CN117808716A

CN117808716A - Security check image processing method and device and electronic equipment

Info

Publication number: CN117808716A
Application number: CN202311846736.6A
Authority: CN
Inventors: 王天舒; 李俊; 黄天; 降俊汝
Original assignee: Hangzhou Ruiying Technology Co ltd
Current assignee: Hangzhou Ruiying Technology Co ltd
Priority date: 2023-12-28
Filing date: 2023-12-28
Publication date: 2024-04-02

Abstract

The application provides a security inspection image processing method and device and electronic equipment. According to the embodiment, the hardening correction coefficient is obtained through the standard die body correction data of the standard die body, the hardening correction coefficient is used for correcting the target data to be corrected, which is obtained after the data acquisition of the security inspection object of the security inspection equipment is carried out, so that the hardening influence of the transmission belt on the X-ray signal can be restrained, the deviation between the non-transmission belt region data and the transmission belt region data (such as low-energy data gray scale and atomic number) is repaired, and the imaging effect of the security inspection object is improved.

Description

Security check image processing method and device and electronic equipment

Technical Field

The present disclosure relates to image processing technologies, and in particular, to a security inspection image processing method and apparatus, and an electronic device.

Background

In a specific application, the X-ray security inspection device is shown in fig. 1, and mainly may include a radiation source, a collimator, a detector, a conveying mechanism, an image processing unit, and the like.

In a specific application, the radiation source is used to emit an X-ray signal which is collimated by a collimator into a fan beam to the detector constituting a scanning plane. The security inspection object is placed on a conveyor belt (such as a belt) of the conveying mechanism and driven by the conveying mechanism to pass through the scanning plane along a specific direction. The detector, such as a linear array detector, may comprise at least one detection plate, each of which may comprise at least one detection unit. In the process that a security inspection object placed on a conveying belt of the conveying mechanism passes through a scanning plane, signal values (such as digital signal values finally obtained through conversion of optical signals, electric signals and digital signals after an X-ray signal arrives) measured by a detection unit on each detection plate in the detector in the same integration time are organized into a row of data collected under the integration time. And the image processing unit splices the columns of data according to the sequence of the integration time, and finally completes the imaging process of the security inspection object. Here, the integration time refers to the time of acquiring signal values set by the detection units on the respective detection boards in the detector, similar to the exposure time of the visible light camera.

In the imaging process of the security inspection object, as shown in fig. 2, a part of X-ray signals pass through the security inspection object and are directly received by a detection unit in the detector (at this time, the detection unit can be considered to not detect the transmission belt region, the X-ray signals received by the detection unit are recorded as non-transmission belt region data), while another part of X-ray signals pass through the security inspection object and further pass through the transmission belt region and are received by a detection unit in the detector (at this time, the detection unit can be considered to detect the detection unit of the transmission belt region, the X-ray signals received by the detection unit are recorded as transmission belt region data), if the hardening effect of the transmission belt on the X-ray signals is not negligible, the effect can cause a larger difference between the non-transmission belt region data and the transmission belt region data (such as low-energy data gray scale, atomic number and the like), and the imaging of the security inspection object is affected (such as the image is deviated as shown in fig. 3).

Disclosure of Invention

The application provides a security inspection image processing method, a security inspection image processing device and electronic equipment, so as to inhibit hardening influence of a transmission belt on X-ray signals.

The embodiment of the application provides a security inspection image processing method, which is applied to X-ray security inspection equipment and comprises the following steps:

If the occurrence of a transmission band hardening event of a transmission band deployed on the X-ray security inspection equipment is found, the boundary detection position of the transmission band and target data to be corrected are obtained; wherein the belt hardening event is used to indicate that the belt caused hardening of the X-ray signal; the boundary detection position of the transmission belt is used for distinguishing a first type detection unit and a second type detection unit in the X-ray security inspection equipment; the first type of detection units comprise detection units for detecting the area of the transmission belt, and the second type of detection units comprise detection units for not detecting the area of the transmission belt; the target data are data obtained by carrying out full-load background correction on low-energy data detected by a second type detection unit in first security inspection data, wherein the first security inspection data are obtained by carrying out data acquisition on security inspection objects placed on a transmission belt within the same t1 integration time by a detection unit deployed on X-ray security inspection equipment;

obtaining a hardening correction coefficient; the hardening correction coefficient is obtained based on standard die body correction data, wherein the standard die body correction data is obtained by carrying out full-load background correction on second security check data, and the second security check data is obtained by carrying out data acquisition on standard die bodies placed on a transmission belt within the same t0 integration time by a detection unit deployed on X-ray security check equipment;

And correcting the target data through the hardening correction coefficient to obtain target correction data.

The embodiment of the application provides a security check image processing device, and the device is applied to X-ray security check equipment, includes:

the acquisition unit is used for acquiring the boundary detection position of the transmission belt and target data to be corrected when the transmission belt hardening event of the transmission belt deployed on the X-ray security inspection equipment is found; wherein the belt hardening event is used to indicate that the belt caused hardening of the X-ray signal; the boundary detection position of the transmission belt is used for distinguishing a first type detection unit and a second type detection unit in the X-ray security inspection equipment; the first type of detection units comprise detection units for detecting the area of the transmission belt, and the second type of detection units comprise detection units for not detecting the area of the transmission belt; the target data are data obtained by carrying out full-load background correction on low-energy data detected by a second type detection unit in first security inspection data, wherein the first security inspection data are obtained by carrying out data acquisition on security inspection objects placed on a transmission belt within the same t1 integration time by a detection unit deployed on X-ray security inspection equipment; the method comprises the steps of,

And the correction unit is used for correcting the target data through the hardening correction coefficient to obtain target correction data.

The embodiment of the application provides electronic equipment, which comprises: a processor and a machine-readable storage medium; the machine-readable storage medium has stored thereon computer instructions which, when executed by a processor, implement the steps in the above method.

As can be seen from the above technical solution, in this embodiment, the hardening correction coefficient is obtained by using the standard die body correction data of the standard die body, and the target data to be corrected obtained after the data acquisition is performed on the security inspection object subjected to the security inspection by the X-ray security inspection is corrected by using the hardening correction coefficient, which can inhibit the hardening effect of the transmission belt on the X-ray signal, repair the deviation between the non-transmission belt region data and the transmission belt region data (such as low-energy data gray scale, atomic number, etc.), and improve the imaging effect of the security inspection object.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 is a schematic structural diagram of an X-ray security inspection device provided in an embodiment of the present application;

Fig. 2 is a schematic diagram of detection of an X-ray security inspection apparatus according to an embodiment of the present application;

FIG. 3 is a schematic diagram illustrating a hardening effect caused by a conveyor belt according to an embodiment of the present disclosure;

FIG. 4 is a flow chart of a method provided in an embodiment of the present application;

FIG. 5 is a schematic diagram of a calibration structure according to an embodiment of the present application;

FIG. 6 is a schematic diagram of standard motif atomic number data provided in an embodiment of the present application;

FIG. 7 is a schematic diagram of smoothing standard motif atomic number data according to an embodiment of the present disclosure;

fig. 8a is a schematic diagram of a transmission band boundary detection position according to an embodiment of the present application;

fig. 8b is a schematic diagram of a transmission band artifact provided in an embodiment of the present application;

fig. 9 is a schematic diagram of transmission band artifact correction according to an embodiment of the present application;

FIG. 10 is a schematic diagram of full load correction data provided in an embodiment of the present application;

fig. 11 is a schematic diagram of transmission band artifact correction according to an embodiment of the present application;

FIG. 12 is a block diagram of an apparatus according to an embodiment of the present application;

fig. 13 is a hardware configuration diagram provided in an embodiment of the present application.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.

The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

In order to better understand the technical solutions provided by the embodiments of the present application and make the above objects, features and advantages of the embodiments of the present application more obvious, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.

Referring to fig. 4, fig. 4 is a flowchart of a method provided in an embodiment of the present application. The method is applied to X-ray security inspection equipment. As shown in fig. 4, the process may include the steps of:

step 401, if a belt hardening event occurs in a belt deployed on the X-ray security inspection device, acquiring a belt boundary detection position and target data to be corrected.

In this embodiment, a belt hardening event is used to indicate that the belt, such as a belt, causes hardening of the X-ray signal. Here, hardening of the X-ray signals is caused by so-called conveyor belts, such as belts, etc., in particular, the difference between the conveyor belt region data detected by the detector disposed on the X-ray security inspection apparatus (i.e., the X-ray signals after passing through the security inspection object and further through the conveyor belt region) and the non-conveyor belt region data (i.e., the X-ray signals received by the detector after passing through the security inspection object without passing through the conveyor belt region) is large, which affects the imaging of the security inspection object.

Alternatively, in this embodiment, the belt hardening event may be determined when calibrating the X-ray security inspection apparatus, and the calibration process will be described below by way of example, which is not repeated here.

In this embodiment, the transmission band boundary detection position refers to position information of a boundary detection unit in the X-ray security inspection device, where the transmission band region is detected, and each detection unit disposed in the X-ray security inspection device can be distinguished based on the transmission band boundary detection position, so as to distinguish a first type of detection unit from a second type of detection unit. Here, the first type of detection unit includes a detection unit that detects a belt region. The second type of detection unit comprises detection units that do not detect the conveyor belt region.

Here, when a security inspection object is inspected, an X-ray signal sent by a ray source passes through the security inspection object and then passes through the conveyor belt region to reach the detection unit, and the detection unit at this time can be considered to detect the detection unit of the conveyor belt region, and belongs to the first detection unit. In contrast, when a security inspection object is inspected, an X-ray signal sent by the ray source passes through the security inspection object and then directly reaches the detection unit, and the detection unit at the moment can consider that the detection unit in the transmission belt area is not detected, and belongs to a second type of detection unit.

Alternatively, in the present embodiment, the conveyor belt boundary detection position may also be determined when calibrated for the X-ray security inspection apparatus. Also described below.

In a specific implementation, the hardening effect of the transmission belt on the X-ray signal is most intuitive, and the effect is that the difference between the low-energy data in the non-transmission belt region data and the low-energy data in the transmission belt region data is large, so in this embodiment, the target data is the data after the low-energy data detected by the second type detection unit in the first security check data is subjected to full background correction.

