WO2019096181A1

WO2019096181A1 - Detection method, apparatus and system for security inspection, and electronic device

Info

Publication number: WO2019096181A1
Application number: PCT/CN2018/115498
Authority: WO
Inventors: 黄鼎隆; 斯科特·马修·罗伯特; 董登科; 王重
Original assignee: 深圳码隆科技有限公司
Priority date: 2017-11-14
Filing date: 2018-11-14
Publication date: 2019-05-23
Also published as: CN107871122A

Abstract

A detection method, apparatus and system for security inspection and an electronic device. Said method comprises: acquiring an X-ray image received by a security inspection terminal and acquired by an X-ray machine in a security inspection machine, and pre-processing the X-ray image, so as to obtain a pre-processed X-ray image (S101); extracting, according to a preset deep learning model, an object feature of a corresponding object to be detected in the pre-processed X-ray image, the preset deep learning model comprising a convolutional neural network-based deep learning model (S102); identifying the object feature by means of a classifier trained on the basis of a preset deep learning model, and generating an identification result corresponding to the object to be detected (S103); and Sending, to the security inspection terminal, the identification result of the object to be detected, so that the security inspection terminal displays the identification result (S104). The method above implements automatic recognition and detection of prohibited goods, effectively ensuring the accuracy of recognition of prohibited goods while improving the efficiency of recognition, preventing the occurrence of security hazards.

Description

Security inspection method, device, system and electronic device

Cross-reference to related applications

This application claims priority to Chinese Patent Application No. CN201711126618.2, entitled "Security Inspection Method, Apparatus, System and Electronic Equipment" submitted by the Chinese Patent Office on November 14, 2017, the entire contents of which are incorporated by reference. In this application.

Technical field

The present application relates to the technical field of security devices, and in particular, to a security detection method, device, system, and electronic device.

Background technique

With the increase of public safety awareness, various security inspection equipment is widely used in important public places such as airports, ports, ports, subways, courts and venues for major events. The most commonly used one is the (X-ray) security inspection machine. At present, the security inspection machine has been widely used in the passenger flow and logistics field. The general security inspection machine includes a motor, a conveyor system driven by a motor, a fuselage that is placed across the middle of the conveyor system, and of course a matching X-ray machine. Usually, a security inspection channel is formed between the body of the security inspection machine and the conveyor belt, and an X-ray machine is provided on at least one side of the security inspection channel. One end of the conveyor system is the area to be inspected. After the object to be inspected is placed in the area to be inspected, it will be transmitted to the other end by the motor-driven conveyor system. In the middle, it must pass through the security inspection channel and be scanned by X-ray machine to generate X-ray imaging. Identify whether the object to be tested is a contraband.

However, the existing detection method is susceptible to external environmental factors such as detection penetration and detection angle or external interference, which greatly reduces the recognition accuracy; and after the terminal displays the X-ray image, the security personnel are required to check the displayed image. . In this way, the security personnel can monitor the screen for a long time, which may cause visual fatigue, resulting in false detection, wrong inspection and missed detection.

Therefore, the existing security detection method is difficult to ensure the accuracy of identification, and the recognition efficiency is low, which is likely to cause security risks.

Summary of the invention

In view of this, the purpose of the present application is to provide a security detection method, device, system, and electronic device, so as to improve the recognition efficiency, effectively ensure the accuracy of identification of contraband, and prevent the occurrence of security risks.

In a first aspect, an embodiment of the present application provides a security detection method, including:

Obtaining an X-ray image acquired by an X-ray machine in the security inspection machine received by the security inspection terminal, and pre-processing the X-ray image to obtain a pre-processed X-ray image;

Extracting an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes a deep learning model based on a convolutional neural network;

Identifying, by the classifier trained based on the preset depth learning model, the item feature, and generating a recognition result corresponding to the object to be detected;

And transmitting the identification result of the object to be detected to the security check terminal, so that the security check terminal displays the recognition result.

With reference to the first aspect, the embodiment of the present application provides a first possible implementation manner of the first aspect, wherein the pre-processing the X-ray image comprises:

The collected X-ray image is smoothed and denoised by a neighborhood averaging method to obtain a smooth and denoised X-ray image;

The edge information of the smoothed and denoised image is enhanced by a histogram equalization method to obtain a preprocessed X-ray image.

With reference to the first aspect, the embodiment of the present application provides a second possible implementation manner of the first aspect, wherein the deep learning model based on a convolutional neural network is trained by using sample data of a quantity exceeding a certain threshold. The item sample data includes pictures corresponding to different forms of contraband.

With reference to the first aspect, the embodiment of the present application provides a third possible implementation manner of the first aspect, where the training process of the classifier includes:

Depth feature of item specimen data is extracted by using a deep learning model based on convolutional neural network;

Training a classifier for the depth feature based on a machine learning algorithm;

The item specimen data includes an X-ray picture of the specified different recognition result.

In a second aspect, the embodiment of the present application further provides a security detection device, including:

The pre-processing module is configured to obtain an X-ray image acquired by the X-ray machine in the security inspection machine received by the security inspection terminal, and pre-process the X-ray image to obtain a pre-processed X-ray image;

a feature extraction module, configured to extract an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes deep learning based on a convolutional neural network model;

a result identifying module configured to identify the item feature by using a classifier trained based on the preset depth learning model to generate a recognition result corresponding to the object to be detected;

And a result display module configured to send the identification result of the object to be detected to the security check terminal, so that the security check terminal displays the recognition result.

In a third aspect, the embodiment of the present application further provides a security inspection system, including a security inspection machine, a security inspection terminal, and a security identification device. The security inspection box of the security inspection machine is provided with an X-ray machine, and the security identification device includes a second The security detecting device of the aspect; the X-ray machine and the security detecting device are respectively connected to the security detecting terminal;

The X-ray machine is configured to collect an X-ray image of the object to be detected passing through the security inspection channel of the security inspection machine, and send the X-ray image to the security inspection terminal;

The security check terminal is configured to send the X-ray image to the security identification device when the received X-ray image is received, and configured to receive the recognition result of the object to be detected sent by the security identification device And displaying the recognition result through a display screen.

With reference to the third aspect, the embodiment of the present application provides a first possible implementation manner of the third aspect, wherein the identification result includes two types of contraband and non-prohibited items; the system further includes an alarm device, An alarm device is connected to the security check terminal;

The security terminal is further configured to send an alarm signal to the alarm device when the received recognition result is a contraband, so that the alarm device performs an alarm prompt.

With reference to the third aspect, the embodiment of the present application provides a second possible implementation manner of the third aspect, wherein a bottom of the security inspection channel of the security inspection device is provided with a pressure sensor, and the pressure sensor is connected to the security inspection terminal;

The pressure sensor is configured to collect pressure information received on the security inspection channel, and send the pressure information to the security inspection terminal;

The security terminal is further configured to turn the X-ray machine on or off according to the pressure information.

With reference to the third aspect and any possible implementation manner thereof, the embodiment of the present application provides a third possible implementation manner of the third aspect, wherein the security identification device includes an Nvidia Jetson TX2 chip.

In a fourth aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor, where the computer stores a computer program executable on the processor, where the processor implements the computer program The method of the first aspect above and any one of its possible embodiments.

The embodiments of the present application bring the following beneficial effects:

The embodiment of the present application provides a security detection method, device, system, and electronic device, wherein the method includes acquiring an X-ray image acquired by an X-ray machine in a security inspection machine received by a security inspection terminal, and pre-processing the X-ray image. Obtaining a pre-processed X-ray image; extracting, according to a preset depth learning model, an item feature of the corresponding to-be-detected object in the pre-processed X-ray image, the preset depth learning model including a convolutional neural network a deep learning model; the classifier trained based on the preset deep learning model identifies the item feature, generates a recognition result corresponding to the object to be detected; sends the recognition result of the object to be detected to the security terminal, so that the security terminal displays the Identify the results. In the technical solution provided by the embodiment of the present application, the pre-processing is firstly used to reduce the influence of external environmental factors, and then the feature of the item is extracted by a deep learning model based on a convolutional neural network, and the classifier trained by the deep learning model is to be detected. The object is identified, which realizes the automatic identification and detection of contraband, and improves the recognition efficiency, effectively guarantees the accuracy of the contraband identification, and prevents the occurrence of security risks.

Other features and advantages of the present application will be set forth in the description which follows and become apparent from the description. The objectives and other advantages of the present invention are realized and attained by the structure of the invention.

The above described objects, features, and advantages of the present invention will become more apparent from the following description.

DRAWINGS

In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the specific embodiments or the description of the prior art will be briefly described below, and obviously, the attached in the following description The drawings are some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without any creative work.

1 is a schematic flowchart of a security detection method provided by an embodiment of the present application;

2 is a schematic structural diagram of a security detecting device according to an embodiment of the present application;

3 is a communication connection diagram of a security detection system according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

The technical solutions of the present application will be clearly and completely described in the following with reference to the accompanying drawings. It is obvious that the described embodiments are a part of the embodiments of the present application, and not all of them. An embodiment. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

At present, the existing security detection method is difficult to ensure the accuracy of the identification, and the recognition efficiency is low, which is easy to cause a security risk. Based on this, the security detection method, device, system and electronic device provided by the embodiments of the present application can be utilized. The processing reduces the influence of external environmental factors, and then extracts the feature of the article through the deep learning model based on the convolutional neural network, and uses the classifier trained by the deep learning model to identify the detected object, thus realizing the automatic identification detection of the contraband And while improving the recognition efficiency, it effectively ensures the accuracy of the identification of contraband and prevents the occurrence of security risks.

In order to facilitate the understanding of the embodiment, a security detection method disclosed in the embodiment of the present application is first introduced in detail.

Embodiment 1:

The security detection method provided by the embodiments of the present application may be, but is not limited to, applied to security inspection scenarios of important public places such as airports, ports, ports, subways, courts, and venues of major events.

FIG. 1 is a schematic flow chart of a security detection method provided by an embodiment of the present application. As shown in FIG. 1, the security detection method includes:

Step S101: Acquire an X-ray image acquired by an X-ray machine in the security inspection machine received by the security inspection terminal, and pre-process the X-ray image to obtain a pre-processed X-ray image.

The security terminal can be, but is not limited to, a computer and a console. Specifically, when the product to be tested passes through the security inspection channel of the security inspection machine, the X-ray opportunity provided in the security inspection box of the security inspection machine scans the detection product and generates an X-ray image, and transmits the X-ray image to the security inspection terminal.

In the process of acquiring the X-ray image transmitted by the security check terminal and detecting the X-ray image, the X-ray image is first required to have good performance. However, the preprocessing operation adopted by the embodiment of the present application mainly includes image enhancement and denoising due to external interference and the X-ray machine's own factors, and the preprocessing of the X-ray image includes:

The collected X-ray image is smoothed and denoised by the neighborhood averaging method to obtain a smooth denoised X-ray image;

The edge information of the smoothed and denoised image is enhanced by histogram equalization method, and the preprocessed X-ray image is obtained.

Through the above preprocessing method, useful information such as edge information in the image can be enhanced, the interference (media scattering, high-speed motion and noise interference) is weakened to some extent, the performance of the image is improved, and the features of the image are fully displayed, and more Conducive to late feature extraction and representation.

Step S102: Extract an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes a deep learning model based on a convolutional neural network.

The deep learning model based on the convolutional neural network is trained by the sample sample data exceeding a certain threshold, and the sample sample data includes X-ray pictures corresponding to different forms of contraband. Among them, different forms of contraband include, for example, the state in which the gun is split into individual parts and the state in which the tool is folded. In a preferred embodiment, the above-described deep learning model based on convolutional neural networks can be implemented by the Caffe deep learning framework.

Specifically, the more the number of the above X-ray pictures is, the better, the more data, the better the versatility of the training-generated deep learning model based on the convolutional neural network, such as the above X-ray picture including multiple angles and multiple penetrations. The degree of various contraband pictures, which facilitates the accurate identification of subsequent detection objects, overcomes the influence of external environmental factors, and improves the recognition ability of the deep learning model based on convolutional neural networks.

The step S102 specifically includes: performing the feature training on the pre-processed X-ray image as an input image in a plurality of base layers included in the preset depth learning model, and extracting the multiple connectivity layers in the integration after the training is completed. Or other feature vectors that specify the output of the base layer as the feature of the item to be detected in the preprocessed X-ray image.

Further, before the image feature is processed in a simple and rapid manner, the object feature of the corresponding object to be detected in the pre-processed X-ray image is extracted according to the preset depth learning model in step S102, and further includes:

According to the gradation characteristics of the preprocessed X-ray image, the preprocessed X-ray image is divided into two types: background and template, and the parameter with the largest variance between the two types is taken as the optimal threshold;

The binarized image is obtained by the optimal threshold segmentation, and the binarized image is used as a preprocessed X-ray image.

Among various threshold optimization segmentation methods, OTSU algorithm proposes that the segmentation method based on the variance between classes is recognized as the optimal threshold segmentation algorithm. It divides the image into two categories according to the grayscale characteristics of the image, and then calculates The variance between the two types takes the largest parameter as the optimal threshold, and then uses the optimal threshold segmentation to obtain a good binarized image.

Thereby, by the above-described binarization processing, the gradation value of the pixel on the X-ray image is set to 0 or 255, the amount of data in the X-ray image is greatly reduced, and the image processing speed can be greatly reduced.

Step S103: Identify the item feature by using a classifier trained based on the preset depth learning model to generate a recognition result corresponding to the object to be detected.

The feature extracted in step 102 is used as an input of a classifier trained based on the preset depth learning model, and after the classifier recognizes, the final recognition result is obtained. Specifically, the identification result is a contraband or a non-prohibited item, and may be, but is not limited to, being correctly or incorrectly identified, and applying different picture identifiers. The specific identification method is not limited herein.

In an optional embodiment, the training process of the classifier applied in step 103 includes:

Training the classifier for the above depth feature based on a machine learning algorithm;

The sample data of the above item includes an X-ray picture of the specified different recognition result. The above machine learning algorithm may be a neighboring algorithm, a maximum expectation algorithm, and a support vector machine algorithm. The specific algorithm may be selected according to a specific situation, which is not limited herein.

In an optional embodiment, the item specimen data includes triple data; wherein the triple data includes: source data, forward data belonging to the same category as the source data, and different categories from the source data. Reverse data.

The source data is sample data with the same recognition result randomly obtained from the item sample data.

The forward data is sample data that is randomly obtained from the item sample data and is consistent with the recognition result of the source data; the matching degree of the source data is higher than the matching degree of the forward data.

The reverse data is sample data randomly acquired from the item sample data that is inconsistent with the recognition result of the source data.

In a specific embodiment, the triplet data is: a first picture (source data) with good X-ray image performance in the item sample data, and a second picture with poor performance of the X-ray image captured in the item sample data ( Forward data), and a third picture as reverse data different from the first picture and the second picture recognition result. The recognition result of the first picture and the second picture is a contraband, and the recognition result of the second picture is a non-prohibited item. The second picture has a poorer image performance, such as a difference in definition and resolution from the first picture, and the matching degree is lower than the first picture. The third picture is the reverse data of the reverse comparison during training, and the positive opposition ratio is used once, which further enhances the recognition ability of the classifier.

Step S104, the recognition result of the object to be detected is sent to the security check terminal, so that the security check terminal displays the recognition result.

Specifically, after receiving the recognition result of the object to be detected, the security check terminal performs rendering on the display interface of the display screen to display the recognition result.

In the technical solution provided by the embodiment of the present application, the pre-processing is firstly used to reduce the influence of external environmental factors, and then the feature of the item is extracted by a deep learning model based on a convolutional neural network, and the classifier trained by the deep learning model is to be detected. The object is identified, which realizes the automatic identification and detection of contraband, and improves the recognition efficiency, effectively guarantees the accuracy of the contraband identification, and prevents the occurrence of security risks.

Embodiment 2:

FIG. 2 is a schematic structural diagram of a security detecting device provided by an embodiment of the present application. As shown in FIG. 2, the security detection device includes:

The pre-processing module 11 is configured to acquire an X-ray image acquired by the X-ray machine in the security inspection machine received by the security inspection terminal, and pre-process the X-ray image to obtain a pre-processed X-ray image;

The feature extraction module 12 is configured to extract an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes a deep learning model based on a convolutional neural network ;

The result identification module 13 is configured to identify the item feature by using a classifier trained based on the preset depth learning model to generate a recognition result corresponding to the object to be detected;

The result display module 14 is configured to send the identification result of the object to be detected to the security check terminal, so that the security check terminal displays the recognition result.

Embodiment 3:

FIG. 3 is a diagram showing the communication connection of the security detection system provided by the embodiment of the present application. As shown in FIG. 3, the security detection system includes: a security inspection machine 400, a security inspection terminal 500, and a security identification device 600. The security inspection box of the security inspection machine is provided with an X-ray machine 700, and the security identification device includes the second embodiment as in the second embodiment. The security inspection device; the X-ray machine and the security identification device are respectively connected with the security inspection terminal.

The X-ray machine is configured to collect an X-ray image of the object to be detected passing through the security inspection channel of the security inspection machine, and send the X-ray image to the security inspection terminal.

The security check terminal is configured to send the X-ray image to the security identification device when the received X-ray image is received, and configured to receive the recognition result of the object to be detected sent by the security identification device, and display the recognition result through the display screen .

In an optional embodiment, the identification result includes two types: contraband and non-prohibited; the security detection system further includes an alarm device 800, and the alarm device is connected to the security terminal.

Specifically, the security check terminal is further configured to send an alarm signal to the alarm device when the received recognition result is a contraband, so that the alarm device performs an alarm prompt. The alarm mode of the alarm device includes a light alarm, a voice alarm or a graphic display alarm.

In another alternative embodiment, the bottom of the security inspection channel of the security machine is provided with a pressure sensor 900 that is coupled to the security terminal.

The pressure sensor is configured to collect pressure information on the security channel and send the pressure information to the security terminal. The security terminal is also configured to turn the X-ray machine on or off based on the pressure information.

Specifically, when the security check channel is idling, the pressure value of the pressure sensor is read, and the pressure value is used as the pressure threshold. When the pressure information sent by the pressure sensor received by the security check terminal exceeds the pressure threshold, the object to be detected is to pass the security check. For the channel, the X-ray machine is turned on so that the X-ray machine collects an X-ray image of the object to be detected. When the pressure information sent by the pressure sensor received by the security check terminal is restored to the pressure threshold, it indicates that the object to be detected has been taken away from the security inspection channel, and the X-ray machine is turned off. In this way, the automatic opening and closing of the X-ray machine is realized, which saves energy and prolongs the service life of the machine.

In one embodiment, the security identification device includes the Nvidia Jetson TX2 chip, which maintains a powerful computing power while achieving low power consumption, and can realize the identification of prohibited items in the X-ray picture at the millisecond level. The entire core is only the size of a credit card, which can realize the real-time identification of contraband without modifying the existing X-ray machine, and can be integrated with the X-ray machine to provide identification service.

Embodiment 4:

Referring to FIG. 4, an embodiment of the present application further provides an electronic device 100, including: a processor 40, a memory 41, a bus 42 and a communication interface 43. The processor 40, the communication interface 43 and the memory 41 are connected by a bus 42; The processor 40 is configured to execute an executable module, such as a computer program, stored in the memory 41.

The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is implemented by at least one communication interface 43 (which may be wired or wireless), and may use an Internet, a wide area network, a local network, a metropolitan area network, or the like.

The bus 42 can be an ISA bus, a PCI bus, or an EISA bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one double-headed arrow is shown in Figure 4, but it does not mean that there is only one bus or one type of bus.

The memory 41 is configured to store a program, and the processor 40 executes the program after receiving the execution instruction, and the method executed by the device defined by the flow process disclosed in any of the foregoing embodiments of the present application may be applied to the processing. In processor 40, or implemented by processor 40.

Processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 40 or an instruction in a form of software. The processor 40 may be a general-purpose processor, including a central processing unit (CPU) and a network processor (NP), and may also be a digital signal processor (DSP). ), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device and/or discrete hardware component. The methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software modules can be located in conventional storage media such as random access memory, flash memory, read only memory, programmable read only memory, electrically erasable programmable memory, and/or registers. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and performs the steps of the above method in combination with its hardware.

The security detection device, system and electronic device provided by the embodiments of the present application have the same technical features as the security detection detection method provided by the above embodiments, so that the same technical problem can be solved and the same technical effects can be achieved.

A computer program product for performing a security detection method provided by an embodiment of the present application, comprising a computer readable storage medium storing non-volatile program code executable by a processor, the program code comprising instructions configurable to execute the foregoing method For the specific implementation of the method in the embodiment, refer to the method embodiment, and details are not described herein again.

A person skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the device, the system and the electronic device described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present application. In this regard, each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that comprises one or more of the Executable instructions. It should also be noted that in some alternative implementations, the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions. Moreover, the terms "first", "second" or "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-transitory computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including The instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Finally, it should be noted that the above-mentioned embodiments are only specific embodiments of the present application, and are used to explain the technical solutions of the present application, and are not limited thereto. The scope of protection of the present application is not limited thereto, although reference is made to the foregoing. The present invention has been described in detail with reference to the embodiments of the present invention. It will be understood by those skilled in the art that the technical solutions described in the foregoing embodiments can still be modified within the technical scope of the present disclosure. The changes may be easily conceived, or equivalently substituted for some of the technical features; and the modifications, variations, or substitutions of the present invention are not intended to depart from the spirit and scope of the technical solutions of the embodiments of the present application. Within the scope of protection. Therefore, the scope of protection of the present application should be determined by the scope of the claims.

Claims

A security detection method, characterized in that it comprises:

Obtaining an X-ray image acquired by an X-ray machine in the security inspection machine received by the security inspection terminal, and pre-processing the X-ray image to obtain a pre-processed X-ray image;

Extracting an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes a deep learning model based on a convolutional neural network;

Identifying, by the classifier trained based on the preset depth learning model, the item feature, and generating a recognition result corresponding to the object to be detected;

And transmitting the identification result of the object to be detected to the security check terminal, so that the security check terminal displays the recognition result.
The method according to claim 1, wherein the preprocessing the X-ray image comprises:

The collected X-ray image is smoothed and denoised by a neighborhood averaging method to obtain a smooth and denoised X-ray image;

The edge information of the smoothed and denoised image is enhanced by a histogram equalization method to obtain a preprocessed X-ray image.
The method according to claim 1, wherein the deep learning model based on a convolutional neural network is trained by an item sample data exceeding a certain threshold, the item sample data including contraband corresponding to different forms. picture of.
The method of claim 1 wherein the training process of the classifier comprises:

Depth feature of item specimen data is extracted by using a deep learning model based on convolutional neural network;

Training a classifier for the depth feature based on a machine learning algorithm;

The item specimen data includes an X-ray picture of the specified different recognition result.
A security detection device, comprising:

The pre-processing module is configured to obtain an X-ray image acquired by the X-ray machine in the security inspection machine received by the security inspection terminal, and pre-process the X-ray image to obtain a pre-processed X-ray image;

a feature extraction module, configured to extract an item feature of the corresponding to-be-detected object in the pre-processed X-ray image according to a preset depth learning model, where the preset depth learning model includes deep learning based on a convolutional neural network model;

a result identifying module configured to identify the item feature by using a classifier trained based on the preset depth learning model to generate a recognition result corresponding to the object to be detected;

And a result display module configured to send the identification result of the object to be detected to the security check terminal, so that the security check terminal displays the recognition result.
A security inspection system, comprising: a security inspection machine, a security inspection terminal and a security identification device, wherein the security inspection box of the security inspection machine is provided with an X-ray machine, and the security identification device comprises the security inspection according to claim 5. a device; the X-ray machine and the security identification device are respectively connected to the security check terminal;

The X-ray machine is configured to collect an X-ray image of the object to be detected passing through the security inspection channel of the security inspection machine, and send the X-ray image to the security inspection terminal;

The security check terminal is configured to send the X-ray image to the security identification device when the received X-ray image is received, and configured to receive the recognition result of the object to be detected sent by the security identification device And displaying the recognition result through a display screen.
The system according to claim 6, wherein said identification result comprises two types of contraband and non-prohibited items; said system further comprising an alarm device, said alarm device being connected to said security check terminal;

The security terminal is further configured to send an alarm signal to the alarm device when the received recognition result is a contraband, so that the alarm device performs an alarm prompt.
The system according to claim 6, wherein a bottom of the security inspection channel of the security inspection machine is provided with a pressure sensor, and the pressure sensor is connected to the security inspection terminal;

The pressure sensor is configured to collect pressure information received on the security inspection channel, and send the pressure information to the security inspection terminal;

The security terminal is further configured to turn the X-ray machine on or off according to the pressure information.
The system of any of claims 6-8, wherein the security identification device comprises an Nvidia Jetson TX2 chip.
An electronic device comprising a memory and a processor having stored thereon a computer program executable on the processor, wherein the processor executes the computer program to implement the above claims 1 to 4 The method of any of the preceding claims.