WO2023071322A1 - 识别二维码定位码区的方法、装置、设备和存储介质 - Google Patents

识别二维码定位码区的方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2023071322A1
WO2023071322A1 PCT/CN2022/107453 CN2022107453W WO2023071322A1 WO 2023071322 A1 WO2023071322 A1 WO 2023071322A1 CN 2022107453 W CN2022107453 W CN 2022107453W WO 2023071322 A1 WO2023071322 A1 WO 2023071322A1
Authority
WO
WIPO (PCT)
Prior art keywords
line segment
candidate line
candidate
cluster
dense
Prior art date
Application number
PCT/CN2022/107453
Other languages
English (en)
French (fr)
Inventor
莫宇
刘健晖
刘枢
吕江波
沈小勇
Original Assignee
深圳思谋信息科技有限公司
上海思谋科技有限公司
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 深圳思谋信息科技有限公司, 上海思谋科技有限公司 filed Critical 深圳思谋信息科技有限公司
Publication of WO2023071322A1 publication Critical patent/WO2023071322A1/zh

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
    • G06K7/1408Methods for optical code recognition the method being specifically adapted for the type of code
    • G06K7/14172D bar codes
    • 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
    • G06K7/1439Methods for optical code recognition including a method step for retrieval of the optical code
    • G06K7/1443Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image

