CN112884085A

CN112884085A - Method, system and equipment for detecting and identifying contraband based on X-ray image

Info

Publication number: CN112884085A
Application number: CN202110360744.4A
Authority: CN
Inventors: 刘杰; 张树武; 郑阳
Original assignee: Institute of Automation of Chinese Academy of Science
Current assignee: Institute of Automation of Chinese Academy of Science
Priority date: 2021-04-02
Filing date: 2021-04-02
Publication date: 2021-06-01

Abstract

The invention belongs to the field of computer vision target detection and identification, and particularly relates to a method, a system and equipment for detecting and identifying forbidden articles based on an X-ray image. The method comprises the following steps: determining a target image set according to preset contraband refinement category information; performing data source expansion preprocessing on the target image set to obtain a training image set; inputting the training image set to a detection and recognition training model for training to obtain a detection and recognition network model; inputting the X-ray image to be detected into the detection and recognition network model to obtain confidence detection values of all detection areas in the X-ray image to be detected; and determining a detection area corresponding to the confidence coefficient detection value in the preset confidence interval as a contraband area. The invention greatly improves the detection accuracy.

Description

Method, system and equipment for detecting and identifying contraband based on X-ray image

Technical Field

The invention belongs to the technical field of computer vision target detection and identification, and particularly relates to a method, a system and equipment for detecting and identifying forbidden articles based on an X-ray image.

Background

The safety inspection of the luggage is a very important defense line for public security defense, and potential safety hazards hidden in the luggage can be timely discovered through perspective scanning of the luggage. For a long time, in the detection and identification of contraband articles such as guns and knives in public places, the naked eyes are mostly used for detecting and identifying the contraband articles in the X-ray security inspection image. Due to the fact that the objects in the luggage are placed densely and overlapped, certain difficulty is brought to safety inspection work, and the safety inspection personnel are prone to false inspection and missing inspection in a high-voltage environment for a long time. Even security personnel with hard professional quality are inevitable to have some errors, so that the problem of serious potential safety hazard is caused. Therefore, it is necessary to construct an intelligent detection and identification system to assist the work of security personnel and improve the work efficiency.

At present, in the prior art, a high-performance image processor is generally used as a basis, and an artificial intelligence deep learning algorithm is adopted to carry out intelligent detection on an X-ray security inspection image.

However, since the machine penetration ability of different X-ray machine manufacturers is different, the captured X-ray image data may have a certain deviation in the representation form and the characteristic distribution. Meanwhile, the forbidden articles can also present different sizes and shapes in different X-ray images, so that the difficulty of detection and identification is further increased, and the detection and identification accuracy is lower.

Disclosure of Invention

In order to solve the above-mentioned problem in the prior art, namely the problem of low accuracy of detection and identification, the invention provides, in a first aspect, a method for detecting and identifying contraband based on X-ray images, comprising the following steps:

determining a target image set according to preset contraband refinement category information;

performing data source expansion preprocessing on the target image set to obtain a training image set;

inputting the training image set to a detection and recognition training model for training to obtain a detection and recognition network model;

inputting the X-ray image to be detected into the detection and recognition network model to obtain confidence detection values of all detection areas in the X-ray image to be detected;

and determining a detection area corresponding to the confidence coefficient detection value in the preset confidence interval as a contraband area.

Optionally, the determining the target image set according to the preset refined category information of the contraband includes:

acquiring a contraband image set;

and screening images consistent with preset contraband thinning category information in the contraband image set as a target image set.

Optionally, the acquiring the contraband image set comprises:

acquiring a first contraband image set;

and/or acquiring a second contraband image set; the first contraband image set is an X-ray image set containing contraband; the second contraband image set is a separate contraband image set;

the step of screening the images consistent with the preset contraband thinning category information in the contraband image set as a target image set comprises the following steps:

screening images consistent with preset contraband thinning category information in the first contraband image set as a target image set;

and/or screening images consistent with preset contraband thinning category information in the second contraband image set to serve as a target image set.

Optionally, the performing data source expansion preprocessing on the target image set to obtain a training image set includes:

performing first preprocessing on a target image set screened in a first contraband image set to obtain a training image set;

and/or performing second preprocessing on the target image set screened in the second contraband image set to obtain a training image set.

Optionally, the first preprocessing process includes:

processing the hue, brightness and saturation of each target image in the target image set at different degrees randomly to obtain a plurality of first intermediate images;

and respectively carrying out random cutting on the plurality of first intermediate images to obtain a training image set.

Optionally, the second preprocessing process includes:

performing rotation and affine transformation operation on each target image in the target image set to obtain a second intermediate image;

and fusing the second intermediate image with the X-ray image without contraband according to a preset fusion rule to obtain a training image set.

Optionally, after determining a detection area corresponding to the confidence detection value in the preset confidence interval as a contraband area, the method further includes:

comparing a confidence coefficient detection value corresponding to the contraband area with a preset detection value;

reserving a confidence detection value higher than or equal to a preset detection value and a corresponding detection area;

inputting a detection area image corresponding to a confidence coefficient detection value lower than a preset detection value into a convolutional neural network classification model so as to further judge the category of the contraband; wherein the preset detection value is any one value in a preset confidence interval.

Optionally, the convolutional neural network classification model is constructed by the following process:

acquiring a third contraband image set and an X-ray image without contraband; wherein the third set of contraband images is the same as the second set of contraband images;

randomly intercepting a partial area image of the X-ray image without the contraband;

performing third preprocessing on the third contraband image set and the partial area image of the X-ray image without the contraband to obtain a classification training image set;

and inputting the classification training image set into a classification training model for training to obtain a convolutional neural network classification model.

In another aspect of the present invention, a system for contraband detection and identification based on X-ray images is provided, including:

the first determining unit is used for determining a target image set according to preset contraband refinement category information;

the data expansion unit is used for carrying out data source expansion preprocessing on the target image set to obtain a training image set;

the training unit is used for inputting the training image set to a detection and recognition training model for training to obtain a detection and recognition network model;

the detection and identification unit is used for inputting the X-ray image to be detected into the detection and identification network model to obtain confidence detection values of all detection areas in the X-ray image to be detected;

and the second determining unit is used for determining the detection area corresponding to the confidence detection value in the preset confidence interval as the contraband area.

In a third aspect of the present invention, an apparatus is provided, which includes:

at least one processor; and

a memory communicatively coupled to at least one of the processors; wherein,

the memory stores instructions executable by the processor for implementing the method for contraband detection and identification based on X-ray images of any of the first aspect.

In a fourth aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for being executed by the computer to implement the method for contraband detection and identification based on X-ray images according to any one of the first aspect.

The invention has the beneficial effects that: according to the method, the target image set is determined according to the preset refined category information of the contraband, the target image set defined in a more detailed classification mode can be obtained, the detection and identification effects of the same type of contraband are prevented from being influenced by individual differences, data expansion preprocessing is carried out on the target image set, the data of the training image set are diversified, and the detection and identification accuracy of the detection and identification network model obtained through training is effectively improved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

fig. 1 is a schematic diagram of a contraband detection and identification method based on X-ray images according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an X-ray image set containing contraband and the result of a first pre-processing;

FIG. 3 is a schematic diagram of the individual image sets of contraband and the results of the second pre-processing;

FIG. 4 is a partial detection result of the X-ray image to be detected after passing through the detection recognition network model according to the present application;

FIG. 5 is a schematic diagram of a contraband detection and identification method based on X-ray images according to another embodiment of the present application;

FIG. 6 is a schematic structural diagram of a contraband detection and identification system based on X-ray images according to the present application;

FIG. 7 is a block diagram of a computer system of a server for implementing embodiments of the method, system, and apparatus of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

The invention provides a contraband detection and identification method based on an X-ray image, which comprises the following steps:

In order to more clearly describe the method for detecting and identifying contraband based on X-ray images, the following will describe each step in the embodiment of the present invention in detail with reference to fig. 1, in the embodiment, two types of contraband including guns and knives are mainly used for description, and of course, the method of the embodiment may also be applied to other contraband capable of directly and obviously judging the type of the contraband through the appearance.

The method for detecting and identifying contraband based on X-ray images in the first embodiment of the invention comprises steps S101-S105, wherein the steps are described in detail as follows:

s101, determining a target image set according to preset contraband refinement category information.

In the embodiment of the present application, the preset detailed classification information of the contraband refers to detailed classification information of the contraband, for example, the detailed classification information includes information of the classification name, shape, size, color, and the like of the contraband. The target image set is a collection of related images of contraband that need to be detected.

a contraband image set is acquired.

In the step, firstly, the category of the contraband image set is definitely obtained, and the contraband image set is obtained on the network according to the category.

Specifically, first, the detailed categories of contraband to be detected are determined according to the detection identification requirement. For example, the detection and identification requirements are that a gun and a knife need to be detected, the gun and the knife are classified in detail according to the size and the shape of the gun and the knife, for example, the gun can be classified into a pistol, a submachine gun, a long gun and the like, and the knife can be classified into a long knife, a short knife, a kitchen knife and the like.

By refining and classifying the contraband, the influence of the contraband of the same type, such as guns, on the detection and identification result due to different shapes and sizes can be effectively avoided.

In the application, after the contraband image set is obtained, images consistent with the preset contraband thinning categories can be manually screened or automatically screened out to serve as the target image set.

If manual screening is adopted, the sizes and the shapes of the guns and the cutters which are defined in advance are compared with the contraband image set by naked eyes, and the non-conforming guns and the cutters are rejected.

In the case of automatic screening, in one example, the images of the two images may be compared with each other, for example, if the degree of coincidence is greater than a preset degree of coincidence, it is determined that the images match, so that the efficiency may be improved.

In a specific embodiment, the acquiring the set of images of contraband includes:

acquiring a first contraband image set;

and/or acquiring a second contraband image set; the first contraband image set is an X-ray image set containing contraband; the second contraband image set is a separate contraband image set.

In this embodiment, the first contraband image set is downloaded from a website of a specific specialty, and the second contraband image set can be downloaded from a network by using a web crawler, and in one example, the process may include the following steps:

the method comprises the steps of firstly, confirming a target address of a crawling image, and initiating a crawling request by utilizing a Gecco network crawler of a Java language to remove the target address.

And secondly, returning the source code of the webpage containing the image connection to the crawling request, and analyzing the structure of the webpage by using a Jsoup analyzer to analyze the link of each image.

And thirdly, traversing the links of the images, initiating a request for the links, writing a return result to the local, and storing the return result as an image file.

In the embodiment of the present application, the contraband image sets can be divided into two categories, one is an X-ray image set containing contraband, and the other is an independent image set of contraband. As shown in fig. 2, four sets of contraband image sets are shown in fig. 2, one set is above and below, the lower image is an X-ray image containing contraband, and the upper image is an image after data source expansion preprocessing. As shown in fig. 3, the left-most column in fig. 3 is a single image of the gun and knife. And (3) after the independent images of the gun and the cutter are subjected to data source expansion preprocessing, the independent images are merged into the X-ray image without contraband, and a final training image set is obtained.

By adopting the two types of contraband image sets as the target image sets, the styles of the target image sets can be greatly increased, the data sources are richer, and the detection accuracy can be further improved.

In order to further enable the detection and recognition effect to have higher generalization and robustness, operations such as enhancement processing and the like need to be further performed on the target image set so as to expand the data source and meet the data requirement of the detection and recognition training model. The specific steps are given below.

And S102, performing data source expansion preprocessing on the target image set to obtain a training image set. According to the above embodiment, the method may specifically include the following steps:

and carrying out first preprocessing on the target image set screened in the first contraband image set to obtain a training image set. The first pretreatment process comprises the following steps:

and processing the hue, brightness, saturation and the like of each target image in the target image set at different degrees randomly to obtain a plurality of first intermediate images.

The process of obtaining the first intermediate image by the operation of the X-ray image containing contraband in the HSV space, which is the target image screened in the first contraband image set, is as follows:

converting the target image from an RGB space to an HSV space by using an OPENCV function;

adjusting the hue H, saturation S and lightness V values of the target image in the HSV space respectively to enable the hue H, saturation S and lightness V values to have obvious changes with the HSV value of the original image;

and converting the image from the HSV space to the RGB space by using an OPENCV function, and storing the image.

Referring to fig. 2, an image representation of an X-ray image containing contraband after first preprocessing is given, and the upper four images are training images respectively subjected to first preprocessing.

By the means, the target image can present different brightness, size and color, the training image set is expanded, and the requirements of detecting and identifying the training model are met.

And/or performing second preprocessing on the target image set screened in the second contraband image set to obtain a training image set. The second pretreatment process comprises the following steps:

as shown in fig. 3, each target image (a) in the target image set is subjected to operations such as rotation and affine transformation to obtain a second intermediate image (b). The image of the middle column is the second intermediate image.

And (c) fusing the second intermediate image with the X-ray image without contraband according to a preset fusion rule to obtain a training image set (c). The same gun or cutter can show different sizes and shapes in different X-ray images, and diversification of data is realized.

In this step, the preset fusion rule may adopt an embedded rule to embed the gun or the knife into the X-ray image without the contraband.

Furthermore, the acquisition of the X-ray image without contraband may be according to the acquisition process of the first and second contraband image sets in the above example.

Referring to fig. 3, a process of blending the gun and the knife into the X-ray image without the contraband according to the preset blending rule after the gun and the knife are subjected to transformation such as rotation and affine transformation is shown.

S103, inputting the training image set to a detection and recognition training model for training to obtain a detection and recognition network model.

In this step, the training image set may be input in five categories, each having approximately 4000 images for a total of 20786 images. As shown in fig. 2 and 3.

Before training, various parameters of the detection and recognition training model need to be set, for example, the size of the parameter, Bathsize, is set to 64, and the number of times of training is set to 10000 times, that is, 64 pictures are used as a set of training parameters, and the set of pictures are trained for 10000 times to obtain the parameters of the detection and recognition network model.

In the embodiment of the application, the initial parameters of the detection and identification training model are based on parameters obtained by training in 80 categories of a COCO data set in the prior art, and the sizes of guns and tools in an X-ray image are different from the sizes of 80 categories in the COCO data set to a certain extent, so that the sizes of contraband in the X-ray image need to be re-clustered, and the sizes of the guns and the tools conform to the size of a preset frame in the detection and identification training model.

And S104, inputting the X-ray image to be detected into the detection and recognition network model to obtain the confidence coefficient detection value of each detection area in the X-ray image to be detected.

In one example, a first-order target detection model YOLO can be adopted as a detection and recognition training model, so that the detection and recognition efficiency can be improved.

S105, determining a detection area corresponding to the confidence coefficient detection value in the preset confidence interval as a contraband area. As shown in fig. 4, a schematic diagram of the detection result is given, and the position of the contraband can be visually seen in the frame of the contraband area in the diagram.

In the present embodiment, the confidence level is also referred to as reliability, or confidence level, or confidence coefficient, that when the sampling estimates the overall parameter, the conclusion is always uncertain due to the randomness of the sample. Therefore, a probabilistic statement method, i.e. interval estimation in mathematical statistics, is used, i.e. how large the corresponding probability of the estimated value and the overall parameter are within a certain allowable error range, and this corresponding probability is called confidence. The confidence interval is then a probability interval.

In one example, the detection area may be determined based on the position of the object in the X-ray image to be detected, for example, a short knife, a toothbrush, and a paper towel are displayed in the X-ray image to be detected, and that may determine the detection area based on the positions of three objects and obtain the confidence of the three detection areas. For example, if the preset confidence interval is 0.5-1, the confidence of the short-knife detection area is 0.6, and the confidence of the toothbrush and paper towel detection areas is 0.3 and 0.2, respectively, the short-knife detection area is determined as the contraband area.

The network model for detecting and identifying can also output the position information of the contraband, such as space coordinate data. And locking contraband according to the confidence coefficient and the coordinate data, and prompting in a frame or voice broadcasting mode.

In order to increase the recall rate of the contraband, the threshold of the preset confidence interval may be decreased, for example, the standard preset confidence interval is 0.5-1, and then may be adjusted to 0.3-1, so that more detection results may be obtained. However, objects which are not contraband, such as toothbrushes, can be regarded as contraband, and detection accuracy is affected.

Therefore, it is necessary to further distinguish the detection results of the above embodiments.

As shown in fig. 5, after determining the detection area corresponding to the confidence detection value in the preset confidence interval as the contraband area, the method further includes:

s501, comparing the confidence coefficient detection value corresponding to the contraband area with a preset detection value.

And S502, reserving the confidence coefficient detection value higher than or equal to the preset detection value and the corresponding detection area.

S503, inputting the detection area image corresponding to the confidence coefficient detection value lower than the preset detection value into the convolutional neural network classification model so as to further judge the type of the contraband. Wherein the preset detection value is any one value in a preset confidence interval.

On the basis of the above example, the preset confidence interval is 0.3-1, the confidence of the detected toothbrush detection area is 0.3, the confidence of the short knife detection area is 0.6, the toothbrush and the short knife are confirmed to be contraband, in one example, the preset detection value is set to be 0.5, then the detection result of the short knife is continuously kept, the detection area image of the toothbrush lower than 0.5 is input into the convolutional neural network classification model for class judgment, if the detection area image is judged to be impurity, the detection area image is excluded, otherwise, the detection result is kept as the final detection result. Of course, in this example, the toothbrush would be excluded from the contraband category according to the classification model.

The construction process of the convolutional neural network classification model comprises the following steps:

acquiring a third contraband image set and an X-ray image without contraband; wherein the third set of contraband images and the second set of contraband images are the same. The images of the single contraband such as guns and knives are obtained by using web crawlers, referring to the above example.

Randomly intercepting a partial area image of the X-ray image without the contraband.

The randomly intercepted portions are stored as categories of impurities so as to exclude items that are not contraband.

And performing third preprocessing on the third contraband image set and the partial area image of the X-ray image without the contraband to obtain a classification training image set.

The third preprocessing can comprise operations of random clipping, affine transformation, color adjustment and the like, and the diversity of data is further enhanced, so that the convolutional neural network classification model has better generalization.

In one example, a classification training model may be constructed using a deep learning network model VGG16 as a backbone network and a Focal local function as a Loss function.

Based on the same inventive concept, a second embodiment of the present application provides a system for contraband detection and identification based on X-ray images, as shown in fig. 6, including:

a first determining unit 610, configured to determine a target image set according to preset contraband refinement category information;

a data expansion unit 620, configured to perform data source expansion preprocessing on the target image set to obtain a training image set;

a training unit 630, configured to input the training image set to a detection and recognition training model for training to obtain a detection and recognition network model;

the detecting unit 640 is configured to input the X-ray image to be detected into the detection and recognition network model to obtain confidence detection values of each detection region in the X-ray image to be detected;

a second determining unit 650, configured to determine a detection region corresponding to the confidence detection value in the preset confidence interval as a contraband region.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and related description of the system described above may refer to the corresponding process in the foregoing method embodiments, and will not be described herein again.

It should be noted that, the contraband detection and identification system based on X-ray images provided in the above embodiment is only illustrated by the division of the above functional modules, and in practical applications, the above functions may be allocated to different functional modules according to needs, that is, the modules or steps in the embodiment of the present invention are further decomposed or combined, for example, the modules in the above embodiment may be combined into one module, or may be further split into multiple sub-modules, so as to complete all or part of the above described functions. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not to be construed as unduly limiting the present invention.

Based on the same inventive concept, an apparatus of a third embodiment of the present invention comprises:

at least one processor; and

a memory communicatively coupled to at least one of the processors; wherein,

the memory stores instructions executable by the processor for performing the method for contraband detection and identification based on X-ray images according to the first embodiment.

A computer-readable storage medium of a fourth embodiment of the present invention stores computer instructions for being executed by the computer to implement the method for contraband detection and identification based on X-ray images described in the first embodiment.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes and related descriptions of the storage device and the processing device described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

Reference is now made to FIG. 7, which illustrates a block diagram of a computer system of a server for implementing embodiments of the method, system, and apparatus of the present application. The server shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 7, the computer system includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for system operation are also stored. The CPU701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An Input/Output (I/O) interface 705 is also connected to the bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application. It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing or implying a particular order or sequence.

The terms "comprises," "comprising," or any other similar term are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.

Claims

1. A contraband detection and identification method based on X-ray images is characterized by comprising the following steps:

2. The method of claim 1, wherein the determining the target set of images according to the preset contraband refinement category information comprises:

acquiring a contraband image set;

3. The method of claim 2, wherein the acquiring the set of images of contraband comprises:

acquiring a first contraband image set;

4. The method of claim 3, wherein the pre-processing the target image set by data source expansion to obtain a training image set comprises:

5. The method of claim 4, wherein the first preprocessing is performed by:

6. The method of claim 4, wherein the second preprocessing is performed by:

7. The method of claim 1, wherein after determining a detection region corresponding to the confidence detection value at a preset confidence interval as a contraband region, the method further comprises:

8. The method of claim 7, wherein the convolutional neural network classification model is constructed by the following process:

9. A system for contraband detection and identification based on X-ray images, comprising:

10. An apparatus, comprising:

at least one processor; and

a memory communicatively coupled to at least one of the processors; wherein,

the memory stores instructions executable by the processor for performing the method for contraband detection and identification based on X-ray images of any of claims 1-8.