Object verification method and device, electronic equipment and computer readable storage medium

Through the object verification method, the object image information is used to identify the page slip and barcode areas, determine the target text information, and realize automatic verification of the verification object, solving the problem that the barcode waybill number in the express delivery page slip does not include the package number, and improving the The efficiency and accuracy of logistics sorting.

CN119007214APending Publication Date: 2024-11-22BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202310552641.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-16
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the prior art, the largest barcode waybill number in the express delivery bill does not include the parcel number, resulting in the logistics sorting equipment being unable to identify the parcel, affecting the efficiency and accuracy of logistics sorting.

Method used

Through the object verification method, the object image information is used to determine the face plate area and the barcode area, the target face plate area image recognition is performed, text information and barcode position information are obtained, and the target text information is determined to realize automatic verification of the checked object.

Benefits of technology

The efficiency and accuracy of object verification are improved, the efficiency and accuracy of logistics sorting are ensured, and the problem of unrecognition of package numbers in the prior art is overcome.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007214A_ABST
    Figure CN119007214A_ABST
Patent Text Reader

Abstract

The invention provides an object verification method and device, electronic equipment and a computer readable storage medium, and can be applied to the technical fields of logistics, deep learning and computer vision. The object verification method comprises the following steps: in response to a received object verification instruction, determining object image information according to an object image of a to-be-verified object indicated by the object verification instruction; determining a target express sheet area image according to the object image, the express sheet position information of the at least one express sheet area and the bar code position information of the at least one bar code area; the target express sheet area image is recognized, recognition information is obtained, and the recognition information comprises respective text information and text position information of at least one text area; determining target text information according to the bar code position information of the at least one bar code area and the text information and the text position information of the at least one text area; and according to the target text information, verifying the to-be-verified object to obtain an object verification result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the fields of logistics technology, deep learning and computer vision technology, and more specifically, to an object verification method and device, an electronic device, a computer-readable storage medium and a computer program product. Background Art

[0002] With the development of logistics technology, how to automatically identify express delivery bills is an urgent problem to be solved. Express delivery bills can refer to the documents used by the express industry to record relevant information such as the sender, recipient, product weight and price during the delivery of goods.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related technology: due to the differences in senders, bill templates and character encoding of bill printing equipment, it is easy for the largest barcode waybill number in the express bill to not include the package number, resulting in the logistics sorting equipment being unable to recognize the package, and thus unable to guarantee the efficiency and accuracy of logistics sorting. Summary of the invention

[0004] In view of this, the present disclosure provides an object verification method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of the present disclosure, there is provided an object verification method, comprising:

[0006] In response to receiving the object verification instruction, determining object image information according to the object image of the object to be verified indicated by the object verification instruction, wherein the object image information includes the respective face sheet position information of at least one face sheet area and the respective barcode position information of at least one barcode area;

[0007] Determine a target document area image according to the object image, the document position information of the at least one document area, and the barcode position information of the at least one barcode area;

[0008] Recognize the single-region image of the target surface to obtain recognition information, wherein the recognition information includes text information and text position information of at least one text region;

[0009] Determining target text information according to the barcode position information of each of the at least one barcode area, the text information and text position information of each of the at least one text area; and

[0010] According to the target text information, the object to be verified is verified to obtain an object verification result.

[0011] According to an embodiment of the present disclosure, the determining of the target text information according to the barcode position information of each of the at least one barcode area, the text information and the text position information of each of the at least one text area includes:

[0012] Determine candidate text information and candidate text position information of at least one candidate text region according to the text information and text position information of the at least one text region;

[0013] Determine at least one first candidate barcode position information according to the target surface single position information and the barcode center point of each of the at least one barcode area;

[0014] Determine the second candidate barcode position information according to the at least one first candidate barcode position information;

[0015] Determine the target barcode position information according to the second candidate barcode position information; and

[0016] The target text information is determined based on the target barcode position information and the candidate text information and candidate text position information of at least one candidate text region.

[0017] According to an embodiment of the present disclosure, determining candidate text information and candidate text position information of at least one candidate text region according to the text information and text position information of the at least one text region includes:

[0018] In response to detecting an input operation of a user, acquiring input text information;

[0019] For each piece of text information in the text information of the at least one text area,

[0020] Determine the number of characters in the text message;

[0021] When the number of characters is greater than or equal to a preset threshold, determining a target number of characters;

[0022] According to the target number of characters, determining sub-text information corresponding to the target number of characters from the text information;

[0023] Performing character matching on the input text information and the sub-text information to obtain a character matching result; and

[0024] In the case where the character matching result indicates that the input text information and the sub-text information match, the candidate text information and the candidate text position information are determined according to the text region corresponding to the text information.

[0025] According to an embodiment of the present disclosure, the determining of at least one first candidate barcode position information according to the target surface single position information and the barcode center point of each of the at least one barcode area includes:

[0026] For each barcode center point of the barcode center points of the at least one barcode region,

[0027] In the case where the barcode center point matches the target surface single position information, the first candidate barcode position information is determined according to the barcode area corresponding to the barcode center point.

[0028] According to an embodiment of the present disclosure, the first candidate barcode position information at least includes a first candidate barcode edge point and a second candidate barcode edge point.

[0029] According to an embodiment of the present disclosure, determining the second candidate barcode position information according to the at least one first candidate barcode position information includes:

[0030] For each first candidate barcode position information in the at least one first candidate barcode position information,

[0031] Determine a first difference value according to the abscissa of the first candidate barcode edge point and the abscissa of the second candidate barcode edge point;

[0032] Determine a second difference value according to the ordinate of the first candidate barcode edge point and the ordinate of the second candidate barcode edge point;

[0033] Determine the candidate barcode area corresponding to the first candidate barcode position information according to the first difference and the second difference; and

[0034] The second candidate barcode position information is determined according to the candidate barcode area corresponding to each of the at least one first candidate barcode position information.

[0035] According to an embodiment of the present disclosure, the second candidate barcode position information at least includes a third candidate barcode edge point and a fourth candidate barcode edge point.

[0036] According to an embodiment of the present disclosure, determining the target barcode position information according to the second candidate barcode position information includes:

[0037] Determine a third difference value according to the abscissa of the third candidate barcode edge point and the abscissa of the fourth candidate barcode edge point;

[0038] Determine a fourth difference value according to the ordinate of the third candidate barcode edge point and the ordinate of the fourth candidate barcode edge point;

[0039] When the third difference is greater than or equal to the fourth difference, the second candidate barcode position information is processed according to a first preset extension rule to obtain the target barcode position information; and

[0040] In the case that the third difference is smaller than the fourth difference, the second candidate barcode position information is processed according to a second preset extension rule to obtain the target barcode position information.

[0041] According to an embodiment of the present disclosure, determining the target text information according to the target barcode position information and the candidate text information and candidate text position information of at least one candidate text area includes:

[0042] For each candidate text position information in the candidate text position information of the at least one candidate text region,

[0043] In the case where the candidate text position information matches the target barcode position information, the target text information is determined based on the candidate text area corresponding to the candidate text position information.

[0044] According to an embodiment of the present disclosure, in response to receiving the object verification instruction, determining the object image information according to the object image of the object to be verified indicated by the object verification instruction includes:

[0045] Extracting features from the object image to obtain an object feature map of at least one scale;

[0046] Fusing the object feature map of at least one scale to obtain a fused feature map;

[0047] According to the fused feature map, determine the location information, category information and confidence of at least one region, wherein the confidence represents the credibility of the category information, and the category information includes the label region and the barcode region;

[0048] Determining the at least one label area and the at least one barcode area from the at least one area according to the confidence level and the category information; and

[0049] According to the position information of the at least one area, the at least one label area and the at least one barcode area, the label position information of each of the at least one label area and the barcode position information of each of the at least one barcode area are determined.

[0050] According to an embodiment of the present disclosure, determining the target face sheet area image according to the object image, the face sheet position information of each of the at least one face sheet area, and the barcode position information of each of the at least one barcode area includes:

[0051] Determine at least one candidate face sheet position information according to the face sheet position information of each of the at least one face sheet area and the barcode position information of each of the at least one barcode area;

[0052] Determine the target document location information according to the at least one candidate document location information; and

[0053] According to the above-mentioned target surface single position information, the above-mentioned target surface single area image is determined from the above-mentioned object image.

[0054] According to an embodiment of the present disclosure, the determining of at least one candidate face sheet position information according to the face sheet position information of each of the at least one face sheet area and the barcode position information of each of the at least one barcode area comprises:

[0055] Determining the barcode center point of each of the at least one barcode area according to the barcode position information of each of the at least one barcode area; and

[0056] For each piece of the waybill location information in the waybill location information of the at least one waybill area,

[0057] When any barcode center point among the at least one barcode center point matches the waybill position information, the waybill position information is determined as the candidate waybill position information.

[0058] According to an embodiment of the present disclosure, the above-mentioned candidate face single position information includes at least a first candidate face single edge point and a second candidate face single edge point.

[0059] According to an embodiment of the present disclosure, determining the target air order location information according to the at least one candidate air order location information includes:

[0060] For each candidate face order position information in the at least one candidate face order position information,

[0061] Determine a fifth difference value according to the abscissa of the first candidate single edge point and the abscissa of the second candidate single edge point;

[0062] Determine a sixth difference value according to the ordinate of the first candidate single edge point and the ordinate of the second candidate single edge point;

[0063] Determine the candidate order area corresponding to the candidate order position information according to the fifth difference and the sixth difference; and

[0064] The target face order position information is determined according to the candidate face order area corresponding to each of the at least one candidate face order position information.

[0065] According to an embodiment of the present disclosure, the object to be verified is verified according to the target text information, and the object verification result obtained includes:

[0066] Based on the preset text information, regularization verification is performed on the target text information to obtain a regularization verification result;

[0067] In a case where the regularization verification result indicates that the preset text information matches the target text information, determining the object verification result indicating that the object verification has passed; and

[0068] In the case where the regularized verification result indicates that the preset text information and the target text information do not match, the object verification result indicating that the object verification has failed is determined.

[0069] According to another aspect of the present disclosure, there is provided an object verification device, comprising:

[0070] A first determination module is used to determine object image information in response to receiving an object verification instruction, according to an object image of the object to be verified indicated by the object verification instruction, wherein the object image information includes the respective bill position information of at least one bill area and the respective barcode position information of at least one barcode area;

[0071] A second determination module is used to determine a target face order area image according to the object image, the face order position information of each of the at least one face order area, and the barcode position information of each of the at least one barcode area;

[0072] A recognition module, used to recognize the above-mentioned single-region image of the target surface to obtain recognition information, wherein the above-mentioned recognition information includes text information and text position information of at least one text region;

[0073] A third determination module is used to determine the target text information according to the barcode position information of each of the at least one barcode area, the text information and the text position information of each of the at least one text area; and

[0074] The verification module is used to verify the object to be verified according to the target text information to obtain the object verification result.

[0075] According to another aspect of the present disclosure, there is provided an electronic device, including:

[0076] one or more processors;

[0077] a memory for storing one or more instructions,

[0078] When the one or more instructions are executed by the one or more processors, the one or more processors implement the method described in the present disclosure.

[0079] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which executable instructions are stored. When the executable instructions are executed by a processor, the processor implements the method described in the present disclosure.

[0080] According to another aspect of the present disclosure, a computer program product is provided. The computer program product includes computer executable instructions. When the computer executable instructions are executed, they are used to implement the method described in the present disclosure.

[0081] According to the embodiments of the present disclosure, since the target face order area image is determined based on the object image, the face order position information of each of at least one face order area, and the barcode position information of each of at least one barcode area, the target face order area image is divided in the object image, thereby improving the object verification efficiency. On this basis, since the target text information is determined based on the barcode position information of each of at least one barcode area, the text information of each of at least one text area, and the text position information, by verifying the object to be verified based on the target text information, an object verification result indicating whether the object to be verified has passed the verification can be obtained, thereby realizing automatic verification of the object to be verified, thereby at least partially overcoming the technical problem in the related art that the efficiency and accuracy of logistics sorting cannot be guaranteed, and improving the accuracy of object verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0083] Figure 1 The system architecture to which the object verification method according to the embodiment of the present disclosure can be applied is schematically shown;

[0084] Figure 2 A flowchart of an object verification method according to an embodiment of the present disclosure is schematically shown;

[0085] Figure 3A An example schematic diagram schematically shows an object image of an object to be verified according to an embodiment of the present disclosure;

[0086] Figure 3B An exemplary schematic diagram schematically shows a process of determining object image information according to an object image of an object to be verified indicated by the object verification instruction in response to receiving an object verification instruction according to an embodiment of the present disclosure;

[0087] Figure 4A flowchart of a method for determining a target document area image according to an object image, document position information of at least one document area, and barcode position information of at least one barcode area is schematically shown according to an embodiment of the present disclosure;

[0088] Figure 5 An example schematic diagram of a process of determining a target face sheet area image according to an object image, face sheet position information of at least one face sheet area, and barcode position information of at least one barcode area is schematically shown according to an embodiment of the present disclosure;

[0089] Figure 6 A flowchart of a method for determining target text information according to barcode position information of at least one barcode region, text information and text position information of at least one text region according to an embodiment of the present disclosure is schematically shown;

[0090] Fig. 7A An example schematic diagram schematically shows a process of determining second candidate barcode position information according to at least one first candidate barcode position information according to an embodiment of the present disclosure;

[0091] Figure 7B An example schematic diagram schematically shows a process of determining target barcode position information according to second candidate barcode position information according to an embodiment of the present disclosure;

[0092] Figure 7C An example schematic diagram of a process of determining target text information according to target barcode position information and candidate text information and candidate text position information of at least one candidate text region according to an embodiment of the present disclosure is schematically shown;

[0093] Figure 8 An example schematic diagram of an object verification process according to an embodiment of the present disclosure is schematically shown;

[0094] Fig. 9 A block diagram schematically shows an object verification device according to an embodiment of the present disclosure; and

[0095] Fig.10 A block diagram of an electronic device suitable for implementing an object verification method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0096] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0097] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0098] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0099] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0100] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0101] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0102] For example, after collecting the object’s image information, we can use methods including de-identification or anonymization to desensitize your information to protect the security of your information.

[0103] In the related art, in order to solve the problem that the largest barcode waybill number in the express delivery bill does not include the package number, the sorting personnel usually take a photo of the parcel bill without the package number in the sorting return area and upload it to the system, and verify the parcel bill without the package number through manual review.

[0104] However, since manual review requires additional manpower costs and takes a long time, the efficiency and accuracy of logistics sorting cannot be guaranteed.

[0105] In order to at least partially solve the technical problems existing in the related art, the present disclosure provides an object verification method and device, an electronic device and a computer-readable storage medium, which can be applied to the fields of logistics technology, deep learning and computer vision technology. The object verification method includes: in response to receiving an object verification instruction, according to the object image of the object to be verified indicated by the object verification instruction, determining the object image information, wherein the object image information includes the face sheet position information of at least one face sheet area and the bar code position information of at least one bar code area; according to the object image, the face sheet position information of at least one face sheet area and the bar code position information of at least one bar code area, determining the target face sheet area image; recognizing the target face sheet area image to obtain recognition information, wherein the recognition information includes the text information and text position information of at least one text area; determining the target text information according to the bar code position information of at least one bar code area, the text information and text position information of at least one text area; verifying the object to be verified according to the target text information to obtain the object verification result.

[0106] Figure 1 The system architecture to which the object verification method according to the embodiment of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0107] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0108] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0109] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0110] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0111] It should be noted that the object verification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the object verification device provided in the embodiment of the present disclosure can generally be set in the server 105. The object verification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the object verification device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0112] Alternatively, the object verification method provided in the embodiment of the present disclosure may also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may also be executed by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the object verification device provided in the embodiment of the present disclosure may also be provided in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may be provided in other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0113] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0114] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0115] Figure 2 The flowchart of the object verification method according to the embodiment of the present disclosure is schematically shown.

[0116] like Figure 2 As shown, the object verification method includes operations S210 to S250.

[0117] In operation S210, in response to receiving an object verification instruction, object image information is determined based on the object image of the object to be verified indicated by the object verification instruction, wherein the object image information includes respective face sheet position information of at least one face sheet area and respective barcode position information of at least one barcode area.

[0118] In operation S220, a target document area image is determined based on the object image, the document position information of each of the at least one document area, and the barcode position information of each of the at least one barcode area.

[0119] In operation S230, the single-region image of the target surface is recognized to obtain recognition information, wherein the recognition information includes text information and text position information of at least one text region.

[0120] In operation S240, target text information is determined based on the barcode position information of each of the at least one barcode regions, the text information of each of the at least one text region, and the text position information.

[0121] In operation S250, the object to be verified is verified according to the target text information to obtain an object verification result.

[0122] According to an embodiment of the present disclosure, the code of the object verification instruction can be pre-written into a script. In response to detecting that the target user initiates an object verification operation using the target terminal for the object to be verified, the target terminal can run the script to generate an object verification instruction. The object to be verified can refer to a package. After obtaining the object verification instruction, the object verification instruction can be sent to a server so that the server can obtain an object image of the object to be verified indicated by the object verification instruction according to the object verification instruction and process the object image.

[0123] According to an embodiment of the present disclosure, the object image may be acquired through real-time acquisition, for example, the object image may be acquired by photographing or scanning the object to be verified. Alternatively, the object image may also be pre-stored in a data source, for example, the data source may include at least one of the following: a local database, a cloud database, and a network resource. For example, a data interface may be called to acquire the object image from the data source using the data interface. Alternatively, the object image may be received from other terminal devices. The embodiment of the present disclosure does not limit the method for acquiring the object image.

[0124] According to an embodiment of the present disclosure, an object image may refer to an image including an object to be verified. The file format of the object image may include JPG (Joint Photographic Experts Group), TIFF (Tag Image File Format), PNG (Portable Network Graphics), PDF (Portable Document Format), GIF (Graphics Interchange Format), etc. The present disclosure embodiment does not limit the file format of the object image.

[0125] According to an embodiment of the present disclosure, a waybill may correspond to a waybill identifier. For example, the waybill identifier may be a waybill number. A waybill may include at least one package. A package may correspond to a package identifier. For example, the package identifier may be a package number. The package number may represent the nth package of the package under the corresponding waybill. The package number may be represented by "Xab", where X may represent the waybill number, a may represent that the package is the ath package of the waybill, and b may represent that the waybill includes a total of b packages. For example, the waybill number of the target waybill is "X0000", and the target waybill includes 3 packages, then the package numbers corresponding to the waybill number "X0000" are "X0000-1-3", "X0000-2-3" and "X0000-3-3".

[0126] According to an embodiment of the present disclosure, after obtaining an object image, target detection can be performed on the object image to obtain object image information. The target detection method can be set according to actual business needs and is not limited here. For example, the target detection method can include at least one of the following: a traditional target detection method and a target detection method based on deep learning.

[0127] According to an embodiment of the present disclosure, a conventional target detection method may include at least one of the following: a target detection method based on macro features and a target detection method based on feature points. Macro features may include at least one of the following: shape, color, and size, etc. For example, a target detection method based on macro features may include a target detection method based on Hough circle transform. A target detection method based on feature points may include at least one of the following: a target detection method based on SIFT (Scale-invariantieature transform) and a target detection method based on SURF (Speeded Up Robust Features).

[0128] According to an embodiment of the present disclosure, a target detection method based on deep learning may include at least one of the following: a single-stage target detection method and a two-stage target detection method. For example, a single-stage target detection method may include at least one of the following: SSD (i.e., Single Shot MultiBox Detector) and YOLO (i.e., You Only Look Once). A two-stage target detection method may include at least one of the following: R-CNN (i.e., Region Convolutional Neural Network), Fast R-CNN, and Faster R-CNN.

[0129] According to an embodiment of the present disclosure, the object image information may include the face sheet position information of each of at least one face sheet area and the bar code position information of each of at least one bar code area. The face sheet may refer to a document used by the express industry to record relevant information in the process of transporting goods. Relevant information may include sender customer information, recipient customer information, origin information, destination information, product weight, price, and package identification, etc. The face sheet position information may characterize the location of the face sheet area. The face sheet position information may be used as a basis for extracting the face sheet area image corresponding to the face sheet area from the object image. The face sheet position information may be characterized using a first detection frame. The first detection frame may include a four-corner point frame, that is, the face sheet position information may be characterized using four coordinates.

[0130] According to an embodiment of the present disclosure, a barcode may refer to a graphic identifier that arranges a plurality of black bars and blank bars of different widths according to a predetermined coding rule to express information. The barcode position information may characterize the location of a barcode single area. The barcode position information may be used as a basis for extracting a barcode area image corresponding to the barcode area from a single face image. The barcode position information may be characterized using a second detection frame. The second detection frame may include a four-corner point frame, that is, the barcode position information may be characterized using four coordinates.

[0131] According to an embodiment of the present disclosure, after obtaining the object image information, the target face sheet position information that meets the first predetermined condition can be determined based on the face sheet position information of each of at least one face sheet area and the barcode position information of each of at least one barcode area. The target face sheet position information can be used to characterize the face sheet area with the largest area in the object image. Based on the target face sheet position information, the target face sheet area image is determined. The first predetermined condition can be set according to actual business needs and is not limited here. For example, the first predetermined condition can be that the positional relationship between the face sheet position information and the barcode position information is less than or equal to a predetermined threshold.

[0132] According to an embodiment of the present disclosure, after obtaining a single-region image of the target surface, a text detection model can be used to perform text detection on the single-region image of the target surface to obtain text position information of each of at least one text region. The text detection model can be obtained by training a second preset model using a second training sample set and a second label set. The second preset model may include a deep learning model or a traditional model. The deep learning model may include a text detection model based on a candidate box, a text detection model based on segmentation, or a text detection model based on a mixture of the two. The traditional model may include a text detection model based on SWT (Stroke Width Transform) or a text detection model based on EdgeBox (i.e., edge box), etc.

[0133] According to an embodiment of the present disclosure, after obtaining the text position information of at least one text area, a text recognition model can be used to perform text recognition on the single area image of the target surface to obtain the text information of at least one text area. The text information can be used to characterize the text content corresponding to the field composed of continuous text in the text area. The text recognition model can be obtained by training a third preset model using a third training sample set and a third label set. The third preset model may include a pattern matching model, a machine learning model, or a deep learning model. The deep learning model may include a text recognition model based on single character recognition or a text recognition model based on overall recognition.

[0134] According to an embodiment of the present disclosure, the target barcode position information can be determined based on the barcode position information of each of at least one barcode area. The target barcode position information can be used to characterize the barcode area with the largest area in the single area image of the target surface. The target text information is determined based on the barcode position information, the text information of each of at least one text area, and the text position information. The target text information can be used to characterize the text information corresponding to the target barcode position information. After obtaining the target text information, the object to be verified can be verified based on the target text information to obtain the object verification result. The object verification result can be used to characterize whether the object to be verified has passed the verification.

[0135] According to the embodiments of the present disclosure, since the target face order area image is determined based on the object image, the face order position information of each of at least one face order area, and the barcode position information of each of at least one barcode area, the target face order area image is divided in the object image, thereby improving the object verification efficiency. On this basis, since the target text information is determined based on the barcode position information of each of at least one barcode area, the text information of each of at least one text area, and the text position information, by verifying the object to be verified based on the target text information, an object verification result indicating whether the object to be verified has passed the verification can be obtained, thereby realizing automatic verification of the object to be verified, thereby at least partially overcoming the technical problem in the related art that the efficiency and accuracy of logistics sorting cannot be guaranteed, and improving the accuracy of object verification.

[0136] Reference below Figure 3A , Figure 3B , Figure 4 , Figure 5 , Figure 6 , Fig. 7A , Figure 7B , Figure 7C and Figure 8 , the object verification method 200 according to an embodiment of the present invention is further described.

[0137] Figure 3A An example schematic diagram of an object image of an object to be verified according to an embodiment of the present disclosure is schematically shown.

[0138] like Figure 3A As shown in 300A, the object image 301 of the object to be verified may include at least one face sheet area, at least one barcode area corresponding to each face sheet area in the at least one face sheet area, and a text area corresponding to each barcode area in the at least one barcode area.

[0139] For example, the object image 301 may include a label area 302 and a label area 303. The label area 302 may include a barcode area 302_11, a text area 302_12 corresponding to the barcode area 302_11, a barcode area 302_21, and a text area 302_22 corresponding to the barcode area 302_21. The label area 303 may include a barcode area 303_11 and a text area 303_12 corresponding to the barcode area 303_11.

[0140] The label position information of at least one label area and the barcode position information of at least one barcode area can be obtained according to the object image 301. For example, a rectangular coordinate system can be established with the upper left corner of the object image 301 as the origin.

[0141] In this case, the location information of the face sheet area 302 can be determined, that is, the upper left corner point M1 (m x1 , m y1 ) and the lower right corner point M2(m x2 , m y2 ). Determine the location information of the face sheet area 303, that is, the upper left corner point M3 (m x3 , m y3 ) and the lower right corner point M4(m x4 , m y4 ).

[0142] On this basis, the barcode position information of the barcode area 302_11 can be determined, that is, the upper left corner point T1 (t x1 , t y1 ) and the lower right corner point T2(t x2 , t y2 ). Determine the barcode position information of the barcode area 302_21, that is, the upper left corner point T3 (t x3 , t y3 ) and the lower right corner point T4(t x4 , t y4 ). Determine the barcode position information of the barcode area 303_11, that is, the upper left corner point T5 (t x5 , t y5 ) and the lower right corner point T6(t x6 , t y6 ).

[0143] On this basis, the text position information of the text area 302_12 corresponding to the barcode area 302_11 can be determined, that is, the upper left corner point W1 (w x1 , w y1 ) and the lower right corner point W2(w x2 , w y2 ). Determine the text position information of the text area 302_22 corresponding to the barcode area 302_21, that is, the upper left corner point W3 (w x3 , w y3 ) and the lower right corner point W4(w x4 , w y4 ). Determine the text position information of the text area 303_12 corresponding to the barcode area 303_11, that is, the upper left corner point W5 (w x5 , w y5 ) and the lower right corner point W6 (w x6 , w y6 ).

[0144] According to an embodiment of the present disclosure, operation S210 may include the following operations.

[0145] Perform feature extraction on the object image to obtain an object feature map of at least one scale. Perform fusion on the object feature map of at least one scale to obtain a fused feature map. Determine the position information, category information and confidence of at least one region based on the fused feature map, wherein the confidence represents the credibility of the category information, and the category information includes the face sheet region and the barcode region. Determine at least one face sheet region and at least one barcode region from at least one region based on the confidence and category information. Determine the face sheet position information of at least one face sheet region and the barcode position information of at least one barcode region based on the position information of at least one region, at least one face sheet region and at least one barcode region.

[0146] According to an embodiment of the present disclosure, a scale may refer to an image resolution. Each scale may have at least one object feature map corresponding to the scale. Feature extraction may be performed on an object image to obtain an object feature map of at least one scale. For example, an object image may be processed using a cross-stage local extraction method to obtain an object feature map of at least one scale. The object feature map of at least one scale may be fused to obtain a fused feature map. For example, a path aggregation method may be used to process an instrument feature map of at least one scale to obtain a fused feature map. The path aggregation method may refer to an aggregation method from a small scale to a large scale. The path aggregation method makes it easier for low-level information to be transmitted to high-level information.

[0147] According to an embodiment of the present disclosure, at least one first target category information can be determined from the category information of at least one area. When it is determined that the confidence corresponding to the first target category information is greater than or equal to the first predetermined confidence threshold, the area corresponding to the first target category information is determined as a face order area. The first target category information can characterize the category information that the area is a face order area. After obtaining at least one face order area, the face order location information of each of the at least one face order area can be determined based on the location information of the at least one area and the at least one face order area.

[0148] According to an embodiment of the present disclosure, at least one second target category information can be determined from the category information of at least one region. When it is determined that the confidence corresponding to the second target category information is greater than or equal to the second predetermined confidence threshold, the region corresponding to the second target category information is determined as a barcode region. The second target category information can characterize the category information that the region is a barcode region. After obtaining at least one barcode region, the barcode position information of each of the at least one barcode region can be determined based on the position information of the at least one region and the at least one barcode region.

[0149] According to an embodiment of the present disclosure, since an object feature map at at least one scale can provide richer information, an object feature map at at least one scale is used to obtain the respective face sheet position information of at least one face sheet area and the respective barcode position information of at least one barcode area, thereby improving the accuracy of the respective category information and position information of at least one area.

[0150] Figure 3B An example schematic diagram of a process of determining object image information according to an object image of an object to be verified indicated by the object verification instruction in response to receiving an object verification instruction according to an embodiment of the present disclosure is schematically shown.

[0151] like Figure 3B As shown, in 300B, feature extraction may be performed on the object image 304 to obtain an object feature map 305 of at least one scale. The object feature map 305 of at least one scale is fused to obtain a fused feature map 306. According to the fused feature map 306, position information 3071, category information 3072, and confidence 3073 of at least one region are determined.

[0152] At least one label area 3081 and at least one barcode area 3082 may be determined from at least one area based on the confidence 3073 and the category information 3072 .

[0153] The waybill location information 309_1 of at least one waybill area 308_1 and the barcode location information 309_2 of at least one barcode area 308_2 can be determined based on the location information 3071 of at least one area, at least one waybill area 308_1 and at least one barcode area 308_2.

[0154] Figure 4 The flowchart of a method for determining a target label area image according to an object image, label position information of at least one label area, and barcode position information of at least one barcode area is schematically shown according to an embodiment of the present disclosure.

[0155] like Figure 4 As shown, the method includes operations S421 to S423.

[0156] In operation S421, at least one candidate form location information is determined based on the form location information of at least one form area and the barcode location information of at least one barcode area.

[0157] In operation S422, target face order position information is determined based on at least one candidate face order position information.

[0158] In operation S423, a target surface single region image is determined from the object image according to the target surface single position information.

[0159] According to an embodiment of the present disclosure, operation S421 may include the following operations.

[0160] According to the barcode position information of the at least one barcode area, the barcode center point of the at least one barcode area is determined. For each piece of face order position information in the face order position information of the at least one face order area, if any barcode center point of the at least one barcode center point matches the face order position information, the face order position information is determined as candidate face order position information.

[0161] According to an embodiment of the present disclosure, the barcode center point of at least one barcode area can be determined according to the barcode position information of at least one barcode area. For example, the barcode position information is the upper left corner point of the barcode (x1, y1) and the lower right corner point of the barcode (x2, y2). In this case, the barcode center point can be determined according to the upper left corner point of the barcode and the lower right corner point of the barcode.

[0162] According to an embodiment of the present disclosure, after obtaining the barcode center point of each barcode region, for each face sheet position information, it can be determined whether any barcode center point in at least one barcode center point matches the face sheet position information, that is, whether any barcode center point is located within the face sheet position information. In the case where it is determined that any barcode center point in at least one barcode center point is located within the face sheet position information, the face sheet position information can be determined as candidate face sheet position information. In the case where it is determined that no barcode center point in at least one barcode center point is located within the face sheet position information, the face sheet position information can be deleted. In the case where no candidate face sheet position information exists in the face sheet position information of each at least one face sheet region, it can be determined that the object verification has failed.

[0163] According to an embodiment of the present disclosure, the candidate face single position information includes at least a first candidate face single edge point and a second candidate face single edge point.

[0164] According to an embodiment of the present disclosure, operation S422 may include the following operations.

[0165] For each candidate face single position information in at least one candidate face single position information, a fifth difference is determined according to the horizontal coordinate of the first candidate face single edge point and the horizontal coordinate of the second candidate face single edge point. A sixth difference is determined according to the vertical coordinate of the first candidate face single edge point and the vertical coordinate of the second candidate face single edge point. A candidate face single area corresponding to the candidate face single position information is determined according to the fifth difference and the sixth difference. The target face single position information is determined according to the candidate face single area corresponding to each of the at least one candidate face single position information.

[0166] According to an embodiment of the present disclosure, the area of ​​a candidate face is calculated as shown in the following formula (1).

[0167] S1=(x4-x3)×(y4-y3) (1)

[0168] According to an embodiment of the present disclosure, S1 may represent the area of ​​the candidate face. x3 may represent the horizontal coordinate of the first candidate face edge point. y3 may represent the vertical coordinate of the first candidate face edge point. x4 may represent the horizontal coordinate of the second candidate face edge point. y4 may represent the vertical coordinate of the second candidate face edge point. (x4-x3) may represent the fifth difference. (y4-y3) may represent the sixth difference.

[0169] According to an embodiment of the present disclosure, taking the first candidate face single edge point (x3, y3) and the second candidate face single edge point (x4, y4) as examples, the fifth difference (x4-x3) and the sixth difference (y4-y3) can be calculated. The candidate face single area (x4-x3)×(y4-y3) corresponding to the candidate face single position information can be determined based on the fifth difference (x4-x3) and the sixth difference (y4-y3). After respectively determining the candidate face single areas corresponding to at least one candidate face single position information, the target face single position information that meets the second predetermined condition can be determined based on at least one candidate face single area. The second predetermined condition can be set according to actual business needs and is not limited here. For example, the second predetermined condition can be the maximum area among the candidate face single areas.

[0170] According to the embodiments of the present disclosure, since the target face order position information is determined based on at least one candidate face order position information, and at least one candidate face order position information is determined based on the face order position information of at least one face order area and the barcode position information of at least one barcode area, by determining the target face order area image from the object image based on the target face order position information, it is possible to exclude face order false detection frames in which no barcode center point falls within the face order area, thereby screening out correct and valid target face order area images, thereby improving the accuracy of object verification.

[0171] Figure 5 The figure schematically shows an example process of determining a target face sheet area image based on an object image, face sheet position information of at least one face sheet area, and barcode position information of at least one barcode area according to an embodiment of the present disclosure.

[0172] like Figure 5 As shown, in 500, the barcode center point 502 of at least one barcode area can be determined according to the barcode position information 501 of at least one barcode area. After the barcode center point 502 is obtained, operation S510 can be performed.

[0173] In operation S510, does the barcode center point 502 match the label location information 503?

[0174] If yes, the waybill location information 503 can be determined as candidate waybill location information 504. If no, the process can be terminated.

[0175] The candidate face single position information 504 includes at least a first candidate face single edge point 5041 and a second candidate face single edge point 5042. A fifth difference 505 may be determined based on the abscissa of the first candidate face single edge point 5041 and the abscissa of the second candidate face single edge point 5042. A sixth difference 506 may be determined based on the ordinate of the first candidate face single edge point 5041 and the ordinate of the second candidate face single edge point 5042.

[0176] The candidate face order area 507 corresponding to the candidate face order position information 504 may be determined according to the fifth difference 505 and the sixth difference 506. The target face order position information 508 may be determined according to the candidate face order area 507 corresponding to at least one candidate face order position information 504.

[0177] Figure 6 The flowchart of a method for determining target text information according to the barcode position information of at least one barcode area, the text information and text position information of at least one text area according to an embodiment of the present disclosure is schematically shown.

[0178] like Figure 6 As shown, the method includes operations S641 to S645.

[0179] In operation S641, candidate text information and candidate text position information of at least one candidate text region are determined according to the text information and text position information of at least one text region.

[0180] In operation S642, at least one first candidate barcode position information is determined according to the target surface single position information and the barcode center point of each of the at least one barcode regions.

[0181] In operation S643, second candidate barcode position information is determined according to at least one first candidate barcode position information.

[0182] In operation S644, target barcode position information is determined according to the second candidate barcode position information.

[0183] In operation S645, target text information is determined based on the target barcode position information and the candidate text information and candidate text position information of each of the at least one candidate text region.

[0184] According to an embodiment of the present disclosure, operation S642 may include the following operations.

[0185] For each barcode center point in the barcode center points of at least one barcode area, when the barcode center point matches the target surface single position information, the first candidate barcode position information is determined according to the barcode area corresponding to the barcode center point.

[0186] According to an embodiment of the present disclosure, after obtaining the target face order position information, for each barcode center point, it can be determined whether the barcode center point matches the target face order position information, that is, whether the barcode center point is located within the target face order position information. In the case where it is determined that the barcode center point is located within the target face order position information, the first candidate barcode position information can be determined based on the barcode area corresponding to the barcode center point. In the case where it is determined that the barcode center point is not located in the target face order position information, the barcode position information can be deleted.

[0187] According to an embodiment of the present disclosure, the first candidate barcode position information at least includes a first candidate barcode edge point and a second candidate barcode edge point.

[0188] According to an embodiment of the present disclosure, operation S643 may include the following operations.

[0189] For each first candidate barcode position information in at least one first candidate barcode position information, a first difference is determined according to the horizontal coordinate of the first candidate barcode edge point and the horizontal coordinate of the second candidate barcode edge point. A second difference is determined according to the vertical coordinate of the first candidate barcode edge point and the vertical coordinate of the second candidate barcode edge point. A candidate barcode area corresponding to the first candidate barcode position information is determined according to the first difference and the second difference. A second candidate barcode position information is determined according to the candidate barcode area corresponding to each of the at least one first candidate barcode position information.

[0190] According to an embodiment of the present disclosure, the area of ​​the candidate barcode is calculated as shown in the following formula (2).

[0191] S2=(x6-x5)×(y6-y5) (2)

[0192] According to an embodiment of the present disclosure, S2 may represent the area of ​​the candidate barcode. x5 may represent the horizontal coordinate of the edge point of the first candidate barcode. y5 may represent the vertical coordinate of the edge point of the first candidate barcode. x6 may represent the horizontal coordinate of the edge point of the second candidate barcode. y6 may represent the vertical coordinate of the edge point of the second candidate barcode. (x6-x5) may represent the first difference. (y6-y5) may represent the second difference.

[0193] According to an embodiment of the present disclosure, taking the first candidate barcode edge point (x5, y5) and the second candidate barcode edge point (x6, y6) as examples, the first difference (x6-x5) and the second difference (y6-y5) can be calculated. The candidate barcode area (x6-x5)×(y6-y5) corresponding to the first candidate barcode position information can be determined based on the first difference (x6-x5) and the second difference (y6-y5). After respectively determining the candidate barcode areas corresponding to at least one candidate barcode position information, the second candidate barcode position information that meets the third predetermined condition can be determined based on at least one candidate barcode area. The third predetermined condition can be set according to actual business needs and is not limited here. For example, the third predetermined condition can be the maximum area among the candidate barcode areas.

[0194] Fig. 7A An example schematic diagram of a process of determining second candidate barcode position information based on at least one first candidate barcode position information according to an embodiment of the present disclosure is schematically shown.

[0195] like Fig. 7A As shown, in 700, operation S710 may be performed for each barcode center point 701 of the barcode center points of at least one barcode region.

[0196] In operation S710, does the barcode center point match the target face sheet position information? If so, the first candidate barcode position information 703 can be determined based on the barcode area corresponding to the barcode center point 701. If not, the process can be terminated.

[0197] The first candidate barcode position information 703 may include at least a first candidate barcode edge point 703_1 and a second candidate barcode edge point 703_2. A first difference 704 may be determined based on the abscissa of the first candidate barcode edge point 703_1 and the abscissa of the second candidate barcode edge point 703_2. A second difference 705 may be determined based on the ordinate of the first candidate barcode edge point 703_1 and the ordinate of the second candidate barcode edge point 703_2.

[0198] The candidate barcode area 706 corresponding to the first candidate barcode position information 703 can be determined according to the first difference 704 and the second difference 705. The second candidate barcode position information 707 can be determined according to the candidate barcode area 706 corresponding to at least one first candidate barcode position information 703.

[0199] According to an embodiment of the present disclosure, the second candidate barcode position information at least includes a third candidate barcode edge point and a fourth candidate barcode edge point.

[0200] According to an embodiment of the present disclosure, operation S644 may include the following operations.

[0201] A third difference is determined based on the horizontal coordinate of the third candidate barcode edge point and the horizontal coordinate of the fourth candidate barcode edge point. A fourth difference is determined based on the vertical coordinate of the third candidate barcode edge point and the vertical coordinate of the fourth candidate barcode edge point. When the third difference is greater than or equal to the fourth difference, the second candidate barcode position information is processed according to the first preset extension rule to obtain the target barcode position information. When the third difference is less than the fourth difference, the second candidate barcode position information is processed according to the second preset extension rule to obtain the target barcode position information.

[0202] According to the embodiments of the present disclosure, for the description of the third difference and the fourth difference, reference may be made to the above related contents regarding the first difference and the second difference, which will not be repeated here.

[0203] According to an embodiment of the present disclosure, the third difference value can be used to characterize the width of the barcode area. The fourth difference value can be used to characterize the height of the barcode area. When the third difference value is greater than or equal to the fourth difference value, it can be determined that the width of the barcode area is greater than or equal to the length, that is, the barcode direction is horizontal. In this case, the second candidate barcode position information can be subjected to region of interest (ROI) expansion processing according to the first preset expansion rule to obtain the target barcode position information.

[0204] According to an embodiment of the present disclosure, when the third difference is less than the fourth difference, it can be determined that the width of the barcode area is less than the length, that is, the barcode direction is vertical and longitudinal. In this case, the second candidate barcode position information can be subjected to an area of ​​interest expansion process according to a second preset expansion rule to obtain the target barcode position information. The target barcode position information may include a first target barcode edge point and a second target barcode edge point.

[0205] According to an embodiment of the present disclosure, the first preset expansion rule can be applied to the case where the barcode direction is horizontal. The first preset expansion rule may include expanding the barcode area by a first predetermined distance in the horizontal direction and a second predetermined distance in the vertical direction. The first predetermined distance and the second predetermined distance can be set according to actual business needs and are not limited here. For example, the first predetermined distance may be 1 / 4 of the width, and the second predetermined distance may be 1 / 2 of the height.

[0206] For example, taking the third candidate barcode edge point (x7, y8) and the fourth candidate barcode edge point (x7, y8) as examples, the third difference (x8-x7) and the fourth difference (y8-y7) can be calculated.

[0207] According to an embodiment of the present disclosure, when the barcode direction is horizontal, the target barcode position information is calculated as shown in the following equations (3) to (6).

[0208] x7′=x7-w / 4 ,0≤x7′ (3)

[0209] x8′=x 8+w / 4 ,x8′≤W (4)

[0210] y7′=y 7-h / 2 ,0≤y7′ (5)

[0211] y8′=y 8+h / 2 , y7′≤H (6)

[0212] According to an embodiment of the present disclosure, x7 may represent the horizontal coordinate of the third candidate barcode edge point. y7 may represent the vertical coordinate of the third candidate barcode edge point. x8 may represent the horizontal coordinate of the fourth candidate barcode edge point. y8 may represent the vertical coordinate of the fourth candidate barcode edge point. w may represent the third difference (x8-x7), that is, the width of the barcode area. h may represent the fourth difference (y8-y7), that is, the height of the barcode area. W may represent the width of the object image. H may represent the height of the object image. x7′ may represent the horizontal coordinate of the first target barcode edge point. y7′ may represent the vertical coordinate of the first target barcode edge point. x8′ may represent the horizontal coordinate of the second target barcode edge point. y8′ may represent the vertical coordinate of the second target barcode edge point.

[0213] According to an embodiment of the present disclosure, the second preset expansion rule can be applied to the case where the barcode direction is vertical. The second preset expansion rule may include expanding the barcode area by a third predetermined distance in the horizontal direction and a fourth predetermined distance in the vertical direction. The third predetermined distance and the fourth predetermined distance can be set according to actual business needs and are not limited here. For example, the third predetermined distance can be 1 / 2 of the width, and the fourth predetermined distance can be 1 / 4 of the height.

[0214] According to an embodiment of the present disclosure, when the barcode direction is vertical, the target barcode position information is calculated as shown in the following equations (7) to (10).

[0215] x7′=x 7-w / 2 ,0≤x7′ (7)

[0216] x8′=x 8+w / 2 ,x8′≤W (8)

[0217] y7′=y 7-h / 4 ,0≤y7′ (9)

[0218] y8′=y 8+h / 4 , y7′≤H (10)

[0219] Figure 7BAn example schematic diagram of a process of determining target barcode position information based on second candidate barcode position information according to an embodiment of the present disclosure is schematically shown.

[0220] like Figure 7B As shown in 700B, the second candidate barcode position information 708 may include at least a third candidate barcode edge point 708_1 and a fourth candidate barcode edge point 708_2. A third difference 709 may be determined based on the abscissa of the third candidate barcode edge point 708_1 and the abscissa of the fourth candidate barcode edge point 708_2. A fourth difference 710 may be determined based on the ordinate of the third candidate barcode edge point 708_1 and the ordinate of the fourth candidate barcode edge point 708_2.

[0221] After obtaining the third difference value 709 and the fourth difference value 710, operation S720 may be performed.

[0222] In operation S720, is the third difference greater than or equal to the fourth difference?

[0223] If so, the second candidate barcode position information 708 may be processed according to the first preset extension rule to obtain the target barcode position information 711 .

[0224] If not, the second candidate barcode position information 708 may be processed according to a second preset extension rule to obtain the target barcode position information 711 .

[0225] According to an embodiment of the present disclosure, operation S641 may include the following operations.

[0226] In response to detecting an input operation of a user, input text information is obtained. For each text information in the text information of each of the at least one text area, the number of characters of the text information is determined. When the number of characters is greater than or equal to a preset threshold, a target number of characters is determined. Based on the target number of characters, sub-text information corresponding to the target number of characters is determined from the text information. Character matching is performed on the input text information and the sub-text information to obtain a character matching result. When the character matching result indicates that the input text information and the sub-text information match, candidate text information and candidate text position information are determined based on the text area corresponding to the text information.

[0227] According to an embodiment of the present disclosure, a user may perform an input operation while initiating an object verification operation. The input text information may be used to characterize an object identifier. For example, the object identifier may be a package number.

[0228] According to an embodiment of the present disclosure, the input text information can be represented as S h , the text information of at least one text region can be represented as a text information set S tr ={s1, s2, ..., sk , ..., s K}. K can be an integer greater than or equal to 1, k∈{1, 2, …, (K-1), K}. You can set the text information s k The preset number of characters N can be used to represent the length of the standard text information.

[0229] According to an embodiment of the present disclosure, for a text information set S tr Each text message in s k , you can traverse each text information s separately k For each text message s k The number of characters N2, when the number of characters N2 is greater than or equal to the preset threshold value N1, the target number of characters N3 can be determined. When the number of characters N2 is less than the preset threshold value N1, it can be determined that the object check has not passed. The preset threshold value N1 can be used to characterize the shortest number of digits for a partial successful match. The preset threshold value N1 can be set according to actual business needs and is not limited here. It only needs to be less than or equal to the preset number of characters N. For example, the preset number of characters N can be 20, and the preset threshold value N1 can be 9. In this case, it can be characterized that the longest number of digits for continuous character matching is 20, and the shortest number of digits for continuous character matching is 9.

[0230] According to an embodiment of the present disclosure, the target number of characters N3 can be obtained from the text information s k The subtext information corresponding to the target number of characters is determined in the target number of characters. The target number of characters N3 can be set according to actual business needs and is not limited here. For example, the target number of characters N3 can belong to the character number set S N3 ={N2, N2-1, ..., N1+1, ..., N1}, that is, the target number of characters N3 can be an integer between the number of characters N2 and the preset threshold N1.

[0231] According to an embodiment of the present disclosure, the character quantity set S can be traversed from large to small N3 For each target character number N3, we can get the value from the text information s k The subtext information S corresponding to the target number of characters N3 is determined n For example, from the text information s k The subtext information S corresponding to the target character number N3 is obtained at position index i=0 n . You can input text information S h and subtext information S n Perform character matching to obtain character matching results. The character matching results can be used to represent the input text information S h and subtext information S nWhether it matches. The character matching result represents the input text information S h and subtext information S n Match, that is, input text information S h Subtext information S n In the case of, you can change the number of successful matches N success , and will be combined with the subtext information S n Corresponding text information k Add to candidate text information set S u Number of successful matches N success The initial value is 0, and the candidate text information set S u Initially an empty set.

[0232] According to an embodiment of the present disclosure, in the case where i+N3>N2, that is, the sub-text information S with a length of the target number of characters N3 n The last index exceeds the text information s k If the last character is found, the matching of the target character quantity N3 can be stopped, the target character quantity N3 is reduced by 1, and the matching of the next target character quantity N3 is continued.

[0233] According to an embodiment of the present disclosure, when traversing the character quantity set S N3 After all the elements in the success >0, the input text information S can be determined h and text message S h The match is successful, that is, the text information S in the object image h Input text information S input by the user input operation h Consistent. After the number of successful matches N success ≤0, the input text information S can be determined h and text message S h Match failed.

[0234] According to an embodiment of the present disclosure, operation S645 may include the following operations.

[0235] For each candidate text position information in the candidate text position information of at least one candidate text area, when the candidate text position information matches the target barcode position information, the target text information is determined according to the candidate text area corresponding to the candidate text position information.

[0236] According to an embodiment of the present disclosure, after obtaining the candidate text information set S u Afterwards, the candidate text information set S can be traversed uFor each candidate text information, match the target barcode position information with the candidate text position information corresponding to the candidate text information. When the candidate text position information matches the target barcode position information, that is, the candidate text position information is located within the target barcode position information, the target text information can be determined based on the candidate text area corresponding to the candidate text position information.

[0237] For example, the candidate text position information may include a first candidate text edge point (e.g., an upper left corner point), a second candidate text edge point (e.g., an upper right corner point), a third candidate text edge point (e.g., a lower left corner point), and a fourth candidate text edge point (e.g., a lower right corner point). In the case where there are two or more corner points located within the target barcode position information, it can be determined that the candidate text position information matches the target barcode position information, that is, the candidate text information is a single number with the largest barcode.

[0238] Figure 7C An example schematic diagram of a process of determining target text information according to target barcode position information and respective candidate text information and candidate text position information of at least one candidate text region according to an embodiment of the present disclosure is schematically shown.

[0239] like Figure 7C As shown, in 700C, in response to detecting the user's input operation, input text information 716 may be obtained. For each text information 712 in the text information of at least one text area, the number of characters 713 of the text information 712 may be determined. After obtaining the number of characters 713 of the text information 712, operation S730 may be performed.

[0240] In operation S730, is the number of characters greater than or equal to a preset threshold? If so, a target number of characters may be determined 714. If not, the process may end.

[0241] Subtext information 715 corresponding to the target character number 714 may be determined from the text information 712 according to the target character number 714. Character matching is performed on the input text information 716 and the subtext information 715 to obtain a character matching result 717. After the character matching result 717 is obtained, operation S740 may be performed.

[0242] In operation S740, does the character matching result indicate that the input text information matches the subtext information? If so, candidate text information 718 and candidate text position information 719 may be determined based on the text area corresponding to the text information 712. If not, the process may be terminated. After obtaining the candidate text position information 719, operation S750 may be performed.

[0243] In operation S750, does the candidate text position information 719 match the target barcode position information 720? If so, the target text information 721 can be determined based on the candidate text area corresponding to the candidate text position information 719. If not, the process can be terminated.

[0244] According to an embodiment of the present disclosure, operation S250 may include the following operations.

[0245] Based on the preset text information, the target text information is regularized and verified to obtain a regularized verification result. When the regularized verification result indicates that the preset text information and the target text information match, an object verification result indicating that the object verification has passed is determined. When the regularized verification result indicates that the preset text information and the target text information do not match, an object verification result indicating that the object verification has not passed is determined.

[0246] According to an embodiment of the present disclosure, the preset text information can be set according to actual business needs and is not limited here. For example, the preset text information can be "\w+-\w+-\w+-", and "\w+" can represent a character consisting of at least one letter or number in the middle of the "-". In this case, the target text information can be regularized and verified based on the preset text information "\w+-\w+-\w+-" to obtain a regularized verification result.

[0247] When the regularized verification result indicates that the preset text information and the target text information match, that is, the order number includes the package number, an object verification result indicating that the object verification has passed may be determined.

[0248] When the regularized verification result indicates that the preset text information and the target text information do not match, that is, the order number does not contain the package number, the object verification result indicating that the object verification has failed can be determined. The object image information corresponding to the object to be verified can be fed back to the upstream of the production order for correction, so as to reduce the sorting return flow of packages without package numbers.

[0249] Figure 8 An example schematic diagram of an object verification process according to an embodiment of the present disclosure is schematically shown.

[0250] like Figure 8 As shown, in 800, in response to receiving an object verification instruction, the object image 801 of the object to be verified indicated by the object verification instruction can be input into the target detection model 802 to obtain the waybill position information of each waybill area 803_1 and the waybill area 803_2, as well as the barcode position information of each barcode area 803_11, the barcode area 803_12, and the barcode area 803_21.

[0251] The target order area image 804 can be determined based on the order position information of the object image 801, order area 803_1, and order area 803_2, and the barcode position information of the barcode area 803_11, barcode area 803_12, and barcode area 803_21.

[0252] The target surface single area image 804 can be input into the text detection model and the text recognition model 805, and the text position information and text information "XX10000-1-1" of the text area 806_12 corresponding to the barcode area 806_11, and the text position information and text information "XX10000" of the text area 806_22 corresponding to the barcode area 806_21 are output.

[0253] The target text information 807 can be determined to be “XX10000-1-1” based on the barcode position information of the barcode area 806_11, the text position information of the text area 806_12, the barcode position information of the barcode area 806_21, and the text position information of the text area 806_22.

[0254] Based on the preset text information and according to the target text information 807 , the object to be verified can be verified to obtain the object verification result 808 .

[0255] The above are only exemplary embodiments, but are not limited thereto, and may also include other object verification methods known in the art, as long as the efficiency and accuracy of object verification can be improved.

[0256] Fig. 9 The block diagram of the object verification device according to the embodiment of the present disclosure is schematically shown.

[0257] like Fig. 9 As shown, the object verification device 900 may include a first determination module 910 , a second determination module 920 , an identification module 930 , a third determination module 940 and a verification module 950 .

[0258] The first determination module 910 is used to determine object image information in response to receiving an object verification instruction and according to the object image of the object to be verified indicated by the object verification instruction, wherein the object image information includes the face sheet position information of each at least one face sheet area and the barcode position information of each at least one barcode area.

[0259] The second determination module 920 is used to determine the target document area image according to the object image, the document position information of at least one document area and the barcode position information of at least one barcode area.

[0260] The recognition module 930 is used to recognize the single-region image of the target surface to obtain recognition information, wherein the recognition information includes text information and text position information of at least one text region.

[0261] The third determination module 940 is used to determine the target text information according to the barcode position information of each of the at least one barcode area, the text information and the text position information of each of the at least one text area.

[0262] The verification module 950 is used to verify the object to be verified according to the target text information to obtain the object verification result.

[0263] According to an embodiment of the present disclosure, the third determination module 940 may include a first determination submodule, a second determination submodule, a third determination submodule, a fourth determination submodule, and a fifth determination submodule.

[0264] The first determination submodule is used to determine candidate text information and candidate text position information of at least one candidate text region according to the text information and text position information of at least one text region.

[0265] The second determination submodule is used to determine at least one first candidate barcode position information according to the target surface single position information and the barcode center point of each of the at least one barcode area.

[0266] The third determination submodule is used to determine the second candidate barcode position information according to at least one first candidate barcode position information.

[0267] The fourth determination submodule is used to determine the target barcode position information according to the second candidate barcode position information.

[0268] The fifth determination submodule is used to determine the target text information according to the target barcode position information and the candidate text information and candidate text position information of at least one candidate text region.

[0269] According to an embodiment of the present disclosure, the first determining submodule may include an acquiring unit, a first determining unit, a second determining unit, a third determining unit, a matching unit, and a fourth determining unit.

[0270] The acquiring unit is used to acquire input text information in response to detecting an input operation of the user.

[0271] The first determining unit is used to determine the number of characters of each text information in the text information of at least one text area.

[0272] The second determining unit is used to determine a target number of characters when the number of characters is greater than or equal to a preset threshold.

[0273] The third determining unit is used to determine sub-text information corresponding to the target number of characters from the text information according to the target number of characters.

[0274] The matching unit is used to perform character matching on the input text information and the sub-text information to obtain a character matching result.

[0275] The fourth determining unit is used to determine candidate text information and candidate text position information according to a text area corresponding to the text information when the character matching result indicates that the input text information and the subtext information match.

[0276] According to an embodiment of the present disclosure, the second determining submodule may include a fifth determining unit.

[0277] The fifth determination unit is used to determine the first candidate barcode position information according to the barcode area corresponding to the barcode center point for each barcode center point of the respective barcode center points of at least one barcode area, when the barcode center point matches the target surface single position information.

[0278] According to an embodiment of the present disclosure, the first candidate barcode position information at least includes a first candidate barcode edge point and a second candidate barcode edge point.

[0279] According to an embodiment of the present disclosure, the third determining submodule may include a sixth determining unit, a seventh determining unit, an eighth determining unit, and a ninth determining unit.

[0280] The sixth determining unit is configured to determine, for each first candidate barcode position information in at least one first candidate barcode position information, a first difference value according to a horizontal coordinate of a first candidate barcode edge point and a horizontal coordinate of a second candidate barcode edge point.

[0281] The seventh determining unit is used to determine the second difference value according to the ordinate of the first candidate barcode edge point and the ordinate of the second candidate barcode edge point.

[0282] The eighth determining unit is used to determine the candidate barcode area corresponding to the first candidate barcode position information according to the first difference and the second difference.

[0283] The ninth determining unit is used to determine the second candidate barcode position information according to the candidate barcode area corresponding to each of the at least one first candidate barcode position information.

[0284] According to an embodiment of the present disclosure, the second candidate barcode position information at least includes a third candidate barcode edge point and a fourth candidate barcode edge point.

[0285] According to an embodiment of the present disclosure, the fourth determining submodule may include a tenth determining unit, an eleventh determining unit, a first processing unit, and a second processing unit.

[0286] The tenth determining unit is used to determine a third difference value according to the horizontal coordinate of the third candidate barcode edge point and the horizontal coordinate of the fourth candidate barcode edge point.

[0287] The eleventh determining unit is used to determine a fourth difference value according to the ordinate of the third candidate barcode edge point and the ordinate of the fourth candidate barcode edge point.

[0288] The first processing unit is used to process the second candidate barcode position information according to the first preset expansion rule to obtain the target barcode position information when the third difference is greater than or equal to the fourth difference.

[0289] The second processing unit is used to process the second candidate barcode position information according to the second preset expansion rule to obtain the target barcode position information when the third difference is less than the fourth difference.

[0290] According to an embodiment of the present disclosure, the fifth determining submodule may include a twelfth determining unit.

[0291] The twelfth determination unit is used to determine the target text information according to the candidate text area corresponding to the candidate text position information for each candidate text position information in the respective candidate text position information of at least one candidate text area, when the candidate text position information matches the target barcode position information.

[0292] According to an embodiment of the present disclosure, the first determination module 910 may include a feature extraction submodule, a fusion submodule, a sixth determination submodule, a seventh determination submodule, and an eighth determination submodule.

[0293] The feature extraction submodule is used to extract features from the object image to obtain an object feature map of at least one scale.

[0294] The fusion submodule is used to fuse the object feature maps of at least one scale to obtain a fused feature map.

[0295] The sixth determination submodule is used to determine the position information, category information and confidence of at least one area based on the fused feature map, wherein the confidence represents the credibility of the category information, and the category information includes the face sheet area and the barcode area.

[0296] The seventh determination submodule is used to determine at least one label area and at least one barcode area from at least one area based on the confidence and category information.

[0297] The eighth determination submodule is used to determine the waybill position information of at least one waybill area and the barcode position information of at least one barcode area based on the position information of at least one area, at least one waybill area and at least one barcode area.

[0298] According to an embodiment of the present disclosure, the second determining module 920 may include a ninth determining submodule, a tenth determining submodule, and an eleventh determining submodule.

[0299] The ninth determination submodule is used to determine at least one candidate waybill position information based on the waybill position information of each at least one waybill area and the barcode position information of each at least one barcode area.

[0300] The tenth determination submodule is used to determine the target face order position information based on at least one candidate face order position information.

[0301] The eleventh determination submodule is used to determine the target surface single area image from the object image according to the target surface single position information.

[0302] According to an embodiment of the present disclosure, the ninth determining submodule may include a thirteenth determining unit and a fourteenth determining unit.

[0303] The thirteenth determining unit is used to determine the barcode center point of each of the at least one barcode areas according to the barcode position information of each of the at least one barcode areas.

[0304] The fourteenth determination unit is used to determine each piece of face sheet position information in the face sheet position information of at least one face sheet area as candidate face sheet position information when any barcode center point of at least one barcode center point matches the face sheet position information.

[0305] According to an embodiment of the present disclosure, the candidate face single position information includes at least a first candidate face single edge point and a second candidate face single edge point.

[0306] According to an embodiment of the present disclosure, the tenth determining submodule may include a fifteenth determining unit, a sixteenth determining unit, a seventeenth determining unit, and an eighteenth determining unit.

[0307] The fifteenth determination unit is used to determine, for each candidate face single position information in the at least one candidate face single position information, a fifth difference value according to the horizontal coordinate of the first candidate face single edge point and the horizontal coordinate of the second candidate face single edge point.

[0308] The sixteenth determining unit is used to determine a sixth difference value according to the longitudinal coordinate of the first candidate single edge point and the longitudinal coordinate of the second candidate single edge point.

[0309] The seventeenth determining unit is used to determine the area of ​​the candidate face order corresponding to the candidate face order position information according to the fifth difference and the sixth difference.

[0310] An eighteenth determination unit is used to determine the target surface order position information according to the candidate surface order areas respectively corresponding to at least one candidate surface order position information.

[0311] According to an embodiment of the present disclosure, the verification module 950 may include a verification submodule and a twelfth determination submodule.

[0312] The verification submodule is used to perform regularization verification on the target text information based on the preset text information to obtain a regularization verification result.

[0313] The twelfth determination submodule is used to determine an object verification result indicating that the object verification has passed when the regularization verification result indicates that the preset text information and the target text information match.

[0314] A thirteenth determination submodule is used to determine an object verification result indicating that the object verification has failed when the regularization verification result indicates that the preset text information and the target text information do not match.

[0315] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0316] For example, any of the first determination module 910, the second determination module 920, the identification module 930, the third determination module 940 and the verification module 950 can be combined in one module / unit / subunit for implementation, or any of the modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more modules / units / subunits in these modules / units / subunits can be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to an embodiment of the present disclosure, at least one of the first determination module 910, the second determination module 920, the identification module 930, the third determination module 940 and the verification module 950 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by a suitable combination of any of them. Alternatively, at least one of the first determination module 910, the second determination module 920, the identification module 930, the third determination module 940 and the verification module 950 may be at least partially implemented as a computer program module, which may perform a corresponding function when executed.

[0317] It should be noted that the object verification device part in the embodiment of the present disclosure corresponds to the object verification method part in the embodiment of the present disclosure. The description of the object verification device part specifically refers to the object verification method part, which will not be repeated here.

[0318] Fig.10 A block diagram of an electronic device suitable for implementing an object verification method according to an embodiment of the present disclosure is schematically shown. Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0319] like Fig.10As shown, the computer electronic device 1000 according to the embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1009 to the random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0320] In RAM 1003, various programs and data required for the operation of electronic device 1000 are stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Processor 1001 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1002 and / or RAM 1003. It should be noted that the program can also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0321] According to an embodiment of the present disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, etc.; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk, etc.; and a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage portion 1008 as needed.

[0322] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the processor 1001, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0323] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0324] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0325] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 1002 and / or the RAM 1003 described above and / or one or more memories other than the ROM 1002 and the RAM 1003 .

[0326] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the object verification method provided by the embodiment of the present disclosure.

[0327] When the computer program is executed by the processor 1001, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0328] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1009, and / or installed from the removable medium 1011. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0329] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0330] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0331] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An object verification method, comprising: In response to receiving the object verification instruction, determining object image information according to the object image of the object to be verified indicated by the object verification instruction, wherein the object image information includes the face sheet position information of each of at least one face sheet area and the bar code position information of each of at least one bar code area; Determine a target face order area image according to the object image, the face order position information of each of the at least one face order area, and the barcode position information of each of the at least one barcode area; Recognize the single-region image of the target surface to obtain recognition information, wherein the recognition information includes text information and text position information of at least one text region; Determining target text information according to the barcode position information of each of the at least one barcode area, the text information and text position information of each of the at least one text area; and According to the target text information, the object to be verified is verified to obtain an object verification result.

2. The method according to claim 1, wherein: The determining the target text information according to the barcode position information of each of the at least one barcode area, the text information and the text position information of each of the at least one text area comprises: Determining candidate text information and candidate text position information of at least one candidate text region according to the text information and text position information of the at least one text region; Determine at least one first candidate barcode position information according to the target surface single position information and the barcode center point of each of the at least one barcode area; Determine second candidate barcode position information according to the at least one first candidate barcode position information; Determining target barcode position information according to the second candidate barcode position information; and The target text information is determined according to the target barcode position information and the candidate text information and candidate text position information of at least one candidate text region.

3. The method according to claim 2, wherein: Determining candidate text information and candidate text position information of at least one candidate text region according to the text information and text position information of the at least one text region comprises: In response to detecting an input operation of a user, acquiring input text information; For each piece of text information in the respective text information of the at least one text area, Determining the number of characters in the text message; If the number of characters is greater than or equal to a preset threshold, determining a target number of characters; According to the target number of characters, determining subtext information corresponding to the target number of characters from the text information; Performing character matching on the input text information and the sub-text information to obtain a character matching result; and In the case where the character matching result indicates that the input text information and the sub-text information match, the candidate text information and the candidate text position information are determined according to a text region corresponding to the text information.

4. The method according to claim 2, wherein: The step of determining at least one first candidate barcode position information according to the target surface single position information and the barcode center point of each of the at least one barcode area comprises: For each barcode center point of the barcode center points of the at least one barcode region, In the case where the barcode center point matches the target surface single position information, the first candidate barcode position information is determined according to the barcode area corresponding to the barcode center point.

5. The method according to claim 2, wherein: The first candidate barcode position information at least includes a first candidate barcode edge point and a second candidate barcode edge point; The determining the second candidate barcode position information according to the at least one first candidate barcode position information comprises: For each first candidate barcode position information in the at least one first candidate barcode position information, Determine a first difference value according to the horizontal coordinate of the first candidate barcode edge point and the horizontal coordinate of the second candidate barcode edge point; Determine a second difference value according to the ordinate of the first candidate barcode edge point and the ordinate of the second candidate barcode edge point; Determining a candidate barcode area corresponding to the first candidate barcode position information according to the first difference and the second difference; and The second candidate barcode position information is determined according to the candidate barcode area corresponding to each of the at least one first candidate barcode position information.

6. The method according to claim 2, wherein: The second candidate barcode position information at least includes a third candidate barcode edge point and a fourth candidate barcode edge point; Determining the target barcode position information according to the second candidate barcode position information includes: Determine a third difference value according to the abscissa of the third candidate barcode edge point and the abscissa of the fourth candidate barcode edge point; Determine a fourth difference value according to the ordinate of the third candidate barcode edge point and the ordinate of the fourth candidate barcode edge point; In the case where the third difference is greater than or equal to the fourth difference, processing the second candidate barcode position information according to a first preset expansion rule to obtain the target barcode position information; and When the third difference is smaller than the fourth difference, the second candidate barcode position information is processed according to a second preset extension rule to obtain the target barcode position information.

7. The method according to claim 2, wherein: Determining the target text information according to the target barcode position information and the candidate text information and candidate text position information of at least one candidate text area comprises: For each piece of candidate text position information in the respective candidate text position information of the at least one candidate text region, In the case where the candidate text position information matches the target barcode position information, the target text information is determined according to the candidate text area corresponding to the candidate text position information.

8. The method according to any one of claims 1 to 7, wherein: In response to receiving the object verification instruction, determining the object image information according to the object image of the object to be verified indicated by the object verification instruction includes: Performing feature extraction on the object image to obtain an object feature map of at least one scale; Fusing the object feature map of the at least one scale to obtain a fused feature map; Determine, according to the fused feature map, the position information, the category information and the confidence of at least one region, wherein the confidence represents the credibility of the category information, and the category information includes the label region and the barcode region; Determining the at least one label area and the at least one barcode area from the at least one area according to the confidence level and the category information; and According to the position information of the at least one area, the at least one face sheet area and the at least one barcode area, the face sheet position information of each of the at least one face sheet area and the barcode position information of each of the at least one barcode area are determined.

9. The method according to any one of claims 1 to 7, wherein: Determining the target document area image according to the object image, the document position information of each of the at least one document area, and the barcode position information of each of the at least one barcode area comprises: Determine at least one candidate face sheet position information according to the face sheet position information of each of the at least one face sheet area and the barcode position information of each of the at least one barcode area; Determine the target face sheet location information according to the at least one candidate face sheet location information; and According to the target surface single position information, the target surface single area image is determined from the object image.

10. The method according to claim 9, wherein: The determining of at least one candidate face sheet position information according to the face sheet position information of each of the at least one face sheet area and the barcode position information of each of the at least one barcode area comprises: Determining the barcode center point of each of the at least one barcode area according to the barcode position information of each of the at least one barcode area; and For each piece of the waybill position information in the waybill position information of the at least one waybill area, When any barcode center point among the at least one barcode center point matches the waybill position information, the waybill position information is determined as the candidate waybill position information.

11. The method according to claim 9, wherein: The candidate face single position information includes at least a first candidate face single edge point and a second candidate face single edge point; The determining the target air order position information according to the at least one candidate air order position information comprises: For each candidate face order position information in the at least one candidate face order position information, Determine a fifth difference value according to the horizontal coordinate of the first candidate single edge point and the horizontal coordinate of the second candidate single edge point; Determine a sixth difference value according to the ordinate of the first candidate single face edge point and the ordinate of the second candidate single face edge point; Determine the candidate order area corresponding to the candidate order position information according to the fifth difference and the sixth difference; and The target surface order position information is determined according to the candidate surface order areas corresponding to each of the at least one candidate surface order position information.

12. The method according to any one of claims 1 to 7, wherein: The verifying the object to be verified according to the target text information to obtain the object verification result includes: Based on the preset text information, regularization verification is performed on the target text information to obtain a regularization verification result; In a case where the regularization verification result indicates that the preset text information and the target text information match, determining the object verification result indicating that the object verification has passed; and In a case where the regularization verification result indicates that the preset text information and the target text information do not match, the object verification result indicating that the object verification has failed is determined.

13. An object verification device, comprising: A first determination module is configured to, in response to receiving an object verification instruction, determine object image information according to an object image of an object to be verified indicated by the object verification instruction, wherein the object image information includes respective bill position information of at least one bill area and respective barcode position information of at least one barcode area; A second determination module is used to determine a target document area image according to the object image, the document position information of each of the at least one document area, and the barcode position information of each of the at least one barcode area; A recognition module, used to recognize the single-region image of the target surface to obtain recognition information, wherein the recognition information includes text information and text position information of at least one text region; A third determination module, configured to determine target text information according to the barcode position information of each of the at least one barcode area, the text information and the text position information of each of the at least one text area; and The verification module is used to verify the object to be verified according to the target text information to obtain an object verification result.

14. An electronic device comprising: one or more processors; a memory for storing one or more instructions, Wherein, when the one or more instructions are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having executable instructions stored thereon, wherein when the executable instructions are executed by a processor, the processor is enabled to implement the method according to any one of claims 1 to 12.

16. A computer program product, comprising computer executable instructions, which are used to implement the method of any one of claims 1 to 12 when executed.

Citation Information

Patent Citations

  • Express package label three-segment code verification method and device

    CN111950648A

  • Radio frequency tag read-write device and radio frequency tag read-write method

    CN113033224A

  • Method and device for acquiring text information of express sheet and terminal equipment

    CN113642352A

  • Information identification method and device and terminal equipment

    CN115393860A

  • Data processing method, system and device, electronic equipment and storage medium

    CN115439037A