Definitions

  • the present application relates to the technical field of two-dimensional code processing, in particular to a method, device, computer equipment, storage medium and computer program product for identifying a two-dimensional code location code area.
  • a two-dimensional code also known as a QR code (Quick Response code)
  • QR code Quick Response code
  • the information code area is used to carry specific information.
  • the positioning code area in the image can be identified first, and then according to the positioning code area and The positional relationship between the information code areas on the two-dimensional code determines the area belonging to the information code area in the image, and then obtains specific information. In order to ensure the recognition accuracy of specific information, it is very important to accurately determine the position of the positioning code area in the image.
  • a method, device, computer equipment, storage medium and computer program product for identifying a location code area of a two-dimensional code are provided, which can accurately identify the location of the location code area in an image.
  • the embodiment of the present application provides a method for identifying the location code area of a two-dimensional code, including:
  • the position of the positioning code area in the image is obtained.
  • the embodiment of the present application provides a device for identifying the location code area of a two-dimensional code, including:
  • Suspected line segment identification module used to identify the line segment in the image containing the two-dimensional code as the suspected line segment of the positioning code area of the two-dimensional code as a candidate line segment;
  • a line segment clustering module configured to cluster the candidate line segments to form a plurality of candidate line segment clusters based on the position of each candidate line segment in the image
  • a dense cluster determination module configured to determine dense candidate line segment clusters among the plurality of candidate line segment clusters according to the intra-cluster line segment density of each candidate line segment cluster;
  • the inter-cluster matching module is used to perform length approximate matching between the dense candidate line clusters according to the length statistics corresponding to the dense candidate line clusters, and determine the matching result as the candidate line segments contained in the dense line segment clusters with similar lengths is a line segment of the positioning code area;
  • the position determination module of the positioning code area is configured to obtain the position of the positioning code area in the image according to the determined position of the line segment of the positioning code area in the image.
  • an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the above method when executing the computer program.
  • the embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the foregoing method is implemented when a processor executes the computer program.
  • the embodiment of the present application provides a computer program product, on which a computer program is stored, and the above method is implemented when a processor executes the computer program.
  • the above-mentioned method, device, computer equipment, storage medium and computer program product for identifying a two-dimensional code location code area first identify a line segment suspected to be a two-dimensional code location code area from an image containing a two-dimensional code and use it as a candidate line segment, and then , based on the position of each candidate line segment in the image, each candidate line segment is clustered to form a plurality of candidate line segment clusters; the dense candidate line segment clusters are determined according to the line segment density in each candidate line segment cluster, because the dense candidate line segment clusters include clusters The inner line segments are relatively dense, and these dense candidate line segment clusters are more likely to belong to the positioning code area; then, according to the length statistics information corresponding to each dense candidate line segment cluster, approximate length matching is performed between each dense candidate line segment cluster, if two dense line segment clusters If the lengths of the clusters are similar, the lengths of the candidate line segments included in the two dense line segment clusters are similar, and they are more likely to be the line segments in the positioning code
  • Fig. 1 is a schematic flowchart of a method for identifying a location code area of a two-dimensional code in an embodiment.
  • Fig. 2 is a schematic diagram of the positions where black and white changes are determined in an embodiment.
  • Fig. 3 is a schematic flowchart of a method for identifying a location code area of a two-dimensional code in an embodiment.
  • Fig. 4 is a structural block diagram of a device for identifying a location code area of a two-dimensional code in an embodiment.
  • Figure 5 is an internal block diagram of a computer device in one embodiment.
  • the method for identifying the two-dimensional code location code area can be applied to computer equipment, which can be but not limited to various personal computers, notebook computers, smart phones, tablet computers, portable wearable devices and server.
  • a method for identifying the location code area of a two-dimensional code is provided, and the application of the method to a computer device is used as an example for illustration, including the following operations:
  • a line segment identified as a location code area suspected of the two-dimensional code in an image containing a two-dimensional code is used as a candidate line segment.
  • the method of extracting line segments from an image may include: extracting the points where black and white changes from the image along parallel directions; Multiple line segments in each direction in the bundle.
  • the parallel direction beam is composed of multiple directions parallel to each other, and the direction can be along one side of the image, or along a direction forming a specific angle with one side of the image; Therefore, the image is scanned along multiple directions parallel to each other, and the points where the black and white changes are extracted from the image.
  • each line segment can be determined according to the number of pixels occupied by the line segment.
  • the length of the line segment a-b can be set to 1, and for example, the line segment b-c occupies 1 pixel, and the line segment b-c can be set
  • the length of is set to 1, and for example, the line segment c-d occupies 3 pixels, the length of the line segment b-c can be set to 3.
  • the image including the QR code after the image including the QR code is obtained, the image can be subdivided at the sub-pixel level, and then the location can be extracted.
  • the line segment identified as the location code area of the suspected QR code in the image containing the QR code is used as a candidate line segment, which may include:
  • the window that can accommodate a preset number of line segments, slide the line segments sequentially arranged in the same direction on the image containing the two-dimensional code, and use the preset number of line segments located in the window as a group, so as to Get multiple line segment groups;
  • each line segment of the same line segment group will be used as a line segment suspected to be the positioning code area of the two-dimensional code, and the suspected two-dimensional code positioning code area will be line segment as a candidate line segment.
  • the number of line segments that can be accommodated in the window and the preset length ratio can be determined according to the characteristics of the positioning code area of the two-dimensional code; specifically, if the positioning code area of the two-dimensional code is set to the shape of "back", then the window can accommodate line segments The number can be set to 5, and the preset length ratio can be set to 1:1:3:1:1.
  • line segment a-b, line segment b-c, line segment c-d, line segment d-e, line segment e-f, line segment f-g, line segment g-h, line segment h-i, line segment i-j and line segment j-k can be regarded as line segments arranged in sequence along the same direction; if the window can accommodate The number of line segments is set to 5, then, in the process of sliding the line segment a-b, line segment b-c, line segment c-d, line segment d-e, line segment e-f, line segment f-g, line segment g-h, line segment h-i, line segment i-j and line segment j-k according to the window, the line segment a-b , line segment b-c, line segment c-d, line segment d-e, and line segment e-f are located in the window, and line segment a-b, line segment b-c, line segment c-d, line segment d-e,
  • the length ratio between the line segments of the line segment group is 1:1:3:1:1, which is consistent with the preset length ratio, and the line segments included in the line segment group can be used as the line segments of the suspected positioning code area.
  • the line segment included in the line segment group can be regarded as a suspected Locate the line segment of the code area to avoid missing the line segment of the positioning code area.
  • Operation S102 based on the position of each candidate line segment in the image, cluster the candidate line segments to form a plurality of candidate line segment clusters. Wherein, the positions of the candidate line segments of the same candidate line segment cluster are similar, and the positions of the candidate line segments of different candidate line segment clusters are not similar.
  • Operation S103 Determine dense candidate line segment clusters among the plurality of candidate line segment clusters according to the intra-cluster line segment density of each candidate line segment cluster.
  • the candidate line segment cluster whose line segment density within the cluster is greater than or equal to a threshold may be used as a dense candidate line segment cluster.
  • Operation S104 according to the length statistical information corresponding to each dense candidate line segment cluster, perform length approximate matching among the dense candidate line segment clusters, and determine the candidate line segment contained in the dense line segment cluster whose matching result is similar in length as the positioning The line segment of the code area.
  • the length statistical information corresponding to the dense candidate line segment cluster is obtained by counting the lengths of the candidate line segments in the dense candidate line segment cluster. If the lengths of the two dense line segment clusters are similar, the candidate line segments included in the two dense line segment clusters are determined as the line segments of the positioning code area.
  • the position of the positioning code area in the image is obtained according to the determined position of the line segment of the positioning code area in the image.
  • the line segment of the positioning code area suspected of being a two-dimensional code is first identified from the image containing the two-dimensional code as a candidate line segment, and then, based on the position of each candidate line segment in the image, Each candidate line segment is clustered to form multiple candidate line segment clusters; the dense candidate line segment clusters are determined according to the intra-cluster line segment density of each candidate line segment cluster. It may belong to the positioning code area; then, according to the length statistical information corresponding to each dense candidate line cluster, approximate length matching is performed between each dense candidate line cluster.
  • the two dense line segment clusters If the lengths of two dense line segment clusters are similar, the two dense line segment clusters The lengths of the candidate line segments included in the clusters are similar, and they are more likely to be the line segments of the positioning code area. Therefore, the candidate line segments contained in the dense line segment clusters whose matching results are similar in length are determined as the line segments of the positioning code area, and according to the determined positioning The position of the line segment of the code area in the image can accurately identify the location of the code area in the image.
  • the way to obtain the length statistics information of dense candidate line segment clusters may be: operation S301, obtain the length of each candidate line segment in the dense candidate line segment cluster; operation S302, the same dense candidate line segment The average length of the candidate line segments of the cluster is used as the length statistical information corresponding to the same dense candidate line segment cluster.
  • the average length of the candidate line segments of the same dense candidate line segment cluster is used as the length statistical information, which is effectively represented as the length of the candidate line segments of the dense candidate line segment cluster, and the accuracy of length matching between clusters is improved.
  • the method of obtaining the intra-cluster line segment density of dense candidate line segment clusters may be: determining the number of candidate line segments included in each candidate line segment cluster; taking each number as the intra-cluster line segment density of the corresponding candidate line segment cluster.
  • 8 may be used as the intra-cluster line segment density of the candidate line segment cluster.
  • the number of candidate line segments is directly used as the intra-cluster line segment density of the candidate line segment clusters to improve processing efficiency.
  • clustering the candidate line segments to form a plurality of candidate line segment clusters includes: calculating the position of the center point of each candidate line segment in the image , as the position of each candidate line segment in the image; the candidate line segments whose center points are close to each other are divided into the same cluster, so as to obtain multiple candidate line segment clusters.
  • the candidate line segments classified into the same cluster may be extracted along the same direction, or may be extracted along different directions parallel to each other.
  • the position of the center point of the candidate line segment is used as the position of the candidate line segment in the image, and the line segments are regarded as points for position clustering to improve the clustering efficiency.
  • integration unit and model deployment unit specifically,
  • the image acquisition unit is mainly used to acquire images including two-dimensional codes.
  • Sub-pixel line scan unit mainly used for:
  • (1) Collect the image including the two-dimensional code, subdivide the image into pixels based on the sub-pixel method to obtain deeper information, and use the line scanning method to extract and store the line segments of the entire image.
  • the line segment clustering unit is mainly used for:
  • Edge fitting unit mainly used for:
  • the position of the fourth vertex is estimated based on the line segments of the three positioning marks through the parallelogram rule.
  • the above algorithm is packaged to obtain a model capable of obtaining two-dimensional code encoding information.
  • the model deployment unit is mainly used to deploy the two-dimensional code encoding information model to the target device; when decoding, input the image into the two-dimensional code encoding information model, obtain the recognition result output by the model, and use the two-dimensional code encoding rules for analysis , Check to get the output content.
  • the line segment of the positioning code area that is suspected to be a two-dimensional code is identified from the image containing the two-dimensional code as a candidate line segment, and then, based on the position of each candidate line segment in the image, each candidate line segment is clustered to form A plurality of candidate line segment clusters; the dense candidate line segment clusters are determined according to the intra-cluster line segment density of each candidate line segment cluster, because the dense candidate line segment clusters include denser intra-cluster line segments, these dense candidate line segment clusters are more likely to belong to the positioning code area; Then, according to the length statistical information corresponding to each dense candidate line segment cluster, approximate length matching is performed between each dense candidate line segment cluster.
  • the candidate line segment contained in the dense line segment cluster whose matching result is similar in length is determined as the line segment of the positioning code area, and according to the determined line segment of the positioning code area in the image The location of the positioning code area can be accurately identified in the image.
  • a device for identifying a two-dimensional code location code area including:
  • the suspected line segment identification module 401 is used to identify the line segment in the image containing the two-dimensional code as the suspected line segment of the positioning code area of the two-dimensional code as a candidate line segment;
  • a line segment clustering module 402 configured to cluster each candidate line segment to form a plurality of candidate line segment clusters based on the position of each candidate line segment in the image;
  • a dense cluster determination module 403, configured to determine dense candidate line segment clusters among the plurality of candidate line segment clusters according to the intra-cluster line segment density of each candidate line segment cluster;
  • the inter-cluster matching module 404 is configured to perform approximate length matching between the dense candidate line clusters according to the length statistics corresponding to the dense candidate line clusters, and convert the matching result into the candidate line segments contained in the dense line segment clusters with similar lengths Determined as the line segment of the positioning code area;
  • the position determination module 405 of the positioning code area is configured to obtain the position of the positioning code area in the image according to the determined position of the line segment of the positioning code area in the image.
  • the device further includes a length statistics module, configured to obtain the length of each candidate line segment in the dense candidate line segment cluster; and use the mean length of the candidate line segments of the same dense candidate line segment cluster as the same dense candidate line segment Cluster length statistics.
  • the device further includes a density acquisition module, configured to determine the number of candidate line segments included in each candidate line segment cluster; each number is used as the intra-cluster line segment density of the corresponding candidate line segment cluster.
  • the line segment clustering module 402 is specifically used for:
  • the candidate line segments with close center points are divided into the same cluster to obtain multiple candidate line segment clusters.
  • the device further includes a line segment extraction module, which is used to extract the points at the black-and-white changes from the image along the beam in a parallel direction; based on the connection of adjacent points in the same direction, the obtained Multiple line segments in each direction in the bundle of parallel directions.
  • a line segment extraction module which is used to extract the points at the black-and-white changes from the image along the beam in a parallel direction; based on the connection of adjacent points in the same direction, the obtained Multiple line segments in each direction in the bundle of parallel directions.
  • the suspected line segment identification module 401 is specifically used for:
  • the window that can accommodate a preset number of line segments, slide the line segments sequentially arranged in the same direction on the image containing the two-dimensional code, and use the preset number of line segments located in the window as a group, so as to Get multiple line segment groups;
  • each line segment of the same line segment group will be used as a line segment suspected to be the positioning code area of the two-dimensional code, and the suspected two-dimensional code positioning code area will be line segment as a candidate line segment.
  • Each module in the above-mentioned device for identifying the location code area of a two-dimensional code can be realized in whole or in part by software, hardware or a combination 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. 5 .
  • 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 operating systems, computer programs and databases.
  • the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
  • the database of the computer device is used for storing data identifying the location code area of the two-dimensional code.
  • the network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for identifying the location code area of the two-dimensional code is realized.
  • FIG. 5 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on 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, the memory stores a computer program, and the processor implements the operations in the foregoing method embodiments when executing the computer program.
  • a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the operations in the foregoing method embodiments are implemented.
  • a computer program product is provided, on which a computer program is stored, and the computer program is used by a processor to execute the operations in the above-mentioned various method embodiments.
  • user information including but not limited to user equipment information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • any references to memory, storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile memory and volatile memory.
  • 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 be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Electromagnetism (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

一种识别二维码定位码区的方法,包括:将包含二维码的图像中识别为疑似二维码的定位码区的线段作为候选线段;基于各候选线段在图像中的位置,将各候选线段聚类形成多个候选线段簇;根据各候选线段簇的簇内线段密集度,确定多个候选线段簇中的密集候选线段簇;根据各密集候选线段簇对应的长度统计信息,在各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为定位码区的线段;根据所确定的定位码区的线段在图像中的位置,得到定位码区在图像中的位置。

Description

识别二维码定位码区的方法、装置、设备和存储介质
相关申请的交叉引用
本申请要求于2021年11月1日提交中国专利局、申请号为2021112795480、发明名称为“识别二维码定位码区的方法、装置、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。
技术领域
本申请涉及二维码处理技术领域,特别是涉及一种识别二维码定位码区的方法、装置、计算机设备、存储介质和计算机程序产品。
背景技术
二维码,也可称为QR码(Quick Response code),包括定位码区和信息码区。信息码区用于携带特定的信息,在对包括二维码的图像进行识别,以得到信息码区所携带的特定信息时,可以先识别出图像中的定位码区,然后根据定位码区和信息码区之间在二维码上的位置关系,确定图像中属于信息码区的区域,进而得到特定信息。为保证特定信息的识别准确性,准确确定定位码区在图像中的位置是非常重要的。
发明内容
根据本申请的各种实施例提供一种识别二维码定位码区的方法、装置、计算机设备、存储介质和计算机程序产品,能够实现准确识别出定位码区在图像中的位置。
第一方面,本申请实施例提供一种识别二维码定位码区的方法,包括:
将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段;
基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇;
根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇;
根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段;
根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
第二方面,本申请实施例提供一种识别二维码定位码区的装置,包括:
疑似线段识别模块,用于将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段;
线段聚类模块,用于基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇;
密集簇确定模块,用于根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇;
簇间匹配模块,用于根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段;
定位码区位置确定模块,用于根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
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程序,所述处理器执行所述计算机程序时实现上述方法。
第四方面,本申请实施例提供一种计算机可读存储介质,其上存储有计算机程序,处理器执行所述计算机程序时实现上述方法。
第五方面,本申请实施例提供一种计算机程序产品,其上存储有计算机程序,处理器执行所述计算机程序时实现上述方法。
上述识别二维码定位码区的方法、装置、计算机设备、存储介质和计算机程序产品,先从包含二维码的图像中识别为疑似二维码的定位码区的线段并作为候选线段,然后,基于各候选线段在图像中的位置,将各候选线段聚类形成 多个候选线段簇;根据各候选线段簇的簇内线段密集度所确定密集候选线段簇,由于密集候选线段簇包括的簇内线段较密集,这些密集候选线段簇较有可能属于定位码区;接着,再根据各密集候选线段簇对应的长度统计信息,在各密集候选线段簇间进行长度近似匹配,若两个密集线段簇的长度近似,则这两个密集线段簇包括的候选线段的长度相近,更大可能是定位码区的线段,因此,将匹配结果为长度近似的密集线段簇所包含的候选线段确定为定位码区的线段,并根据所确定的定位码区的线段在图像中的位置,准确识别出定位码区在图像中的位置。
附图说明
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为一个实施例中识别二维码定位码区的方法的流程示意图。
图2为一个实施例中确定黑白变化处的位点示意图。
图3为一个实施例中识别二维码定位码区的方法的流程示意图。
图4为一个实施例中识别二维码定位码区的装置的结构框图。
图5为一个实施例中计算机设备的内部结构图。
具体实施方式
为使本申请实施例的技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。
因此,以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围,而是仅仅表示本申请的选定实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某 一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
在本申请的描述中,需要说明的是,若出现术语“上”、“下”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系,或者是该发明产品使用时惯常摆放的方位或位置关系,仅是为了便于描述本申请和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本申请的限制。
此外,若出现术语“第一”、“第二”等仅用于区分描述,而不能理解为指示或暗示相对重要性。
需要说明的是,在不冲突的情况下,本申请的实施例中的特征可以相互结合。
本申请提供的识别二维码定位码区的方法,可以应用于计算机设备中,该计算机设备可以是可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑、便携式可穿戴设备和服务器。
在一些实施例中,如图1所示,提供了一种识别二维码定位码区的方法,以该方法应用于计算机设备为例进行说明,包括以下操作:
操作S101,将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段。
具体来说,从图像中提取线段的方式可以包括:沿平行方向束,从所述图像中提取出黑白变化处的位点;基于对同一方向的相邻位点的连接,得到所述平行方向束中各方向的多个线段。
其中,平行方向束由相互平行的多个方向组成,该方向可以是沿图像的其中一边的方向,也可以沿与图像的其中一边形成特定的夹角的方向;由于二维码是通过黑白像素的阵列排布形成的,因此,沿相互平行的多个方向,对图像进行扫描,从图像中提取出黑白变化处的位点。
结合图2介绍从图像提取出黑白变化处的位点:沿平行方向束的其中一个方向对某一行的像素进行扫描,黑像素和白像素的相接处的颜色变化较大,因此将该相接处对应的位点作为提取得到的黑白变化处的位点,如位点a、b、c、 d、e、f、g、h、i、j和k。
由于位点a、b、c、d、e、f、g、h、i、j和k是沿同一方向提取得到的,因此,将相邻两个位点连接,形成多个线段,如线段a-b、线段b-c和线段c-d等。其中每个线段的长度可以是根据该线段占有的像素数量确定,例如线段a-b占有的1个像素,可以将线段a-b的长度设为1,又例如线段b-c占有的1个像素,可以将线段b-c的长度设为1,再例如线段c-d占有的3个像素,可以将线段b-c的长度设为3。
按照上述方式对图像进行位点提取以及同一方向的位点连接后,可以得到多个线段,并将这些线段作为从图像提取出的线段。
在一些场景中,在得到包括二维码的图像后,可以对图像进行亚像素级别的细分,然后进行位点提取。
在一些场景中,将包含二维码的图像中识别为疑似二维码的定位码区的线段作为候选线段,可以包括:
按照可容纳预设数量的线段的窗口,对在包含二维码的图像上沿同一方向依次排布的线段进行滑动,将位于所述窗口内的所述预设数量的线段作为一组,以得到多个线段组;
若同一线段组中的线段间长度比值与预设长度比值近似,则将所述同一线段组的各线段作为疑似所述二维码的定位码区的线段,将疑似二维码的定位码区的线段作为候选线段。
其中,窗口可容纳线段的数量和预设长度比值可以根据二维码的定位码区的特点确定;具体来说,二维码的定位码区设定为“回”字形,那么窗口可容纳线段的数量可以设为5,预设长度比值可以设为1:1:3:1:1。
示例性地,线段a-b、线段b-c、线段c-d、线段d-e、线段e-f、线段f-g、线段g-h、线段h-i、线段i-j和线段j-k,可以视为沿同一方向依次排布的线段;若窗口可容纳的线段数量设为5,那么,按照该窗口对线段a-b、线段b-c、线段c-d、线段d-e、线段e-f、线段f-g、线段g-h、线段h-i、线段i-j和线段j-k进行滑动的过程中,线段a-b、线段b-c、线段c-d、线段d-e和线段e-f位于窗口内,并将线段a-b、线段b-c、线段c-d、线段d-e和线段e-f作为一组,线段b-c、线 段c-d、线段d-e、线段e-f和线段f-g位于窗口内,并将线段b-c、线段c-d、线段d-e、线段e-f和线段f-g作为一组。
其中,针对线段a-b、线段b-c、线段c-d、线段d-e和线段e-f这个线段组,若线段a-b、线段b-c、线段c-d、线段d-e和线段e-f的长度分别为1、1、3、1和1,那么该线段组的线段间长度比值为1:1:3:1:1,与预设长度比值一致,可以将该线段组包括的线段作为疑似定位码区的线段。
在提取到的位点不十分准确的情况下,对应的线段长度也不十分准确,因此,只要线段组的线段间长度比值近似为预设长度比值,就可以将该线段组包括的线段作为疑似定位码区的线段,避免遗漏定位码区的线段。
操作S102,基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇。其中,同一候选线段簇的候选线段间的位置相近,不同候选线段簇的候选线段间的位置不相近。
操作S103,根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇。其中,可以将簇内线段密集度大于或等于阈值的候选线段簇作为密集候选线段簇。
操作S104,根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段。
其中,密集候选线段簇对应的长度统计信息是对该密集候选线段簇内的候选线段的长度统计得到的。若两个密集线段簇的长度近似,则将这两个密集线段簇包括的候选线段确定为定位码区的线段。
操作S105,根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
上述识别二维码定位码区的方法中,先从包含二维码的图像中识别为疑似二维码的定位码区的线段并作为候选线段,然后,基于各候选线段在图像中的位置,将各候选线段聚类形成多个候选线段簇;根据各候选线段簇的簇内线段密集度所确定密集候选线段簇,由于密集候选线段簇包括的簇内线段较密集,这些密集候选线段簇较有可能属于定位码区;接着,再根据各密集候选线段簇 对应的长度统计信息,在各密集候选线段簇间进行长度近似匹配,若两个密集线段簇的长度近似,则这两个密集线段簇包括的候选线段的长度相近,更大可能是定位码区的线段,因此,将匹配结果为长度近似的密集线段簇所包含的候选线段确定为定位码区的线段,并根据所确定的定位码区的线段在图像中的位置,准确识别出定位码区在图像中的位置。
在一些实施例中,如图3所示,得到密集候选线段簇的长度统计信息的方式可以是:操作S301,获取密集候选线段簇中的各候选线段的长度;操作S302,将同一密集候选线段簇的候选线段的长度均值,作为所述同一密集候选线段簇对应的长度统计信息。
上述实施例中,将同一密集候选线段簇的候选线段的长度的均值作为长度统计信息,有效的表征为该密集候选线段簇的候选线段的长度,提升簇间长度匹配的准确性。
在一些实施例中,得到密集候选线段簇的簇内线段密集度的方式可以是:确定各候选线段簇包括的候选线段的数量;将各数量作为对应的候选线段簇的簇内线段密集度。
示例性地,若某个候选线段簇包括的候选线段的数量为8个,则可以将8作为该候选线段簇的簇内线段密集度。
上述方式中,直接将候选线段的数量作为候选线段簇的簇内线段密集度,提高处理效率。
在一些实施例中,上述基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇,包括:将各候选线段的中心点在所述图像中的位置,作为各候选线段在所述图像中的位置;将中心点距离相近的候选线段划分至同一簇,以得到多个候选线段簇。
其中,被划分至同一簇的候选线段可以是沿同一方向提取得到的,也可以是沿相互平行的不同方向提取得到的。
上述实施例中,将候选线段的中心点的位置作为候选线段在图像中的位置,将线段看成点进行位置聚类,提高聚类效率。
为了更好地理解上述方法,以下详细阐述一个本申请识别二维码定位码区 的方法的应用实例,该应用实例主要包括图像采集单元、亚像素线扫法单元、线段聚类单元、边缘拟合单元和模型部署单元,具体来说,
图像采集单元,主要用于获取包括二维码的图像。
亚像素线扫法单元,主要用于:
(1)收集包括二维码的图像,基于亚像素的方法将图像进行像素细分,得到更加深层次的信息,并利用线扫法提取出整张图像的线段并存储。
(2)将上述(1)得到的线段以每五个线段为一组,并将同组的线段进行模板匹配(模板为1:1:3:1:1),通过设置适当的阈值筛选出疑似二维码定位码区的线段。
线段聚类单元,主要用于:
(3)将上述(2)中筛选出的疑似二维码定位码区的线段进行位置相近的聚类,得到多个线段簇;
(4)将上述(3)得到的多个线段簇进行密集簇的查找,得到多个密集线段簇;并对密集线段簇进行簇间长度近似匹配,将长度近似的密集线段簇所包括的线段作为定位码区的线段。
边缘拟合单元,主要用于:
(5)由于上述(4)得到的定位码区的线段分别属于对应于三个顶点的定位标识,通过平行四边形法则,基于这三个定位标识的线段,估算出第四个顶点的位置。
(6)将以估算出来的顶点位置作为约束通过最小二乘法边缘匹配得二维码的第四个顶点,结合三个定位标识从而获得整个码区信息。
对上述算法进行打包,得到能够获得二维码编码信息模型。
模型部署单元,主要用于将二维码编码信息模型部署到目标设备上;进行解码时将图像输入到二维码编码信息模型,得到模型输出的识别结果,并使用二维码编码规则进行解析、校验得到输出内容。
本应用实例中,先从包含二维码的图像中识别为疑似二维码的定位码区的线段并作为候选线段,然后,基于各候选线段在图像中的位置,将各候选线段聚类形成多个候选线段簇;根据各候选线段簇的簇内线段密集度所确定密集候 选线段簇,由于密集候选线段簇包括的簇内线段较密集,这些密集候选线段簇较有可能属于定位码区;接着,再根据各密集候选线段簇对应的长度统计信息,在各密集候选线段簇间进行长度近似匹配,若两个密集线段簇的长度近似,则这两个密集线段簇包括的候选线段的长度相近,更大可能是定位码区的线段,因此,将匹配结果为长度近似的密集线段簇所包含的候选线段确定为定位码区的线段,并根据所确定的定位码区的线段在图像中的位置,准确识别出定位码区在图像中的位置。
应该理解的是,虽然如上所述的各实施例所涉及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,如上所述的各实施例所涉及的流程图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。
在一些实施例中,如图4所示,提供了一种识别二维码定位码区的装置,包括:
疑似线段识别模块401,用于将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段;
线段聚类模块402,用于基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇;
密集簇确定模块403,用于根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇;
簇间匹配模块404,用于根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段;
定位码区位置确定模块405,用于根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
在一些实施例中,所述装置还包括长度统计模块,用于获取密集候选线段簇中的各候选线段的长度;将同一密集候选线段簇的候选线段的长度均值,作为所述同一密集候选线段簇的长度统计信息。
在一些实施例中,所述装置还包括密集度获取模块,用于确定各候选线段簇包括的候选线段的数量;将各数量作为对应的候选线段簇的簇内线段密集度。
在一些实施例中,所述线段聚类模块402,具体用于:
将各候选线段的中心点在所述图像中的位置,作为各候选线段在所述图像中的位置;
将中心点距离相近的候选线段划分至同一簇,以得到多个候选线段簇。
在一些实施例中,所述装置还包括线段提取模块,用于沿平行方向束,从所述图像中提取出黑白变化处的位点;基于对同一方向的相邻位点的连接,得到所述平行方向束中各方向的多个线段。
在一些实施例中,所述疑似线段识别模块401,具体用于:
按照可容纳预设数量的线段的窗口,对在包含二维码的图像上沿同一方向依次排布的线段进行滑动,将位于所述窗口内的所述预设数量的线段作为一组,以得到多个线段组;
若同一线段组中的线段间长度比值与预设长度比值近似,则将所述同一线段组的各线段作为疑似所述二维码的定位码区的线段,将疑似二维码的定位码区的线段作为候选线段。
关于识别二维码定位码区的装置的具体限定可以参见上文中对于识别二维码定位码区的方法的限定,在此不再赘述。上述识别二维码定位码区的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。
在一些实施例中,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5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、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储识别二维码定位码区的数据。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。该计算机程序被处理器执行时以实现一种识别二维码定位码区的方法。
本领域技术人员可以理解,图5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。
在一些实施例中,提供了一种计算机设备,包括存储器和处理器,存储器存储有计算机程序,处理器执行计算机程序时实现上述各个方法实施例中的操作。
在一些实施例中,提供了一种计算机可读存储介质,其上存储有计算机程序,计算机程序被处理器执行时实现上述各个方法实施例中的操作。
在一些实施例中,提供了一种计算机程序产品,其上存储有计算机程序,所述计算机程序被处理器执行上述各个方法实施例中的操作。
需要说明的是,本申请所涉及的用户信息(包括但不限于用户设备信息、用户个人信息等)和数据(包括但不限于用于分析的数据、存储的数据、展示的数据等),均为经用户授权或者经过各方充分授权的信息和数据。
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,是可以通过计算机程序来指令相关的硬件来完成,上述的计算机程序可存储于一非易失性计算机可读取存储介质中,该计算机程序在执行时,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。
以上的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 (20)

  1. 一种识别二维码定位码区的方法,其特征在于,包括:
    将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段;
    基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇;
    根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇;
    根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段;
    根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
  2. 根据权利要求1所述的方法,其特征在于,所述根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配之前,所述方法还包括:
    获取密集候选线段簇中的各候选线段的长度;
    将同一密集候选线段簇的候选线段的长度均值,作为所述同一密集候选线段簇对应的长度统计信息。
  3. 根据权利要求1所述的方法,其特征在于,所述根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇之前,所述方法还包括:
    确定各候选线段簇包括的候选线段的数量;
    将各数量作为对应的候选线段簇的簇内线段密集度。
  4. 根据权利要求1所述的方法,其特征在于,所述基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇,包括:
    将各候选线段的中心点在所述图像中的位置,作为所述各候选线段在所述 图像中的位置;
    将中心点距离相近的候选线段划分至同一簇,以得到多个候选线段簇。
  5. 根据权利要求1至4任一项所述的方法,其特征在于,所述将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段之前,所述方法还包括:
    沿平行方向束,从所述图像中提取出黑白变化处的位点;
    基于对同一方向的相邻位点的连接,得到所述平行方向束中各方向的多个线段。
  6. 根据权利要求5所述的方法,其特征在于,所述将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段,包括:
    按照可容纳预设数量的线段的窗口,对在包含二维码的图像上沿同一方向依次排布的线段进行滑动,将位于所述窗口内的所述预设数量的线段作为一组,以得到多个线段组;
    若同一线段组中的线段间长度比值与预设长度比值近似,则将所述同一线段组的各线段作为疑似所述二维码的定位码区的线段,将疑似所述二维码的定位码区的线段作为候选线段。
  7. 根据权利要求6所述的方法,其特征在于,所述按照可容纳预设数量的线段的窗口,对在包含二维码的图像上沿同一方向依次排布的线段进行滑动,将位于所述窗口内的所述预设数量的线段作为一组,以得到多个线段组之前,所述方法还包括:
    根据二维码的定位码区的特点,确定窗口可容纳线段的数量和预设长度比值。
  8. 根据权利要求5所述的方法,其特征在于,所述沿平行方向束,从所述图像中提取出黑白变化处的位点,包括:
    沿平行方向束对像素进行扫描,确定黑像素和白像素之间的相接处;
    将所述黑像素和白像素之间的相接处,作为黑白变化处的位点。
  9. 根据权利要求1所述的方法,其特征在于,所述根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇,包括:
    获取各候选线段簇的簇内线段密集度;
    将簇内线段密集度大于或等于阈值的候选线段簇,作为所述多个候选线段簇中的密集候选线段簇。
  10. 一种识别二维码定位码区的装置,其特征在于,包括:
    疑似线段识别模块,用于将包含二维码的图像中识别为疑似所述二维码的定位码区的线段作为候选线段;
    线段聚类模块,用于基于各候选线段在所述图像中的位置,将所述各候选线段聚类形成多个候选线段簇;
    密集簇确定模块,用于根据各候选线段簇的簇内线段密集度,确定所述多个候选线段簇中的密集候选线段簇;
    簇间匹配模块,用于根据各密集候选线段簇对应的长度统计信息,在所述各密集候选线段簇间进行长度近似匹配,并将匹配结果为长度近似的密集线段簇所包含的候选线段确定为所述定位码区的线段;
    定位码区位置确定模块,用于根据所确定的定位码区的线段在所述图像中的位置,得到所述定位码区在所述图像中的位置。
  11. 根据权利要求10所述的装置,其特征在于,所述装置还包括长度统计模块,用于:
    获取密集候选线段簇中的各候选线段的长度;将同一密集候选线段簇的候选线段的长度均值,作为所述同一密集候选线段簇对应的长度统计信息。
  12. 根据权利要求10所述的装置,其特征在于,所述装置还包括密集度获取模块,用于:
    确定各候选线段簇包括的候选线段的数量;将各数量作为对应的候选线段簇的簇内线段密集度。
  13. 根据权利要求10所述的装置,其特征在于,所述线段聚类模块,具体用于:
    将各候选线段的中心点在所述图像中的位置,作为所述各候选线段在所述图像中的位置;
    将中心点距离相近的候选线段划分至同一簇,以得到多个候选线段簇。
  14. 根据权利要求10至13任一项所述的装置,其特征在于,所述装置还包括线段提取模块,用于:
    沿平行方向束,从所述图像中提取出黑白变化处的位点;基于对同一方向的相邻位点的连接,得到所述平行方向束中各方向的多个线段。
  15. 根据权利要求14所述的装置,其特征在于,所述疑似线段识别模块,具体用于:
    按照可容纳预设数量的线段的窗口,对在包含二维码的图像上沿同一方向依次排布的线段进行滑动,将位于所述窗口内的所述预设数量的线段作为一组,以得到多个线段组;
    若同一线段组中的线段间长度比值与预设长度比值近似,则将所述同一线段组的各线段作为疑似所述二维码的定位码区的线段,将疑似所述二维码的定位码区的线段作为候选线段。
  16. 根据权利要求15所述的装置,其特征在于,所述装置还包括确定模块,用于:
    根据二维码的定位码区的特点,确定窗口可容纳线段的数量和预设长度比值。
  17. 根据权利要求14所述的装置,其特征在于,所述线段提取模块,还用于:
    沿平行方向束对像素进行扫描,确定黑像素和白像素之间的相接处;
    将所述黑像素和白像素之间的相接处,作为黑白变化处的位点。
  18. 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程序,其特征在于,所述处理器执行所述计算机程序时实现权利要求1至9中任一项所述的方法。
  19. 一种计算机可读存储介质,其上存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1至9中任一项所述的方法。
  20. 一种计算机程序产品,包括计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1至9中任一项所述的方法。
PCT/CN2022/107453 2021-11-01 2022-07-22 识别二维码定位码区的方法、装置、设备和存储介质 WO2023071322A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111279548.0A CN113705270B (zh) 2021-11-01 2021-11-01 识别二维码定位码区的方法、装置、设备和存储介质
CN202111279548.0 2021-11-01

Publications (1)

Publication Number Publication Date
WO2023071322A1 true WO2023071322A1 (zh) 2023-05-04

Family

ID=78647548

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/107453 WO2023071322A1 (zh) 2021-11-01 2022-07-22 识别二维码定位码区的方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN113705270B (zh)
WO (1) WO2023071322A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113705270B (zh) * 2021-11-01 2022-02-18 深圳思谋信息科技有限公司 识别二维码定位码区的方法、装置、设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104517090A (zh) * 2013-09-29 2015-04-15 北大方正集团有限公司 一种qr码探测图形的检测方法及系统
CN109815762A (zh) * 2018-12-29 2019-05-28 福建天泉教育科技有限公司 远距离识别二维码的方法、存储介质
US10509934B1 (en) * 2018-02-01 2019-12-17 Accusoft Corporation Methods and apparatus for improving QR code locator detectability and/or finding the corners of a locator pattern
CN111368573A (zh) * 2020-03-02 2020-07-03 凌云光技术集团有限责任公司 一种基于几何特征约束的定位方法
CN112733565A (zh) * 2020-12-29 2021-04-30 美的集团股份有限公司 二维码粗定位方法、设备及存储介质
CN113705270A (zh) * 2021-11-01 2021-11-26 深圳思谋信息科技有限公司 识别二维码定位码区的方法、装置、设备和存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9355293B2 (en) * 2008-12-22 2016-05-31 Canon Kabushiki Kaisha Code detection and decoding system
CN110334560B (zh) * 2019-07-16 2023-04-07 山东浪潮科学研究院有限公司 一种二维码定位方法和装置
CN110414649B (zh) * 2019-07-29 2023-06-06 广州柔视智能科技有限公司 Dm码的定位方法、装置、终端及存储介质
CN112541370B (zh) * 2020-12-16 2022-03-15 电子科技大学 一种基于fpga的qr码位置探测图形定位方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104517090A (zh) * 2013-09-29 2015-04-15 北大方正集团有限公司 一种qr码探测图形的检测方法及系统
US10509934B1 (en) * 2018-02-01 2019-12-17 Accusoft Corporation Methods and apparatus for improving QR code locator detectability and/or finding the corners of a locator pattern
CN109815762A (zh) * 2018-12-29 2019-05-28 福建天泉教育科技有限公司 远距离识别二维码的方法、存储介质
CN111368573A (zh) * 2020-03-02 2020-07-03 凌云光技术集团有限责任公司 一种基于几何特征约束的定位方法
CN112733565A (zh) * 2020-12-29 2021-04-30 美的集团股份有限公司 二维码粗定位方法、设备及存储介质
CN113705270A (zh) * 2021-11-01 2021-11-26 深圳思谋信息科技有限公司 识别二维码定位码区的方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN113705270B (zh) 2022-02-18
CN113705270A (zh) 2021-11-26

Similar Documents

Publication Publication Date Title
US10482349B2 (en) Systems and methods for reducing data density in large datasets
JP6402265B2 (ja) 意思決定モデルを構築する方法、コンピュータデバイス及び記憶デバイス
US9367766B2 (en) Text line detection in images
US10192138B2 (en) Systems and methods for reducing data density in large datasets
US10217241B2 (en) System and method for compressing graphs via cliques
WO2018021942A2 (ru) Распознавание лиц с помощью искусственной нейронной сети
KR102047953B1 (ko) 얼굴 인식 시스템 및 방법
Bellavia SIFT matching by context exposed
WO2023071322A1 (zh) 识别二维码定位码区的方法、装置、设备和存储介质
Aiger et al. Reporting neighbors in high-dimensional Euclidean space
Jeon et al. Measuring and explaining the inter-cluster reliability of multidimensional projections
JP6882329B2 (ja) Ihc画像解析のための空間インデックス作成
CN110083731B (zh) 图像检索方法、装置、计算机设备及存储介质
CN114443880A (zh) 一种装配式建筑的大样图审图方法及审图系统
CN113537026A (zh) 建筑平面图中的图元检测方法、装置、设备及介质
CN105190689A (zh) 包括基于毗连特征的对象检测和/或双边对称对象分段的图像处理
Chan et al. F-sort: An alternative for faster geometric verification
CN115880362A (zh) 码区定位方法、装置、计算机设备及计算机可读存储介质
WO2022110492A1 (zh) 指静脉身份识别方法、装置、计算机设备和存储介质
CN112750124A (zh) 模型生成、图像分割方法、装置、电子设备及存储介质
Paudel et al. Robust and optimal registration of image sets and structured scenes via sum-of-squares polynomials
CN116579960B (zh) 一种地理空间数据融合方法
CN117274366B (zh) 线条边距确定方法和装置
EP4125066B1 (en) Method and system for table structure recognition via deep spatial association of words
Qian et al. Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection