CN113971443A - Image processing method, device and system for intelligent image judgment - Google Patents
Image processing method, device and system for intelligent image judgment Download PDFInfo
- Publication number
- CN113971443A CN113971443A CN202111274432.8A CN202111274432A CN113971443A CN 113971443 A CN113971443 A CN 113971443A CN 202111274432 A CN202111274432 A CN 202111274432A CN 113971443 A CN113971443 A CN 113971443A
- Authority
- CN
- China
- Prior art keywords
- image
- current
- intelligent
- ray imaging
- package
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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
Abstract
The invention discloses an image processing method for intelligently judging a picture, which comprises the following steps of: s1: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture; s2: pushing the current image data to an intelligent image recognizer; s3: the intelligent image recognizer determines a pushing mode according to the image complexity level of the current X-ray imaging image. According to the invention, the package pictures are subjected to complexity level classification processing, different pushing modes are selected according to the complexity levels of the pictures, the differentiation algorithm processing is carried out on the package pictures, the pictures with the image complexity level of 'simple package' are identified by an intelligent image recognizer, the pictures with the image complexity level of 'responsible package' are pushed to a centralized image judging system for judgment, and meanwhile, the simple package is subjected to spot inspection, so that the workload of image judging personnel is reduced, and the accuracy of intelligent image judging is improved.
Description
Technical Field
The invention relates to the technical field of centralized judgment of subway security inspection, in particular to an image processing method, device and system for intelligent judgment.
Background
The centralized image judging service mainly comprises a security inspection intelligent analyzer, a centralized image judging system, an image judging workstation, a monitoring terminal system and a security inspection supervision platform, and can realize the functions of automatic identification of contraband by a parcel image, uploading of the parcel image, remote image judgment by an image judging person, informatization and intelligent closed loop of object inspection disposal by the monitoring terminal and the like.
At present, an intelligent analyzer (edge calculation unit) analyzes all security check packages through the same algorithm model, the universality of the same algorithm in a subway scene is insufficient, and the omission factor and the false detection rate are insufficient to meet the subway requirements. In addition, the capabilities of manufacturers are different, the algorithm precision difference is obvious, the recognition of different articles has various characteristics, the practical problem is brought to the standard unification of intelligent image recognition, the workload of intelligent image recognition is not substantially reduced, and the practical difficulty is faced in the landing practice.
Meanwhile, the current intelligent graph recognition algorithm carries out recognition through the same model, the recognition problem of various scenes needs to be considered, the algorithm effect and efficiency are measured under the same scale, and the improvement of the algorithm speed, the false detection rate, the missing detection rate and the like is difficult. The intelligent graph recognition classifies the alarm of the analyzed result, the high-risk type directly pushes a package opening table to open the package, and the middle-low alarm type is manually rechecked by a background centralized graph recognition person. Due to the packet opening table alarm push information error and high-risk article missing detection caused by false detection and missing detection, the product has insufficient confidence in the actual scene, and the effect of reducing people and trouble is not achieved.
Disclosure of Invention
The present invention is directed to an image processing method, an image processing device and an image processing system for intelligently judging a picture, so as to solve the problems in the background art.
In order to solve the technical problem, the invention adopts the following scheme:
an image processing method for intelligent image judgment comprises the following steps:
s1: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
s2: and pushing the current image data to an intelligent image recognizer.
Further, the method also comprises the following steps:
s3: the intelligent image recognizer determines a pushing mode according to the image complexity level of the current image data;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', generating alarm data when the intelligent image identifier identifies that the current X-ray imaging image has contraband, and pushing the alarm data to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system; when the current X-ray imaging image is judged to have contraband by the centralized image judging system, alarm data is generated and pushed to the unpacking terminal.
Further, when S3 is executed, when the image complexity level of the current image data recognized by the intelligent image recognizer is "simple package", the item recognition confidence of the current X-ray imaging image is set, and if the level is greater than or equal to the confidence threshold, alarm data is generated and pushed to the package opening terminal.
Further, if the item identification confidence of the current X-ray imaging image with the image complexity level of 'simple package' is smaller than the confidence threshold, an adjustable sampling inspection range is set, and the current X-ray imaging image with the image complexity level of 'simple package' in the sampling inspection range is dynamically sampled and inspected by the centralized image judging system.
Further, the number of the dynamic spot checks can be adjusted according to the amount of the judgment graph load.
Further, the method also comprises the following steps: s0: obtaining a current X-ray imaging map of a security check package
The invention also provides an image processing device for intelligently judging the image, which comprises:
an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
an output module: and pushing the current image data to an intelligent image recognizer.
The invention also provides an image processing system for intelligently judging the image, which comprises: the system comprises an X-ray machine, an image processing device, an intelligent graph recognizer, a centralized graph judging system and a package opening terminal; .
An X-ray machine: acquiring a current X-ray imaging picture of the security check package;
an image processing apparatus: the image processing apparatus includes: an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture; an output module: pushing the current image data to an intelligent image recognizer;
intelligent graph recognizing instrument: the intelligent image recognizer determines a pushing mode according to the image complexity level of the current image data;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', generating alarm data when the intelligent image identifier identifies that the current X-ray imaging image has contraband, and pushing the alarm data to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system;
centralized graph judging system: the system is used for judging whether the X-ray imaging graph has contraband or not, generating alarm data when the X-ray imaging graph contains the contraband, finding a package opening terminal corresponding to a security inspection point through a centralized graph judging system, pushing the alarm data to the package opening terminal, and performing dynamic selective inspection on the current X-ray imaging graph with the image complexity level of 'simple package' in the selective inspection range;
opening a package terminal: and receiving alarm data sent by the centralized graph judging system and displaying the alarm data to a package opening terminal interface.
Further, still include: the system comprises a passenger flow prediction system, an intelligent scheduling system and a judgment graph detection system;
passenger flow prediction system: passenger flow data of the security check door is used as a data source to predict the passenger flow;
intelligent shift scheduling system: configuring the number of the judging members of the centralized judging group;
judging the picture detecting system: and monitoring the on Shift situation of the pattern judging person and the pattern judging load quantity in real time.
The invention has the following beneficial effects:
1. according to the invention, the package pictures are subjected to complexity level classification processing, different pushing modes are selected according to the complexity levels of the pictures, the differentiation algorithm processing is carried out on the package pictures, the pictures with the image complexity level of 'simple package' are identified by an intelligent image recognizer, the pictures with the image complexity level of 'responsible package' are pushed to a centralized image judging system for judgment, and meanwhile, the simple package is subjected to spot inspection, so that the workload of image judging personnel is reduced, and the accuracy of intelligent image judging is improved.
Drawings
FIG. 1 is a prior art work flow diagram;
FIG. 2 is a flow chart of the operation of the present invention;
FIG. 3 is a flowchart of the operation of embodiment 1 of the present invention;
FIG. 4 is a flowchart of the operation of embodiment 1 of the present invention;
fig. 5 is a flowchart of the operation of embodiment 2 of the present invention.
Detailed Description
In order to make the technical solutions, technical problems to be solved, and technical effects of the present invention more clearly apparent, the technical solutions of the present invention are described below in detail with reference to specific embodiments. All embodiments that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention are within the protection scope of the present invention.
The present invention is described in detail below with reference to the accompanying drawings and specific embodiments, wherein a centralized interpretation workflow of the prior art is shown in fig. 1, after an intelligent image recognizer acquires an X-ray imaging picture, the X-ray imaging picture is recognized and contraband marking is performed, the marked X-ray imaging picture is pushed to a centralized interpretation system, a diagraph performs interpretation, when the diagraph interprets that there is contraband, alarm data is generated and pushed to a package opening terminal, the package opening terminal performs alarm prompting and package opening inspection, and when no contraband is recognized, a package is normally passed. In the invention, before the packaged X-ray imaging picture enters the intelligent image recognizer, the complexity level of the image is determined, the image judging process is divided, the picture containing the simple package is accurately recognized by adopting the existing algorithm, and the picture containing the complex package is directly pushed to a centralized image judging system to perform centralized image judging or a more accurate algorithm model is performed on the centralized image judging system to perform secondary intelligent judgment assistance.
The principle of image complexity level classification is as follows: the intelligent image recognition method aims at high-risk articles (without serious shielding), and the algorithm precision basically meets the requirements of the subway industry. But aiming at the packages with serious shielding, even high-risk products, false detection or missing detection also often occurs, and the safety requirement of the subway industry cannot be met. Based on the data, the invention provides differential algorithm processing and intelligent map recognition differential algorithm processing on the packages, the packages are firstly divided into simple packages and complex packages in an AI mode, and based on the principle of relation between attenuation coefficient and atomic number of X-rays in substances (author: Zhang 32704), the conventional articles are more finely distinguished in security inspection, the simple packages are defined as the packages with single arrangement and combination, low coverage rate and less metal occupation ratio, and the situations are totally attributed to the complex packages in addition.
The specific scheme is that the image processing method for intelligently judging the image comprises the following steps:
s0: acquiring a current X-ray imaging picture of the security check package;
s1: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
s2: and pushing the current image data to an intelligent image recognizer.
S3: the intelligent image recognizer recognizes the image complexity level of the current image data, and the image complexity level is divided into 'simple package' and 'complex package';
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', the intelligent image identifier identifies that the current X-ray imaging image has contraband, and alarm data is pushed to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system; the current X-ray imaging image is judged to have contraband by the centralized image judging system, and alarm data is pushed to the unpacking terminal.
And when S3 is executed, when the complexity level of the image identified by the intelligent image identifier is 'simple package', the item identification confidence of the current X-ray imaging image is set, and if the complexity level is greater than or equal to the confidence threshold, the alarm data is pushed to the package opening terminal. If the object recognition confidence coefficient of the current X-ray imaging picture with the image complexity level of 'simple package' is smaller than the confidence coefficient threshold value, an adjustable sampling inspection range is set, and the current X-ray imaging picture with the image complexity level of 'simple package' in the sampling inspection range is dynamically sampled and inspected by the centralized image judging system. The number of the dynamic spot checks can be adjusted according to the amount of the judging graph load.
The invention also provides an image processing device for intelligently judging the image, which comprises:
an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
an output module: and pushing the current image data to an intelligent image recognizer.
The invention also provides an image processing system for intelligently judging the image, which comprises: the system comprises an X-ray machine, an image processing device, an intelligent graph recognizer, a centralized graph judging system and a package opening terminal;
an X-ray machine: acquiring a current X-ray imaging picture of the security check package;
an image processing apparatus: the image processing apparatus includes: an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture; an output module: pushing the current image data to an intelligent image recognizer;
intelligent graph recognizing instrument: the intelligent image recognizer recognizes the image complexity level of the current X-ray imaging image, wherein the image complexity level is divided into 'simple package' and 'complex package';
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', the intelligent image identifier identifies that the current X-ray imaging image has contraband, and alarm data is pushed to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system;
centralized graph judging system: the system is used for judging whether the X-ray imaging graph has contraband or not, finding out that the X-ray imaging graph contains the contraband through a centralized graph judging system, finding out a package opening terminal corresponding to a security inspection point through the centralized graph judging system, pushing alarm data to the package opening terminal, and performing dynamic selective inspection on the current X-ray imaging graph with the image complexity level of 'simple package' in the selective inspection range;
opening a package terminal: and receiving alarm data sent by the centralized graph judging system and displaying the alarm data to a package opening terminal interface.
Example 1:
after the package passes through the X-ray machine, the X-ray machine outputs a current X-ray imaging picture of the package, the image processing device intelligently classifies the current X-ray imaging picture, the picture processing device pushes current image data comprising the current X-ray imaging picture and the image complexity level to an intelligent image recognizer, and the intelligent image recognizer selects a pushing mode according to the image complexity level of the current image data;
as shown in fig. 3, when the image complexity level identified by the intelligent image identifier is "simple package", identifying whether contraband exists through the existing algorithm, generating alarm data when the contraband exists, directly pushing the alarm data of the current image data to a package opening terminal, carrying out alarm prompt and package opening check by the package opening terminal, and when the contraband is not identified, normally passing the package;
as shown in fig. 4, when the image complexity level identified by the intelligent image identifier is "complex package", contraband marking is performed on the current X-ray imaging image, the marked current X-ray imaging image is pushed to the centralized image judging system, the current X-ray imaging image is judged by the centralized image judging system to have contraband, alarm data is pushed to the unpacking terminal to give an alarm prompt and unpacking inspection, and when the centralized image judging system judges that no contraband exists, the package normally passes.
Example 2:
as shown in fig. 5, after the parcel passes through the X-ray machine, the X-ray machine outputs the current X-ray imaging graph of the parcel, the image processing device intelligently classifies the current X-ray imaging graph, the image processing device pushes the current image data including the current X-ray imaging graph and the image complexity level to the intelligent graph recognizer, the intelligent graph recognizer recognizes the current image data, when the image complexity level recognized by the intelligent graph recognizer is 'simple parcel', the article recognition confidence level of the X-ray imaging graph can be preset, and if the image complexity level is greater than or equal to the confidence level threshold value, the alarm data is pushed to the unpacking terminal. If the item identification confidence of the current X-ray imaging map with the image complexity level of "simple package" is less than the confidence threshold, an adjustable spot check range is set, taking data as an example, under the condition that the complexity level of the image is 'simple package', the identification confidence coefficient of the object is set to 98 percent, the object is regarded as a confident object when the identification confidence coefficient exceeds 98 percent, the alarm data is pushed to a package opening terminal for package opening inspection, and an adjustable sampling inspection range is set, such as 97 to 98 percent, the 'simple package' image data in the range is subjected to spot check or full check through a centralized image judging system, when detecting that the contraband exists, generating alarm data and pushing the alarm data to the unpacking terminal, wherein the quantity of the spot checks can be dynamically adjusted according to the centralized judgment chart package distribution statistics, the method comprises the steps of judging the loading capacity of a graph, adjusting the loading capacity of the graph, and dynamically sampling and checking 'simple package' image data in real time according to the loading capacity of the graph.
As shown in fig. 2, the intelligent image recognizer in the figure is the same device, and the image processing system for intelligently judging the image further includes: passenger flow prediction system, intelligent scheduling system and judge picture detecting system.
The passenger flow prediction system is used for predicting passenger flow by taking passenger flow data of a security check door as a data source; the intelligent scheduling system is used for scientifically configuring the number of the panel judging members of the centralized panel judging group; the image judging detection system is used for monitoring the on Shift situation and the image judging load quantity of the image judging person in real time.
The principle and embodiments of the present invention are described in detail by using specific examples, which are only used to help understanding the core technical content of the present invention, and are not used to limit the protection scope of the present invention, and the technical solution of the present invention is not limited to the specific embodiments described above. Based on the above embodiments of the present invention, those skilled in the art should make any improvements and modifications to the present invention without departing from the principle of the present invention, and therefore, the present invention should fall into the protection scope of the present invention.
Claims (9)
1. An image processing method for intelligently judging a picture is characterized by comprising the following steps of:
s1: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
s2: and pushing the current image data to an intelligent image recognizer.
2. The image processing method of intelligent interpretation according to claim 1, further comprising the steps of:
s3: the intelligent image recognizer determines a pushing mode according to the image complexity level of the current image data;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', generating alarm data when the intelligent image identifier identifies that the current X-ray imaging image has contraband, and pushing the alarm data to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system; when the current X-ray imaging image is judged to have contraband by the centralized image judging system, alarm data is generated and pushed to the unpacking terminal.
3. The image processing method of an intelligent image judgment according to claim 2, wherein when S3 is executed, when the image complexity level of the current image data recognized by the intelligent image recognition instrument is "simple package", the item recognition confidence level of the current X-ray imaging image is set, and if the level is greater than or equal to the confidence level threshold, the alarm data is pushed to the package opening terminal.
4. The image processing method according to claim 3, wherein if the item recognition confidence of the current X-ray imaging image with the image complexity level of "simple package" is less than the confidence threshold, an adjustable sampling range is set, and the current X-ray imaging image with the image complexity level of "simple package" within the sampling range is dynamically sampled by the centralized image processing system.
5. The image processing method of an intelligent judging map according to claim 4, wherein the number of the dynamic spot checks can be adjusted according to the judging map load amount.
6. The image processing method of intelligent interpretation according to claim 1, further comprising the steps of: s0: and acquiring a current X-ray imaging picture of the security check package.
7. An image processing apparatus that intelligently judges a picture, the image processing apparatus comprising:
an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture;
an output module: and pushing the current image data to an intelligent image recognizer.
8. An image processing system for intelligently judging a picture, comprising: the system comprises an X-ray machine, an image processing device, an intelligent graph recognizer, a centralized graph judging system and a package opening terminal;
an X-ray machine: acquiring a current X-ray imaging picture of the security check package;
an image processing apparatus: the image processing apparatus includes: an acquisition module: acquiring current image data, wherein the current image data comprises a current X-ray imaging picture and an image complexity level corresponding to the current X-ray imaging picture; an output module: pushing the current image data to an intelligent image recognizer;
intelligent graph recognizing instrument: the intelligent image recognizer determines a pushing mode according to the image complexity level of the current image data;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'simple package', generating alarm data when the intelligent image identifier identifies that the current X-ray imaging image has contraband, and pushing the alarm data to a package opening terminal;
when the complexity level of the image of the current image data identified by the intelligent image identifier is 'complex package', marking contraband on the current X-ray imaging image, and pushing the marked current X-ray imaging image to a centralized image judging system;
centralized graph judging system: the system is used for judging whether the X-ray imaging graph has contraband or not, generating alarm data when the X-ray imaging graph contains the contraband, finding a package opening terminal corresponding to a security inspection point through a centralized graph judging system, pushing the alarm data to the package opening terminal, and performing dynamic selective inspection on the current X-ray imaging graph with the image complexity level of 'simple package' in the selective inspection range;
opening a package terminal: and receiving alarm data sent by the centralized graph judging system and displaying the alarm data to a package opening terminal interface.
9. The system for improving the accuracy of intelligent graph interpretation according to claim 8, further comprising: the system comprises a passenger flow prediction system, an intelligent scheduling system and a judgment graph detection system;
passenger flow prediction system: passenger flow data of the security check door is used as a data source to predict the passenger flow;
intelligent shift scheduling system: configuring the number of the judging members of the centralized judging group;
judging the picture detecting system: and monitoring the on Shift situation of the pattern judging person and the pattern judging load quantity in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111274432.8A CN113971443A (en) | 2021-10-29 | 2021-10-29 | Image processing method, device and system for intelligent image judgment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111274432.8A CN113971443A (en) | 2021-10-29 | 2021-10-29 | Image processing method, device and system for intelligent image judgment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113971443A true CN113971443A (en) | 2022-01-25 |
Family
ID=79589031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111274432.8A Pending CN113971443A (en) | 2021-10-29 | 2021-10-29 | Image processing method, device and system for intelligent image judgment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113971443A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115567586A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Centralized intelligent pushing method and device for separating intelligent image recognition result from original image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651841A (en) * | 2016-12-02 | 2017-05-10 | 北京航星机器制造有限公司 | Analysis method for security inspection of image complexity |
| CN108303747A (en) * | 2017-01-12 | 2018-07-20 | 清华大学 | The method for checking equipment and detecting gun |
| WO2019096181A1 (en) * | 2017-11-14 | 2019-05-23 | 深圳码隆科技有限公司 | Detection method, apparatus and system for security inspection, and electronic device |
| CN109975332A (en) * | 2019-02-25 | 2019-07-05 | 北京声迅电子股份有限公司 | A kind of intelligent quality testing system applied to X-ray machine |
-
2021
- 2021-10-29 CN CN202111274432.8A patent/CN113971443A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651841A (en) * | 2016-12-02 | 2017-05-10 | 北京航星机器制造有限公司 | Analysis method for security inspection of image complexity |
| CN108303747A (en) * | 2017-01-12 | 2018-07-20 | 清华大学 | The method for checking equipment and detecting gun |
| WO2019096181A1 (en) * | 2017-11-14 | 2019-05-23 | 深圳码隆科技有限公司 | Detection method, apparatus and system for security inspection, and electronic device |
| CN109975332A (en) * | 2019-02-25 | 2019-07-05 | 北京声迅电子股份有限公司 | A kind of intelligent quality testing system applied to X-ray machine |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115567586A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Centralized intelligent pushing method and device for separating intelligent image recognition result from original image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110018524B (en) | X-ray security inspection contraband identification method based on vision-attribute | |
| EP1866230B1 (en) | Elevator system | |
| US20210156781A1 (en) | Real-time online monitoring and source apportionment method for atmospheric fine particles containing heavy metals | |
| AU2018216105B2 (en) | Quality control method, quality control system, management apparatus, analyzer, and quality control abnormality determination method | |
| CN112115897B (en) | Multi-pointer instrument alarm detection method, device, computer equipment and storage medium | |
| CN103728429A (en) | Water quality online monitoring method and monitoring system | |
| CN113093308B (en) | Correction method, device, equipment and storage medium for X-ray baggage inspection equipment | |
| CN108298393A (en) | Method based on the wrong report of depth network filtering elevator malfunction | |
| CN113971443A (en) | Image processing method, device and system for intelligent image judgment | |
| EP3376198A1 (en) | Vehicle-mounted exhaust gas analyzer, exhaust gas analysis system, information processing device, program for exhaust gas analysis system, and exhaust gas analysis method | |
| CN113724226A (en) | Centralized image judging system for subway security check and image processing device and method | |
| CN111337989A (en) | Active double-visual-angle screening method and device for multistage security inspection instrument | |
| US20170228602A1 (en) | Method for detecting height | |
| CN114397712A (en) | Differentiated security check method and system for urban rail transit | |
| CN113960075A (en) | Security check equipment, article size determination method, storage medium and equipment | |
| CN108169248B (en) | Self-adaptive S parameter matching method for detecting liquid dangerous goods | |
| CN112446320B (en) | Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method | |
| CN113362302B (en) | Fault detection method of subway train electric box cover based on image recognition | |
| CN116069092A (en) | Intelligent warehouse safety management method and system | |
| CN111985326B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN114167870A (en) | Data processing method, system, device and storage medium for gas inspection device | |
| CN114137635A (en) | Method, device and equipment for testing detection efficiency of security check machine and storage medium | |
| CN111798237A (en) | Abnormal transaction diagnosis method and system based on application log | |
| CN110458228A (en) | A kind of hazardous material detection method of information source number time-varying and self-adaptive blind source separation | |
| CN115147964B (en) | Multi-element information security inspection method, system, computer equipment and readable medium |
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 |