CN116433565A

CN116433565A - Security check graph judging method, device, equipment and computer storage medium

Info

Publication number: CN116433565A
Application number: CN202111679337.6A
Authority: CN
Inventors: 陈志强; 彭华; 党杰; 宁洪志; 李玮; 王涛; 田龙; 张洋; 刘福建; 佟宣
Original assignee: Nuctech Co Ltd
Current assignee: Nuctech Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2023-07-14

Abstract

The embodiment of the application provides a security check graph judging method, a device, equipment and a computer storage medium, wherein the method comprises the following steps: firstly, acquiring a security inspection image; responding to the identification operation of a user on a target object in the security inspection image, obtaining a first graph judgment result of the security inspection image, and identifying the target object in the security inspection image through an artificial intelligence algorithm, so as to obtain a second graph judgment result; and when a second graph judging result of the security check image is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result. The security check graph judging method combines the auxiliary graph judging method of the artificial intelligent recognition method, and the final graph judging result is determined by combining the graph judging result and the artificial intelligent graph judging result, so that missing check can be avoided, and the accuracy of the security check graph judging is improved.

Description

Security check graph judging method, device, equipment and computer storage medium

Technical Field

The application belongs to the technical field of detection, and particularly relates to a security check graph judging method, a security check graph judging device, security check graph judging equipment and a computer storage medium.

Background

In recent years, the investment of China in the security field is more and more, and the security level of public places is higher and higher. In the field of logistics, various security check devices are arranged in transportation hubs and public places where people are more dense. The existing security inspection method mainly comprises the steps of acquiring image data of luggage articles carried by people through security inspection equipment, and judging the image data to identify dangerous articles.

However, the dangerous goods identification of the images acquired by the security inspection equipment is mainly performed by manual identification, the manual identification mode is to train the image judgment personnel, the image judgment personnel need to focus on the screen in a highly concentrated mode, and the working intensity is very high, so that the manual identification method is easy to generate missed inspection depending on the experience and working state of the image judgment personnel.

Disclosure of Invention

The embodiment of the application provides a security check graph judging method, a device, equipment and a computer storage medium, which can improve the accuracy of the security check graph judging.

In a first aspect, an embodiment of the present application provides a security check graph determining method, where the security check graph determining method may include: acquiring a security inspection image; responding to the identification operation of a user on a target object in the security inspection image, and obtaining a first graph judging result of the security inspection image; when a second graph judging result of the security inspection image is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security inspection image according to the first graph judging result and the second graph judging result; and the second graph judging result is obtained by identifying the target object in the security inspection image through an artificial intelligence algorithm.

In some embodiments, the method further comprises: and when the second graph judging result of the security inspection image is not received within a preset time period after the first graph judging result is obtained, determining the first graph judging result as a final graph judging result of the security inspection image.

In some embodiments, the obtaining the final graph result of the security inspection image according to the first graph result and the second graph result may specifically include: comparing the first graph judgment result with the second graph judgment result; under the condition that the first graph judging result is consistent with the second graph judging result, determining the first graph judging result as a final graph judging result; under the condition that the first graph judging result is inconsistent with the second graph judging result, responding to the repeated graph judging operation of the user on the security check image, and obtaining a third graph judging result of the security check image; and determining the third graph judging result as a final graph judging result of the security check image.

In some embodiments, when the first graph determining result is inconsistent with the second graph determining result, before the second graph determining operation is performed on the security check image by the user, obtaining a third graph determining result of the security check image may further include: generating prompt information under the condition that the target object is not recognized by the first graph judging result and the target object is recognized by the second graph judging result, wherein the prompt information is as follows: judging whether the security inspection image is subjected to image judging operation again; and under the condition that the first graph judging result is inconsistent with the second graph judging result, responding to the repeated graph judging operation of the user on the security check image to obtain a third graph judging result of the security check image, wherein the method specifically comprises the following steps: responding to confirmation operation of a user on prompt information and re-image judging operation of the user on the security inspection image, and obtaining the third image judging result of the security inspection image; and if the fact that the second graph judging operation is not carried out on the security inspection image is determined, determining the first graph judging result as the third graph judging result.

In some embodiments, when the first graph determining result is inconsistent with the second graph determining result, responding to the second graph determining operation of the user on the security check image to obtain a third graph determining result of the security check image, and further may include: and if the first graph judgment result is that the target object is identified and the second graph judgment result is that the target object is not identified, determining the first graph judgment result as the third graph judgment result.

In some embodiments, the obtaining, in response to the user performing the second graph determining operation on the security check image, a third graph determining result of the security check image may specifically include: labeling the target object in the security inspection image according to a second judgment result to obtain a labeled security inspection image; and responding to the identification operation of the user on the target object in the labeling security inspection image, and obtaining a third graph judging result.

In a second aspect, an embodiment of the present application provides a security check graph determining apparatus, where the security check graph determining apparatus may include:

the acquisition module is used for acquiring the image to be identified;

the image judging module is used for responding to the identification operation of a user on a target object in the security inspection image and obtaining a first image judging result of the security inspection image;

The determining module is used for obtaining a final graph judging result of the security inspection image according to the first graph judging result and the second graph judging result under the condition that the second graph judging result of the security inspection image is received in a preset time period after the first graph judging result is obtained;

and the second graph judging result is obtained by identifying the target object in the security inspection image through an artificial intelligence algorithm.

In a third aspect, an embodiment of the present application provides another security check graph determining method, where the method may include:

acquiring a security check image, wherein the security check image is sent by a scheduling server;

responding to the identification operation of a user on a target object in the security inspection image, and obtaining a first graph judging result of the security inspection image;

when a second graph judging result of the security inspection image sent by the scheduling server is received in a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security inspection image according to the first graph judging result and the second graph judging result;

and the second graph judging result is obtained by identifying a target object in the security inspection image sent by the scheduling server through an artificial intelligent algorithm by using an artificial intelligent graph judging device, and then the second graph judging result is sent to the scheduling server.

In a fourth aspect, an embodiment of the present application provides a security check graph determining system, where the system may include: the system comprises security inspection equipment, a dispatching server, security inspection graph judgment equipment and artificial intelligence graph judgment equipment;

the security inspection equipment is used for acquiring security inspection images and sending the security inspection images to the scheduling server;

the scheduling server is used for receiving the security inspection image sent by the security inspection equipment; the security inspection images are respectively sent to the security inspection image judging device and the artificial intelligence image judging device; receiving a second graph judging result obtained by identifying a target object in the security inspection image returned by the artificial intelligence graph judging device; sending the second graph judging result to the security check graph judging device;

the artificial intelligence graph judging device is used for receiving the security check image sent by the scheduling server; identifying a target object in the security inspection image through an artificial intelligence algorithm to obtain a second graph judging result; sending the second graph judging result to the scheduling server;

the security inspection image judging device is used for responding to the identification operation of a user on a target object in the security inspection image to obtain a first image judging result of the security inspection image; and when the second graph judging result of the security check image sent by the scheduling server is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result.

In a fifth aspect, embodiments of the present application provide an electronic device, which may include: a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the security diagnostic graph method as described in any one of the embodiments of the first or third aspects.

In a sixth aspect, embodiments of the present application provide a computer storage medium having a computer program stored thereon, the computer program implementing the steps of the security check graph determining method according to any one of the first or third aspects when the computer program is executed by a processor.

According to the security inspection graph judging method, the security inspection graph judging device, the security inspection graph judging equipment and the computer storage medium, a first graph judging result is obtained through the identification operation of a user on the security inspection image; performing identification operation on the security inspection image through an artificial intelligence algorithm to obtain a second graph judging result; and under the condition that the first graph judging result is inconsistent with the second graph judging result, combining the first graph judging result and the second graph judging result to determine the final graph judging result of the security inspection image. Therefore, when the user graph judgment result is inconsistent with the artificial intelligence graph judgment result, the user graph judgment result is combined with the artificial intelligence graph judgment result to determine the final graph judgment result of the security check image, and the accuracy of the security check graph judgment is improved. Therefore, the embodiment of the application assists the user to conduct the security check graph judgment through the artificial intelligence graph judgment method, and accuracy of the security check graph judgment is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.

Fig. 1 is a flow chart of a security check graph judging method provided in an embodiment of the present application;

fig. 2 is a schematic structural diagram of a security inspection graph judging device provided in an embodiment of the present application;

FIG. 3 is a schematic diagram illustrating an implementation of the security inspection graph method according to the embodiment of the present application;

fig. 4 is a flow chart of another security check graph judging method provided in the embodiment of the present application;

fig. 5 is a schematic diagram of a security inspection graph judging system provided in an embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application are described in detail below to make the objects, technical solutions and advantages of the present application more apparent, and to further describe the present application in conjunction with the accompanying drawings and the detailed embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative of the application and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

In recent years, with the development of artificial intelligence technology, the integration of artificial intelligence image recognition technology and security inspection technology has become a new direction of security inspection industry development. The image artificial intelligent recognition technology can effectively solve the problems of huge recognition data, great consumption of manpower and material resources, missed detection due to dependence on experience and working state of image judgment staff and the like in the security inspection field. However, the effective rate of the existing artificial intelligence dangerous goods identification is still to be improved, the false alarm can be caused by completely relying on the artificial intelligence judgment, meanwhile, the dependence of the judgment staff on the artificial intelligence judgment can be caused, and the advantage of the artificial judgment of the judgment staff can not be effectively exerted.

Therefore, how to effectively fuse the artificial intelligent judgment chart and the judgment chart of the judgment chart operator, cooperate with each other, make the best of the other, exert the auxiliary capacity of the machine, and become the problem to be solved when the artificial intelligent judgment chart is applied in the security inspection field. The inventor of the application has paid out a large amount of labor researches and has obtained the technical scheme of this application, can effectively utilize the experience and the sharp sense of touch of the person of judging the picture under original security inspection mode, can exert the stable high-efficient of artificial intelligence judgement picture again, lets the person of judging the picture not rely on the machine judgement picture simultaneously to the advantage stack of realization reduces the omission ratio, effectively improves security inspection judgement picture wisdom level.

Based on the above research findings, the embodiments of the present application provide a method, an apparatus, a device, and a computer storage medium for security inspection graph judgment, which are used for solving the above technical problems.

The following first describes a security check graph judging method provided in the embodiment of the present application.

Fig. 1 is a flow chart of a security check graph judging method provided in an embodiment of the present application. As shown in fig. 1, the method may include the steps of:

s101, acquiring a security inspection image;

s102, responding to the identification operation of a user on a target object in the security inspection image, and obtaining a first graph judging result of the security inspection image;

And S103, when a second graph judging result of the security check image is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result.

The specific implementation of each of the above steps will be described in detail below.

According to the embodiment of the application, when the user graph judgment result is inconsistent with the artificial intelligent graph judgment result, the user graph judgment result is combined with the artificial intelligent graph judgment result to determine the final graph judgment result of the security inspection image, so that the accuracy of the security inspection graph judgment is improved. Therefore, the embodiment of the application assists the user to conduct the security check graph judgment through the artificial intelligence graph judgment method, and accuracy of the security check graph judgment is improved.

In S101, a security check image of a baggage item carried by a person or another item to be checked may be acquired by a security check device. The security inspection device may be a security inspection X-ray machine, a baggage security inspection machine, a channel type X-ray machine, a physical inspection X-ray machine, an X-ray security inspection instrument, etc., which is not limited in this application.

For example, the security inspection image may be obtained by an X-ray security inspection apparatus that may obtain a transmission image of an object to be inspected according to the degree of absorption of X-rays by the object, in which part of the X-ray beam emitted by the X-ray source is absorbed when passing through the object to be inspected on the conveyor belt.

In S102, the target object in the security image is identified according to the user identifying the security image acquired in S101, and the first graph judging result is determined according to whether the target object exists in the security image.

Here, the user may be a diagramming person, and the target object may be a dangerous object, a forbidden object, or another object that needs security inspection identification.

In some embodiments, the user may identify the security inspection image, if a target object exists in the security inspection image, mark the target object, and determine the first graph judgment result as the existence of the target object in the security inspection image; and if the target object does not exist in the security inspection image, determining the first graph judgment result as that the target object does not exist.

In some embodiments, in some public places such as subways and railway stations, the baggage carried by passengers is checked, and if dangerous goods are detected, the passengers need to be checked in a unpacking mode to confirm whether the dangerous goods are carried; and if no dangerous article is detected, passing the passenger. Therefore, if the target object exists in the security inspection image, the security inspection object needs to be inspected, so that the graph judgment result can be determined as open inspection; if the target object does not exist in the security inspection image, the security inspection object passes through, so that the graph judgment result can be determined as pass or pass.

For example: the security inspection machine acquires security inspection images, the security inspection images are sent to a graph judging station, workers (graph judges) of the graph judging station recognize the security inspection images, if dangerous goods (target objects) exist in the security inspection images, the dangerous goods are marked, and a first graph judging result is determined to be open inspection; and if dangerous articles (target objects) do not exist in the security inspection image, determining the first graph judgment result as release.

In S103, when the second graph judgment result of the security image is received within the preset time period after the first graph judgment result is obtained, a final graph judgment result of the security image is obtained according to the first graph judgment result and the second graph judgment result.

The second graph judging result is obtained by identifying the target object in the security inspection image through an artificial intelligence algorithm. Specifically, identifying a target object in the security inspection image by adopting an artificial intelligence algorithm; if the target object exists in the security inspection image, marking the target object, and determining a second graph judging result as the existence of the target object; and if the target object does not exist in the security inspection image, determining the second graph judgment result as that the target object does not exist. If the target object exists in the security inspection image, marking the target object, and determining the second graph judgment result as the open inspection; and if the target object does not exist in the security inspection image, determining the second graph judgment result as release.

And determining the first judgment result and the second judgment result according to the actual requirement and the judgment result of the target object in the security inspection image.

In order to ensure the efficiency of the security inspection and graph judgment, in some embodiments, when the second graph judgment result of the security inspection image is not received within a preset time period after the first graph judgment result is obtained, the first graph judgment result is determined as the final graph judgment result of the security inspection image.

The preset time period can be set according to actual needs, and the application is not limited.

For example, the preset time period may be set to 2s, after the first graph judgment result is obtained, the second graph judgment result needs to be waited to be obtained, if the second graph judgment result is received within 2s, the final graph judgment result of the security inspection image is obtained according to the first graph judgment result and the second graph judgment result; if the second graph judging result is received after waiting for 2s, the first graph judging result is directly determined as the final graph judging result of the security check image without waiting.

In some embodiments, according to the first graph judgment result and the second graph judgment result, a final graph judgment result of the security inspection image is obtained, which may be:

comparing the first graph judgment result with the second graph judgment result;

Under the condition that the first graph judging result is consistent with the second graph judging result, determining the first graph judging result as a final graph judging result;

under the condition that the first graph judging result is inconsistent with the second graph judging result, responding to the repeated graph judging operation of the user on the security check image, and obtaining a third graph judging result of the security check image;

and determining the third judgment result as a final judgment result of the security inspection image.

In this embodiment, if the first graph determination result is consistent with the second graph determination result, it is explained that the user graph determination result is correct, so the first graph determination result is directly determined as the final graph determination result of the security inspection image. If the first graph judging result is inconsistent with the second graph judging result, the fact that the graph judging result of the user possibly has errors is indicated, so that the second graph judging operation is needed to be carried out on the security check image, namely the security check image is identified again, whether the target object exists in the security check image is identified, and a third graph judging result is obtained.

In some embodiments, the re-mapping of the security inspection image may be that the user re-identifies the security inspection image, and determines a third mapping result according to the mapping result of the user on the target object in the security inspection image.

In some embodiments, when the first graph judgment result is inconsistent with the second graph judgment result, before responding to the second graph judgment operation of the user on the security check image, the method further includes:

When the first judgment result is that the target object is not identified, and the second judgment result is that the target object is identified, generating prompt information, wherein the prompt information is as follows: judging whether the security check image is subjected to image judging operation again;

under the condition that the first graph judging result is inconsistent with the second graph judging result, responding to the repeated graph judging operation of the user on the security check image to obtain a third graph judging result of the security check image, wherein the method specifically comprises the following steps:

responding to the confirmation operation of the user on the prompt information and the repeated graph judging operation of the user on the security check image, and obtaining a third graph judging result of the security check image;

and if the fact that the image judgment operation is not performed again on the security inspection image is determined, determining the first image judgment result as a third image judgment result.

In this embodiment, when the first graph judgment result is that the target object is not identified, and the second graph judgment result is that the target object is identified, that is, the user does not identify that the target object exists in the security inspection image, and the graph judgment result of the artificial intelligence algorithm identifies that the target object exists in the security inspection image, in this case, it is explained that the user is likely to have an error in the graph judgment of the security inspection image, so that a prompt message is generated to prompt the user to confirm whether to perform the graph judgment operation again on the security inspection image.

In some embodiments, the prompt information may be displayed in a pop-up or embedded page.

In some embodiments, the user can confirm whether the security inspection image needs to be subjected to the image judging operation again according to actual needs. If the user considers that the first graph judging result is not wrong according to the self working experience, the user can confirm that the second graph judging operation is not performed on the security check image; if the accuracy of the security check graph is ensured, the user can confirm that the graph is judged again for the security check image.

Therefore, if the first graph judging result is that the target object is not identified and the second graph judging result is that the target object is identified, if the user confirms that the security inspection image is operated again, a third graph judging result is obtained through the re-identification of the security inspection image by the user; if the user confirms that the security inspection image is not operated again, the first graph judging result is directly determined to be a third graph judging result; finally, determining the third graph judging result as a final graph judging result of the security check image; .

In some embodiments, in response to the confirmation operation of the prompt information by the user and the re-image judgment operation of the security inspection image by the user, obtaining the third image judgment result of the security inspection image may include:

Labeling the target object in the security inspection image according to the second graph judging result to obtain a labeled security inspection image;

and responding to the identification operation of the user on the target object in the labeling security inspection image, and obtaining a third graph judging result.

In this embodiment, if the user confirms that the image re-judging operation is performed on the security image, before the user performs the image re-judging operation on the security image, the target object in the security image may be labeled according to the second image judging result. Because the second graph judgment result is the identification of the target object, namely the existence of the target object in the security inspection image is determined by an artificial intelligent identification method and the target object is marked, the security inspection image is marked according to the second graph judgment result obtained by artificial intelligent identification; by conducting the security inspection operation again on the security inspection image marked with the target object, the accuracy of the security inspection judgment chart can be improved.

In some embodiments, in order to avoid missing a target object in the security inspection image, if the first graph result is that the target object is identified and the second graph result is that the target object is not identified, the first graph result is determined to be the third graph result.

In this embodiment, the first graph judgment result is that the target object exists in the security inspection image is identified, and the second graph judgment result is that the target object exists in the security inspection image is not identified; the fact that the target object is likely to exist in the security inspection image is explained, so that in order to avoid missing inspection, the first graph judgment result can be directly determined to be a third graph judgment result, and then the third graph judgment result is determined to be a final graph judgment result of the security inspection image.

In addition, in the embodiment of the application, the user graph judging operation and the artificial intelligence graph judging operation are respectively and independently carried out, so that the dependence of a user on artificial intelligence can be reduced, the interference of a conclusion artificial intelligence graph judging result on the user is avoided, and the experience and flexibility of the user can be fully exerted.

The following description is made with reference to a specific application example, as shown in fig. 2, when a security inspection image is subjected to image judgment in a subway security inspection scene, the following steps may be adopted to carry out image judgment on the security inspection image, and if a target object is identified in the security inspection image, the image judgment result is open inspection (i.e. open package inspection), and if the target object is not identified in the security inspection image, the image judgment result is clear (i.e. safe passing).

S201, judging the graph by a graph judge person, performing image processing (identifying a target object in the security inspection image), marking suspected objects and giving a graph judge result (a first graph judge result), (namely, responding to the identification operation of a user on the target object in the security inspection image, and obtaining the first graph judge result of the security inspection image);

s202, AI judgment is carried out, a suspected object (target object) is identified through an AI judgment algorithm (artificial intelligence algorithm), the suspected object is marked, and a judgment result (second judgment result) is given;

s203, judging whether an AI graph judging result (a second graph judging result) of the security check image is received within a preset time period (such as within 2S) after the graph judging result (a first graph judging result) of the graph judging person is obtained; if not, determining the graph judging result of the graph judging person as the final graph judging result of the security check image, and ending the graph judging; if yes, go to S204;

s204, judging whether the graph judging results are consistent (whether the first graph judging result is consistent with the second graph judging result or not), if so, determining the graph judging result of the graph judging person as the final graph judging result of the security check image, recording the graph judging result of the graph judging person and the AI graph judging result, and ending the graph judging; if not, go to S205;

s205, judging whether the image judgment result of the image judgment person is a start test, if so, determining the image judgment result of the image judgment person as a final image judgment result of the security check image, recording the image judgment result of the image judgment person and the image judgment result of the AI, and ending the image judgment; if not, go to S206;

S206, determining whether to perform secondary graph judgment, generating prompt information, prompting a graph judge whether to perform secondary graph judgment, if not, determining the graph judge result of the graph judge operator as a final graph judge result of the security check image, recording the graph judge result of the graph judge operator and the AI graph judge result, and ending the graph judge; if yes, go to S207;

s207, performing secondary graph judgment by a graph judge person to obtain a final graph judge result of the security check image, displaying the mark of the AI graph judge on the suspicious object on the security check image (namely, labeling a target object in the security check image according to the second graph judge result to obtain a labeled security check image), performing graph judgment again on the security check image displayed with the AI graph judge mark by the graph judge person to obtain the final graph judge result of the security check image (namely, responding to the secondary graph judge operation of the security check image by a user to obtain a third graph judge result of the security check image), recording the graph judge result of the graph judge person, the AI graph judge result and the final graph judge result, and ending the graph judge.

In the embodiment, the security check graph judging level is promoted by utilizing an artificial intelligence technical means, the functions of preventing the inspection, controlling the suspicious baggage and the like can be effectively promoted through an artificial intelligence image analysis technology, and the passing efficiency and the security check graph judging level are improved.

Based on the security check graph judging method provided by the embodiment, correspondingly, the application also provides a specific implementation mode of the security check graph judging device. Please refer to the following examples.

Referring first to fig. 3, a security check graph determining apparatus 300 provided in an embodiment of the present application may include the following modules:

an acquisition module 301, configured to acquire an image to be identified;

the image judging module 302 is configured to obtain a first image judging result of the security inspection image in response to an identification operation of a user on a target object in the security inspection image;

the determining module 303 is configured to obtain a final graph determining result of the security check image according to the first graph determining result and the second graph determining result when the second graph determining result of the security check image is received within a preset time period after the first graph determining result is obtained;

the second graph judging result is obtained by identifying the target object in the security inspection image through an artificial intelligence algorithm.

In the embodiment of the application, when the user graph judgment result is inconsistent with the artificial intelligence graph judgment result, the user graph judgment result is combined with the artificial intelligence graph judgment result to determine the final graph judgment result of the security check image, so that the accuracy of the security check graph judgment is improved. Therefore, the embodiment of the application assists the user to conduct the security check graph judgment through the artificial intelligence graph judgment method, and accuracy of the security check graph judgment is improved.

In some embodiments, to obtain the graph judgment result in time, the determining module 303 may be further configured to:

And when the second graph judging result of the security check image is not received within a preset time period after the first graph judging result is obtained, determining the first graph judging result as a final graph judging result of the security check image.

In some embodiments, the determining module 303 may include:

the comparison unit is used for comparing the first graph judgment result with the second graph judgment result;

the determining unit is used for determining the first graph judging result as a final graph judging result under the condition that the first graph judging result is consistent with the second graph judging result;

the graph judging module 302 is further configured to, in case that the first graph judging result is inconsistent with the second graph judging result, respond to a second graph judging operation of the user on the security check image, and obtain a third graph judging result of the security check image;

the determining unit may be further configured to determine the third graph result as a final graph result of the security check image.

In some embodiments, the determining module 303 may further include:

the prompting unit is used for generating prompting information when the first judgment result is that the target object is not recognized and the second judgment result is that the target object is recognized, wherein the prompting information is as follows: judging whether the security check image is subjected to image judging operation again;

The determining unit is further configured to obtain a third graph judging result of the security check image in response to a confirmation operation of the prompt message by the user and a graph judging operation of the security check image by the user;

In some embodiments, the determining unit may be further configured to:

and if the first graph judgment result is that the target object is identified and the second graph judgment result is that the target object is not identified, determining the first graph judgment result as a third graph judgment result.

In some embodiments, the determining unit may be further configured to label the target object in the security inspection image according to the second graph judging result, to obtain a labeled security inspection image;

The modules/units in the apparatus shown in fig. 3 have functions of implementing the steps in fig. 1 or fig. 2, and achieve corresponding technical effects, which are not described herein for brevity.

The application also provides another security check graph judging method. Fig. 4 is a flow chart of another security check graph judging method provided in the embodiment of the present application. As shown in fig. 4, the method may include the steps of:

S401, acquiring a security check image, wherein the security check image is sent by a scheduling server.

In this embodiment, a security check image sent by the scheduling server is received. Specifically, the image data of the luggage articles carried by people or other articles needing security inspection can be obtained through security inspection equipment, the security inspection equipment sends security inspection images to a dispatching server, and then the dispatching server sends the security inspection images.

S402, responding to the identification operation of a user on a target object in the security inspection image, and obtaining a first graph judging result of the security inspection image.

Specifically, the security inspection image acquired in S401 is identified according to a user, a target object in the security inspection image is identified, and a first graph judgment result is determined according to whether the target object exists in the security inspection image. Similar to S102, a detailed description is omitted here.

S403, when a second graph judging result of the security check image sent by the scheduling server is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result.

And the second graph judging result is obtained by identifying a target object in the security inspection image sent by the scheduling server through an artificial intelligent algorithm by the artificial intelligent graph judging device, and then the second graph judging result is sent to the scheduling server.

Specifically, after the scheduling server receives the security inspection image, the security inspection image is sent to an artificial intelligence image judging device, the artificial intelligence image judging device identifies a target object in the security inspection image sent by the scheduling server through an artificial intelligence algorithm to obtain a second image judging result, if the target object exists in the security inspection image, the target object is marked, and the second image judging result is determined to be the existence of the target object; if the target object does not exist in the security inspection image, determining the second graph judging result as the absence of the target object; and then sending the second graph judging result to the scheduling server.

And after receiving the second graph judging result sent by the scheduling server, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result.

In the embodiment of the application, each flow of the security check graph is scheduled through the scheduling server, and when the user graph judgment result is inconsistent with the artificial intelligence graph judgment result, the user graph judgment result is combined with the artificial intelligence graph judgment result to determine the final graph judgment result of the security check image, so that the efficiency and the accuracy of the security check graph judgment are improved. Therefore, the embodiment of the application utilizes the scheduling server to assist the user in carrying out the security check and judgment by the artificial intelligence graph judgment method, and improves the efficiency and accuracy of the security check and judgment.

Based on the security check graph judging method provided by the embodiment, correspondingly, the application also provides a security check graph judging system. Please refer to the following examples.

Referring first to fig. 5, a security inspection graph determining system provided in an embodiment of the present application may include: security check equipment 501, a scheduling server 502, an artificial intelligence graph judging equipment 503 and security check graph judging equipment 504.

The security inspection device 501 is configured to acquire a security inspection image, and send the security inspection image to the scheduling server 502;

a scheduling server 502, configured to receive a security check image sent by the security check device 501; the security inspection images respectively sent to the security inspection image judging device 504 and the artificial intelligence image judging device 503; receiving a second graph judging result obtained by identifying the target object in the security inspection image returned by the artificial intelligence graph judging device 503; sending a second graph judgment result to the security check graph judgment equipment 504;

the artificial intelligence graph judging device 503 is configured to receive the security check image sent by the scheduling server 502; identifying a target object in the security inspection image through an artificial intelligence algorithm to obtain a second graph judging result; sending a second graph judging result to the scheduling server 502;

the security inspection graph judging device 504 is configured to obtain a first graph judging result of the security inspection image in response to a user identifying operation on a target object in the security inspection image; and when the second graph judging result of the security check image sent by the scheduling server 502 is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security check image according to the first graph judging result and the second graph judging result.

In some embodiments, the security inspection graph system provided in the embodiments of the present application may have a plurality of security inspection devices 501, and the scheduling server 502 may receive security inspection images sent by the plurality of security inspection devices 501.

In some embodiments, the security check machine may be a security check machine in a line check, travel check, or cargo check business system.

In some embodiments, the security inspection graph judging system provided in the embodiments of the present application may have a plurality of artificial intelligence graph judging devices 503, and the scheduling server 502 may distribute the security inspection image to the artificial intelligence graph judging devices 503 according to the load condition of each artificial intelligence graph judging device 503, so as to improve the efficiency of artificial intelligence graph judgment.

In some embodiments, the artificial intelligence graph determining device 503 may be a single device with image intelligent recognition algorithm functionality or a cloud-based intelligent graph determining service.

In some embodiments, the security check graph judging device 504 may be a security check machine device with a local graph judging function or a graph judging workstation for centralized graph judgment.

The system shown in fig. 5 has the function of implementing each step in fig. 1, fig. 2 or fig. 4, and can achieve the corresponding technical effects, and for brevity, will not be described in detail herein.

The application of the security inspection graph judging system provided in the embodiment of the present application is described below with reference to a specific application example,

In step 1, the security inspection machine obtains security inspection images of luggage articles carried by people or other articles needing security inspection, and sends the security inspection images to the dispatch server 502. The security inspection device 501 may be a security inspection X-ray machine, a baggage security inspection machine, a channel type X-ray machine, a material inspection X-ray machine, an X-ray security inspection instrument, etc., and the type and number of the security inspection machines are not limited in this application.

Step 2, after receiving the security inspection image sent by the security inspection machine, the scheduling server 502 may send the security inspection image to the security inspection image determining device 504 and the artificial intelligence image determining device 503 at the same time. If there are multiple artificial intelligence graph judging devices 503 in the security check graph judging system, the scheduling server 502 schedules according to the load condition of each artificial intelligence graph judging device 503, and distributes graph judging tasks to the artificial intelligence graph judging devices 503 (i.e. distributes security check images to the artificial intelligence graph judging devices 503 according to the load condition of each artificial intelligence graph judging device 503).

Step 3, the security inspection graph judging device 504 receives the security inspection image sent by the scheduling server 502, and the graph judging person performs image processing on the security inspection image and marks the suspected object to obtain a first graph judging result (i.e. in response to the user identifying the target object in the security inspection image, the first graph judging result of the security inspection image is obtained).

Step 4, the artificial intelligence graph judging device 503 receives the security check image sent by the scheduling server 502, and identifies the target object in the security check image through an artificial intelligence algorithm to obtain a second graph judging result; sending a second graph judging result to the scheduling server 502;

the above steps 3 and 4 may be performed simultaneously.

Step 5, the scheduling server 502 receives the second graph judgment result obtained by identifying the target object in the security inspection image returned by the artificial intelligence graph judgment device 503, and sends the second graph judgment result to the security inspection graph judgment device 504;

in step 6, the security check graph judging device 504 receives the second graph judging result sent by the scheduling server 502, and obtains the final graph judging result of the security check image according to the first graph judging result and the second graph judging result when the second graph judging result of the security check image sent by the scheduling server 502 is received in the preset time period after the first graph judging result is obtained.

Based on the security check graph judging method provided by the embodiment, correspondingly, the application also provides a specific implementation mode of the electronic equipment. Please refer to the following examples.

Fig. 6 shows a schematic hardware structure of an electronic device according to an embodiment of the present application.

The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

In particular, the processor 601 may include a central processing unit (Central Processing Unit, CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.

Memory 602 may include mass storage for data or instructions. By way of example, and not limitation, memory 602 may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the above. In one example, the memory 602 may include removable or non-removable (or fixed) media, or the memory 602 is a non-volatile solid state memory. Memory 602 may be internal or external to the integrated gateway disaster recovery device.

In one example, memory 602 may be Read Only Memory (ROM). In one example, the ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

The memory 602 may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described with reference to methods in accordance with aspects of the present disclosure.

The processor 601 reads and executes the computer program instructions stored in the memory 602 to implement the methods/steps in the embodiments shown in fig. 1, 2 or 4, and achieve the corresponding technical effects achieved by the implementation of the methods/steps in the illustrated embodiments, which are not described herein for brevity.

In one example, the electronic device may also include a communication interface 603 and a bus 610. As shown in fig. 6, the processor 601, the memory 602, and the communication interface 603 are connected to each other through a bus 610 and perform communication with each other.

The communication interface 63 is mainly used for implementing communication between each module, device, unit and/or apparatus in the embodiments of the present application.

Bus 610 includes hardware, software, or both, coupling components of the online data flow billing device to each other. By way of example, and not limitation, the buses may include an accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) Bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, ISA) Bus, an infiniband interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (MCa) Bus, a Peripheral Component Interconnect (PCI) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a video electronics standards association local (VLB) Bus, or other suitable Bus, or a combination of two or more of the above. Bus 910 may include one or more buses, where appropriate. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

In addition, in combination with the security check graph judging method in the above embodiment, the embodiment of the application may provide a computer storage medium for implementation. The computer storage medium has stored thereon computer program instructions; the computer program instructions, when executed by the processor, implement any of the security check graph judging methods of the above embodiments.

In summary, according to the security check graph judging method, device, equipment and computer storage medium of the embodiment of the application, when the user graph judging result is inconsistent with the artificial intelligence graph judging result, the final graph judging result of the security check image is determined by combining the user graph judging result and the artificial intelligence graph judging result, so that the accuracy of the security check graph judging is improved. Therefore, the embodiment of the application assists the user to conduct the security check graph judgment through the artificial intelligence graph judgment method, and accuracy of the security check graph judgment is improved.

It should be clear that the present application is not limited to the particular arrangements and processes described above and illustrated in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps, after appreciating the spirit of the present application.

The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be different from the order in the embodiments, or several steps may be performed simultaneously.

Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, which are intended to be included in the scope of the present application.

Claims

1. The security check graph judging method is characterized by comprising the following steps of:

acquiring a security inspection image;

when a second graph judging result of the security inspection image is received within a preset time period after the first graph judging result is obtained, obtaining a final graph judging result of the security inspection image according to the first graph judging result and the second graph judging result;

2. The method according to claim 1, wherein the method further comprises:

and when the second graph judging result of the security inspection image is not received within a preset time period after the first graph judging result is obtained, determining the first graph judging result as a final graph judging result of the security inspection image.

3. The method according to claim 1, wherein the obtaining the final graph judgment result of the security inspection image according to the first graph judgment result and the second graph judgment result specifically includes:

and determining the third graph judging result as a final graph judging result of the security check image.

4. The method according to claim 3, wherein, in the case that the first graph determining result is inconsistent with the second graph determining result, before the third graph determining result of the security check image is obtained in response to the user performing the graph determining operation on the security check image again, the method further includes:

Generating prompt information under the condition that the target object is not recognized by the first graph judging result and the target object is recognized by the second graph judging result, wherein the prompt information is as follows: judging whether the security inspection image is subjected to image judging operation again;

and under the condition that the first graph judging result is inconsistent with the second graph judging result, responding to the repeated graph judging operation of the user on the security check image to obtain a third graph judging result of the security check image, wherein the method specifically comprises the following steps:

responding to confirmation operation of a user on prompt information and re-image judging operation of the user on the security inspection image, and obtaining the third image judging result of the security inspection image;

and if the fact that the second graph judging operation is not carried out on the security inspection image is determined, determining the first graph judging result as the third graph judging result.

5. The method according to claim 4, wherein in the case that the first graph determining result is inconsistent with the second graph determining result, in response to the user performing the graph determining operation on the security check image again, obtaining a third graph determining result of the security check image, further includes:

and if the first graph judgment result is that the target object is identified and the second graph judgment result is that the target object is not identified, determining the first graph judgment result as the third graph judgment result.

6. The method of claim 4, wherein the obtaining a third graph determination result of the security inspection image in response to the user performing the graph determination operation again on the security inspection image specifically includes:

labeling the target object in the security inspection image according to a second judgment result to obtain a labeled security inspection image;

7. A security check graph judging device, characterized in that the device comprises:

the acquisition module is used for acquiring the image to be identified;

8. The security check graph judging method is characterized by comprising the following steps of:

9. The security check graph judging system is characterized by comprising:

the system comprises security inspection equipment, a dispatching server, security inspection graph judgment equipment and artificial intelligence graph judgment equipment;

10. An electronic device, the electronic device comprising: a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor carries out the steps of the security decision method as claimed in any one of claims 1 to 6 and 8.

11. A computer storage medium, wherein a computer program is stored on the computer readable storage medium, the computer program implementing the steps of the security decision method according to any of claims 1 to 6 or 8 when executed by a processor.