Optionally, in this embodiment, the data detected by any detection unit deployed on the X-ray security inspection device at any integration time may include high-energy data and low-energy data. In a specific implementation, as an embodiment, the detection unit deployed on the X-ray security inspection device may be a dual-energy detection unit, which may include a first subunit and a second subunit, where the data detected by the first subunit is low-energy data, and the data detected by the second subunit is high-energy data. Based on the above, the target data may be the data after the low-energy data detected by the first subunit of each detecting unit in the second detecting unit is subjected to the full-load background correction in the first security check data.

Here, the first security inspection data are obtained by data acquisition of security inspection objects placed on the conveyor belt by a detection unit deployed on the X-ray security inspection device within the same t1 integration times. The data detected at any integration time based on any detection unit as described above may include high-energy data and low-energy data, and the first security check data may include first high-energy data and first low-energy data; here, the first high-energy data is composed of high-energy data detected by the second sub-unit in each detection unit (including the first type detection unit and the second type detection unit) at each integration time, and the first low-energy data is composed of low-energy data detected by the first sub-unit in each detection unit (including the first type detection unit and the second type detection unit) at each integration time.

Step 402, obtaining a hardening correction coefficient, wherein standard die body correction data is obtained by carrying out full background correction on second security check data, and the second security check data is obtained by carrying out data acquisition on standard die bodies placed on a transmission belt within the same t0 integration time by a detection unit deployed on an X-ray security check device.

In this embodiment, the determination of the hardening correction coefficient may refer to the calibration process of the X-ray security inspection apparatus described below, which is not described herein.

In this embodiment, the standard mold body may be a mold body with uniform material, for example, an L-shaped standard mold body.

In this embodiment, the standard die body correction data includes high-energy correction data and low-energy correction data of at least one detection unit at least one integration time, where the high-energy correction data of any detection unit at any integration time refers to the high-energy data detected by the detection unit at the integration time (for example, the data detected by the second subunit of the detection unit) obtained after full background correction is performed, and the low-energy correction data of any detection unit at any integration time refers to the low-energy data detected by the detection unit at the integration time (for example, the data detected by the first subunit of the detection unit) obtained after full background correction is performed.

And step 403, correcting the target data by the hardening correction coefficient to obtain target correction data.

Alternatively, in the present embodiment, the above target data may be corrected according to the following formula:

l1 (n) =l (n) ×k; wherein L (n) represents the target data, k represents the hardening correction coefficient, and L1 (n) represents the corrected target data. Here, n represents a detection unit in a non-transmission band region.

Thus, the flow shown in fig. 4 is completed.

As can be seen from the flow shown in fig. 4, in this embodiment, the hardening correction coefficient is obtained by using the standard die body correction data of the standard die body, and the hardening correction coefficient is used to correct the target data to be corrected obtained after the data acquisition of the security inspection object through the X-ray security inspection, which can inhibit the hardening effect of the transmission belt on the X-ray signal, repair the deviation between the non-transmission belt region data and the transmission belt region data (such as low-energy data gray scale, atomic number, etc.), and improve the imaging effect of the security inspection object.

The calibration process described above is described below:

as shown in fig. 5, when calibration is performed, the detection unit deployed on the X-ray security inspection device performs data acquisition on the standard die body placed on the conveyor belt within the same t0 integration time to obtain second security inspection data. And then carrying out full-load background correction on the second security inspection data to obtain standard die body correction data. The full background correction here is specifically: and carrying out full-load background correction on the second security data by utilizing the background data and full-load data which are obtained before the second security data. For example, full background correction may be implemented as follows: Wherein (1)>Representing the background data of the image,representing full data.

During calibration, the occurrence of a belt hardening event in the belt may be determined based on the standard phantom correction data. For example, first, obtaining standard die body atomic number data based on the standard die body correction data, and if the standard die body atomic number data meets a set hardening requirement, determining that a transmission belt hardening event occurs in the transmission belt.

In this embodiment, atomic number data is used to distinguish between values of substances such as air and non-air. As one example, the standard motif atomic number data herein may be composed of target atomic numbers corresponding to a plurality of detection units.

As an embodiment, the target atomic number of any detection unit is determined from the candidate atomic number of that detection unit at least one integration time. The candidate atomic number of any detection unit at any integration time is determined according to the high-energy correction data and the low-energy correction data detected by the detection unit at the integration time, for example, the candidate atomic number can be determined according to the following formula:wherein t represents an integration time, i represents an ith detection unit, H represents high-energy data of the ith detection unit at the integration time t, and L represents low-energy data of the ith detection unit at the integration time t. R is R _it Representing the candidate atomic number of the ith detection cell at integration time t.

Optionally, after obtaining the candidate atomic number of each detecting unit under each integration time, denoising the candidate atomic number of each detecting unit under different integration times for each detecting unit to obtain the reference atomic number corresponding to the detecting unit. Here, denoising specifically removes the influence of the air region, and in general, the atomic number under the air region is generally lower than a set threshold (for example, the atomic number is 0), and denoising the candidate atomic numbers of the detection unit at different integration times may include: candidate atomic numbers below a set threshold are deleted from the candidate atomic numbers at different integration times of the detection unit. Based on the above denoising, it is finally possible to realize: for each detection unit, if the candidate atomic number of the detection unit at an integration time meets a set requirement (for example, is greater than the set threshold), the candidate atomic number at the integration time is referred to as a reference atomic number at the integration time. And finally obtaining the reference atomic number corresponding to the detection unit.

And then, determining the target atomic number of the detection unit according to the reference atomic number of the detection unit. For example, the average value of the reference atomic numbers of the detection unit is calculated, and the calculation result is determined as the target atomic number of the detection unit. Finally, for any detection unit, its target atomic number may be a one-dimensional vector to mitigate noise effects. And then organizing the target atomic numbers of all the detection units together to obtain the standard die body atomic number data. FIG. 6 illustrates, by way of example, standard motif atomic number data.

After obtaining the atomic number data of the standard phantom, the standard phantom is generally a single homogeneous material, and if the target atomic numbers of the detection units are found to satisfy the third set balance requirement (e.g., substantially the same or the difference between the target atomic numbers is within the set range). It is determined that the conveyor belt does not cause hardening of the X-ray signal, which means that the conveyor belt deployed on the X-ray security device does not have a conveyor belt hardening event. On the contrary, if the target atomic numbers of the detection units are found to meet the first set balance requirement (for example, the difference between the target atomic numbers is out of the set range, which means that there is a large deviation), for example, the standard phantom atomic number data shown in fig. 6, it is determined that the transmission band will cause hardening of the X-ray signal, and this means that the transmission band disposed on the X-ray security inspection device has a transmission band hardening event.

Based on this, as an embodiment, the standard die body atomic number data satisfying the set hardening requirement may be: the target atomic number of each detection unit in the standard motif atomic number data meets a first set balance requirement.

In this embodiment, the absolute value of the gradient may reflect the equilibrium condition, and based on this, the present embodiment may further perform at least one of specified smoothing processing, such as mean filtering, gaussian filtering, box filtering, and the like, on the standard motif atomic number data to obtain a processing result. The following formula illustrates the smoothing process:

Wherein,represents standard motif atomic number data, and smooth represents at least one of smoothing such as mean filtering, gaussian filtering, box filtering, etc.)>The processing result is shown. Fig. 7 shows the processing result by way of example.

Then, the absolute gradient value of the processing result can be calculated, for example, the absolute gradient value is calculated according to the following formula:wherein gradient () represents the absolute value function of the gradient,/->The absolute value of the gradient representing the result of the above-mentioned processing. In this embodiment, the absolute gradient values of the processing results include absolute gradient values corresponding to the respective detection units. For example, for a non-first detection unit (i-th detection unit is taken as an example), the absolute value of the gradient corresponding to the i-th detection unit may be determined by the atomic number corresponding to the i-1 th detection unit and the atomic number corresponding to the i-th detection unit in the processing result (for example, the difference between the atomic number corresponding to the i-1 th detection unit and the atomic number corresponding to the i-th detection unit divided by the positional deviation between the i-1 th detection unit and the i-th detection unit). Whereas for the first detection unit its absolute value of the gradient may be a default value.

Generally, if the absolute gradient values of the processing results meet the fourth set balance requirement (for example, the absolute gradient values of the detection units are substantially the same, or the absolute gradient values of the detection units are within a set range), then the transmission belt is considered to not cause hardening of the X-ray signal, which means that the transmission belt deployed on the X-ray security inspection apparatus will not have a transmission belt hardening event. On the contrary, if the absolute gradient value of the processing result meets the second set balance requirement (for example, the difference between the absolute gradient values of the detection units is out of the set range, which means that a large deviation exists), the transmission belt is determined to cause the hardening of the X-ray signal, and at the moment, the hardening event of the transmission belt occurs in the transmission belt deployed on the X-ray security inspection equipment.

How to determine the belt hardening event during calibration is described above, and the following description is made of the belt boundary detection position:

as an embodiment, the above-mentioned detection position of the boundary of the transmission belt may be determined depending on the absolute value of the gradient of each detection unit in the above-mentioned processing result, for example, the absolute value of the gradient of each detection unit is subjected to threshold filtering to set the absolute value of the gradient smaller than the set threshold to a specified value. Taking the example that the designated value is 0 as an example, if the absolute value of the gradient of the i-th detection unit is smaller than the set threshold T, the absolute value of the gradient of the i-th detection unit is set to 0, and the following formula is exemplified:fig. 8a illustrates threshold filtering. And then, determining the position of a detection unit corresponding to the absolute value of the target gradient as the boundary detection position of the transmission belt. The target gradient absolute value here is different from the above specified value, which may be the maximum gradient absolute value. If the position of the detection unit corresponding to the maximum absolute value of the gradient is the position of the 100 th detection unit, the position of the 100 th detection unit can be used as the boundary detection position of the transmission belt. Finally, the determination of the boundary detection position of the transmission belt is realized.

After determining the detection position of the boundary of the transmission belt, the first detection unit and the second detection unit can be distinguished. For example, as shown in fig. 8a, if the position of the 100 st detection unit is taken as the boundary detection position of the transmission belt, the embodiment may take the 1 st to 100 th detection units as the second type of detection units, and take the remaining detection units (for example, the 101 st to 1400 th detection units) as the first type of detection units.

The hardening correction coefficient is described further below:

as an embodiment, the hardening correction coefficient may be determined based on an atomic number corresponding to the first type of detection unit and an atomic number corresponding to the second type of detection unit. Here, the atomic numbers corresponding to the first type of detection units refer to candidate atomic numbers of each detection unit in the first type of detection units under each integration time.

The atomic number corresponding to the second type of detection unit is determined based on the high-energy correction data and the low-energy correction data of each detection unit in the second type of detection unit at each integration time.

As one embodiment, the atomic numbers corresponding to the first type of detection units may be obtained by performing a first assignment operation on candidate atomic numbers of each detection unit in the first type of detection units at each integration time. The first specification operation is, for example, an average value operation, or other operations, and the present embodiment is not particularly limited. Taking the first specified operation as an average value operation as an example, the following shows the atomic numbers corresponding to the first type of detection units: mean () represents the mean operation,/>Representing candidate atomic numbers for each detection cell in the first class of detection cells at each integration time.

As an embodiment, the atomic number corresponding to the second type of detection unit may be determined by: adjusting the low-energy correction data of each detection unit in the second type of detection units under each integration time based on the hardening correction coefficient k to obtain target low-energy correction data of each detection unit in the second type of detection units under each integration time; for each detection unit in the second type of detection units, determining an adjusted atomic number of the detection unit based on the high-energy data and the target low-energy correction data of the detection unit at each integration time; and performing a first specified operation on the adjusted atomic numbers of the detection units in the second type of detection units under each integration time to obtain the atomic numbers corresponding to the second type of detection units.

Optionally, each of the second type of detection unitsThe target low-energy correction data of the detection unit under each integration time can be L ₂ * k; wherein L2 represents low energy correction data at any integration time for any detection unit of the second type of detection unit. Correspondingly, the above-mentioned adjusted atomic number can be calculated by the following formula: Wherein i represents any one of the second type of detection units (i-th detection unit), t represents any one of the integration times of the i-th detection unit, R _i-t Indicating the atomic number, H, of the ith detection cell adjusted at integration time t ₂ High-energy correction data, L, representing the ith detection cell at integration time t ₂ * k represents the target low-energy correction data of the ith detection unit at the integration time t, L ₂ Indicating low energy correction data for the ith detection cell at integration time t.

It can be seen that the final atomic number corresponding to the second type of detection unit will contain a hardening correction coefficient k, and then the hardening correction coefficient k is determined according to the principle that the error between the atomic number corresponding to the first type of detection unit and the atomic number corresponding to the second type of detection unit is minimum. The final hardening correction coefficient k is represented by the following formula:wherein (1)>Representing the atomic number, R_mean, corresponding to a first type of detection unit ₂ Representing the atomic number corresponding to the second type of detection unit.

It should be noted that, in this embodiment, when the security inspection object enters the X-ray security inspection device to perform security inspection, the X-ray security inspection device is triggered to start the radiation source to collect the current latest full-load data The full data->Full data +.>

On this premise, the present embodiment can be based on the latest full-load dataAnd carrying out full-load background correction on the first high-energy data and the first low-energy data in the first security check data respectively. Alternatively, in the present embodiment, full-load background correction of high-energy data and low-energy data in the second security data or full-load background correction of high-energy data and low-energy data in the current first security data may be performed in units of stripes regardless of the above-described calibration. Here, either stripe is composed of t1 columns of data. Any column consists of high-energy data detected by n1 detection units used for detection in the X-ray security inspection device at the same integration time. For example, any column of data in any one band of the first high-energy data is composed of high-energy data detected by n1 detection units used for detection in the X-ray security inspection device at the same integration time; any column of data in any one of the first low-energy data is composed of low-energy data detected by n1 detection units used for detection in the X-ray security inspection device at the same integration time.

Taking the high energy data stripe as an example, the full background correction is shown as follows: The low energy data stripes are similar and will not be described in detail.

In a specific application, the long-time running of the X-ray security inspection equipment can cause the phenomenon of vertical deflection of the transmission belt. This phenomenon may lead to transmission band artifacts such as the transmission band artifact diagram shown in fig. 8 b. Based on this, this embodiment needs to further suppress the transmission band artifact. The following is described by fig. 9:

referring to fig. 9, fig. 9 is a schematic diagram of transmission band artifact correction according to an embodiment of the present application. As shown in fig. 9, the process may include the steps of:

step 901, a transmission band artifact location range is obtained.

Here, the transmission band artifact location range includes the location of the detection unit that acquired the transmission band artifact; the width of the transmission band artifact position range is W _sub 。

As an embodiment, if it is found that the belt deployed on the X-ray security inspection apparatus has a belt hardening event, the positions of the detection units that are adjacent to the boundary detection positions of the belt and meet the set requirements may be combined into a belt artifact position range. For example, it can be according to W _sub The positions of the respective detection units in a set range (for example, a range of 5 detection unit positions) centering on the above-mentioned transmission band boundary detection position are selected to constitute a transmission band artifact position range.

As an embodiment, if it is found that the transmission band deployed on the X-ray security inspection apparatus does not have a transmission band hardening event, high-energy data mutation in full-load data may be caused due to transmission band offset, at this time, full-load background correction may be performed on full-load data (i.e., first full-load data) acquired before and background data to obtain full-load correction data, and then a reference detection unit is determined based on an absolute gradient value of each detection unit in the full-load correction data, and the position range of the transmission band artifact is determined according to the position of each reference detection unit.

In this embodiment, the first full data is collected by a detection unit in the X-ray security device under the triggering of a current security event, which is generated based on the triggering of a security object currently to be checked via the X-ray security device. The second full data is acquired by a detection unit in the X-ray security inspection device before the first full data is acquired. For example, the first full data is as described aboveThe second full data is the above +.>As one example, the full correction data may be represented by the following equation:

Representing full correction data. Fig. 10 shows, by way of example, full-load correction data.

In this embodiment, the full-load background correction for the second full-load data may be full-load background correction for high-energy data or low-energy data in the second full-load data, which is not particularly limited and does not affect the determination of the above-mentioned transmission band artifact position range.

In the present embodiment, determining the reference detection unit based on the absolute value of the gradient of each detection unit in the full-load correction data may include:

calculating absolute gradient values of full correction data according to the following Wherein |gradient () | represents gradient absolute value operation; then, absolute value of gradient for each detection unit +.>And carrying out threshold division, and finding out all detection units with gradient absolute values larger than a preset gradient absolute value threshold value, wherein the found detection units are the reference detection units.

After the reference detection units are found, determining the transmission band artifact location range according to the locations of the reference detection units may be: the positions of the reference detection units are directly combined into the transmission band artifact position range. For example, a reference probe unit at a start position and a reference probe unit at an end position are found in the deployment order of the probe units, and the positions from the reference probe unit at the start position to the reference probe unit at the end position are determined as the transmission band artifact position ranges [ w1, w2].

Step 902, for each stripe, after the stripe is subjected to full background correction, obtaining transmission band artifact data from correction data of the stripe based on a transmission band artifact position range, determining correction parameters corresponding to the transmission band artifact data based on the transmission band artifact data, and correcting each transmission band artifact data by using the correction parameters corresponding to each transmission band artifact data.

In this step 902, each stripe may be a stripe in the first high energy data or the first low energy data. The correction data for the band after it has been subjected to full background correction may be:

if the stripe correction data has a height and a width of width, the embodiment can obtain the stripe correction data with the height of width of W _sub Is provided. The transmission band artifact data is composed of the following data in the band correction data: and transmitting the corrected data after the background correction of the data detected by the detection unit in the artifact position range of the transmission band. If the transmission band artifact data is represented by: b=d (0:height-1, w 1:w2).

In this embodiment, in the step 902, determining the correction parameter corresponding to the transmission band artifact data based on the transmission band artifact data may include: performing a second specified operation such as average value processing on the data of each detection unit under each integration time in the transmission band artifact data to obtain an operation result V _{Calculation of} (w); for V _{Calculation of} (w) performing specified smoothing such as mean filtering, gaussian filtering, and box filtering to obtain smoothed result V _smooth The method comprises the steps of carrying out a first treatment on the surface of the For V _{Calculation of} (w) and V _smooth A third prescribed operation such as subtraction operation, division operation, or the like is performed to obtain a correction coefficient.

Correspondingly, the correcting each transmission band artifact data by using the correction parameter corresponding to each transmission band artifact data includes: and carrying out third specified operation on the transmission band artifact data and correction parameters corresponding to the transmission band artifact data according to each transmission band artifact data. Artifact correction is finally achieved.

The following is an example description:

taking high-energy data as an example, the transmission band artifact data is formed by data obtained by correcting high-energy data detected by the detection units in the transmission band artifact position range by full load background, and the embodiment can perform mean value operation on the high-energy data of each detection unit in the transmission band artifact data under each integration time, for example, the following formula:

then, the mean value operation result V _mean (w) performing a specified smoothing process such as mean filtering, gaussian filtering, box filtering, etc. to eliminate variation in gray scale caused by belt artifacts to obtain a smoothed result V _smooth 。V _smooth Represented by the formula: v (V) _smooth ＝smooth(V _mean (w))。

As an example, V _mean And V is equal to _smooth Subtracting to obtain correction coefficient V _cali1 。V _cali1 Represented by the formula: v (V) _cali1 ＝V _mean -V _smooth 。V _cali1 A gray difference value indicating a gray error of the edge of the transmission band. Then, for the transmission band artifact data, subtracting the correction parameter corresponding to the transmission band artifact data from the transmission band artifact data, specifically: b (B) _cali (h,w)＝B(h,w)-V _cali1 (w); wherein h is in the range of [ 0:height-1 ]]W is in the range of [ 0:W _sub ]. I.e. a correction of the transmission band artifact data is achieved.

As another example, V _mean And V is equal to _smooth Dividing to obtain correction coefficient V _cali2 。V _cali2 Indicating a transmission band edge gray scale weighted estimation. V (V) _cali2 By the following tableThe illustration is:then, for the above transmission band artifact data, dividing the transmission band artifact data by a correction parameter corresponding to the transmission band artifact data, specifically: />Wherein h is in the range of [ 0:height-1 ]]W is in the range of [ 0:W _sub ]. I.e. a correction of the transmission band artifact data is achieved.

The corrected transmission belt artifact data are subjected to the steps of high-low energy image fusion, image enhancement, artifact coloring and the like in the subsequent security inspection object imaging process, and the final imaging result is free of artifacts, and the specific correction effect is shown in fig. 11.

The method provided by the embodiment of the present application is described above, and the device provided by the embodiment of the present application is described below:

Referring to fig. 12, fig. 12 is a block diagram of an apparatus according to an embodiment of the present application. The device is applied to X-ray security inspection equipment, includes:

Optionally, the standard die body correction data includes high-energy correction data and low-energy correction data of at least one detection unit under at least one integration time, the high-energy correction data of any detection unit under any integration time is obtained after full background correction is performed on the high-energy data detected by the detection unit under the integration time, and the low-energy correction data of any detection unit under any integration time is obtained after full background correction is performed on the low-energy data detected by the detection unit under the integration time;

the occurrence of a belt hardening event in the belt is determined by: obtaining standard die body atomic number data based on the standard die body correction data, and determining that a transmission belt hardening event occurs to the transmission belt if the standard die body atomic number data meets a set hardening requirement; the standard die body atomic number data consists of target atomic numbers corresponding to a plurality of detection units; the target atomic number of any detection unit is determined according to the candidate atomic number of the detection unit under at least one integration time, and the candidate atomic number of any detection unit under any integration time is determined according to the high-energy correction data and the low-energy correction data detected by the detection unit under the integration time.

Optionally, the obtaining standard motif atomic number data includes:

for each detection unit, if the candidate atomic number of the detection unit under an integration time meets a set requirement, the candidate atomic number under the integration time is the reference atomic number under the integration time;

determining the target atomic number of the detection unit according to the reference atomic number of the detection unit;

and organizing the target atomic numbers of all the detection units together to obtain the standard motif atomic number data.

Optionally, the standard die body atomic number data meets a set hardening requirement, which means that:

the target atomic number of each detection unit in the standard motif atomic number data meets a first set balance requirement; or,

the absolute value of the gradient of the processing result meets the second set equalization requirement; the processing result is obtained by performing specified smoothing processing on the standard motif atomic number data.

Optionally, the conveyor belt boundary detection position is determined by:

threshold filtering is carried out on the absolute value of the gradient of each detection unit so as to set the absolute value of the gradient smaller than the set threshold value as a specified value; the absolute value of the gradient of each detection unit is determined based on the processing result obtained after the standard motif atomic number data is subjected to specified smoothing processing;

Determining the position of a detection unit corresponding to the absolute value of the target gradient as the boundary detection position of the transmission belt; the target gradient absolute value is different from the specified value.

Optionally, the hardening correction factor is determined by:

determining the atomic number corresponding to the first type of detection units based on the candidate atomic numbers of the detection units in the first type of detection units under each integration time;

determining the atomic number corresponding to the second type of detection units based on the high-energy correction data and the low-energy correction data of each detection unit in the second type of detection units under each integration time;

and determining the hardening correction coefficient based on the atomic numbers corresponding to the first type of detection units and the atomic numbers corresponding to the second type of detection units.

Optionally, the determining the atomic number corresponding to the first type of detection unit based on the candidate atomic numbers of each detection unit in the first type of detection unit at each integration time includes: performing first appointed operation on candidate atomic numbers of each detection unit in the first type of detection units under each integration time to obtain atomic numbers corresponding to the first type of detection units;

the determining the atomic number corresponding to the second type of detection unit based on the high-energy correction data and the low-energy correction data of each detection unit in the second type of detection unit under each integration time comprises: adjusting the low-energy correction data of each detection unit in the second detection unit under each integration time based on the hardening correction coefficient to obtain target low-energy correction data of each detection unit in the second detection unit under each integration time; for each detection unit in the second type of detection units, determining an adjusted atomic number of the detection unit based on the high-energy data and the target low-energy correction data of the detection unit at each integration time; performing a first specified operation on the adjusted atomic numbers of each detection unit in the second type of detection units under each integration time to obtain the atomic numbers corresponding to the second type of detection units;

The determining the hardening correction coefficient based on the atomic numbers corresponding to the first type of detection units and the atomic numbers corresponding to the second type of detection units includes: and determining the hardening correction coefficient according to the principle of minimum error of the atomic numbers corresponding to the first type of detection units and the atomic numbers corresponding to the second type of detection units.

Optionally, the first security data includes first high-energy data and first low-energy data; the first high-energy data consists of high-energy data detected by each detection unit under each integration time, and the first low-energy data consists of low-energy data detected by each detection unit under each integration time;

the first high energy data and the first low energy data each comprise L stripes; either stripe consists of t1 column data; any column of data in any one of the first high-energy data consists of high-energy data detected by n1 detection units used for detection in the X-ray security inspection equipment at the same integration time; any column of data in any band of the first low-energy data consists of low-energy data detected by n1 detection units used for detection in the X-ray security inspection equipment at the same integration time;

The obtaining unit further obtains a transmission band artifact position range; the transmission band artifact position range comprises the position of a detection unit for acquiring transmission band artifacts; the width of the transmission band artifact position range is W _sub The method comprises the steps of carrying out a first treatment on the surface of the For each band, after the band is subjected to full-load background correction, obtaining transmission band artifact data in the transmission band artifact position range from correction data of the band based on the transmission band artifact position range, determining correction parameters corresponding to the transmission band artifact data based on the transmission band artifact data, and correcting each transmission band artifact data by utilizing the correction parameters corresponding to each transmission band artifact data; the height of the transmission band artifact data is the same as the height of the strip, and the width of the transmission band artifact data is W _sub 。

Optionally, obtaining the transmission band artifact location range includes:

if the occurrence of a transmission band hardening event of a transmission band deployed on the X-ray security inspection equipment is found, determining that the positions of detection units which are adjacent to the boundary detection position of the transmission band and meet the set requirements form the transmission band artifact position range; and/or the number of the groups of groups,

if the transmission belt deployed on the X-ray security inspection equipment is found to have no transmission belt hardening event, determining a reference detection unit with the absolute gradient value larger than a set absolute gradient value threshold value based on the absolute gradient value of each detection unit in full-load correction data, and determining the position range of the transmission belt artifact according to the position of each reference detection unit; the full-load correction data are obtained by carrying out full-load background correction on second full-load data based on first full-load data and background data, the first full-load data are acquired through a detection unit in the X-ray security inspection equipment under the triggering of a current security inspection event, and the current security inspection event is generated based on the triggering of a security inspection object to be currently checked through the X-ray security inspection equipment; the second full data is acquired by a detection unit in the X-ray security inspection equipment before the first full data is acquired.

Optionally, aThe determining, based on the transmission band artifact data, a correction parameter corresponding to the transmission band artifact data includes: performing a second specifying operation on the data of each detection unit in the transmission band artifact data under each integration time to obtain an operation result V _{Calculation of} (w); for the V _{Calculation of} (w) performing a specified smoothing process to obtain a smoothed result V _smooth The method comprises the steps of carrying out a first treatment on the surface of the For the V _{Calculation of} (w) and the V _smooth Performing a third specified operation to obtain a correction coefficient corresponding to the transmission band artifact data;

the correcting each transmission band artifact data by using the correction parameters corresponding to each transmission band artifact data comprises: and carrying out third specified operation on the transmission band artifact data and correction parameters corresponding to the transmission band artifact data according to each transmission band artifact data.

The structural description of the apparatus shown in fig. 12 is thus completed.

Based on the same application concept as the above method, the embodiment of the present application further provides a hardware structure of the apparatus shown in fig. 12. As shown in fig. 13, the hardware structure includes: a processor and a machine-readable storage medium. The machine-readable storage medium has stored thereon computer instructions which, when executed by a processor, enable the method disclosed in the above examples of the present application.

Based on the same application concept as the above method, the embodiments of the present application further provide a machine-readable storage medium, where a number of computer instructions are stored, where the computer instructions can implement the method disclosed in the above example of the present application when executed by a processor.

By way of example, the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, and the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.

The system, apparatus, template, or unit illustrated in the above embodiments may be implemented by a computer or an entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described 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 flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or 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, embedded processor, 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A security inspection image processing method, which is characterized in that the method is applied to an X-ray security inspection device and comprises the following steps:

2. The method according to claim 1, wherein the standard phantom correction data includes high-energy correction data and low-energy correction data of at least one detection unit at least one integration time, the high-energy correction data of any detection unit at any integration time is obtained after full background correction is performed on the high-energy data detected by the detection unit at the integration time, and the low-energy correction data of any detection unit at any integration time is obtained after full background correction is performed on the low-energy data detected by the detection unit at the integration time;

3. The method of claim 2, wherein the obtaining standard motif atomic number data comprises:

4. The method of claim 2, wherein the standard die body atomic number data meets set hardening requirements by:

5. The method of claim 2, wherein the conveyor belt boundary detection position is determined by:

6. The method according to claim 1, wherein the hardening correction factor is determined by:

7. The method of claim 6, wherein determining the atomic number corresponding to the first type of detection cell based on the candidate atomic numbers for each detection cell of the first type of detection cell at each integration time comprises: performing first appointed operation on candidate atomic numbers of each detection unit in the first type of detection units under each integration time to obtain atomic numbers corresponding to the first type of detection units;

8. The method according to any one of claims 1 to 7, wherein,

the first security inspection data comprise first high-energy data and first low-energy data; the first high-energy data consists of high-energy data detected by each detection unit under each integration time, and the first low-energy data consists of low-energy data detected by each detection unit under each integration time;

the method further comprises the steps of:

obtaining a transmission band artifact position range; the transmission band artifact position range comprises the position of a detection unit for acquiring transmission band artifacts; the width of the transmission band artifact position range is W _sub ；

For each band, after the band is subjected to full-load background correction, obtaining transmission band artifact data in the transmission band artifact position range from correction data of the band based on the transmission band artifact position range, determining correction parameters corresponding to the transmission band artifact data based on the transmission band artifact data, and correcting each transmission band artifact data by utilizing the correction parameters corresponding to each transmission band artifact data; the height of the transmission band artifact data is the same as the height of the strip, and the width of the transmission band artifact data is W _sub 。

9. The method of claim 8, wherein obtaining a range of transmission band artifact locations comprises:

10. The method of claim 8, wherein determining the correction parameter corresponding to the transmission band artifact data based on the transmission band artifact data comprises: performing a second specifying operation on the data of each detection unit in the transmission band artifact data under each integration time to obtain an operation result V _{Calculation of} (w); for the V _{Calculation of} (w) performing a specified smoothing process to obtain a smoothed result V _smooth The method comprises the steps of carrying out a first treatment on the surface of the For the V _{Calculation of} (w) and the V _smooth Performing a third specified operation to obtain a correction coefficient corresponding to the transmission band artifact data;

11. A security inspection image processing apparatus, characterized in that the apparatus is applied to an X-ray security inspection device, comprising:

12. An electronic device, comprising: a processor and a machine-readable storage medium;

stored on a machine-readable storage medium are computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 10.