WO2020187077A1

WO2020187077A1 - Deep neural network-based security check system and method

Info

Publication number: WO2020187077A1
Application number: PCT/CN2020/078425
Authority: WO
Inventors: 屈立成; 李萌萌; 李坤伦; 吕娇; 赵明; 王海飞; 屈艺华
Original assignee: 长安大学
Priority date: 2019-03-21
Filing date: 2020-03-09
Publication date: 2020-09-24
Also published as: CN109946746A

Abstract

A neural network-based security check system and method. Said security check system comprises an X-ray imaging module, a detection model training and learning module, an object identification module, and a security management module; an output end of the X-ray imaging module is connected to an input end of the object identification module; the object identification module is in bidirectional connection with the detection model training and learning module; and an output end of the object identification module is connected to an input end of the security management module. An X-ray image is divided on the basis of color features thereof and is synthesized into a multi-plane detection image, a deep neural network detection model is established, and feature training and learning of common articles are performed using big data, so as to achieve identification and classification of rotating, telescopic, and deformed objects by a detector.

Description

Security inspection system and method based on deep neural network

Technical field

The invention belongs to the technical field of security inspection, and specifically relates to a security inspection system and method based on a deep neural network.

Background technique

With the rapid economic development, high-speed rail, airplanes, etc. have become indispensable means of transportation for people's daily travel. However, passengers who intentionally or unintentionally carry dangerous goods in transportation have become the biggest threat to transportation safety. X-ray security inspection machines play an important role in the safety inspection of dangerous goods and the safety of transportation vehicles. However, the traditional X-ray security inspection machine requires the staff to carefully check the X-ray luggage image to determine whether it contains dangerous goods. The device is low in intelligence, and the cost required for manual inspection is high. At the same time, misjudgment may occur. , Thereby posing a great threat to people's safe travel, and even causing major accidents.

The “an automatic identification device for contraband security inspection” (CN 201710233696.6) published in the patent application converts the image from the RGB color space to the HSV color space and copies three copies, which are divided into three colors for identification. After optimizing the image quality, the three The patterns after the recognition of different colors are processed in parallel with the pre-stored contraband templates under the corresponding colors, and the SURF feature matching is performed. If the matching rate is above 55%, it is considered that the luggage has contraband.

SURF feature matching is mainly to match the X-ray image with the number of SURF descriptors in the pre-stored contraband image template. It can only identify objects of the same style and color. The detection accuracy of similar items is low (such as toy pistols and The shape of the real gun is the same), the generalization ability is poor, and the category classification is not clear. It has a certain detection capability for rotating, expanding and deforming objects in luggage, but it is difficult to accurately detect and distinguish between disorderly stacked luggage or overlapping objects.

The patent application published "A device and method for rapid automatic detection and alarm of dangerous goods in X-ray security inspection machine" (CN 201610748757.8). First, Gaussian filtering is used to denoise the image, and secondly, the nonlinear enhancement method is used for image enhancement and danger. Product image segmentation, and finally, perform feature extraction and feature analysis on the suspected dangerous goods image. If dangerous goods are found, circle the dangerous goods and transmit the image data to the computer through the network port and display it on the LCD. Select the setting to make a sound And the flashing alarm of the LED light.

The existing dangerous goods detection technology adopts image processing technology, which is mainly to segment according to the color of the object and then extract and analyze the feature of the image object. During the segmentation process, the same object of different materials cannot be handled well, for example: the tip of the scissors is blue The handle is usually an orange feature, so that the segmentation of the object only obtains the local features of the object, resulting in low object accuracy and unclear object categories. The detection accuracy of objects that rotate, expand, and deform in luggage items is low, and because of luggage items The stacking is messy, and it is difficult to accurately detect overlapping objects.

With the rapid development of artificial intelligence technology, the intelligent security inspection system integrated with deep learning algorithms will greatly improve the intelligent procedures of security inspection devices, improve the accuracy of dangerous goods identification, and effectively reduce the pressure on security inspection staff. Improve the passage efficiency of security check channels, reduce congestion, and ensure people's traffic and travel safety to the greatest extent.

Summary of the invention

Aiming at the problems of low object detection and positioning accuracy in existing X-ray baggage inspection technology, unclear classification of dangerous goods, and low intelligence in the detection process, a new X-ray intelligence based on color segmentation and multi-plane deep neural network is proposed. The security inspection device and method solve the problem of detection and identification of items carried in daily luggage and parcels. Based on the color feature of X-ray image segmentation and synthesis of multi-plane detection images, a deep neural network detection model is established, and big data is used for feature training and learning of common objects, so that the detector can recognize and recognize rotating, stretching and deforming objects. classification. Especially for the luggage items that are piled up in disorder, entangled and overlapped, carry out meticulous detection and screening, and learn their color, shape and texture characteristics in depth to achieve the effect of accurate identification and classification, improve the accuracy of dangerous goods identification, and improve X-rays The intelligence of the security check process and the passing efficiency of the security check channel reduce congestion, reduce the work intensity of security personnel, and maximize people's traffic safety.

In order to achieve the above objective, a security inspection system based on a deep neural network of the present invention includes an X-ray imaging module, a detection model training and learning module, an object recognition module, and a security management module. The output terminal of the X-ray imaging module and the object recognition The input end of the module is connected, the object recognition module and the detection model training and learning module are bidirectionally connected, and the output end of the object recognition module is connected to the input end of the security management module; the X-ray imaging module is used to obtain the X image video sequence of the object, and then A digital picture is obtained through analog-to-digital conversion, and the obtained digital picture is transferred to the object recognition module; the detection model training learning module is used for image training to obtain a learning model, and the learning model is transferred to the object recognition module; the object The recognition module is used to load the learning model in the detection model training module, classify and locate items, and transmit the type and coordinate information of the detected objects to the security management module; the security management module is used to identify objects based on The object type and coordinate information output by the module will transport the objects to different transport channels.

Further, it also includes an object transmission module. The object transmission module includes an object entry channel, a dangerous goods output channel, and a non-dangerous goods output channel.

Further, the safety management module includes an information management module, a warning module, a baggage control module, and a display module; among them, the information management module is used to receive object classification and location information sent by the object recognition module, and based on the received object classification and location information Determine whether the object is a dangerous item; the alarm module is used to alarm; the baggage control module is used to transport the baggage to different channels in the object transmission module, and the display module is used to display X-ray pictures and detection results.

A security inspection method based on deep neural networks. First, use pictures to train an image learning model. During item inspection, collect X image video sequences of the items to be inspected, and X image video sequences are converted to digital pictures by analog to digital conversion; then load image learning The model uses the image learning model to identify the types and coordinates of the items in the digital picture; then according to the types and coordinates of the items, the items are divided into different conveying channels according to the types.

Specifically include the following steps:

Step 1. Use the X-ray emission device to perform imaging after penetrating the object to obtain an X image video sequence, and the X image video sequence undergoes analog-to-digital conversion to obtain a digital picture;

Step 2. Load the image learning model, and use the image learning model to identify and locate digital pictures; the image learning model is obtained through training. The specific training method is: firstly, use the convolutional layer of the convolutional neural network to pool Layer and fully connected layer to build the object training model; then the X-ray images obtained in the early stage are classified according to the security inspection object category, and the category and coordinate information of the object are marked. The coordinate information includes the coordinates of the object center point x, y and the target frame Length w and width h; Then set the parameters of the training model, including learning rate, batch processing scale, learning strategy, etc.; Then send the labeled pictures to the convolutional neural network, and use the built convolutional neural network to label The image learning model is trained to obtain the image learning model; then the image learning model is verified. If the expected effect is achieved, the image learning model is saved to the model learning library; if the expected effect is not achieved, the parameters of the convolutional neural network are adjusted and the training continues, Until the image learning model achieves the desired effect.

Step 3. Divide the items into different conveying channels according to the types and coordinates of the items.

Further, in step 2, the pictures used for training the learning model adopt pictures with different angles and positions.

Further, sending the marked pictures into the convolutional neural network, and training the marked pictures with the built convolutional neural network includes the following steps:

S1. Segment the digital picture into the area to be detected according to the characteristics of the X-ray background, the colored area is the detection area, and the digital picture is an rgb image;

S2. Take out the r channel, g channel and b channel of the digital picture and store them in the first three channels of the picture to be input to the convolutional neural network; then convert the rgb image model to the hsv color model, and extract the h channel of the hsv model, The s channel and the v channel are stored in the three channels behind the rgb of the input picture; the hsv model is divided into organic orange, inorganic blue, and mixed green by the hue H, purity S and brightness V of the hsv color model , And other colors are divided into 4 color channels, stored in the last four channels of the input picture, and the training pictures of 10 channels are input into the convolutional neural network;

S3. Use convolution operation to perform feature extraction on the area to be detected, and the convolutional features are expressed as:

Among them, n_in is the dimension of the last dimension of the tensor. Xk represents the k-th input matrix. Wk represents the k-th sub-convolution kernel matrix of the convolution kernel. s(i,j) is the value of the corresponding position element of the output matrix corresponding to the convolution kernel W, and b is the amount of paranoia;

S4. Perform pooling;

S5. Use Softmax to classify each target box to obtain the bbox after classification;

S6. The loss function adopts the focalloss loss function,

FL(pt)=-α _t (1-pt) ^γ log(pt)

γ is the focusing parameter, γ>=0, 1-pt is called the modulation coefficient, α _{t is} used to adjust the ratio of positive and negative samples, when the foreground category uses α _t , the corresponding background category uses 1-α, and pt is different Classification probability of category;

S7. The bbox with the highest confidence is selected as the detection result and output.

Furthermore, in S2, when the value of H is between 20° and 60°, the value of S is between 0.4 and 1.0, and the value of V is between 0.4 and 1.0, it is an organic orange channel; when the value of H is between 100° and 140°, S When the value of 0.4～1.0, the value of V is 0.4～1.0, it is the green channel of the mixture; when the value of H is 220°～260°, the value of S is 0.4～1.0, and the value of V is 0.4～1.0, it is the inorganic blue channel ; When the value of H is not within the range of the orange channel, the green channel, and the blue channel, the value of S is 0.4 to 1.0, and the value of V is 0.4 to 1.0, which are other color channels.

Further, in S5, the maximum pooling method is adopted for pooling.

Furthermore, in S7, α=0.25 and γ=2.

Compared with the prior art, the present invention has at least the following beneficial technical effects:

(1) Segmentation and synthesis of multi-plane inspection images based on the color characteristics of X-ray images improves the accuracy of item recognition.

(2) Classify different object pictures in the object detection algorithm. By building models, adjusting parameters, and using convolutional neural networks for feature learning, the object categories in the luggage can be clearly classified;

(3) In X-ray image detection, daggers, guns, knives, etc. all have blue characteristics, gasoline, lighters, ammunition, etc. have green characteristics, alcohol and gasoline have orange characteristics, and the color characteristics of dangerous goods are mainly blue and green And orange, the organic combination of object geometric features, texture features and color features can greatly reduce the interference of toy pistols and ornaments on the detection of dangerous goods, and improve the accuracy of object detection and positioning.

(4) In the X-ray image learning process, a large number (at least 500) of image data with different angles and positions are used for learning. Blurred, rotated, and deformed objects can also be accurately identified, which effectively improves the accuracy of object detection.

(5) The classification of objects is clear: for object detection, there are mainly seven categories. Flammable and explosive objects mainly include: kerosene, liquefied petroleum gas, solid alcohol, compressed gas, firecrackers, fireworks, fireworks, etc.; guns and ammunition objects Mainly include: simulation guns, steel ball guns, stun guns, gun-type lighters, bullets, empty bullets, bullet clips, etc.; explosives mainly include: scale-shaped TNT, plastic explosives, fuse, detonator, timed firecracker Devices, etc.; controlled knives mainly include: daggers, switch knives, three-sided knives, lock knives, etc.; dangerous goods mainly include: scissors, axes, kitchen knives, slingshots, etc.; police equipment mainly include: electric shock sticks, double Knuckles, handcuffs, smoke bombs, etc.;

Daily luggage items mainly include: bottled water, bottled wine, liquid alcohol, glass glue, etc. The classification of objects is clear, which effectively assists staff in safety inspections and can add object categories according to the actual situation to improve safety.

(6) According to the security inspection system under different scene requirements, set the alarm threshold of dangerous types, select the appropriate object detection model from the model training library and transmit it to the object detection module, which has a certain real-time linkage.

Description of the drawings

Figure 1 is a block diagram of an X-ray intelligent security inspection system based on a deep neural network;

Figure 2 is a flowchart of the object recognition detection module and the safety management module;

Figure 3 is a flowchart of the model training module;

Figure 4 is a flowchart of the color segmentation algorithm;

Figure 5 is the original X-ray image;

Figure 6a is a plan view of R;

Figure 6b is a plan view of G;

Figure 6c is a plan view of B;

Figure 7a is an H plan view;

Figure 7b is an S plan view;

Figure 7c is a V plan view;

Figure 8a is a plan view of the mixture;

Figure 8b is a plan view of organic matter;

Figure 8c is a plan view of an inorganic substance;

Figure 8d is another plan view.

detailed description

The present invention will be described in detail below with reference to the drawings and specific embodiments.

1, a security inspection system based on a deep neural network includes an object transmission module, an X-ray imaging module, a detection model training and learning module, an object recognition module, and a security management module. The working process is that the object transfer module transfers the luggage items into the detection range of the X-ray imaging machine module. The X-ray imaging machine module emits X-rays, passes through the X-ray images of the luggage, and obtains the X image video sequence, and then passes through the module The digital image is converted, and the security check item learning model is loaded, and the convolutional neural network is used to classify and locate the object. The output image recognition category and location are sent to the security management module, and the security management module determines the path to which the luggage flows.

Among them, the object transfer module is mainly used to transfer luggage items during security check;

The X-ray imaging module mainly uses the X-rays generated by the X-ray emission tube to penetrate the luggage items in the channel to obtain the X image video sequence, and then obtain the digital picture through the analog-to-digital conversion;

The detection model training learning module is used to collect and annotate object pictures, and then send them to the convolutional god-level network for learning, and finally get the learned object detection model, and pass the trained model to the object recognition module;

The object recognition module is used to load the X-ray image learning model of the detection model training module, use the built-in object detection algorithm for object recognition and positioning, and transmit the detected object type and coordinate information to the security management module;

The alarm module and the baggage control module in the safety management module are used to determine whether an alarm is needed and to transmit the items to the dangerous goods channel according to the object type and coordinate information output by the object recognition module. The security management module includes an information management module, a warning module, a baggage control module and a display module.

Among them, the information management module is used to receive the object classification and location information sent by the object recognition module, and to determine whether the detected object is a dangerous article according to the received object classification and location information, the alarm module is used to alarm, and the baggage control module is used to The baggage is conveyed to different channels in the object transmission module, and the display module is used to display X-ray pictures and detected result pictures during the working process of the security inspection machine.

This system can be used as a new type of intelligent security inspection system, and can also update the object recognition module, model training module, and safety management module to the existing security inspection system, and intelligently upgrade the existing security inspection system.

The intelligent security inspection method mainly includes four parts: detection area extraction, image plane processing, detector learning and training, and intelligent detection of dangerous goods.

The detection area extraction process is as follows: segment the area to be detected according to the characteristics of the X-ray background, and discard a large number of white candidate detection areas directly, avoiding subsequent time-consuming recognition operations and improving the speed of item detection.

Image plane processing: The preprocessing is mainly to convert the image from the RGB model to the hsv model. The hsv model includes three color planes H, S and V. The image is then divided into four colors: orange, green, blue and other colors by hue H flat;

Usually the picture input to the convolutional neural network is represented by the RGB color model, which is composed of three color planes: R, G, and B. In addition to these three color planes, the present invention adds the H, S, and V color planes obtained in the preprocessing stage, as well as the orange, green, blue and other colors generated after color segmentation, a total of 10 color planes. After data fusion processing, input the convolutional neural network for target recognition.

Detector learning and training: The intelligent security inspection system uses a large number of X-ray object pictures of different angles and positions to classify and label the collected X-ray images, mark the type and coordinates of the object, and divide it into 8:2 Learning picture sets and test picture sets, and generating the .xml annotation format required by the algorithm based on the original pictures of the acquired X-ray images (including the object category, size and its coordinate position in the X-ray image, etc.).

Build a learning model and adjust appropriate parameters, learn geometric features, texture features, and color features of objects through a convolutional neural network, save the learning model, and then transfer the trained X-ray object learning model to the object recognition module through the network communication interface. The baggage items are transferred from the transmission module to the X-ray imaging module. The X-ray transmitter passes through the imaging of the baggage to obtain an X image video sequence. The X image video sequence undergoes analog-to-digital conversion to obtain a digital picture. Load the X-ray learning model to detect The type and coordinates of the object are transmitted to the safety management module through the communication interface. According to the alarm strategy and confidence threshold set by the safety management module, it is determined whether the system alarms and whether it is transmitted to the dangerous goods channel. The confidence threshold can be set by itself according to the needs of security inspection. It is 70%. If the object detection confidence is greater than the threshold, it will alarm.

The object detection module is updated on the basis of the original security inspection system and transmitted to the security inspection machine through the network communication interface. The X-ray learning model is used to output the type and coordinate information of the object to the existing security inspection screen through the communication interface. Alarm threshold, if dangerous goods are detected, the object conveyor will be suspended.

Referring to Figure 3, the detector learning training includes the following steps:

Step 1. Use the convolutional layer, pooling layer and fully connected layer of the convolutional neural network to build an object training model.

Step 2. Classify the pictures in the X-ray picture library according to the security check object category, and manually mark the category and coordinate information of the object in the picture.

Step 3. Set the parameters of the training model. The parameters include learning rate, batch processing scale, learning strategy, etc.

Step 4. Send the marked pictures into the convolutional neural network.

Step 5. Use the built convolutional neural network to train the labeled pictures to obtain a learning model.

Step 6. Verify the learning model. If the expected effect is achieved, save the learning model to the model learning library; if the expected effect is not achieved, adjust the parameters of the convolutional neural network and continue training until the learning model achieves the expected effect. MAP (Mean Average Precision) for object detection, if the value reaches 80%, the expected effect can be achieved.

Step 4 includes the following steps:

Step 4.1 Detection area extraction

The area to be detected is segmented according to the characteristics of the X-ray background, and a large number of candidate detection areas with blank backgrounds are directly discarded, and the colored area is the detection area, which avoids subsequent time-consuming identification operations and improves the speed of item detection.

Step 4.2 Image plane processing

The input HSV is divided into organic orange channel, inorganic blue channel, mixed green channel and other color channels according to the value range of hue, purity and brightness.

When the value of H is between 20°～60°, the value of S is between 0.4～1.0, and the value of V is between 0.4～1.0, it is an organic orange channel; when the value of H is between 100°～140°, the value of S is between 0.4～1.0, When the value of V is 0.4～1.0, it is the green channel of the mixture; when the value of H is 220°～260°, the value of S is 0.4～1.0, and the value of V is 0.4～1.0, it is the inorganic blue channel; when the value of H is not When the orange channel, the green channel and the blue channel are within the range, the value of S is 0.4-1.0, and the value of V is 0.4-1.0, which are other color channels.

Step 4.3 Take the r, g, and b channels of the picture and store them in the first three channels of the picture that will be input to the convolutional neural network, and then convert the rgb image model to the hsv color model, and extract the h, s, and v three of the hsv model Two channels are stored in the three channels behind the rgb of the input image, and the image is divided into 4 colors through the different value ranges of hsv hue, purity and brightness. The image is divided into organic orange, inorganic blue, mixed green, and other colors. The channel is stored in the last four channels of the input image, and the training image of 10 channels is input into the convolutional neural network.

The detection model training and learning module segment the image based on the color features of the X-ray image, and synthesize a multi-plane detection image that integrates R, G, B, H, S, V and material information, which improves the accuracy of the detection of objects.

Step 5 includes the following steps:

Step 5.1. Use convolution operation to perform feature extraction on the area to be detected

The input image size is 416*416, the channel is 10, and the convolution operation is performed using 3*3 and 1*1 convolutional layers. Feature representation after convolution

Among them, n_in is the dimension of the last dimension of the tensor. Xk represents the k-th input matrix. Wk represents the k-th sub-convolution kernel matrix of the convolution kernel. s(i,j) is the value of the corresponding position element of the output matrix corresponding to the convolution kernel W, and b represents the amount of paranoia.

Step 5.2. Pooling:

The maximum pooling method is adopted, that is, the maximum value of the 2*2 pooling area is selected as the characteristic value, and the core step is 1.

Step 5.3. Use Softmax to classify each Bbox;

Step 5.4. Loss function adopts focalloss loss function

FL(pt)=-α _t (1-pt) ^γ log(pt)

γ is called the focusing parameter, γ>=0, (1-pt) is called the modulation coefficient, α _{t is} used to adjust the ratio of positive and negative, when the foreground category uses α _t , the corresponding background category uses 1-α, and pt is The classification probability of different categories; when α=0.25, γ=2, the effect is best. α is used to adjust the ratio of positive and negative. When the foreground category uses α, the corresponding background category uses 1-α, and pt is the classification probability of different categories.

Step 5.5. The local maximum method is adopted, that is, the bbox (the rectangular area containing the object) with the highest confidence is selected as the detection result output, that is, the position information of the detected object. Among them, the Bbox information contains 5 data values, namely x, y, w, h, and confidence. Where x, y refer to the coordinates of the center position of the bounding box of the object predicted by the current grid. w, h refers to the width and height of the bounding box of the object predicted by the current grid, and confidence refers to the confidence of the predicted object.

For ease of understanding, schematic diagrams of the pictures are given, among which Figure 5 is the X-ray image after grayscale, Figure 6a is the R plan view of the X-ray image, Figure 6b is the G plan view; Figure 6c is the B plan view of the X-ray image; 7a is the H plan view of the X-ray image; FIG. 7b is the S plan view of the X-ray image; FIG. 7c is the V plan view of the X-ray image; FIG. 8a is the mixture plan view of the X-ray image; FIG. 8b is the organic matter plan view of the X-ray image; 8c is an inorganic plan view of the X-ray image; other plan views of the X-ray image.

Referring to Figure 2, the security inspection system includes the following steps:

Step 1: Set the alarm threshold of different objects.

The first step: transfer the luggage items through the conveyor belt of the object transfer module.

The second step: X-ray imaging module emits X-rays, through X-ray imaging of luggage to obtain X image video sequence.

Step 3: Get the digital picture of the luggage item after analog-digital conversion.

Step 4: Load the X-ray image learning model of the model training module.

Step 5: Use the learning model to classify and locate objects.

Step 6: Output the object type and coordinate information in the picture and send it to the safety management module.

Step 7: The alarm module of the security management module decides whether to give an alarm and the baggage control module determines the channel of baggage flow. The technology of the present invention mainly uses deep learning for object recognition and positioning, and organically combines the geometric features and texture features of the object with the color of the object in the X-ray image in the process of object feature learning. Using a large number of image data from different angles and different positions for learning can not only detect and recognize blurred, rotated, and deformed images, but also update the trained model to a series of security inspection machines in real time. In the management module, the administrator can set the object type threshold, category and coordinates according to the degree of danger of the object. The intelligent security inspection system based on deep learning mainly improves the manual identification of dangerous goods in the traditional security inspection system into a process that relies on deep learning to assist the security inspection personnel, greatly reducing labor costs and making the security inspection system more intelligent.

The functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

The above content is only to illustrate the technical ideas of the present invention, and cannot be used to limit the scope of protection of the present invention. Any changes made on the basis of the technical solutions according to the technical ideas proposed by the present invention fall into the claims of the present invention. Within the scope of protection.

Claims

A security inspection system based on a deep neural network, which is characterized by comprising an X-ray imaging module, a detection model training and learning module, an object recognition module, and a security management module, the output end of the X-ray imaging module and the input end of the object recognition module Connection, the object recognition module and the detection model training and learning module are bidirectionally connected, and the output end of the object recognition module is connected to the input end of the safety management module;

The X-ray imaging module is used to obtain the X image video sequence of the article, and then obtain a digital picture through analog-to-digital conversion, and transfer the obtained digital picture to the object recognition module;

The detection model training and learning module is used for image training to obtain a learning model, and transfer the learning model to the object recognition module;

The object recognition module is used to load the learning model in the detection model training module, classify and locate objects, and transmit the type and coordinate information of the detected objects to the security management module;

The security management module is used to transport the articles to different article transportation channels according to the object type and coordinate information output by the object recognition module.
The security inspection system based on a deep neural network according to claim 1, further comprising an object transmission module, the object transmission module including an article entry channel, a dangerous goods output channel, and a non-dangerous goods output channel.
A security inspection system based on a deep neural network according to claim 1, wherein the security management module includes an information management module, a warning module, a luggage control module, and a display module; wherein the information management module is used to receive the object recognition module Send the object classification and location information, and determine whether the object is a dangerous object according to the received object classification and location information; the alarm module is used to alarm; the baggage control module is used to transport the baggage to different channels in the object transmission module and display The module is used to display X-ray pictures and inspection results.
A security inspection method based on a deep neural network, which is characterized by first training an image learning model using pictures, and collecting X image video sequences of the objects to be inspected during item detection, and X image video sequences undergoing analog-to-digital conversion to obtain digital pictures; Then load the image learning model, and use the image learning model to identify the types and coordinates of the items in the digital picture; then, according to the types and coordinates of the items, the items are divided into different conveying channels according to the types.
A security inspection method based on a deep neural network according to claim 4, characterized in that it comprises the following steps:

Step 1. Use the X-ray emission device to perform imaging after penetrating the object to obtain an X image video sequence, and the X image video sequence undergoes analog-to-digital conversion to obtain digital pictures;

Step 2. Load the image learning model, and use the image learning model to identify and locate digital pictures; the image learning model is obtained through training. The specific training method is: firstly, use the convolutional layer of the convolutional neural network to pool Layer and fully connected layer to build the object training model; then the X-ray images obtained in the early stage are classified according to the security inspection object category, and the category and coordinate information of the object are marked. The coordinate information includes the coordinates of the object center point x, y and the target frame Length w and width h; then set the parameters of the training model, including learning rate, batch processing scale and learning strategy; then send the labeled pictures to the convolutional neural network, and use the built convolutional neural network to The image is trained to obtain the image learning model; then the image learning model is verified. If the expected effect is achieved, the image learning model is saved to the model learning library; if the expected effect is not achieved, the parameters of the convolutional neural network are adjusted and the training continues until The image learning model achieves the expected effect;

Step 3. Divide the items into different conveying channels according to the types and coordinates of the items.
A security inspection method based on a deep neural network according to claim 5, wherein, in step 2, the pictures used for training the learning model adopt pictures with different angles and positions.
A security inspection method based on a deep neural network according to claim 5, characterized in that in step 2, the marked pictures are sent to the convolutional neural network, and the constructed convolutional neural network is used to Picture training, including the following steps:

S1. Segment the digital picture into the area to be detected according to the characteristics of the X-ray background, the colored area is the detection area, and the digital picture is an rgb image;

S2. Take out the r channel, g channel and b channel of the digital picture and store them in the first three channels of the picture to be input to the convolutional neural network; then convert the rgb image model to the hsv color model, and extract the h channel of the hsv model, The s channel and the v channel are stored in the three channels behind the rgb of the input picture; the hsv model is divided into organic orange, inorganic blue, and mixed green by the hue H, purity S and brightness V of the hsv color model , And other colors are divided into 4 color channels, stored in the last four channels of the input picture, and the training pictures of 10 channels are input into the convolutional neural network;

S3. Use convolution operation to perform feature extraction on the area to be detected, and the convolutional features are expressed as:

Among them, n_in is the last dimension of the tensor, Xk represents the k-th input matrix, Wk represents the k-th sub-convolution kernel matrix of the convolution kernel, and s(i,j) is the output corresponding to the convolution kernel W The value of the corresponding position element of the matrix, b is the amount of paranoia;

S4. Perform pooling;

S5. Use Softmax to classify each target box to obtain the bbox after classification;

S6. The loss function adopts the focalloss loss function,

FL(pt)=-α t (1-pt) γ log(pt)

γ is the focusing parameter, γ>=0, 1-pt is called the modulation coefficient, α t is used to adjust the ratio of positive and negative samples, when the foreground category uses α t , the corresponding background category uses 1-α, and pt is different Classification probability of category;

S7. The bbox with the highest confidence is selected as the detection result and output.
A security inspection method based on a deep neural network according to claim 7, characterized in that, in S2, when the value of H is between 20° and 60°, the value of S is between 0.4 and 1.0, and the value of V is between 0.4 and 1.0. When, it is the orange channel of organic matter; when the value of H is 100°～140°, the value of S is 0.4～1.0, and the value of V is 0.4～1.0, it is the green channel of mixture; when the value of H is 220°～260°, the value of S 0.4-1.0, when the value of V is 0.4-1.0, it is an inorganic blue channel; when the value of H is not within the range of the orange channel, green channel and blue channel, the value of S is 0.4-1.0, and the value of V is 0.4 ~1.0, for other color channels.
A security inspection method based on a deep neural network according to claim 7, wherein in S5, a maximum pooling method is used for pooling.
A security inspection method based on a deep neural network according to claim 7, wherein in S7, α=0.25 and γ=2.