Security inspection machine calibration method and device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of security check, and provides a security check machine calibration method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a security check sample set of a current security check machine, the security check sample set comprising multiple frames of security check sample images; performing color calibration on the security check sample set by using a plurality of groups of calibration hyper-parameters to obtain a calibration sample set corresponding to each group of calibration hyper-parameters; inputting each calibration sample set into the detection model to obtain an identification score of each calibration sample set; and selecting the calibration hyper-parameter corresponding to the calibration sample set with the highest identification score as the target calibration hyper-parameter of the current security inspection machine.

Description

Technical Field

[0001] The present application belongs to the field of security inspection, and in particular, relates to a security inspection machine calibration method and device, electronic equipment and computer-readable storage medium. Background Art

[0002] Security inspection machines are common security inspection tools, widely used in transportation, venue security inspection and other fields. Common security inspection machines generally use X-rays for imaging. X-rays have a very short wavelength and strong penetrating power, and can penetrate materials that visible light cannot penetrate. The security inspection image obtained by the security inspection machine is essentially a grayscale image, and the size of the pixel value represents the density of the object. Since the human eye is not as sensitive to grayscale changes as color changes, in order to facilitate observation, the security inspection machine generally performs color calibration on the security inspection image, that is, assigning a specific color to the specified grayscale range.

[0003] The image detection technology of security inspection machines based on deep learning can improve the efficiency and accuracy of dangerous goods detection and is widely used in various security detection occasions. The detection model of existing security inspection machines is obtained by training a large number of security inspection images through neural networks. The recognition effect of the detection model is directly related to the training samples. Images similar to the training samples can achieve better detection results.

[0004] Since the colors in the security inspection images are assigned by the security inspection machine, different security inspection machines use different sensors and color calibration schemes, resulting in different imaging styles of the security inspection images they capture. That is, the same object has different colors in the security inspection images captured by different security inspection machines. The accuracy of using the trained detection model to identify security inspection images with different imaging styles may drop significantly; to maintain the original accuracy, different detection models need to be trained for different security inspection machines, which requires a large amount of manually labeled sample data for each security inspection machine, creating obstacles to the promotion of intelligent detection of security inspection images. Summary of the invention

[0005] The embodiments of the present application provide a security inspection machine calibration method and device, an electronic device and a computer-readable storage medium, which can solve the problem in the related art that different imaging styles cause obstacles to the promotion of intelligent detection of security inspection images.

[0006] In a first aspect, an embodiment of the present application provides a security inspection machine calibration method, the method comprising: obtaining a security inspection sample set of a current security inspection machine, the security inspection sample set comprising multiple frames of security inspection sample images; using multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, to obtain a calibration sample set corresponding to each set of calibration hyperparameters; inputting each calibration sample set into a detection model respectively, to obtain a recognition score for each calibration sample set; and selecting the calibration hyperparameter corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameter of the current security inspection machine.

[0007] In the second aspect, an embodiment of the present application provides a security inspection machine calibration device, which includes: an acquisition module, used to obtain a security inspection sample set of the current security inspection machine, the security inspection sample set including multiple frames of security inspection sample images; a calibration module, used to use multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, to obtain a calibration sample set corresponding to each set of calibration hyperparameters; a detection module, used to input each calibration sample set into a detection model respectively, to obtain a recognition score for each calibration sample set; a selection module, used to select the calibration hyperparameters corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameters of the current security inspection machine.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the security inspection machine calibration method described in the first aspect above is implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the security inspection machine calibration method described in the first aspect above.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the security inspection machine calibration method described in the first aspect above.

[0011] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by obtaining the security inspection sample set of the current security inspection machine, the security inspection sample set includes multiple frames of security inspection sample images; using multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, and obtaining calibration sample sets corresponding to each set of calibration hyperparameters; inputting each calibration sample set into the detection model respectively, and obtaining the recognition score of each calibration sample set; selecting the calibration hyperparameter corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameter of the current security inspection machine. The calibration hyperparameters are determined based on the principle of the highest recognition score. Using the calibration hyperparameters, the security inspection images obtained by different security inspection machines can be unified into the imaging style applicable to the detection model, so that there is no need to train new detection models for security inspection images with different imaging styles, and the recognition accuracy of security inspection images obtained by different security inspection machines can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application;

[0014] Figure 2 It is a flowchart of a security inspection machine calibration method provided in an embodiment of the present application;

[0015] Figure 3 yes Figure 2 The specific process diagram of S3 in the figure;

[0016] Figure 4 It is a structural schematic diagram of a security inspection machine calibration device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0018] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0019] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0020] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0021] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0023] The security inspection machine calibration method provided in the embodiment of the present application can be applied to electronic devices, including but not limited to servers, server clusters, mobile phones, tablet computers, laptop computers, desktop computers, personal digital assistants, wearable devices and other electronic devices with computing functions. The embodiment of the present application does not impose any restrictions on the specific type of electronic devices.

[0024] Figure 1 FIG. 1 is a block diagram of a partial structure of an electronic device provided in an embodiment of the present application. Figure 1 , the electronic device includes: a processor 10, a memory 20, a bus 30, an input device 40, an output device 50 and a communication device 60. The processor 10 and the memory 20 are connected to each other through the bus 30, and the input device 40, the output device 50 and the communication device 60 are also connected to the bus 30. Those skilled in the art can understand that Figure 1 The structure of the electronic device shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0025] Combine the following Figure 1 A detailed introduction to the various components of electronic equipment:

[0026] The processor 10 is the control center of the electronic device, and can run the program stored in the memory 20 to perform various functions and process data. The processor 10 can be a central processing unit (CPU), and the processor 10 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In some embodiments, the processor 10 may include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0027] The memory 20 is used to store an operating system, an application program, a boot loader, data, and other programs, such as program codes of computer programs. The memory 20 can also be used to temporarily store data required for executing the program and generated. The memory 20 may include a high-speed random access memory, and may also include a non-volatile memory, such as a flash memory, a hard disk, a multimedia card, a card-type memory, etc. The memory 20 may include a storage unit disposed inside the electronic device, such as a hard disk of the electronic device, and / or a removable external storage unit, such as a mobile hard disk, a USB flash drive, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, etc.

[0028] The input device 40 may include at least one of a keyboard, a mouse, a touch panel, a joystick, etc., and is used to collect user input operations to generate corresponding operation instructions.

[0029] The output device 50 is used to output information to be provided to the user. The output device 50 generally includes a display, and optionally, a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. can be used. In addition, the output device can further include a speaker.

[0030] The communication device 60 may include a modem, a network card, etc., for establishing a network connection with other electronic devices and communicating with each other.

[0031] The security inspection machine calibration method provided in the embodiment of the present application can be implemented as a computer software program. For example, the embodiment of the present application provides a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 60, and / or installed from a removable external storage unit. When the computer program is executed by the processor 10, the various functions defined in the security inspection machine calibration method provided in the embodiment of the present application are implemented.

[0032] For ease of understanding, the following is a brief introduction to X-ray imaging.

[0033] The X-ray imaging system includes an X-ray source and a detector that are arranged relatively to each other. The X-ray source is used to generate X-rays, and the detector is used to convert received X-rays into electrical signals.

[0034] In X-ray imaging systems, there are two main types of interactions between photons and matter: the photoelectric effect and Compton scattering. The photoelectric effect and Compton scattering effects are not only related to the energy of the X-rays, but also to the material properties such as the density and atomic number of the matter. Therefore, when X-rays pass through an object, some photons are absorbed or scattered, and some photons pass directly through the object without interacting with the matter. The final effect is that the intensity of the X-rays is attenuated when passing through the object.

[0035] For monochromatic, narrow beam X-rays passing through an arbitrary object, the formula for the intensity of the outgoing X-rays is as follows.

[0036]

[0037] Among them, I0 is the incident ray intensity, I is the outgoing ray intensity, L is the intersection length of the X-ray path through the object, and the coefficient μ is, is the attenuation coefficient of the object The line integral along the intersection line is are the coordinates of the point on the intersection line. Specifically, the intersection line is the intersection portion where the X-ray path passes through the object. The attenuation coefficient of the object is affected by the density of the object and the energy of the X-ray.

[0038] The detector is used to convert the received X-rays into electrical signals, thereby outputting an image. The output original image is a grayscale image, and the size of its pixel value represents the intensity of the received X-rays, which is positively correlated with the intensity of the outgoing rays in the above formula. Assuming that the X-ray source is uniform, monochromatic, and narrow beam, according to the above formula, it can be seen that the size of the pixel value represents the density of the object placed between the X-ray source and the detector.

[0039] Since the human eye is not as sensitive to grayscale changes as color changes, in order to facilitate human observation, security inspection machines generally perform color calibration on security inspection images, that is, assign specific colors to the grayscale range corresponding to the density range of common dangerous goods for operators to identify. There is no unified standard for color calibration, and each manufacturer can design a color calibration solution based on demand.

[0040] Figure 2 A schematic flowchart of a security inspection machine calibration method provided in an embodiment of the present application is shown. As an example but not a limitation, the method can be applied to the above-mentioned electronic device.

[0041] S1: Get the security inspection sample set of the current security inspection machine.

[0042] The security inspection sample set includes multiple security inspection samples, each of which includes a frame of security inspection sample image. Specifically, multiple calibration samples can be prepared, such as luggage, metal knives, lighters, flammable oils, compressed cans, thermos cups, clothing, daily chemicals, food, etc. The current security inspection machine is used to bag the above samples, and the samples are photographed to obtain multiple security inspection sample images.

[0043] In addition to the security inspection sample images, the security inspection samples also include the annotation information of the security inspection sample images. The goal of security inspection is to identify dangerous goods in the images. The dangerous goods in each security inspection sample image can be annotated to obtain the annotation information of each security inspection sample image.

[0044] S2: Use multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, and obtain the calibration sample set corresponding to each set of calibration hyperparameters.

[0045] Each set of calibration hyperparameters includes hyperparameters for the three RGB channels. Optionally, the value range of the hyperparameters is [0.5, 1.5].

[0046] For each set of calibration hyperparameters, the pixel values ​​of the three RGB channels of each frame of the security inspection sample image can be multiplied by the hyperparameters of the corresponding channels, and then rounded and truncated to obtain the calibration sample image corresponding to the security inspection sample image. Each frame of the security inspection sample image in the security inspection sample set is replaced with the corresponding calibration sample image to obtain the calibration sample set. The annotation information is not processed and is still retained.

[0047] The pixel value itself is an integer, but the hyperparameter may have a decimal part. Accordingly, the product obtained by multiplication may have a decimal part. Rounding means removing the decimal part of the product and retaining only the integer part. Specifically, it can be rounded up, rounded down, or rounded up, which is not restricted here. Truncation means setting the pixel value that exceeds the upper limit to the upper limit. For example, the pixel value range is [0,255], the hyperparameter is selected as 1.5, and the rounding method is rounded down. The pixel value of a pixel in the security inspection sample image is 101, and the pixel value of the corresponding pixel in the calibration sample image is 151 after rounding; the pixel value of a pixel in the security inspection sample image is 200, and the pixel value of the corresponding pixel in the calibration sample image is 255 after truncation.

[0048] S3: Input each calibration sample set into the detection model respectively to obtain the recognition score of each calibration sample set.

[0049] like Figure 3 As shown, in a specific embodiment of the present application, the process of obtaining the recognition score of a single calibration sample set includes the following parts.

[0050] S31: Input the calibration sample set into the detection model to obtain the recognition result of the calibration sample set.

[0051] The detection model is a dangerous goods detection model that has been pre-trained using a large number of security inspection images.

[0052] S32: Calculate the recognition evaluation index of the calibration sample set according to the matching degree between the recognition result and the annotation information.

[0053] The recognition evaluation index may include at least one of accuracy, precision, recall rate and other indexes calculated based on the above indexes, which are not limited here.

[0054] S33: Determine a recognition score of the calibration sample set according to the recognition evaluation index of the calibration sample set.

[0055] There is no restriction on the specific calculation method, as long as the recognition score is positively correlated with the recognition effect. For example, the better the recognition effect, the higher the accuracy, precision, recall and other indicators, and the higher the corresponding recognition score.

[0056] The above process is performed for each calibration sample set to obtain the recognition score of each calibration sample set.

[0057] S4: Select the calibration hyperparameters corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameters of the current security inspection machine.

[0058] The higher the recognition score, the closer the color calibration scheme of the corresponding calibration sample set is to the sample set used for detection model training, and the better the performance of the detection model running on the calibration sample set. Selecting the calibration hyperparameters corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameters of the current security inspection machine can effectively ensure the recognition effect of the model without training a new detection model.

[0059] S5: Obtain the security inspection image from the current security inspection machine.

[0060] S6: Use target calibration hyperparameters to perform color calibration on security inspection images.

[0061] Specifically, the pixel values ​​of the three RGB channels of the security inspection image may be multiplied by the hyperparameters of the channels corresponding to the target calibration hyperparameters, and then rounded and truncated to achieve color calibration.

[0062] S7: Input the security inspection image into the detection model to obtain the recognition result of the security inspection image.

[0063] S5-S7 describe the specific process of calibration using target calibration hyperparameters. In some embodiments, S5-S7 and S1-S4 can be performed by different devices.

[0064] Through the implementation of this embodiment, the calibration hyperparameters are determined based on the principle of the highest recognition score. Using the calibration hyperparameters, the security inspection images obtained by different security inspection machines can be unified into an imaging style applicable to the detection model. Therefore, there is no need to train new detection models for security inspection images of different imaging styles, and the recognition accuracy of security inspection images obtained by different security inspection machines can be guaranteed.

[0065] Figure 4 A schematic structural diagram of a security inspection machine calibration device provided in an embodiment of the present application is shown. The security inspection machine calibration device includes an acquisition module 11, a calibration module 12, a detection module 13 and a selection module 14.

[0066] The acquisition module 11 is used to acquire the security inspection sample set of the current security inspection machine, and the security inspection sample set includes multiple frames of security inspection sample images.

[0067] The calibration module 12 is used to use multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, and obtain a calibration sample set corresponding to each set of calibration hyperparameters.

[0068] The detection module 13 is used to input each calibration sample set into the detection model to obtain the recognition score of each calibration sample set.

[0069] The selection module 14 is used to select the calibration hyper-parameters corresponding to the calibration sample set with the highest recognition score as the target calibration hyper-parameters of the current security inspection machine.

[0070] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0071] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0072] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0073] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0074] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0077] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0078] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A security inspection machine calibration method, characterized in that: The method comprises: Obtaining a security inspection sample set of a current security inspection machine, wherein the security inspection sample set includes multiple frames of security inspection sample images; Using multiple sets of calibration hyperparameters to perform color calibration on the security inspection sample set respectively, to obtain calibration sample sets corresponding to each set of calibration hyperparameters; Inputting each of the calibration sample sets into a detection model respectively to obtain a recognition score of each of the calibration sample sets; The calibration hyperparameter corresponding to the calibration sample set with the highest recognition score is selected as the target calibration hyperparameter of the current security inspection machine.

2. The method according to claim 1, characterized in that Each group of calibration hyperparameters includes hyperparameters of three channels of RGB. The color calibration of the security inspection sample set is performed using multiple groups of calibration hyperparameters respectively, and the calibration sample set corresponding to each group of calibration hyperparameters includes: For each set of the calibration hyperparameters, the pixel values ​​of the three RGB channels of each frame of the security inspection sample image are multiplied by the hyperparameters of the corresponding channels, and then rounded and truncated to obtain a calibration sample image corresponding to the security inspection sample image; Each frame of the security inspection sample image in the security inspection sample set is replaced with the corresponding calibration sample image to obtain the calibration sample set.

3. The method according to claim 2, characterized in that The value range of the hyperparameter is [0.5, 1.5].

4. The method according to claim 2, characterized in that The truncation includes setting the pixel value exceeding the upper limit as the upper limit.

5. The method according to claim 1, characterized in that The security inspection sample set also includes annotation information of each of the security inspection sample images. The step of inputting each of the calibration sample sets into the detection model to obtain the recognition score of each of the calibration sample sets includes: For each calibration sample set, inputting the calibration sample set into a detection model to obtain a recognition result of the calibration sample set; Calculating the recognition evaluation index of the calibration sample set according to the matching degree between the recognition result and the annotation information; A recognition score of the calibration sample set is determined according to a recognition evaluation index of the calibration sample set.

6. The method according to claim 5, characterized in that The obtaining of the security inspection sample set of the current security inspection machine includes: Obtaining the annotation information of each of the security inspection sample images.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: Acquire a security inspection image from the current security inspection machine; Performing color calibration on the security inspection image using the target calibration hyperparameters; The security inspection image is input into the detection model to obtain a recognition result of the security inspection image.

8. A security inspection machine calibration device, characterized in that: The device comprises: An acquisition module, used to acquire a security inspection sample set of the current security inspection machine, wherein the security inspection sample set includes multiple frames of security inspection sample images; A calibration module, used to perform color calibration on the security inspection sample set using multiple sets of calibration hyperparameters to obtain calibration sample sets corresponding to each set of calibration hyperparameters; A detection module, used to input each calibration sample set into a detection model to obtain a recognition score of each calibration sample set; The selection module is used to select the calibration hyperparameter corresponding to the calibration sample set with the highest recognition score as the target calibration hyperparameter of the current security inspection machine.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images