cache memory.
- RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Discrete Mathematics (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
一种图形码识别方法，包括：获取待识别图形码图像中的定位框检测区域；基于快速傅里叶变换处理，对待测图形码的多个边缘部分进行边缘特征提取，得到多个边缘部分各自对应的周期信息；根据预设的图形码制码规则和多个边缘部分各自对应的目标频率，确定待测图形码的条码规格；基于条码规格，对待测图形码的多个边缘部分进行边缘频域采样，得到待测图形码的重建结果；采用重建结果，生成待测图形码的识别信息。
Description
相关申请的交叉引用
本申请要求于2021年7月12日提交中国专利局、申请号为2021107843253、发明名称为“图形码识别方法、装置、计算机设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及图像处理技术领域，特别是涉及一种图形码识别方法、装置、计算机设备和存储介质。
目前，二维点阵码(Data Matrix，DM码)由于其高效的数据容量和相对较低的绘制要求，在工业生产链中应用较多。在工业场景中，DM码可以采用打点的形式标记于各类材质上，如玻璃、金属、树脂等。
但对于传统解码器，光照和材质带来的影响，使其难以在工业场景中发挥作用，如因环境噪声和条码规格的误判，无法进行准确的数据点采样，识别解码准确率低。
发明内容
根据本申请的各种实施例提供一种图形码识别方法、装置、计算机设备和存储介质。
第一方面，本申请实施例提供一种图形码识别方法，所述方法包括：
获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；
基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；及
采用所述重建结果，生成所述待测图形码的识别信息。
第二方面，本申请实施例提供一种图形码识别装置，所述装置包括：
定位框检测区域获取模块，用于获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
快速傅里叶变换处理模块，用于基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
条码规格确定模块，用于根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；
重建模块，用于基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；及
识别信息生成模块，用于采用所述重建结果，生成所述待测图形码的识别信息。
第三方面，本申请实施例提供一种计算机设备，包括存储器和处理器，所述存储器存储有计算机可读指令，所述处理器执行所述计算机可读指令时实现如上所述的图形码识别方法的操作。
第四方面，本申请实施例提供一种计算机可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现如上所述的图形码识别方法的操作。
上述一种图形码识别方法、装置、计算机设备和存储介质，通过获取待识别图形码图像中的定位框检测区域，定位框检测区域包括待测图形码的多个边缘部分，然后基于快速傅里叶变换处理，对待测图形码的多个边缘部分进行边缘特征提取，得到多个边缘部分各自对应的周期信息，周期信息包括目标频率，根据预设的图形码制码规则和多个边缘部分各自对应的目标频率，确定待测图形码的条码规格，进而基于条码规格，对待测图形码的多个边缘部分进行边缘频域采样，得到待测图形码的重建结果，采用重建结果，生成待测图形码的识别信息，实现了对图形码的条码规格和周期进行准确判断，通过应用快速傅里叶变换处理确定条码规格和周期，进而利用边缘频域特征进行自适应采样重建，极大地提升了解码速度及准确性，且能够兼容不同工业场景。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1为根据一个或多个实施例中一种图形码识别方法的应用环境图。
图2为根据一个或多个实施例中一种图形码识别方法的流程示意图。
图3a为根据一个或多个实施例中一种定位框检测区域的示意图。
图3b为根据一个或多个实施例中一种边缘频域采样的示意图。
图3c为根据一个或多个实施例中一种图形码识别流程的示意图。
图4为根据一个或多个实施例中另一种图形码识别方法的流程示意图。
图5为根据一个或多个实施例中一种图形码识别装置的结构框图。
图6为根据一个或多个实施例中一种计算机设备的内部结构图。
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例提供的一种图形码识别方法，可以应用于如图1所示的应用环境中。其中，终端102通过网络与服务器104进行通信。终端102可以发送待识别图片至服务器104，以作为输入图片(即待识别图形码图像)采用服务器104进行图形码识别处理，进而服务器104可以将得到的识别信息返回至终端102。终端102可以但不限于是个人计算机、笔记本电脑、智能手机、平板电脑、物联网设备和便携式可穿戴设备，物联网设备可为智能音箱、智能电视、智能空调、智能车载设备等。便携式可穿戴设备可为智能手表、智能手环、头戴设备等，服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一个实施例中，如图2所示，提供了一种图形码识别方法，本实施例以该方法应用于服务器104进行举例说明，可以理解的是，该方法也可以应用于终端，还可以应用于包括终端和服务器的系统，并通过终端和服务器的交互实现。本实施例中，该方法包括以下操作：
操作201，获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
其中，图形码可以为DM码(Data Matrix Code)，是一种二维条码，DM码的四条边缘可以由两条长边(如L形边)和两条定位边组成，内部具有二进制数据；待识别图形码图像可以为二维灰度图像，例如，可以获取待识别图形码图像的二维灰度图像。
作为一示例，定位框检测区域可以为在待识别图形码图像中的定位框的内部图像区域，该内部图像区域存在待测图形码，例如，可以将待识别图形码图像在定位框中的图像区域作为待检测的定位框检测区域(如图3a中1)。
在实际应用中，通过获取待识别图形码图像，可以确定待识别图形码图像中存在待测图形码的定位框，进而可以将定位框中的图像区域作为定位框检测区域，该定位框检测区域可以包括待测图形码的多个边缘部分。
具体地，在获取待识别图形码图像的二维灰度图像后，可以基于该二维灰度图像进行条码定位，得到二维灰度图像中的定位框，进而可以根据二维灰度图像和定位框，得到待识别图形码图像中的定位框检测区域。
在一个可选实施例中，对待识别图形码图像的二维灰度图像进行条码定位，可以获取一个或多个四边形的定位框，每个四边形的定位框可以在待识别图形码图像中具有对应的定位框检测区域。
操作202，基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
其中，快速傅里叶变换(fast Fourier transform，FFT)为将信号由空域转为频域的数学变换，是一种离散傅里叶变换(Discrete Fourier Transform，DFT)的高效算法，其可以将图片中的空间信息转换为频率信息。
在获取定位框检测区域后，可以基于快速傅里叶变换处理，对定位框检测区域中待测图形码的多个边缘部分进行边缘特征提取，进而可以得到多个边缘部分各自对应的周期信息，该周期信息可以包括边缘部分对应的目标频率。
具体地，对定位框检测区域中待测图形码的四个边缘部分进行快速傅里叶变换，可以得到频率响应值，进而针对每一边缘部分，可以选取出该边缘部分对应的目标频率，如高响应频率f。
操作203，根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；
其中，条码规格可以为图形码中所包含的数据点数量，例如，DM条码规格为二维点阵码所包含的数据点的数量，其可以为10*10至144*144，条码规格可以由DM码的两个定位边的边缘得到，因此需要精确的判断出DM码边缘的周期性，以得出相应的条码规格。
在具体实现中，可以根据预设的图形码制码规则，对待测图形码的多个边缘部分各自对应的目标频率进行筛选匹配，进而可以确定待测图形码的条码规格，以进一步根据条码规格和周期信息进行自适应采样重建。
在一示例中，预设的图形码制码规则可以为DM制码规则，可以根据DM制码规则，对待测图形码的四个边缘部分各自对应的高响应频率f进行筛选匹配，确定待测DM码的条码规格。
操作204，基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；
在得到条码规格后，可以根据该条码规格，结合待测图形码的多个边缘部分各自对应的周期信息，对各个边缘部分进行边缘频域采样，进而可以得到待测图形码的重建结果。
例如，根据待测DM码的条码规格和周期信息，可以对四个边缘部分进行自适应采样重建，得到修复重建后的待测DM码。
在一个可选实施例中，根据待识别图形码图像中的一个或多个四边形的定位框检测区域，可以针对每个四边形的定位框检测区域，得到对应的待测图形码的重建结果。
操作205，采用所述重建结果，生成所述待测图形码的识别信息。
在得到重建结果后，可以根据图形码的译码规则，将重建结果转换为字符串，进而可以生成待测图形码的识别信息。
具体地，针对每个定位框检测区域对应的重建结果，可以应用DM译码规则，将重建结果转换为字符串，进而可以输出待测DM码的识别信息。
在本申请实施例中，通过获取待识别图形码图像中的定位框检测区域，定位框检测区域包括待测图形码的多个边缘部分，然后基于快速傅里叶变换处理，对待测图形码的多个边缘 部分进行边缘特征提取，得到多个边缘部分各自对应的周期信息，周期信息包括目标频率，根据预设的图形码制码规则和多个边缘部分各自对应的目标频率，确定待测图形码的条码规格，进而基于条码规格，对待测图形码的多个边缘部分进行边缘频域采样，得到待测图形码的重建结果，采用重建结果，生成待测图形码的识别信息，实现了对图形码的条码规格和周期进行准确判断，通过应用快速傅里叶变换处理确定条码规格和周期，进而利用边缘频域特征进行自适应采样重建，极大地提升了解码速度及准确性，且能够兼容不同工业场景。
在一个实施例中，所述基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息，可以包括如下操作：
对所述待测图形码的多个边缘部分进行快速傅里叶变换处理，得到所述多个边缘部分各自对应的频率响应值；针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息。
在实际应用中，为了得到待测图形码的四个边缘的频率，可以对四个边缘部分进行快速傅里叶变换处理，得到四个边缘部分各自对应的频率响应值，进而针对每一边缘部分，可以从频率响应值中选取出目标频率，如频率响应值f，并得到该边缘部分对应的周期信息。
例如，通过对边缘部分的信号进行快速傅里叶变换，将信号由空域转为频域，进而可以获取频率响应值。
通过上述实施例对待测图形码的多个边缘部分进行快速傅里叶变换处理，得到多个边缘部分各自对应的频率响应值，进而针对每一边缘部分，根据频率响应值，确定边缘部分对应的周期信息，可以基于快速傅里叶变换，准确获取待测图形码的四个边缘部分各自对应的周期信息，提升了解码准确率。
在一个实施例中，频率响应值可以包括多个，所述针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息，可以包括如下操作：
针对每一边缘部分，从多个所述频率响应值中确定候选频率响应值；所述候选频率响应值为根据预设的条码规则对多个所述频率响应值进行筛选得到的响应值；根据归一化后的候选频率响应值，确定最大频率响应值，并将所述最大频率响应值作为目标频率，得到所述边缘部分对应的周期信息。
在实际应用中，针对待测图形码的每一边缘部分，可以根据预设的条码规则对多个频率响应值进行筛选，得到候选频率响应值，进而可以从归一化后的候选频率响应值中确定最大 频率响应值，即最大频率，作为该边缘部分对应的目标频率，并可以得到定位框检测区域中四个边缘部分的周期信息。
在一个可选实施例中，针对定位框检测区域中的每一边缘部分，可以将多个频率响应值中不符合DM条码规则的高频响应值与低频响应值去除，得到剩余的频率响应值(即候选频率响应值)，进而可以从归一化后剩余的多个频率响应值中确定最大频率响应值，即最大频率f，并可以得到该定位框检测区域的周期信息，其中，周期信息可以包括四个边缘的多个频率响应值及其对应的最大频率f。根据待识别图形码图像中的一个或多个四边形的定位框检测区域，可以针对每个四边形的定位框检测区域，得到对应的周期信息。
通过上述实施例针对每一边缘部分，根据预设条件，从多个频率响应值中确定候选频率响应值,候选频率响应值为根据预设的条码规则对多个频率响应值进行筛选得到的响应值，进而根据归一化后的候选频率响应值，确定最大频率响应值，并将最大频率响应值作为目标频率，得到边缘部分对应的周期信息，可以基于预设条件选取出每一边缘部分的最大频率，能够准确得到边缘部分对应的周期信息，为后续DM码自适应采样重建提供了数据支持。
在一个实施例中，所述基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果，可以包括如下操作：
根据所述条码规格，确定所述待测图形码的目标采样步长；
在具体实现中，针对得到的条码规格，基于DM码的边缘规则，可以确定待测图形码的目标采样步长。
由于基于DM制码规则，DM码的边缘有两种规则，以正方形码为例，一方面，针对印刷码，其四个边缘的频率一般为(1，1，x，x),x对应黑白交错的边缘，即定位边；另一方面，针对打点码，其四个边缘的频率一般为(x，x，2x，2x)，即四个边缘中L形边的频率与定形边的频率具有两倍关系。通过以上DM码的边缘规则，可以得到合适的采样步长s，作为目标采样步长。
采用所述目标采样步长，对所述定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果；
在确定目标采样步长后，可以采用该目标采样步长，对定位框检测区域进行二值化采样处理，进而可以得到二值化采样结果。
例如，通过获取合适的采样步长s(即目标采样步长)，可以根据采样步长s对定位框检 测区域进行二值化采样，通过局部阈值二值化可以得到二值化信息，如图3b中a为基于目标采样步长(即划分的每一小方格)的处理结果，图3b中b为二值化采样结果。
在一示例中，如图3b所示，基于定位框检测区域中待测DM码的四个边缘部分的周期信息，可以得到L形边频率为14，定位边频率为7，根据DM制码规则，可以确定待测DM码的条码规格，进而可以得到合适的采样步长(即目标采样步长)。
在又一示例中，自适应二值化采样处理可以采用如下方式进行：
基于输入的仿射变换后图像I，由图像边缘部分的目标频率可以得到条码规格g，如g＝(g_h,g_w)，其中，h可以表征条码规格中的高，w可以表征条码规格中的宽；还可以计算得到目标采样步长s，如s＝(s_h,s_w)，其中，h可以表征步长(即划分的每一小方格)的高，w可以表征步长(即划分的每一小方格)的宽。
通过采用s*s尺寸大小的窗口，对仿射变换后的图像I进行均值滤波处理，并可以根据条码规格g与目标采样步长s采样滤波处理后的图像中每个模块的中心灰度，进而可以得到一个大小为g的灰度矩阵v。
以min(g_h/2,g_w/2)为二维窗口边长，对灰度矩阵v进行均值滤波处理，可以得到采样点局部灰度平均矩阵t，进而针对灰度矩阵v中的每一个点，比较其与采样点局部灰度平均矩阵t在相同位置上的灰度大小，可以得到二值化后的矩阵b，即自适应二值化采样结果。
基于所述自适应二值化采样结果，得到所述待测图形码的重建结果。
在实际应用中，可以基于自适应二值化采样结果，对待测图形码的边缘信息进行修复重建，进而可以得到待测图形码的重建结果。
通过上述实施例根据条码规格，确定待测图形码的目标采样步长，然后采用目标采样步长，对定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果，进而基于自适应二值化采样结果，得到待测图形码的重建结果，可以准确获取待测图形码的目标采样步长，提升了解码准确率。
在一个实施例中，所述基于所述自适应二值化采样结果，得到所述待测图形码的重建结果，可以包括如下操作：
基于所述自适应二值化采样结果，对所述待测图形码的多个边缘部分进行跳跃点计算，确定所述多个边缘部分各自对应的边缘信息；根据所述图形码制码规则，对所述多个边缘部分各自对应的边缘信息进行修复重建，得到所述待测图形码的重建结果。
其中，边缘信息可以为待测图形码未修复重建前的实际边缘条码情况，例如，条码的边缘存在污损/缺失的情况。
在实际应用中，可以基于自适应二值化采样结果，对待测图形码的四个边缘进行跳跃点计算，进而可以基于DM制码规则对存在污损/缺失情况的边缘信息进行修复重建，得到待测图形码的重建结果。
在一个可选实施例中，针对待识别图形码图像中的一个或多个四边形的定位框检测区域，可以基于每个四边形的定位框检测区域，得到对应的重建结果。
相较于传统二值化图像的边缘跳跃点计算，其是简单地进行0/1区分，以得到条码的制式，本申请实施例中可以通过已知周期的二值化图像和边缘跳跃点判断，对待测DM码中存在污损/缺失情况的边缘信息进行重建。
由于不同的材质和条码印刷技术的限制，简单的二值化跳跃点计算难以满足所有应用场景，导致了传统解码器无法适应变化较大的场景，需要针对性的对不同场景进行调整，不具有普适性；且传统解码器需要大量的边缘采样测试，算法时间成本高，增大了产品的生产成本。本申请实施例中可以应用快速傅里叶变换处理确定条码规格和周期，并利用边缘频域特征进行自适应采样重建，降低了兼容不同场景的技术难度，加快了整体解码流程，提升了解码准确率，适用于大多数工业场景。
通过上述实施例基于自适应二值化采样结果，对待测图形码的多个边缘部分进行跳跃点计算，确定多个边缘部分各自对应的边缘信息，进而根据图形码制码规则，对多个边缘部分各自对应的边缘信息进行修复重建，得到待测图形码的重建结果，可以通过图像二值化和边缘跳跃点判断，对待测DM码中存在污损/缺失情况的边缘信息进行重建，降低了兼容不同场景的技术难度，加快了整体解码流程，提升了解码准确率。
在一个实施例中，所述获取待识别图形码图像中的定位框检测区域，可以包括如下操作：
获取待识别图形码图像；确定所述待识别图形码图像对应的条码定位结果；当所述条码定位结果中存在定位框检测信息，从所述待识别图形码图像中确定所述定位框检测区域。
其中，定位框检测信息可以表征待识别图形码图像中具有定位框。
在实际应用中，可以获取待识别图形码图像，采用多尺度梯度连通域算法对待识别图形码图像进行条码定位，得到条码定位结果，即是否存在包含待测图形码的定位框，当检测到待识别图形码图像中未具有定位框，可以确认条码定位结果为空，输出空结果，程序中断， 并进入下一张待识别图形码图像的识别流程；当检测到待识别图形码图像中具有定位框，可以将定位框中的图像区域作为定位框检测区域。
在一示例中，还可以基于线检测的定位算法，对获取的待识别图形码图像进行条码定位，以检测定位框。
通过上述实施例获取待识别图形码图像，然后确定待识别图形码图像对应的条码定位结果，当条码定位结果中存在定位框检测信息，从待识别图形码图像中确定定位框检测区域，可以在确定待识别图形码图像中具有定位框后，得到定位框检测区域，加快了整体解码流程，提升了解码准确率。
在一个实施例中，在所述基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息的操作之前，可以包括如下操作：
对所述定位框检测区域进行仿射变换处理，以将所述定位框检测区域转换为矩形的定位框检测区域。
在实际应用中，为了将定位框中图像区域部分转换为矩形，以便于进一步进行边缘特征提取与二值化采样操作，可以对定位框检测区域进行仿射变换处理。
在一个可选实施例中，针对待识别图形码图像中的一个或多个四边形的定位框检测区域，可以对每个四边形的定位框检测区域进行仿射变换处理。
通过上述实施例对定位框检测区域进行仿射变换处理，以将定位框检测区域转换为矩形的定位框检测区域，可以有助于进一步进行边缘特征提取与二值化采样操作。
为了使本领域技术人员能够更好地理解上述操作，以下结合图3c通过一个例子对本申请实施例加以示例性说明，但应当理解的是，本申请实施例并不限于此。
图形码识别处理的过程可以为：
1、通过条码定位模块，可以对输入图片(即待识别图形码图像)进行条码定位，在检测到待识别图形码图像中未具有定位框，即无定位框时，输出空结果；在检测到待识别图形码图像中具有定位框时，可以将输入图片和输入图片对应的一个或多个定位框输入边缘特征提取模块。
2、通过边缘特征提取模块，可以对由输入图片和输入图片对应的一个或多个定位框得 到的一个或多个定位框检测区域进行仿射变换处理，进而对仿射变换处理后的一个或多个定位框检测区域进行快速傅里叶变换，得到每个定位框检测区域对应的周期信息，以输入自适应采样模块。
3、通过自适应采样模块，可以对每个定位框检测区域进行边缘频域采样，根据合适的目标采样步长得到自适应二值化采样结果，进而可以基于自适应二值化采样结果进行跳跃点计算，重设L边，以对每个定位框检测区域中的边缘信息修复重建，得到重建结果。
4、通过译码模块，可以针对每个定位框检测区域对应的重建结果，应用DM译码规则将重建结果转换为字符串，进而可以输出待测DM码的条码结果(即识别信息)。
在一个实施例中，如图4所示，提供了另一种图形码识别方法的流程示意图。本实施例中，该方法包括以下操作：
在操作401中，获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分。在操作402中，对所述定位框检测区域进行仿射变换处理，以将所述定位框检测区域转换为矩形的定位框检测区域。在操作403中，对所述待测图形码的多个边缘部分进行快速傅里叶变换处理，得到所述多个边缘部分各自对应的频率响应值。在操作404中，针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息；所述周期信息包括目标频率。在操作405中，根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格。在操作406中，根据所述条码规格，确定所述待测图形码的目标采样步长。在操作407中，采用所述目标采样步长，对所述定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果。在操作408中，基于所述自适应二值化采样结果，对所述待测图形码的多个边缘部分进行跳跃点计算，确定所述多个边缘部分各自对应的边缘信息。在操作409中，根据所述图形码制码规则，对所述多个边缘部分各自对应的边缘信息进行修复重建，得到所述待测图形码的重建结果。在操作410中，采用所述重建结果，生成所述待测图形码的识别信息。需要说明的是，上述操作的具体限定可以参见上文对一种图形码识别方法的具体限定，在此不再赘述。
应该理解的是，虽然图1-4的流程图中的各个操作按照箭头的指示依次显示，但是这些操作并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些操作的执行 并没有严格的顺序限制，这些操作可以以其它的顺序执行。而且，图1-4中的至少一部分操作可以包括多个操作或者多个阶段，这些操作或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些操作或者阶段的执行顺序也不必然是依次进行，而是可以与其它操作或者其它操作中的操作或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中，如图5所示，提供了一种图形码识别装置，包括：
定位框检测区域获取模块501，用于获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
快速傅里叶变换处理模块502，用于基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
条码规格确定模块503，用于根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；
重建模块504，用于基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；
识别信息生成模块505，用于采用所述重建结果，生成所述待测图形码的识别信息。
在一个实施例中，所述快速傅里叶变换处理模块502包括：
频率响应值得到子模块，用于对所述待测图形码的多个边缘部分进行快速傅里叶变换处理，得到所述多个边缘部分各自对应的频率响应值；
周期信息得到子模块，用于针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息。
在一个实施例中，所述频率响应值包括多个，所述周期信息得到子模块包括：
频率响应值筛选单元，用于针对每一边缘部分，从多个所述频率响应值中确定候选频率响应值；所述候选频率响应值为根据预设的条码规则对多个所述频率响应值进行筛选得到的响应值；
目标频率确定单元，用于根据归一化后的候选频率响应值，确定最大频率响应值，并将所述最大频率响应值作为目标频率，得到所述边缘部分对应的周期信息。
在一个实施例中，所述重建模块504包括：
目标采样步长确定子模块，用于根据所述条码规格，确定所述待测图形码的目标采样步长；
自适应二值化采样子模块，用于采用所述目标采样步长，对所述定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果；
重建结果得到子模块，用于基于所述自适应二值化采样结果，得到所述待测图形码的重建结果。
在一个实施例中，所述重建结果得到子模块：
边缘信息确定单元，用于基于所述自适应二值化采样结果，对所述待测图形码的多个边缘部分进行跳跃点计算，确定所述多个边缘部分各自对应的边缘信息；
修复重建单元，用于根据所述图形码制码规则，对所述多个边缘部分各自对应的边缘信息进行修复重建，得到所述待测图形码的重建结果。
在一个实施例中，所述定位框检测区域获取模块501包括：
图像获取子模块，用于获取待识别图形码图像；
条码定位子模块，用于确定所述待识别图形码图像对应的条码定位结果；
定位框检测区域确定子模块，用于当所述条码定位结果中存在定位框检测信息，从所述待识别图形码图像中确定所述定位框检测区域。
在一个实施例中，所述装置还包括：
仿射变换模块，用于对所述定位框检测区域进行仿射变换处理，以将所述定位框检测区域转换为矩形的定位框检测区域。
关于一种图形码识别装置的具体限定可以参见上文中对于一种图形码识别方法的限定，在此不再赘述。上述一种图形码识别装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图6所示。该计算机设备包括通过系统总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机可读指令和数据库。该内存 储器为非易失性存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储图形码识别数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现图形码识别方法。
本领域技术人员可以理解，图6中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机可读指令，该处理器执行计算机可读指令时实现以下操作：
获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；
基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；及
采用所述重建结果，生成所述待测图形码的识别信息。
在一个实施例中，处理器执行计算机可读指令时还实现上述其他实施例中的图形码识别方法的操作。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机可读指令，计算机可读指令被处理器执行时实现以下操作：
获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；
基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；
根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图 形码的条码规格；
基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；及
采用所述重建结果，生成所述待测图形码的识别信息。
在一个实施例中，计算机可读指令被处理器执行时还实现上述其他实施例中的图形码识别方法的操作。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存或光存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。
Claims (16)
- 一种图形码识别方法，所述方法包括：获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；及基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；采用所述重建结果，生成所述待测图形码的识别信息。
- 根据权利要求1所述的方法，所述基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息，包括：对所述待测图形码的多个边缘部分进行快速傅里叶变换处理，得到所述多个边缘部分各自对应的频率响应值；及针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息。
- 根据权利要求2所述的方法，所述频率响应值包括多个，所述针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息，包括：针对每一边缘部分，从多个所述频率响应值中确定候选频率响应值；所述候选频率响应值为根据预设的条码规则对多个所述频率响应值进行筛选得到的响应值；及根据归一化后的候选频率响应值，确定最大频率响应值，并将所述最大频率响应值作为目标频率，得到所述边缘部分对应的周期信息。
- 根据权利要求1所述的方法，所述基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果，包括：根据所述条码规格，确定所述待测图形码的目标采样步长；采用所述目标采样步长，对所述定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果；及基于所述自适应二值化采样结果，得到所述待测图形码的重建结果。
- 根据权利要求4所述的方法，所述基于所述自适应二值化采样结果，得到所述待测图形码的重建结果，包括：基于所述自适应二值化采样结果，对所述待测图形码的多个边缘部分进行跳跃点计算，确定所述多个边缘部分各自对应的边缘信息；及根据所述图形码制码规则，对所述多个边缘部分各自对应的边缘信息进行修复重建，得到所述待测图形码的重建结果。
- 根据权利要求1所述的方法，所述获取待识别图形码图像中的定位框检测区域，包括：获取待识别图形码图像；确定所述待识别图形码图像对应的条码定位结果；及当所述条码定位结果中存在定位框检测信息，从所述待识别图形码图像中确定所述定位框检测区域。
- 根据权利要求1至6任一项所述的方法，在所述基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息之前，还包括：对所述定位框检测区域进行仿射变换处理，以将所述定位框检测区域转换为矩形的定位框检测区域。
- 一种图形码识别装置，所述装置包括：定位框检测区域获取模块，用于获取待识别图形码图像中的定位框检测区域；所述定位框检测区域包括待测图形码的多个边缘部分；快速傅里叶变换处理模块，用于基于快速傅里叶变换处理，对所述待测图形码的多个边缘部分进行边缘特征提取，得到所述多个边缘部分各自对应的周期信息；所述周期信息包括目标频率；条码规格确定模块，用于根据预设的图形码制码规则和所述多个边缘部分各自对应的目标频率，确定所述待测图形码的条码规格；重建模块，用于基于所述条码规格，对所述待测图形码的多个边缘部分进行边缘频域采样，得到所述待测图形码的重建结果；及识别信息生成模块，用于采用所述重建结果，生成所述待测图形码的识别信息。
- 根据权利要求8所述的装置，所述快速傅里叶变换处理模块包括：频率响应值得到子模块，用于对所述待测图形码的多个边缘部分进行快速傅里叶变换处理，得到所述多个边缘部分各自对应的频率响应值；及周期信息得到子模块，用于针对每一边缘部分，根据所述频率响应值，确定所述边缘部分对应的周期信息。
- 根据权利要求9所述的装置，所述频率响应值包括多个，所述周期信息得到子模块包括：频率响应值筛选单元，用于针对每一边缘部分，从多个所述频率响应值中确定候选频率响应值；所述候选频率响应值为根据预设的条码规则对多个所述频率响应值进行筛选得到的响应值；及目标频率确定单元，用于根据归一化后的候选频率响应值，确定最大频率响应值，并将所述最大频率响应值作为目标频率，得到所述边缘部分对应的周期信息。
- 根据权利要求8所述的装置，所述重建模块包括：目标采样步长确定子模块，用于根据所述条码规格，确定所述待测图形码的目标采样步长；自适应二值化采样子模块，用于采用所述目标采样步长，对所述定位框检测区域进行自适应二值化采样处理，得到自适应二值化采样结果；及重建结果得到子模块，用于基于所述自适应二值化采样结果，得到所述待测图形码的重建结果。
- 根据权利要求11所述的装置，所述重建结果得到子模块：边缘信息确定单元，用于基于所述自适应二值化采样结果，对所述待测图形码的多个边缘部分进行跳跃点计算，确定所述多个边缘部分各自对应的边缘信息；及修复重建单元，用于根据所述图形码制码规则，对所述多个边缘部分各自对应的边缘信息进行修复重建，得到所述待测图形码的重建结果。
- 根据权利要求8所述的装置，所述定位框检测区域获取模块包括：图像获取子模块，用于获取待识别图形码图像；条码定位子模块，用于确定所述待识别图形码图像对应的条码定位结果；及定位框检测区域确定子模块，用于当所述条码定位结果中存在定位框检测信息，从所述 待识别图形码图像中确定所述定位框检测区域。
- 根据权利要求8至13任一项所述的装置，所述装置还包括：仿射变换模块，用于对所述定位框检测区域进行仿射变换处理，以将所述定位框检测区域转换为矩形的定位框检测区域。
- 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机可读指令，所述处理器执行所述计算机可读指令时实现权利要求1至7中任一项所述的图形码识别方法的操作。
- 一种计算机可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现权利要求1至7中任一项所述的图形码识别方法的操作。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110784325.3A CN113468905B (zh) | 2021-07-12 | 2021-07-12 | 图形码识别方法、装置、计算机设备和存储介质 |
| CN202110784325.3 | 2021-07-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023284609A1 true WO2023284609A1 (zh) | 2023-01-19 |
Family
ID=77879843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/104117 WO2023284609A1 (zh) | 2021-07-12 | 2022-07-06 | 图形码识别方法、装置、计算机设备和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113468905B (zh) |
| WO (1) | WO2023284609A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909909A (zh) * | 2024-03-19 | 2024-04-19 | 青岛鼎信通讯股份有限公司 | 一种配电网弧光接地故障识别方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468905B (zh) * | 2021-07-12 | 2024-03-26 | 深圳思谋信息科技有限公司 | 图形码识别方法、装置、计算机设备和存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09160997A (ja) * | 1995-12-08 | 1997-06-20 | Toshiba Corp | バーコード検出方法およびバーコード検出装置 |
| CN107545207A (zh) * | 2017-09-28 | 2018-01-05 | 云南电网有限责任公司电力科学研究院 | 基于图像处理的dm二维码识别方法及装置 |
| CN112651256A (zh) * | 2019-10-12 | 2021-04-13 | 大族激光科技产业集团股份有限公司 | 二维码识别方法、装置、计算机设备及存储介质 |
| CN113468905A (zh) * | 2021-07-12 | 2021-10-01 | 深圳思谋信息科技有限公司 | 图形码识别方法、装置、计算机设备和存储介质 |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100456628B1 (ko) * | 2001-12-28 | 2004-11-10 | 한국전자통신연구원 | 물류 정보 자동식별 처리시스템 및 그 방법 |
| JP4724802B1 (ja) * | 2010-07-30 | 2011-07-13 | 株式会社シフト | 二次元コードリーダおよびプログラム |
| JP4724800B1 (ja) * | 2010-07-30 | 2011-07-13 | 株式会社シフト | 物品検出装置およびプログラム |
| KR101658592B1 (ko) * | 2010-09-30 | 2016-09-21 | 에스케이 텔레콤주식회사 | 영상의 구조적 정보를 이용한 적응적 움직임 벡터 부호화/복호화 방법 및 장치와 그를 이용한 영상 부호화/복호화 방법 및 장치 |
| CN103294980A (zh) * | 2013-06-18 | 2013-09-11 | 四川大学 | 基于图像处理的微型qr码识别方法 |
| CN106485182B (zh) * | 2016-06-27 | 2018-10-30 | 中国计量大学 | 一种基于仿射变换的模糊qr码复原方法 |
| CN107301366B (zh) * | 2017-05-12 | 2020-07-31 | 赵毅 | 一种嵌码视频中图形码的解码方法及装置 |
| CN107862659B (zh) * | 2017-10-31 | 2020-05-26 | Oppo广东移动通信有限公司 | 图像处理方法、装置、计算机设备及计算机可读存储介质 |
| CN109325503B (zh) * | 2018-09-05 | 2021-07-02 | 西安工业大学 | 一种用于压缩编码孔径成像的目标轮廓识别方法 |
| CN111604909A (zh) * | 2020-06-24 | 2020-09-01 | 辽宁工业大学 | 一种四轴工业码垛机器人的视觉系统 |
| CN111832561B (zh) * | 2020-07-03 | 2021-06-08 | 深圳思谋信息科技有限公司 | 基于计算机视觉的字符序列识别方法、装置、设备和介质 |
| CN112949338A (zh) * | 2021-03-16 | 2021-06-11 | 太原科技大学 | 深度学习与Hough变换结合的二维条码精确定位方法 |
| CN113076768B (zh) * | 2021-04-08 | 2023-04-11 | 中山大学 | 一种模糊可识别二维码的畸变校正方法 |
-
2021
- 2021-07-12 CN CN202110784325.3A patent/CN113468905B/zh active Active
-
2022
- 2022-07-06 WO PCT/CN2022/104117 patent/WO2023284609A1/zh unknown
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09160997A (ja) * | 1995-12-08 | 1997-06-20 | Toshiba Corp | バーコード検出方法およびバーコード検出装置 |
| CN107545207A (zh) * | 2017-09-28 | 2018-01-05 | 云南电网有限责任公司电力科学研究院 | 基于图像处理的dm二维码识别方法及装置 |
| CN112651256A (zh) * | 2019-10-12 | 2021-04-13 | 大族激光科技产业集团股份有限公司 | 二维码识别方法、装置、计算机设备及存储介质 |
| CN113468905A (zh) * | 2021-07-12 | 2021-10-01 | 深圳思谋信息科技有限公司 | 图形码识别方法、装置、计算机设备和存储介质 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909909A (zh) * | 2024-03-19 | 2024-04-19 | 青岛鼎信通讯股份有限公司 | 一种配电网弧光接地故障识别方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113468905B (zh) | 2024-03-26 |
| CN113468905A (zh) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023284609A1 (zh) | 图形码识别方法、装置、计算机设备和存储介质 | |
| US11138738B2 (en) | Image processing method and image processing device | |
| CN111275660B (zh) | 一种平板显示器缺陷检测方法及装置 | |
| US11164306B2 (en) | Visualization of inspection results | |
| CN112949767B (zh) | 样本图像增量、图像检测模型训练及图像检测方法 | |
| CN111914654B (zh) | 一种文本版面分析方法、装置、设备和介质 | |
| CN110287125A (zh) | 基于图像识别的软件例行化测试方法及装置 | |
| KR20190040755A (ko) | 파일 이미지를 이용한 악성코드 탐지 방법 및 이를 위한 장치 | |
| CN114926374B (zh) | 一种基于ai的图像处理方法、装置、设备及可读存储介质 | |
| CN111460355A (zh) | 一种页面解析方法和装置 | |
| CN114611102A (zh) | 可视化恶意软件检测与分类方法、系统、存储介质及终端 | |
| CN112101386A (zh) | 文本检测方法、装置、计算机设备和存储介质 | |
| CN111724396A (zh) | 图像分割方法及装置、计算机可读存储介质、电子设备 | |
| CN117191816B (zh) | 基于多光谱融合的电子元器件表面缺陷检测方法和装置 | |
| EP3156943A1 (en) | Method and device for clustering patches of a degraded version of an image | |
| CN113516697A (zh) | 图像配准的方法、装置、电子设备及计算机可读存储介质 | |
| CN115393868B (zh) | 文本检测方法、装置、电子设备和存储介质 | |
| US9292763B2 (en) | System, method, and medium for image object and contour feature extraction | |
| WO2020241074A1 (ja) | 情報処理方法及びプログラム | |
| CN112861874A (zh) | 一种基于多滤波器去噪结果的专家场去噪方法及系统 | |
| CN110704153B (zh) | 界面逻辑解析方法、装置、设备及可读存储介质 | |
| CN111985423A (zh) | 活体检测方法、装置、设备及可读存储介质 | |
| Huang et al. | Anti-forensics for double JPEG compression based on generative adversarial network | |
| CN111950727B (zh) | 图像数据的神经网络训练和测试方法及设备 | |
| CN113255657B (zh) | 票据表面刮痕检测方法、装置、电子设备、机器可读介质 |
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: 22841246 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |