CN112162324A - Intelligent security inspection method for effectively improving contraband identification rate - Google Patents

Intelligent security inspection method for effectively improving contraband identification rate Download PDF

Info

Publication number
CN112162324A
CN112162324A CN202010907854.3A CN202010907854A CN112162324A CN 112162324 A CN112162324 A CN 112162324A CN 202010907854 A CN202010907854 A CN 202010907854A CN 112162324 A CN112162324 A CN 112162324A
Authority
CN
China
Prior art keywords
security inspection
contraband
energy information
low
ray
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010907854.3A
Other languages
Chinese (zh)
Other versions
CN112162324B (en
Inventor
戴剑彬
王晨曦
陈家欢
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Haishen Intelligent Technology Shanghai Co ltd
Original Assignee
Haishen Intelligent Technology Shanghai Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Haishen Intelligent Technology Shanghai Co ltd filed Critical Haishen Intelligent Technology Shanghai Co ltd
Priority to CN202010907854.3A priority Critical patent/CN112162324B/en
Publication of CN112162324A publication Critical patent/CN112162324A/en
Application granted granted Critical
Publication of CN112162324B publication Critical patent/CN112162324B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
    • G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
    • G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
    • G01V5/232—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays having relative motion between the source, detector and object other than by conveyor
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/401—Imaging image processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/423—Imaging multispectral imaging-multiple energy imaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Quality & Reliability (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

The invention relates to the technical field of security inspection equipment and security inspection methods, in particular to an intelligent security inspection method for effectively improving the identification rate of contraband, which is used for detecting and identifying the contraband on an X-ray image by a security inspection machine and comprises the following steps: step A: shooting an X-ray image of an article by using an X-ray machine, and outputting a high-energy spectrum gray-scale image and a low-energy spectrum gray-scale image; and B: analyzing the X-ray image by adopting an example segmentation algorithm to find out the non-overlapped part and the overlapped part of the X-ray image; and C: selecting high-energy information and low-energy information of non-overlapped parts of articles made of different materials for the non-overlapped parts, and finding out the color mapping relation of article overlapping through linear regression; step D: and calculating the corrected atomic number of the substance by using the example segmentation algorithm in the step B for the overlapped part of the X-ray images. The method overcomes the influence of object overlapping on the recognition rate, and greatly improves the accuracy and stability of recognition.

Description

Intelligent security inspection method for effectively improving contraband identification rate
Technical Field
The invention relates to the technical field of security inspection equipment and security inspection methods, in particular to an intelligent security inspection method for effectively improving the identification rate of contraband.
Background
In order to ensure the safety of public transportation, safety inspection has become a necessary means for ensuring the safety of public lives and properties. However, the demand of security inspection is increasing due to high mobility and large passenger flow of Chinese population. At present, the operation of security inspection equipment is implemented by security inspection personnel.
However, the X-ray security inspection machine luggage detection mainly depends on manual image viewing and judgment of security inspectors, the accuracy of the X-ray security inspection machine luggage detection depends on the self experience of the security inspectors, the detection speed is limited by the workload of the security inspectors, the efficiency is not easy to be further improved, the false alarm rate and the false alarm rate in the industry exceed 30%, and the situation that contraband articles are not mistakenly and mistakenly missed in the manual security inspection identification process is difficult to ensure, so that potential safety hazards are brought.
The image identification technology based on deep learning is introduced into the security inspection equipment industry, however, the existing image identification technology has certain limitations in contraband identification, and the difficult points include: multiple objects are overlapped and shielded, images are blurred in low resolution, contraband is various in types and shapes, and the like. In view of this, an intelligent security inspection method for effectively improving the identification rate of contraband is provided.
Disclosure of Invention
The invention aims to provide an intelligent security inspection method for effectively improving the identification rate of contraband so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
an intelligent security inspection method for effectively improving the identification rate of contraband is used for detecting and identifying the contraband of an X-ray image by a security inspection machine, and comprises the following steps:
step A: shooting an X-ray image of an article by using an X-ray machine, and outputting a high-energy spectrum gray-scale image and a low-energy spectrum gray-scale image;
and B: analyzing the X-ray image by adopting an example segmentation algorithm to find out the non-overlapped part and the overlapped part of the X-ray image;
and C: selecting high-energy information and low-energy information of non-overlapped parts of articles made of different materials for the non-overlapped parts, and finding out the color mapping relation of article overlapping through linear regression;
step D: for the overlapped part of the X-ray images, obtaining outlines and classifications of contraband articles in the articles through an example segmentation algorithm in the step B, wherein each classification corresponds to a material, finding out the positions, which are not in the atomic number range of the material, in the outlines, obtaining high-energy information and low-energy information of the positions from the high-energy spectrum gray-scale image and the low-energy spectrum gray-scale image, and calculating the atomic number of the materials after correction through the high-energy information and the low-energy information;
step E: and obtaining whether the substance is a contraband or not through the corrected atomic number.
Further, in the step a, the X-ray machine is a dual-source X-ray machine.
Further, in step B, the example segmentation algorithm is a Mask R-CNN framework.
Further, in step D, the method for calculating the corrected atomic number of the substance through the high energy information and the low energy information includes:
suppose Hx,y,Lx,yThe high energy spectrogram is a value corresponding to a pixel position (x, y) of the low energy spectrogram;
(Rx,y，Gx,y，Bx,y) RGB values corresponding to the (x, y) position;
for each material, using a series of (x, y) position-corresponding (R) in the non-overlapping set S of points for such materialx,y,Gx,y,Bx,y,Hx,y,Lx,y) Regression of a set of parameters (a)R,aG,aB,bR,bG,bB,cR,cG,cB)；
The specific relationship is shown in the following formula:
Rx,y＝aRHx,y+bRLx,y+cR (1)；
Gx,y＝aGHx,y+bGLx,y+cG (2)；
Bx,y＝aBHx,y+bBLx,y+cB (3)；
(x,y)∈S；
for each material, a set of parameter estimates can be obtained by linear regression:
Figure BDA0002662128390000031
c, calculating the high energy information and the low energy information H obtained in the step Cx,y,Lx,yThe adjusted RGB values of the overlapped portion may be calculated and then taken into the formula (4) to obtain the corrected atomic number, instead of the formula (1), the formula (2), and the formula (3).
Compared with the prior art, the invention has the beneficial effects that: according to the intelligent security inspection method for effectively improving the contraband identification rate, the Mask R-CNN framework is used for carrying out example segmentation on the X-ray image, so that the X-ray image can be layered and the overlapped part can be restored, the robustness of a loss function is improved, the shape and color information of an individual object can be obtained, the influence of object overlapping on the identification rate is overcome, and the identification accuracy rate and stability are greatly improved.
Drawings
FIG. 1 is a schematic structural view of example 1 of the present invention;
fig. 2 is a flowchart of embodiment 2 of the present invention.
In the figure: 100. a transmission belt; 200. a dual source X-ray machine; 300. a security inspection machine; 400. a display screen.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
A security inspection device, as shown in FIG. 1, comprises a transmission belt 100, a dual-source X-ray machine 200, a security inspection machine 300 and a display screen 400; the conveyor belt 100 is used to transport objects; the dual-source X-ray machine 200 is arranged on the transmission belt 100 and used for extracting X-ray pictures of articles; the security check machine 300 is used for detecting and analyzing the X-ray picture extracted by the dual-source X-ray machine 200; the display screen 400 is used for displaying the detection result of the security inspection machine 300.
Example 2
As shown in fig. 2, an intelligent security inspection method for effectively improving the identification rate of contraband is used for detecting and identifying contraband on an X-ray image by a security inspection machine, and includes the following steps:
step A: shooting an X-ray image of an article by using an X-ray machine, and outputting a high-energy spectrum gray-scale image and a low-energy spectrum gray-scale image;
and B: analyzing the X-ray image by adopting an example segmentation algorithm to find out the non-overlapped part and the overlapped part of the X-ray image;
and C: selecting high-energy information and low-energy information of non-overlapped parts of articles made of different materials for the non-overlapped parts, and finding out the color mapping relation of article overlapping through linear regression;
step D: for the overlapped part of the X-ray images, obtaining outlines and classifications of contraband articles in the articles through an example segmentation algorithm in the step B, wherein each classification corresponds to a material, finding out the positions, which are not in the atomic number range of the material, in the outlines, obtaining high-energy information and low-energy information of the positions from the high-energy spectrum gray-scale image and the low-energy spectrum gray-scale image, and calculating the atomic number of the materials after correction through the high-energy information and the low-energy information;
step E: and obtaining whether the substance is a contraband or not through the corrected atomic number.
Specifically, in the step a, the X-ray machine is a dual-source X-ray machine.
It is worth noting that in step B, the example segmentation algorithm is a Mask R-CNN framework.
In the step D, the method for calculating the corrected atomic number of the substance through the high-energy information and the low-energy information comprises the following steps:
suppose Hx,y,Lx,yThe high energy spectrogram is a value corresponding to a pixel position (x, y) of the low energy spectrogram;
(Rx,y，Gx,y，Bx,y) RGB values corresponding to the (x, y) position;
for each material, using a series of (x, y) position-corresponding (R) in the non-overlapping set S of points for such materialx,y,Gx,y,Bx,y,Hx,y,Lx,y) Regression of a set of parameters (a)R,aG,aB,bR,bG,bB,cR,cG,cB)；
The specific relationship is shown in the following formula:
Rx,y＝aRHx,y+bRLx,y+cR (1)；
Gx,y＝aGHx,y+bGLx,y+cG (2)；
Bx,y＝aBHx,y+bBLx,y+cB (3)；
(x,y)∈S；
for each material, a set of parameter estimates can be obtained by linear regression:
Figure BDA0002662128390000051
c, calculating the high energy information and the low energy information H obtained in the step Cx,y,Lx,yThe adjusted RGB values of the overlapped portion may be calculated and then taken into the formula (4) to obtain the corrected atomic number, instead of the formula (1), the formula (2), and the formula (3).
When the intelligent security inspection method for effectively improving the identification rate of the contraband is used, the X-ray image is subjected to example segmentation through the MaskR-CNN frame, so that the X-ray image shot by the X-ray machine can be layered and the overlapped part can be restored, the atomic number of the shot object is corrected, the robustness of a loss function is improved, the shape and color information of an individual object can be obtained, the influence of object overlapping on the identification rate is overcome, and the identification accuracy and stability are greatly improved.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (4)

1. An intelligent security inspection method for effectively improving the identification rate of contraband is used for detecting and identifying the contraband on an X-ray image by a security inspection machine, and is characterized by comprising the following steps:
step A: shooting an X-ray image of an article by using an X-ray machine, and outputting a high-energy spectrum gray-scale image and a low-energy spectrum gray-scale image;
and B: analyzing the X-ray image by adopting an example segmentation algorithm to find out the non-overlapped part and the overlapped part of the X-ray image;
and C: selecting high-energy information and low-energy information of non-overlapped parts of articles made of different materials for the non-overlapped parts, and finding out the color mapping relation of article overlapping through linear regression;
step D: for the overlapped part of the X-ray images, obtaining outlines and classifications of contraband articles in the articles through an example segmentation algorithm in the step B, wherein each classification corresponds to a material, finding out the positions, which are not in the atomic number range of the material, in the outlines, obtaining high-energy information and low-energy information of the positions from the high-energy spectrum gray-scale image and the low-energy spectrum gray-scale image, and calculating the atomic number of the materials after correction through the high-energy information and the low-energy information;
step E: and obtaining whether the substance is a contraband or not through the corrected atomic number.
2. The intelligent security inspection method for effectively improving the identification rate of contraband according to claim 1, wherein: in the step A, the X-ray machine is a double-source X-ray machine.
3. The intelligent security inspection method for effectively improving the identification rate of contraband according to claim 1, wherein: in the step B, the example segmentation algorithm is a Mask R-CNN framework.
4. The intelligent security inspection method for effectively improving the identification rate of contraband according to claim 1, wherein: in the step D, the method for calculating the corrected atomic number of the substance through the high-energy information and the low-energy information comprises the following steps:
suppose Hx,y,Lx,yThe high energy spectrogram is a value corresponding to a pixel position (x, y) of the low energy spectrogram;
(Rx,y，Gx,y，Bx,y) RGB values corresponding to the (x, y) position;
for each material, using a series of (x, y) position-corresponding (R) in the non-overlapping set S of points for such materialx,y,Gx,y,Bx,y,Hx,y,Lx,y) Regression of a set of parameters (a)R,aG,aB,bR,bG,bB,cR,cG,cB)；
The specific relationship is shown in the following formula:
Rx,y＝aRHx,y+bRLx,y+cR (1)；
Gx,y＝aGHx,y+bGLx,y+cG (2)；
Bx,y＝aBHx,y+bBLx,y+cB (3)；
(x,y)∈S；
for each material, a set of parameter estimates can be obtained by linear regression:
Figure FDA0002662128380000021
c, calculating the high energy information and the low energy information H obtained in the step Cx,y,Lx,yThe adjusted RGB values of the overlapped portion may be calculated and then taken into the formula (4) to obtain the corrected atomic number, instead of the formula (1), the formula (2), and the formula (3).
CN202010907854.3A 2020-09-02 2020-09-02 Intelligent security inspection method for effectively improving contraband identification rate Active CN112162324B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010907854.3A CN112162324B (en) 2020-09-02 2020-09-02 Intelligent security inspection method for effectively improving contraband identification rate

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010907854.3A CN112162324B (en) 2020-09-02 2020-09-02 Intelligent security inspection method for effectively improving contraband identification rate

Publications (2)

Publication Number Publication Date
CN112162324A true CN112162324A (en) 2021-01-01
CN112162324B CN112162324B (en) 2024-08-02

Family

ID=73858652

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010907854.3A Active CN112162324B (en) 2020-09-02 2020-09-02 Intelligent security inspection method for effectively improving contraband identification rate

Country Status (1)

Country Link
CN (1) CN112162324B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113781426A (en) * 2021-09-07 2021-12-10 海深智能科技(上海)有限公司 Intelligent security inspection method for identifying liquid components
CN118247586A (en) * 2024-05-28 2024-06-25 杭州睿影科技有限公司 Material identification method and device, storage medium and electronic equipment

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1333899A (en) * 1999-01-12 2002-01-30 模拟技术公司 Apparatus and method for detecting concealed objects in computed tomography data
CN101387610A (en) * 2008-10-14 2009-03-18 重庆大学 Double source double energy straight-line type safety inspection CT apparatus and inspection method thereof
CN101592579A (en) * 2009-07-03 2009-12-02 公安部第一研究所 The method and the device that utilize multi-view X ray that explosive substances in luggage is surveyed automatically
EP2458408A2 (en) * 2010-11-01 2012-05-30 Beijing Zhongdun Anmin Analysis Technology Co., Ltd. Dual-energy X-ray body scanning device and image processing method
US20160084984A1 (en) * 2014-07-15 2016-03-24 Rapiscan Systems, Inc. Systems and Methods For The Automatic Detection of Lithium Batteries in Cargo, Baggage, Parcels, and Other Containers
CN105954808A (en) * 2016-05-04 2016-09-21 薛景森 Security check machine prohibited items automatic identification method
CN107209946A (en) * 2015-01-20 2017-09-26 皇家飞利浦有限公司 View data is split and shown
CN109902643A (en) * 2019-03-07 2019-06-18 浙江啄云智能科技有限公司 Intelligent safety inspection method, device, system and its electronic equipment based on deep learning
CN109975885A (en) * 2019-03-28 2019-07-05 上海中通吉网络技术有限公司 A kind of express delivery prohibited items recognition methods and safe examination system
CN109977877A (en) * 2019-03-28 2019-07-05 北京邮电大学 A kind of safety check is intelligent to be assisted sentencing drawing method, system and system control method
CN110018524A (en) * 2019-01-28 2019-07-16 同济大学 A kind of X-ray safety check contraband recognition methods of view-based access control model-attribute
CN110133739A (en) * 2019-04-04 2019-08-16 南京全设智能科技有限公司 A kind of X-ray rays safety detection apparatus and its drawing method is known automatically
CN110488368A (en) * 2019-07-26 2019-11-22 中控智慧科技股份有限公司 A kind of contraband recognition methods and device based on dual intensity X-ray screening machine
CN110543857A (en) * 2019-09-05 2019-12-06 安徽启新明智科技有限公司 Contraband identification method, device and system based on image analysis and storage medium
CN111161275A (en) * 2018-11-08 2020-05-15 腾讯科技（深圳）有限公司 Method and device for segmenting target object in medical image and electronic equipment

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1333899A (en) * 1999-01-12 2002-01-30 模拟技术公司 Apparatus and method for detecting concealed objects in computed tomography data
CN101387610A (en) * 2008-10-14 2009-03-18 重庆大学 Double source double energy straight-line type safety inspection CT apparatus and inspection method thereof
CN101592579A (en) * 2009-07-03 2009-12-02 公安部第一研究所 The method and the device that utilize multi-view X ray that explosive substances in luggage is surveyed automatically
EP2458408A2 (en) * 2010-11-01 2012-05-30 Beijing Zhongdun Anmin Analysis Technology Co., Ltd. Dual-energy X-ray body scanning device and image processing method
US20160084984A1 (en) * 2014-07-15 2016-03-24 Rapiscan Systems, Inc. Systems and Methods For The Automatic Detection of Lithium Batteries in Cargo, Baggage, Parcels, and Other Containers
CN107209946A (en) * 2015-01-20 2017-09-26 皇家飞利浦有限公司 View data is split and shown
CN105954808A (en) * 2016-05-04 2016-09-21 薛景森 Security check machine prohibited items automatic identification method
CN111161275A (en) * 2018-11-08 2020-05-15 腾讯科技（深圳）有限公司 Method and device for segmenting target object in medical image and electronic equipment
CN110018524A (en) * 2019-01-28 2019-07-16 同济大学 A kind of X-ray safety check contraband recognition methods of view-based access control model-attribute
CN109902643A (en) * 2019-03-07 2019-06-18 浙江啄云智能科技有限公司 Intelligent safety inspection method, device, system and its electronic equipment based on deep learning
CN109975885A (en) * 2019-03-28 2019-07-05 上海中通吉网络技术有限公司 A kind of express delivery prohibited items recognition methods and safe examination system
CN109977877A (en) * 2019-03-28 2019-07-05 北京邮电大学 A kind of safety check is intelligent to be assisted sentencing drawing method, system and system control method
CN110133739A (en) * 2019-04-04 2019-08-16 南京全设智能科技有限公司 A kind of X-ray rays safety detection apparatus and its drawing method is known automatically
CN110488368A (en) * 2019-07-26 2019-11-22 中控智慧科技股份有限公司 A kind of contraband recognition methods and device based on dual intensity X-ray screening machine
CN110543857A (en) * 2019-09-05 2019-12-06 安徽启新明智科技有限公司 Contraband identification method, device and system based on image analysis and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113781426A (en) * 2021-09-07 2021-12-10 海深智能科技(上海)有限公司 Intelligent security inspection method for identifying liquid components
CN113781426B (en) * 2021-09-07 2024-02-13 海深智能科技(上海)有限公司 Intelligent security inspection method for identifying liquid components
CN118247586A (en) * 2024-05-28 2024-06-25 杭州睿影科技有限公司 Material identification method and device, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN112162324B (en) 2024-08-02

Similar Documents

Publication Publication Date Title
CN104636707B (en) The method of automatic detection cigarette
CN110133739B (en) X-ray security check equipment and automatic image recognizing method thereof
CN109977877B (en) Intelligent auxiliary image judging method, system and system control method for security inspection
CN111612020B (en) Positioning method for abnormal object to be detected, security inspection analysis equipment and security inspection analysis system
WO2020173021A1 (en) Artificial intelligence-based forbidden object identification method, apparatus and device, and storage medium
CN104616275A (en) Defect detecting method and defect detecting device
CN106874845B (en) Image recognition method and device
CN112162324A (en) Intelligent security inspection method for effectively improving contraband identification rate
CN105069805B (en) Passive type Terahertz image partition method
CN113435543B (en) Visible light and X-ray image matching method and device based on conveyor belt identification
US20130100089A1 (en) Newton ring mura detection system
CN113960075A (en) Security check equipment, article size determination method, storage medium and equipment
CN111539251B (en) Security check article identification method and system based on deep learning
CN117911380A (en) X-ray security inspection detection method based on improved FCOS network
CN112069907A (en) X-ray machine image recognition method, device and system based on example segmentation
CN107545565B (en) Solar screen plate detection method
KR102030768B1 (en) Poultry weight measuring method using image, recording medium and device for performing the method
US20160283805A1 (en) Method and device for classifying an object in an image
CN118033768A (en) Method for detecting falling articles of carry-on luggage basket of passenger
CN105448095B (en) Method and apparatus are surveyed in a kind of yellow mark car test
CN103605973B (en) A kind of image character detection and identification method
CN113960687A (en) X-ray image processing device and X-ray image processing method
CN103942792A (en) Impurity detecting method in medicine detection robot based on time domain features of sequence images
CN114022415B (en) Liquid crystal display defect detection method based on single-pixel feature clustering cluster establishment
CN106934789A (en) Packaging dynamic testing method and device based on Three image difference

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant