Method and device for detecting parcel image in security inspection equipment and medium

Abstract

The invention provides a method and a device for detecting parcel images in security inspection equipment and a medium, and relates to the technical field of security inspection, the method comprises the following steps: obtaining a first strip uploaded by the security inspection equipment, the security inspection equipment carrying out one-time image scanning on a detection area at intervals of one period to generate a strip, and the security inspection equipment carrying out one-time image scanning on the detection area according to a scanning sequence; all the strips are marked and then uploaded in sequence; based on the strip identifier, determining whether the security inspection equipment has uploaded first N second strips and last M third strips of the first strip, N and M being positive integers; if the second strip and the third strip are uploaded, the strip attribute of the first strip is determined based on the first strip, the second strip and the third strip, and the strip attribute comprises any one of a single parcel image, an overlapped parcel image and a non-parcel image. According to the scheme, whether the overlapped parcels are contained in the strip or not can be more accurately determined.

Description

Technical Field

[0001] The present application relates to the field of security inspection technology, and in particular to a method, device and medium for detecting package images in security inspection equipment. Background Art

[0002] Security inspection machines are widely used in travel inspection scenarios. When performing package inspection, passengers usually place their packages on a conveyor belt, which then transports the packages to the security inspection machine for scanning and imaging. The machine detects whether the packages contain prohibited items based on the scanned images. However, packages on the conveyor belt are prone to stacking. After multiple stacked packages are scanned, only one package image is formed, which puts a lot of pressure on a single security inspector to judge the images.

[0003] In the prior art, for such an image with multiple overlapping packages, it is usually segmented to obtain segmented images, and each segmented image preferably contains only one package to reduce the pressure on security inspectors to judge the images.

[0004] However, the existing image segmentation method cannot accurately classify the package images, the segmentation accuracy of the package images is poor, and the images of each package cannot be accurately segmented. Summary of the invention

[0005] The present application provides a method, device and medium for detecting package images in security inspection equipment, which are at least used to solve the problem of low accuracy in classification of existing package images or low accuracy in recognition of overlapping packages.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting a package image in a security inspection device, the method comprising:

[0007] The first strip uploaded by the security inspection device is obtained. The security inspection device scans the detection area once every period to generate a strip. The security inspection device marks each strip in the order of scanning and uploads them in sequence.

[0008] Based on the stripe identifier, determining whether the security inspection device has uploaded the first N second stripes and the last M third stripes of the first stripe, where N and M are positive integers;

[0009] If the second strip and the third strip have been uploaded, the strip attribute of the first strip is determined based on the first strip, the second strip and the third strip, and the strip attribute includes any one of the existence of a wrapped image, the existence of an overlapping wrapped image, and the absence of a wrapped image.

[0010] In a possible design of the first aspect, determining a stripe attribute of the first stripe based on the first stripe, the second stripe, and the third stripe includes:

[0011] Based on the scanning order, the first strip, the second strip, and the third strip are spliced, and the spliced ​​image is binarized to obtain a binarized image;

[0012] Performing isolated point removal and edge smoothing processing on the binary image to obtain a processed image;

[0013] Performing edge detection on the processed image to obtain edge data;

[0014] Based on the edge data and the spliced ​​image before binarization, a stripe attribute of the first stripe is determined.

[0015] In another possible design of the first aspect, binarizing the spliced ​​image includes:

[0016] Setting a first grayscale threshold according to the attribute of the package scanned by the security inspection device;

[0017] Acquire a first target pixel point whose pixel value is less than the first grayscale threshold and a second target pixel point whose pixel value is greater than or equal to the first grayscale threshold in the stitched image;

[0018] Updating the pixel value of the first target pixel to a grayscale maximum value;

[0019] Update the pixel value of the second target pixel to the grayscale minimum value.

[0020] In another possible design of the first aspect, removing isolated points from the binary image includes:

[0021] Obtain a hollow circular filter kernel, wherein the hollow circular filter kernel is composed of K*L square units, the size of each square unit matches the size of a pixel point, and the K*L square units are divided into valid units and invalid units, wherein the center of the hollow circular filter kernel is a valid unit arranged in a cross shape, and M valid units are arranged at intervals around the valid units arranged in the cross shape, and K and L are both positive integers;

[0022] Controlling the hole circular filter kernel to perform a sliding window operation on the binary image to determine a first pixel point where each effective unit is located on the binary image;

[0023] Get the pixel value of each first pixel;

[0024] The minimum pixel value among the pixel values ​​of all the first pixel points is used as the pixel value of the pixel point where the valid unit at the center of the hole circular filter kernel is located on the binary image.

[0025] In yet another possible design of the first aspect, performing edge smoothing on the binary image includes:

[0026] Controlling the hole circular filter kernel to perform a sliding window operation on the binary image after isolated point removal, and determining a second pixel point where each effective unit is located on the binary image after isolated point removal;

[0027] The maximum pixel value among the pixel values ​​of all the second pixel points is used as the pixel value of the pixel point where the valid unit at the center of the hole circular filter kernel is located on the binary image after isolated point removal.

[0028] In another possible design of the first aspect, performing edge detection on the processed image to obtain edge data includes:

[0029] Performing edge detection on the processed image to determine whether there is a target edge point on the edge curve of the processed image;

[0030] If there is a target edge point, obtain a first vector between each target edge point and a predecessor point, and a second vector between each edge point and a successor point; the predecessor point refers to an edge point before the target edge point according to the strip generation order, and the successor point refers to an edge point after the target edge point according to the strip generation order;

[0031] The angle between the first vector and the second vector is obtained as the edge data.

[0032] In yet another possible design of the first aspect, determining the stripe attribute of the first stripe based on the edge data and the spliced ​​image before binarization includes:

[0033] Get the grayscale mean and grayscale variance of the spliced ​​image before binarization;

[0034] The stripe attribute of the first stripe is determined based on the value of the angle, the relationship between the grayscale mean and the set grayscale mean threshold, and the relationship between the grayscale variance and the set grayscale variance threshold.

[0035] In yet another possible design of the first aspect, determining a stripe attribute of the first stripe includes:

[0036] If the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and the angle exists, it is determined that a package image exists in the first strip;

[0037] If the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and the value of the angle is less than the set angle value, it is determined that there is an overlapping wrapped image in the first strip;

[0038] If the grayscale mean is greater than or equal to the grayscale mean threshold, or if the grayscale variance is less than or equal to the grayscale variance threshold, or if the angle does not exist, it is determined that there is no wrapped image in the first strip.

[0039] In another possible design of the first aspect, the present invention further includes:

[0040] If there are overlapping package images in the first strip, the first strip is used as the starting position or the ending position of each overlapping package image;

[0041] The overlapping package images are segmented based on the start position or the end position of each package image.

[0042] In yet another possible design of the first aspect, after determining the stripe attribute of the first stripe, the method further includes:

[0043] The first strip is sent to a display device for display; wherein the display order of the first N second strips is earlier than that of the first strip.

[0044] In a second aspect, an embodiment of the present application provides a package image detection device in a security inspection device, the device comprising:

[0045] A strip acquisition module is used to acquire the first strip uploaded by the security inspection device. The security inspection device scans the detection area once every period to generate a strip. The security inspection device marks each strip in the order of scanning and uploads them in sequence.

[0046] A stripe determination module, used to determine whether the security inspection device has uploaded the first N second stripes and the last M third stripes of the first stripe based on the stripe identifier, where N and M are positive integers;

[0047] The attribute determination module is used to determine the stripe attribute of the first stripe based on the first stripe, the second stripe and the third stripe if the second stripe and the third stripe have been uploaded, wherein the stripe attribute includes any one of the existence of a wrapped image, the existence of an overlapping wrapped image, and the absence of a wrapped image.

[0048] In a third aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0049] The package image detection method, device and medium in the security inspection equipment provided in the embodiments of the present application can determine the strip attributes by acquiring the second strip before the first strip and the third strip after the first strip, combining the image information of the first strip, the second strip and the third strip, so as to more accurately determine whether the first strip contains overlapping packages and realize accurate classification of the package image. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application;

[0051] Figure 1 A schematic diagram of overlapping packages during security inspection provided by an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a scanned image provided in an embodiment of the present application;

[0053] Figure 3 A schematic diagram of a process for detecting package images of security inspection equipment provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of a stripe cache display provided in an embodiment of the present application;

[0055] Figure 5 A schematic diagram of stripe attribute determination provided in an embodiment of the present application;

[0056] Figure 6 A scanned image obtained by splicing the original strip data provided in the embodiment of the present application;

[0057] Figure 7 A schematic diagram of the filtering effect provided in the embodiment of the present application;

[0058] Figure 8 A schematic diagram of the structure of a hollow circular filter kernel provided in an embodiment of the present application;

[0059] Fig. 9 A schematic diagram of edge detection results provided in an embodiment of the present application;

[0060] Fig.10 A schematic diagram of the package segmentation effect provided in an embodiment of the present application;

[0061] Fig.11 A schematic diagram of the structure of a package image detection device provided in an embodiment of the present application;

[0062] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0063] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] At present, in the scenario of passenger inspection, the frequency of operation of security inspection machines has obvious differences in sites and time periods. For example, there will be continuous bag passing during rush hour, while other time periods are relatively idle. Based on this situation, in order to reduce manpower input, a single security inspection entrance is usually equipped with 1 to 2 security inspectors to check the bag passing images for contraband, which leads to a high risk of misjudgment and missed judgment during peak hours. For the missed judgment and misjudgment during rush hour, the relevant technology proposes to upload the local bag passing video stream to the cloud platform and segment different bag images, and finally distribute them to the remote security inspector monitor to realize remote centralized image judgment. In this way, the 1 to 2 locally configured security inspectors can also accurately complete the bag security inspection with the assistance of the remote security inspectors.

[0066] Figure 1 A schematic diagram of overlapping packages during security inspection provided by an embodiment of the present application, such as Figure 1 As shown, the passenger places the package he carries on the conveyor belt, and then the conveyor belt conveys the package in a set direction. A detector is set at the end of the set direction. The detector is a linear array detector for scanning. When the detector senses that the package enters the detection area, the detector scans the detection area, thereby obtaining a scanned image of the package in the detection area.

[0067] In practical applications, since current security inspection equipment uses linear array detectors for scanning, the scanning results need to be transmitted to the monitor for rolling imaging. The remote centralized image judgment mode has high requirements for the timeliness and accuracy of package segmentation. Figure 2 A schematic diagram of a scanned image provided in an embodiment of the present application, such as Figure 2 As shown in the figure, each time the detector scans the detection area, it generates a strip of data (equivalent to a small image). This strip of data may contain partial images of one or more packages. When judging the image remotely, the remote judgment client needs to receive all the strips of data and then combine them to form a complete package image. However, in the remote judgment mode, in order to ensure the real-time transmission of the image, each strip of data is usually uploaded to the remote judgment device as soon as it is generated.

[0068] In the remote centralized image judgment mode, some packages may be stacked together during security inspection, which will cause these stacked packages to be identified as one package image. If the security inspection machine sends this package image to the remote client for image judgment, and in fact this package image contains images of multiple packages, this will increase the workload of the remote security inspector (that is, one package image contains multiple packages) and may reduce the accuracy of the remote security inspector's image judgment. Therefore, it is necessary to identify this situation and perform further image segmentation, and segment the overlapping packages in the same image to form multiple images, so that the remote security inspector only performs security inspection on one package in one image at the same time. Although there are some package image segmentation schemes at present, they all have the following two disadvantages: ① A single thin package or a package with a long strap is identified as multiple packages; ② Multiple packages overlap or do not overlap, but when the detector direction overlaps, they will be identified as one package image.

[0069] Based on this, the inventors proposed a package image detection scheme, which detects whether there are multiple packages overlapping in each strip data, so as to segment the images of each overlapping package and assign them to remote image judges for image judgment. Specifically, the scheme first divides the package scan data into a binary image through threshold segmentation, then performs maximum filtering and edge detection on the binary image, performs gradient calculation on the edge detection result, and then classifies the current strip data in combination with the statistical information of the original strip data to determine whether it contains multiple overlapping package images, thereby achieving low latency and high-precision overlapping package detection.

[0070] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0071] Figure 3 The present invention provides a flowchart of a method for detecting package images of security inspection equipment in an embodiment of the present invention. The method can be applied to electronic devices. The security inspection equipment transmits the strip data obtained by scanning itself by remote communication with the electronic device. For example, the electronic device can be a remote image judgment client. Figure 3 As shown, the method may specifically include the following steps:

[0072] Step S310: Obtain the first strip uploaded by the security inspection device.

[0073] In this embodiment, the detector in the security inspection device performs an image scan on the detection area once every period to generate a strip. The security inspection device marks each strip in the order of scanning and uploads them in sequence.

[0074] For example, continue to refer to the above Figure 1 ,exist Figure 1 There is a detection area configured in the conveyor belt. The conveyor belt will continue to convey packages to the detection area. Assuming that package A is divided into three parts (such as the head, the middle and the tail), when the head of package A is conveyed to the detection area, the detector performs an image scan to generate strip 1, which contains the scanned image of the head of package A. Further, the conveyor belt continues to drive package A to move, and then the middle of package A enters the detection area. The detector continues to perform an image scan to generate strip 2, which contains the scanned image of the middle of package A. By analogy, each strip contains a scanned image of a part of a package. For details, please refer to Figure 2 .

[0075] In order to avoid confusion that may result in the inability of the subsequent remote image judgment client to combine and form a complete scanned image, each strip needs to be identified, for example, strip 1, strip 2, ..., strip n are identified by numbers. In this way, after the security inspection equipment uploads these strips to the remote image judgment client, the remote image judgment client can sort these strips according to the identification to form a complete image.

[0076] In addition, when there are many security inspection devices, if each security inspection device uploads a strip to the remote image judgment client, then each security inspection device is required to carry its own device identification information so that the remote image judgment client can determine which security inspection device uploaded the strip, and then all the strips uploaded by this security inspection device can be combined to form a complete scan image.

[0077] In this embodiment, the first strip does not refer to a specific strip. For example, the first strip may be the above-mentioned Figure 2 It can be stripe 1 or stripe 2, without limiting which stripe it is.

[0078] Step S320: Based on the stripe identifier, determine whether the security inspection device has uploaded the first N second stripes and the last M third stripes of the first stripe. Wherein N and M are positive integers;

[0079] Among them, since the security inspection equipment uses a linear array detector to scan and roll images on the monitor, for the sake of convenience, we call the image obtained by the linear array detector of the security inspection equipment as line scan data (see Figure 2, line scan data includes multiple strip data). As mentioned above, in the remote centralized image judgment mode, in order to ensure the real-time transmission of the image, usually each strip data is generated and uploaded to the remote image judgment device, and then the remote image judgment client displays the current strip data after image processing, so that the content displayed on the display interface of the remote image judgment client is exactly the package being inspected in the local security inspection machine. This synchronization method between the remote image judgment client and the local security inspection machine can ensure the accuracy of the remote security inspector's image judgment, and once contraband is found, it can also locate which package it is as soon as possible.

[0080] However, a single strip has little image information, and it is not possible to accurately determine whether there are overlapping packages in this strip during image processing (that is, it is impossible to determine whether there are multiple packages overlapping each other), which leads to a high degree of mis-segmentation. In addition, if there are overlapping packages in an image and this image is displayed on the display interface, it is not convenient for remote security inspectors to judge the image (because when the security inspector judges the image, it is guaranteed that there is only one package image in the image seen by the security inspector, and the judgment accuracy is the highest, and there will be no missed judgment). For details, please refer to Figure 2 Strip 2, strip 3 and strip 4 in the display interface all contain images of package A and package B. For example, if strip 2 is displayed on the display interface, the remote security inspector will actually see the images of package A and package B on the display interface at the same time, which may cause the remote security inspector to make misjudgments or missed judgments.

[0081] In response to this situation, in this embodiment, when the security inspection device uploads strips to the remote image judgment client, the remote image judgment client first performs cache processing, and then continues to receive the remaining strips uploaded by the security inspection device. Because each stripe is uploaded in sequence according to the scanning order, when the remote image judgment client receives the first stripe uploaded by the security inspection device, it can detect whether there are N second stripes before the first stripe in the cache. If detected, the remote image judgment client continues to receive M stripes after the first stripe uploaded by the security inspection device.

[0082] For example, taking the values ​​of N and M as 1, Figure 4 A schematic diagram of a stripe cache display provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the line scan strip data of the security inspection device is cached. Strip No. 0 in the line scan data is usually an initialized blank strip. After the remote image judgment client caches strip No. 0, the security inspection device uploads strip No. 1 to the remote image judgment client. The remote image judgment client does not perform subsequent image processing. When the security inspection device uploads strip No. 2 to the remote image judgment client, strips No. 0, 1, and 2 are sent to subsequent image processing.

[0083] In this embodiment, the values ​​of N and M can be selected according to the actual situation. Generally, the larger the values ​​of N and M, the more accurately it can be judged whether there are multiple package images in the first strip, but it will affect the synchronization between the local security inspection machine and the remote image judgment client. For example, the values ​​of N and M can be selected to be 1, so that the remote image judgment client can continue to be synchronized with the local security inspection machine to a certain extent, that is, the package being passed by the local security inspection machine can be synchronously displayed on the display interface of the remote image judgment client.

[0084] Step S330: If the second stripe and the third stripe have been uploaded, determine the stripe attribute of the first stripe based on the first stripe, the second stripe and the third stripe.

[0085] The strip attribute includes any one of the following: the presence of a wrapped image, the presence of a wrapped overlapping image, and the absence of a wrapped image.

[0086] In this embodiment, by using the first strip, the N second strips before the first strip, and the M third strips after the first strip, more image information will be included. Therefore, compared with the above-mentioned method of using a single strip for overlapping package identification, it is possible to more accurately identify whether there are overlapping packages in the first strip.

[0087] Furthermore, in some implementations, if overlapping packages are identified in the first strip, image segmentation may be performed to separate the images of the individual packages.

[0088] In addition, in some implementations, after the stripe attribute of the first stripe is determined, the first stripe may be sent to a display device for display, wherein the display order of the first N second stripes before the first stripe is earlier than the first stripe.

[0089] For example, continue to refer to the above Figure 4 After receiving strip No. 2, the remote image judgment client determines the strip attributes of strip No. 1. If there is no overlapping package, strip No. 1 can be displayed on the display interface first. When strip No. 3 is received, strips 1, 2, and 3 are sent to subsequent image processing and the strip attributes of strip No. 2 are determined. If there is no overlapping package, strip No. 2 is displayed. This operation is repeated for subsequent strips, that is, there is only a delay of one strip data between the display interface of the remote image judgment client and the package passed by the local security inspection machine, which ensures synchronization as much as possible. It should be understood that the specific number of strips displayed with a delay is determined based on the number of the last M third strips.

[0090] The embodiment of the present application obtains the second strip before the first strip and the third strip after the first strip, and combines the image information of the first strip, the second strip and the third strip to determine the properties of the strip, so as to more accurately determine whether the first strip contains overlapping packages and avoid mis-segmentation.

[0091] How to perform image processing on strips is described in detail below through some embodiments.

[0092] Figure 5 The strip attribute determination schematic diagram provided in the embodiment of the present application is as follows: Figure 5 As shown, it includes the following steps:

[0093] Step S510: Obtain the line scan data of the security inspection equipment and cache it.

[0094] In this embodiment, the line scan data is composed of multiple strips. The security inspection device uses a linear array detector for scanning. Each time the detector scans the detection area, a strip of data is generated. Each time a strip of data is generated, the security inspection device uploads the strip of data to the remote image judgment client to avoid transmission delay caused by excessive data. In this way, the remote image judgment client will continue to receive strips, and these strips of data can be cached in the order of scanning. For example, if the remote image judgment client receives strip 1, caches it, and then receives strip 2, strip 2 will be cached after strip 1.

[0095] Step S520: Binarize the stripe data.

[0096] In this embodiment, the strip data here includes a first strip, a second strip and a third strip, and these three strip data can be spliced ​​to form an image to be processed.

[0097] For example, refer to the above Figure 2 , with strip 2 as the first strip, strip 1 as the second strip, and strip 3 as the third strip. The image to be processed formed by the combination of these three strips includes the head image of package A, the middle head image of package A, and the head image of package B.

[0098] Among them, binarization refers to representing the pixel points in the above-mentioned image to be processed with the maximum pixel value and the minimum pixel value. Specifically, a grayscale threshold can be set. If the pixel value of the pixel point in the image is greater than or equal to the grayscale threshold, the pixel point is converted to the maximum pixel value. If the pixel value of the pixel point in the image is less than the grayscale threshold, the pixel point is converted to the minimum pixel value.

[0099] Exemplarily, in some embodiments, a first grayscale threshold can be set. If the pixel value of the first target pixel in the target image is less than the first grayscale threshold, the pixel value of the first target pixel is updated to the grayscale maximum value; if the pixel value of the second target pixel in the target image is greater than or equal to the first grayscale threshold, the pixel value of the second target pixel is updated to the grayscale minimum value.

[0100] The target image consists of a first strip, a second strip and a third strip.

[0101] The purpose of binarizing the strip data is to obtain a rough mask of the strip data. The strip data can be represented by a matrix A. The simplest way to obtain the mask matrix Mask can be expressed as:

[0102]

[0103] In the above formula, Thre1 is the first grayscale threshold set, A ij Indicates the pixel value of the pixel in the i-th row and j-th column in the strip data, Mask ij Represents the mask value of the pixel at the i-th row and j-th column. Usually, 1 indicates that the pixel value is assigned to the minimum value, and 0 indicates that the pixel value is assigned to the maximum value.

[0104] Among them, in actual passenger inspection scenarios, more attention is paid to prohibited items in the medium and low grayscale areas. Therefore, the first grayscale threshold can be set lower to directly filter out the influence of the package strap or ultra-thin objects on the strip properties, thereby improving the subsequent recognition efficiency of overlapping packages.

[0105] In addition, in some other implementations, other binarization methods such as Otsu threshold method, adaptive threshold method, etc. may be used to binarize the stripe data.

[0106] Step S530: performing isolated point removal and edge smoothing processing on the binary image.

[0107] In this embodiment, the binary image is processed to find out whether there is a package in the target image and the location of the package. Figure 6 The scanned image after splicing the original strip data provided in the embodiment of the present application is Figure 7 This is a schematic diagram of the filtering effect provided in the embodiment of the present application. Figure 6 After binarization, it is processed again to obtain Figure 7 The rendering shown can be used to more accurately find the area where the package is located.

[0108] Exemplarily, in some embodiments, edge smoothing may include performing maximum filtering on the binary image, and isolated point removal may include performing minimum filtering on the binary image. In some implementations, the processing order may be to perform minimum filtering first and then maximum filtering.

[0109] Among them, the minimum value filtering can eliminate the small-scale isolated mask noise generated by the binarization process, so as to directly distinguish the packages with slight overlap. The maximum value filtering is performed again to smooth the mask edge after the previous binarization and minimum value filtering, so that the main body of the mask is spherical, so that there will be obvious contact points between two packages with more overlap, and the contact points can be used to further understand whether the packages overlap.

[0110] Specifically, in some embodiments, when performing minimum value filtering, a hole circular filter kernel of K rows and L columns can be constructed in advance. The hole circular filter kernel can be set as a square, which includes a number of valid units and invalid units. The valid units and invalid units can be set at intervals, and the center of the hole circular filter kernel and the adjacent units of the center can be set as valid units. In this embodiment, the hole circular filter kernel can be adjusted according to the actual required wrapping edge shape.

[0111] For example, Figure 8 The schematic diagram of the structure of the hollow circular filter kernel provided in the embodiment of the present application is as follows: Figure 8 As shown, the center is a cross-shaped effective unit, and a number of effective units are arranged at intervals around the cross-shaped effective unit. For example, the values ​​of K and L are both 5. Figure 8 In the figure, black cells are valid cells, and white cells are invalid cells. Black cells are valid cells that participate in the filtering window (that is, the pixels corresponding to valid cells participate in the subsequent related isolated point removal operations and edge smoothing operations, and the pixels corresponding to invalid cells do not participate in related operations). Minimum filtering is to use the minimum value of all pixels in valid cells as the final value of the pixel at the center of the filter kernel during the filtering window. The specific steps are as follows:

[0112] (1) Controlling the hole circular filter kernel to perform a sliding window operation on the binary image to determine the first pixel point of each valid unit on the binary image;

[0113] (2) Obtaining a pixel value of a first pixel;

[0114] (3) The minimum pixel value is determined among all pixel values ​​as the pixel value of the pixel point where the effective unit at the center of the hole circular filter kernel is located on the binary image.

[0115] In this embodiment, it is possible to control Figure 8The hole circular filter kernel shown slides on the binary image. During the sliding process, the valid units on the hole circular filter kernel will be located at a certain pixel point on the binary image. These pixel points are called first pixel points. Taking a 5*5 hole circular filter kernel as an example, it includes 13 valid units, so there are at least 13 first pixel points corresponding to the sliding process.

[0116] Each first pixel point has a corresponding pixel value, and the minimum value of these pixel values ​​is used as the final pixel value of the first pixel point where the center of the hole circular filter kernel is located.

[0117] Furthermore, in some implementations, when performing maximum filtering, the above-mentioned hollow circular filter kernel can be reused, and the maximum value of the pixels at all valid units in the filtering sliding window process is used as the final value of the pixel at the center of the filter kernel. The specific steps of maximum filtering are as follows:

[0118] ① Control the hole circular filter kernel to perform a sliding window operation on the binary image after isolated point removal, and determine the second pixel point of each valid unit on the binary image after isolated point removal;

[0119] ② The maximum pixel value among all the second pixel values ​​is taken as the pixel value of the pixel at the center of the valid unit of the hole circular filter kernel on the binary image after the isolated point removal is performed.

[0120] In this implementation, the maximum value filtering process is similar to the minimum value filtering process, the difference being that the final pixel value of the pixel value of the second pixel point where the center of the hole circular filtering kernel is located is different.

[0121] By designing a hollow circular filter kernel, the embodiment of the present application can take into account both filtering processing efficiency and filtering effect when performing minimum filtering and maximum filtering on the binary image, so that more obvious contact points appear between two packages with more overlap, so as to facilitate the subsequent identification and segmentation of overlapping packages.

[0122] Step S540: performing edge detection on the processed image.

[0123] In this embodiment, edge detection is to find the edge curve of the wrapped image and extract the smooth edge of the processed image. Fig. 9 The edge detection result diagram provided in the embodiment of the present application is as follows: Fig. 9 As shown, the smooth edge is extracted for subsequent edge gradient calculation.

[0124] Step S550: performing gradient calculation on edge data.

[0125] In this embodiment, the gradient calculation is to determine whether there is a wrapping edge in the filtered image, and to obtain the edge points on the wrapping edge when there is a wrapping edge. There may be some maximum or minimum edge points in the edge curve, and these extreme points are the contact points between the wrappings, which are important basis for judging whether there are overlapping wrappings in the strip attributes.

[0126] Furthermore, in some embodiments, when edge points are found during edge detection, it can be determined whether there are target edge points on the edge curve of the processed image. If there are target edge points, the first vector between each target edge point and the predecessor point, the second vector between each edge point and the successor point are obtained, and then the angle between the first vector and the second vector is obtained as edge data.

[0127] The predecessor point refers to an edge point before the target edge point according to the strip generation order, and the successor point refers to an edge point after the target edge point according to the strip generation order.

[0128] In this embodiment, the predecessor point refers to the Xth pixel point in front of the edge point. For example, there is an edge point B1 in the edge curve. Along the edge curve, another edge point B2 in front of the edge point B1 and separated from the edge point B1 by 5 pixels can be regarded as the predecessor point of the edge point B1. Similarly, the successor point refers to the Xth pixel point in the rear of the edge point. For example, there is an edge point B1 in the edge curve. Along the edge curve, another edge point B3 in the rear of the edge point B1 and separated from the edge point B1 by 5 pixels can be regarded as the successor point of the edge point B1. X is a positive integer.

[0129] After the edge point is connected to the previous point, a first vector is formed, and after the edge point is connected to the next point, a second vector is formed. The angle between the two vectors is used as edge data. In addition, when the two packages are separated by a long distance (i.e., when there is no overlap), the above angle does not exist, and the angle θ can be set to NULL.

[0130] In this embodiment, the strip generally only includes an upper edge and a lower edge. Figure 2 , strip 2 only contains the upper and lower edges of image A and the upper and lower edges of image B. In some embodiments, taking the upper edge as an example, when obtaining the angle θ, it can be calculated by the following formula:

[0131]

[0132] In the above formula, X upn Indicates the horizontal coordinate of the nth edge point on the upper edge, Y upnIt represents the ordinate of the nth edge point on the upper edge, where N is the distance between the predecessor point and the successor point (for example, if the distance between the predecessor point and the edge point is 5 pixels, and the distance between the successor point and the edge point is 5 pixels, then N=10).

[0133] When the angle θ is less than π / 2, it means that the current edge point is an extreme point.

[0134] Step S560: Determine the stripe attribute in combination with the original stripe data.

[0135] In this embodiment, based on the original strip data, it can be determined whether there is a package in the first strip, and based on the obtained value of the angle θ, it is necessary to further determine whether there is a package overlap. Exemplarily, in some embodiments, after the first strip, the second strip, and the third strip are combined to form a target image, the grayscale mean and grayscale variance of the spliced ​​image before binarization can be obtained; then, based on the value of the angle, the relationship between the grayscale mean and the set grayscale mean threshold, and the relationship between the grayscale variance and the set grayscale variance threshold, the strip attribute of the first strip is determined.

[0136] The following judgment conditions can be set:

[0137] (1) If the grayscale mean is less than the grayscale mean threshold, the grayscale variance is greater than the grayscale variance threshold, and there is an angle, it is determined that there is a wrapped image in the first strip;

[0138] (2) If the grayscale mean is less than the grayscale mean threshold, the grayscale variance is greater than the grayscale variance threshold, and the value of the angle is less than the set angle value, it is determined that there is an overlapping wrapped image in the first strip;

[0139] (3) If the grayscale mean is greater than or equal to the grayscale mean threshold, or if the grayscale variance is less than or equal to the grayscale variance threshold, or if there is no angle, it is determined that there is no wrapped image in the first strip.

[0140] The specific judgment conditions can be referred to the following formula:

[0141]

[0142] In the above formula, Thre2 is the adjustable grayscale mean threshold, Thre3 is the adjustable grayscale variance threshold, Mean is the grayscale mean of the target image, and Var is the grayscale variance of the target image. That is:

[0143] 1. When the grayscale mean Mean is less than the grayscale mean threshold Thre2, the grayscale variance Var is greater than the grayscale variance threshold Thre3, and the value of the angle θ is not equal to the set value NULL, it is determined that there is a package in the first strip.

[0144] 2. When the grayscale mean Mean is less than the grayscale mean threshold Thre2, and the grayscale variance Var is greater than the grayscale variance threshold Thre3, and the value of the angle θ is less than the angle threshold π / 2, it is determined that there is an overlapping package in the first strip.

[0145] 3. When the grayscale mean Mean is greater than or equal to the grayscale mean threshold Thre2, or the grayscale variance Var is less than or equal to the grayscale variance threshold Thre3, or the angle θ is equal to the set value NULL, it is determined that there is no package in the first strip.

[0146] The embodiment of the present application is based on the angle θ. On the basis of determining whether the first strip contains a package image, it can also more accurately determine whether there are overlapping packages in the first strip, thereby facilitating the subsequent segmentation of the package image and avoiding the appearance of multiple package images when the strip data is displayed on the display interface of the remote image judgment client.

[0147] In other embodiments, when it is determined that overlapping packages are included in a strip, segmentation is required, and the first strip is used as the starting position or the ending position of each overlapping package image during segmentation; then, each overlapping package image is segmented based on the starting position or the ending position of each package image.

[0148] In this embodiment, Fig.10 A schematic diagram of the package segmentation effect provided in the embodiment of the present application is shown in FIG. Fig.10 As shown, by detecting the strip, it is found that there is an overlap between the previous package A and the next package B. At this time, the strip can be used as the end position of the previous package A, and then the image before the strip is segmented as the package image of the previous package A. At the same time, the strip can be used as the starting position of the next package B, and the image after the strip is segmented as the package image of the next package B.

[0149] Among them, after segmentation, the package image of the previous package A and the package image of the next package B can be displayed on different display interfaces of the remote image judgment client respectively, thus avoiding the situation where overlapping packages are displayed on the same display interface.

[0150] The embodiment of the present application has a good segmentation effect on overlapping packages by accurately giving the strip attributes of the strips, which can well meet the package segmentation requirements in the current remote centralized image judgment mode and improve the efficiency of remote centralized image judgment.

[0151] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0152] Fig.11A schematic diagram of the structure of a package image detection device provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, the detection device 1100 specifically includes: a stripe acquisition module 1110 , a stripe determination module 1120 , and an attribute determination module 1130 .

[0153] Among them, the strip acquisition module 1110 is used to obtain the first strip uploaded by the security inspection device. The security inspection device performs an image scan on the detection area once every period to generate a strip. The security inspection device identifies each strip and uploads it in sequence according to the scanning order. The strip determination module 1120 is used to determine whether the security inspection device has uploaded the first N second strips and the last M third strips of the first strip based on the strip identification, where N and M are positive integers. The attribute determination module 1130 is used to determine the strip attribute of the first strip based on the first strip, the second strip and the third strip if the second strip and the third strip have been uploaded. The strip attribute includes any one of the existence of a package image, the existence of an overlapping package image, and the absence of a package image.

[0154] Optionally, the attribute determination module can be specifically used to: splice the first strip, the second strip, and the third strip based on the scanning order, and binarize the spliced ​​image to obtain a binarized image; perform isolated point removal and edge smoothing on the binarized image to obtain a processed image; perform edge detection on the processed image to obtain edge data; determine the strip attribute of the first strip based on the edge data and the spliced ​​image before binarization.

[0155] Optionally, the attribute determination module can be specifically used to: set a first grayscale threshold according to the attributes of the package scanned by the security inspection device; obtain a first target pixel point whose pixel value is less than the first grayscale threshold and a second target pixel point whose pixel value is greater than or equal to the first grayscale threshold in the spliced ​​image; update the pixel value of the first target pixel point to a grayscale maximum value; and update the pixel value of the second target pixel point to a grayscale minimum value.

[0156] Optionally, the attribute determination module can be specifically used to: obtain a hollow circular filter kernel, the hollow circular filter kernel is composed of K*L square units, the size of each square unit matches the size of a pixel point, and the K*L square units are divided into valid units and invalid units, wherein the center of the hollow circular filter kernel is a "cross"-arranged valid unit, and the periphery of the "cross"-arranged valid unit is further spaced apart with M valid units, and K and L are both positive integers; control the hollow circular filter kernel to perform a sliding window operation on the binary image to determine the first pixel point of each valid unit on the binary image; obtain the pixel value of each first pixel point; and use the minimum pixel value among the pixel values ​​of all first pixels as the pixel value of the pixel point where the valid unit at the center of the hollow circular filter kernel is located on the binary image.

[0157] Optionally, the attribute determination module can be specifically used to: control the hole circular filter kernel to perform a sliding window operation on the binary image after isolated point removal, and determine the second pixel point at which each valid unit is located on the binary image after isolated point removal; and use the maximum pixel value among the pixel values ​​of all second pixels as the pixel value of the pixel point at which the valid unit at the center of the hole circular filter kernel is located on the binary image after isolated point removal.

[0158] Optionally, the attribute determination module can be specifically used to: perform edge detection on the processed image to determine whether there is a target edge point on the edge curve of the processed image; if there is a target edge point, obtain the first vector between each target edge point and the predecessor point, and the second vector between each edge point and the successor point; the predecessor point refers to the edge point before the target edge point in the strip generation order, and the successor point refers to the edge point after the target edge point in the strip generation order; obtain the angle between the first vector and the second vector as edge data.

[0159] Optionally, the attribute determination module can be specifically used to: obtain the grayscale mean and grayscale variance of the spliced ​​image before binarization; determine the strip attributes of the first strip based on the value of the angle, the relationship between the grayscale mean and the set grayscale mean threshold, and the relationship between the grayscale variance and the set grayscale variance threshold.

[0160] Optionally, the attribute determination module can be specifically used for: if the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and there is an angle, then it is determined that there is a wrapped image in the first strip; if the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and the value of the angle is less than the set angle value, then it is determined that there is an overlapping wrapped image in the first strip; if the grayscale mean is greater than or equal to the grayscale mean threshold, or if the grayscale variance is less than or equal to the grayscale variance threshold, or if there is no angle, then it is determined that there is no wrapped image in the first strip.

[0161] Optionally, a segmentation module is further included, for if there are overlapping package images in the first strip, using the first strip as the starting position or the ending position of each overlapping package image; and segmenting each overlapping package image based on the starting position or the ending position of each package image.

[0162] Optionally, a display module is further included, which is used to send the first strip to a display device for display; wherein the display order of the first N second strips is earlier than that of the first strip.

[0163] The device provided in the embodiment of the present application can be used to execute the method in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0164] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the strip acquisition module can be a separately established processing element, or it can be integrated in a certain processing unit of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0165] Fig.12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.12 As shown, the electronic device 1200 includes: at least one processor 1201, a memory 1202, a bus 1203 and a communication interface 1204. In the embodiment, the processor, the communication interface and the memory communicate with each other through the bus. The communication interface is used to communicate with other devices. The communication interface includes a communication interface for data transmission and a display interface or an operation interface for human-computer interaction. The processor is used to execute computer execution instructions, and specifically can execute the relevant steps in the method described in the above embodiment.

[0166] The processor may be a central processing unit, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs. The memory is used to store computer execution instructions. The memory may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0167] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When at least one processor of an electronic device executes the computer instructions, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0168] This embodiment also provides a computer program product, which includes computer instructions. The computer instructions are stored in a readable storage electronic device. At least one processor can read the computer instructions from the readable storage medium. At least one processor executes the computer instructions so that the electronic device implements the methods provided by the above-mentioned various embodiments.

[0169] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0170] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0171] The division of units is only a logical function division, and there may be other divisions 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0172] 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.

[0173] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. If the function 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 technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0174] In the present application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0175] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process 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.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting a package image in a security inspection device, characterized in that: include: The first strip uploaded by the security inspection device is obtained. The security inspection device scans the detection area once every period to generate a strip. The security inspection device marks each strip in the order of scanning and uploads them in sequence. Based on the stripe identifier, determining whether the security inspection device has uploaded the first N second stripes and the last M third stripes of the first stripe, where N and M are positive integers; If the second strip and the third strip have been uploaded, the strip attribute of the first strip is determined based on the first strip, the second strip and the third strip, and the strip attribute includes any one of the existence of a wrapped image, the existence of an overlapping wrapped image, and the absence of a wrapped image.

2. The method according to claim 1, characterized in that The determining the stripe attribute of the first stripe based on the first stripe, the second stripe, and the third stripe includes: Based on the scanning order, the first strip, the second strip, and the third strip are spliced, and the spliced ​​image is binarized to obtain a binarized image; Performing isolated point removal and edge smoothing processing on the binary image to obtain a processed image; Performing edge detection on the processed image to obtain edge data; Based on the edge data and the spliced ​​image before binarization, a stripe attribute of the first stripe is determined.

3. The method according to claim 2, characterized in that The binarization of the spliced ​​image includes: Setting a first grayscale threshold according to the attribute of the package scanned by the security inspection device; Acquire a first target pixel point whose pixel value is less than the first grayscale threshold and a second target pixel point whose pixel value is greater than or equal to the first grayscale threshold in the stitched image; Updating the pixel value of the first target pixel to a grayscale maximum value; Update the pixel value of the second target pixel to the grayscale minimum value.

4. The method according to claim 2, characterized in that: The removing of isolated points from the binary image comprises: Obtain a hollow circular filter kernel, wherein the hollow circular filter kernel is composed of K*L square units, the size of each square unit matches the size of a pixel point, and the K*L square units are divided into valid units and invalid units, wherein the center of the hollow circular filter kernel is a valid unit arranged in a "cross" shape, and M valid units are arranged at intervals around the valid units arranged in the "cross" shape, and K and L are both positive integers; Controlling the hole circular filter kernel to perform a sliding window operation on the binary image to determine a first pixel point where each effective unit is located on the binary image; Get the pixel value of each first pixel; The minimum pixel value among the pixel values ​​of all the first pixel points is used as the pixel value of the pixel point where the valid unit at the center of the hole circular filter kernel is located on the binary image.

5. The method according to claim 4, characterized in that The binary image is subjected to edge smoothing processing, comprising: Controlling the hole circular filter kernel to perform a sliding window operation on the binary image after isolated point removal, and determining a second pixel point where each effective unit is located on the binary image after isolated point removal; The maximum pixel value among the pixel values ​​of all the second pixel points is used as the pixel value of the pixel point where the valid unit at the center of the hole circular filter kernel is located on the binary image after isolated point removal.

6. The method according to claim 2, characterized in that The performing edge detection on the processed image to obtain edge data includes: Performing edge detection on the processed image to determine whether there is a target edge point on the edge curve of the processed image; If there is a target edge point, obtain a first vector between each target edge point and a predecessor point, and a second vector between each edge point and a successor point; the predecessor point refers to an edge point before the target edge point according to the strip generation order, and the successor point refers to an edge point after the target edge point according to the strip generation order; The angle between the first vector and the second vector is obtained as the edge data.

7. The method according to claim 6, characterized in that The determining of the stripe attribute of the first stripe based on the edge data and the spliced ​​image before binarization includes: Get the grayscale mean and grayscale variance of the spliced ​​image before binarization; The stripe attribute of the first stripe is determined based on the value of the angle, the relationship between the grayscale mean and the set grayscale mean threshold, and the relationship between the grayscale variance and the set grayscale variance threshold.

8. The method according to claim 7, characterized in that The determining the stripe attribute of the first stripe includes: If the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and the angle exists, it is determined that a package image exists in the first strip; If the grayscale mean is less than the grayscale mean threshold, and the grayscale variance is greater than the grayscale variance threshold, and the value of the angle is less than the set angle value, it is determined that there is an overlapping wrapped image in the first strip; If the grayscale mean is greater than or equal to the grayscale mean threshold, or if the grayscale variance is less than or equal to the grayscale variance threshold, or if the angle does not exist, it is determined that there is no wrapped image in the first strip.

9. The method according to any one of claims 1 to 8, characterized in that Also includes: If there are overlapping package images in the first strip, the first strip is used as the starting position or the ending position of each overlapping package image; The overlapping package images are segmented based on the start position or the end position of each package image.

10. The method according to any one of claims 1 to 8, characterized in that After determining the stripe attribute of the first stripe, the method further includes: The first strip is sent to a display device for display; wherein the display order of the first N second strips is earlier than that of the first strip.

11. A package image detection device in a security inspection device, characterized in that: include: A strip acquisition module is used to acquire the first strip uploaded by the security inspection device. The security inspection device scans the detection area once every period to generate a strip. The security inspection device marks each strip in the order of scanning and uploads them in sequence. A stripe determination module, used to determine whether the security inspection device has uploaded the first N second stripes and the last M third stripes of the first stripe based on the stripe identifier, where N and M are positive integers; The attribute determination module is used to determine the stripe attribute of the first stripe based on the first stripe, the second stripe and the third stripe if the second stripe and the third stripe have been uploaded, wherein the stripe attribute includes any one of the existence of a wrapped image, the existence of an overlapping wrapped image, and the absence of a wrapped image.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 10 when being executed by a processor.

Images