CN115147939A - Data distribution management system and method in large-scale scene - Google Patents
Data distribution management system and method in large-scale scene Download PDFInfo
- Publication number
- CN115147939A CN115147939A CN202210794209.4A CN202210794209A CN115147939A CN 115147939 A CN115147939 A CN 115147939A CN 202210794209 A CN202210794209 A CN 202210794209A CN 115147939 A CN115147939 A CN 115147939A
- Authority
- CN
- China
- Prior art keywords
- information
- image
- matching
- data
- module
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/11—Hand-related biometrics; Hand pose recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Ophthalmology & Optometry (AREA)
- General Health & Medical Sciences (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a data distribution management system and a data distribution management method under a large-scale scene, which belong to the technical field of data distribution management systems and comprise a data acquisition module, a data analysis processing module, a characteristic comparison judgment module, a verification notification module and a database updating module, wherein the data acquisition module is used for acquiring data, the data analysis processing module is used for analyzing and processing the acquired data, the characteristic comparison judgment module is used for comparing and matching the data characteristics of the acquired information with the corresponding characteristic information in an original database, the verification notification module is used for notifying a worker of the comparison and matching result of the characteristic information in real time and carrying out field verification on the condition of information mismatch, the database updating module is used for storing new data to complete database updating, when the image information acquired in real time is abnormal in matching with a handheld object, the system can remind the worker of carrying out manual verification, and the database is updated after the verification is passed.
Description
Technical Field
The invention relates to the technical field of data distribution management systems, in particular to a data distribution management system and a data distribution management method in a large-scale scene.
Background
With the increase of economy and the development of society, people often organize large-scale activities to carry out entertainment, propaganda, study, health detection and the like, but some large-scale activities have some condition limitations on participators, and due to the fact that the number of the participators is large, the phenomenon that others take part in the activities by faking exists, and the rapid and effective identity detection of the participators is very important;
the existing data distribution management system mainly carries out identity verification and identification in a mode of scanning an identity card to obtain a two-dimensional code with identity information, so that the phenomenon that some people take the identity card or the two-dimensional code of other people for detection is caused, and some serious potential safety hazards exist;
therefore, a data distribution management system and method in a large-scale scene are needed to solve the above problems.
Disclosure of Invention
The present invention aims to provide a data distribution management system in a large-scale scene, so as to solve the problems in the background art.
In order to achieve the above purpose, the invention provides the following technical scheme: a data distribution management system under a large-scale scene comprises a data acquisition module, a data analysis processing module, a characteristic comparison judging module, a verification informing module and a database updating module;
the identity recognition can be accurately carried out in a large-scale scene;
the data acquisition module is used for transmitting the data acquired in the large-scale scene to the data analysis processing module;
the data analysis processing module is used for analyzing and processing the acquired data;
the characteristic comparison and judgment module is used for comparing and matching the characteristic information of the acquired information with the corresponding characteristic information in the original database;
the verification notification module is used for notifying the comparison and matching result of the characteristic information to a worker in real time and carrying out on-site verification on the unmatched condition;
the database updating module is used for storing the acquired data to an original database;
the output end of the data acquisition module is connected with the input end of the data analysis processing module; the output end of the data analysis processing module is connected with the input end of the characteristic comparison judging module; the output end of the characteristic comparison module is connected with the input end of the verification notification module, and the output end of the verification notification module is connected with the input end of the database updating module.
According to the technical scheme, the data acquisition module acquires data through image input equipment and image scanning equipment; the image input equipment and the image scanning equipment refer to scanning equipment with a camera, such as a mobile phone, and transmit the acquired data to the data analysis processing module.
According to the technical scheme, the data analysis processing module comprises an information extraction unit, a feature extraction unit and a data storage unit;
the information extraction unit is used for extracting useful personal information from the acquired data, wherein the personal information comprises name, gender, home address, identity card number, head portrait, telephone and two-dimensional code information, so that the personal identity information is more perfect, and the extracted personal information is transmitted to the data storage unit;
the characteristic extraction unit is used for extracting characteristics of the acquired data and transmitting the extracted characteristic information to the data storage unit;
the data storage unit is used for storing the extracted personal information and the extracted characteristic information;
the output end of the information extraction unit is connected with the input end of the characteristic extraction unit; the output end of the characteristic extraction unit is connected with the input end of the data storage unit.
According to the technical scheme, the feature comparison judging module comprises an information matching unit, a handheld object matching unit, a hand feature matching unit and an angle matching unit;
the information matching unit is used for matching the acquired personal information with the personal information in the original database; the original database refers to a database in which the acquired data is not stored in the database;
the handheld object matching unit is used for matching the handheld object information in the acquired picture with the corresponding handheld object information in the original database; the handheld object refers to an identity card and a mobile phone;
the hand feature matching unit is used for matching the collected pictures matching the hand characteristics with corresponding characteristic information in an original database; the corresponding characteristic information refers to characteristic information under the condition that the user information in the acquired image is matched with the personal information in the original database;
the angle matching unit is used for matching the angle of the hand-held object with the angle of the corresponding hand-held object in the original database; the angle of the hand-held object refers to the angle of the hand-held object in the collected image;
the feature comparison judging module carries out feature matching for four times, so that the judging result of the feature comparison judging module is more accurate and convincing;
the output end of the personal information matching unit is connected with the input ends of the handheld object matching unit, the hand characteristic matching unit and the angle matching unit.
According to the technical scheme, the verification notification module is used for notifying the staff of the result of the feature matching in real time and carrying out on-site verification on the mismatch condition, so that the staff can carry out processing before the first time.
According to the technical scheme, the database updating module is used for storing the collected correct information to the corresponding position of the original database to complete the updating of the database; the corresponding position of the original database refers to that the characteristic information in the collected image is stored in a storage unit matched with the personal information box in the collected image, wherein the personal user information in the collected image is stored in the original database.
A data distribution management method under a large-scale scene comprises the following steps:
s1, collecting image information by using an image input device and an image scanning device and transmitting the image information to a data analysis processing module in real time;
s2, extracting the personal information in the collected image by using an information extraction unit; carrying out feature extraction on the acquired picture information by using a feature extraction unit; storing the extracted personal information and the extracted characteristic information by using a data storage unit;
s3, matching the personal information in the original database by using the information matching unit, and matching the personal information with the corresponding characteristic information of the original database through the handheld object matching unit, the hand characteristic matching unit and the angle matching unit after the personal information is successfully matched;
s4, notifying in real time according to the personal information and the feature matching result in the S3, and prompting manual verification for the unmatched condition;
and S5, intelligently updating the database according to the result of passing verification in the S4.
9. According to the technical scheme, the personal information in the collected image is extracted in the step S2 and is divided into two types, one type is that the personal information in the two-dimensional code is automatically identified and read through the image input device and the image scanning device, the other type is that the image is preprocessed, the human face of the image is identified through a dlib library, eye feature points are found, the inclination angle of eyes is calculated, the image is rotated, a head image is extracted and is converted into a binary image, then the character information on the image is identified through a pytesseract library, and the personal information is extracted through a print function; the feature extraction comprises hand feature extraction, hand feature extraction and angle extraction; the characteristic extraction of the hand-held object the hand feature extraction is to extract by using a convolutional neural network; the binary image is a special gray image, namely the gray value of any pixel point is 0 or 255, and represents black and white respectively; the dlib library, the pytespect library, the print function and the convolutional neural network are known technologies, and are not specifically described herein; the pre-processed character image is picked out and sent to an identification module for identification, so that the aims of eliminating useless information in the image, retaining useful information and simplifying data to the maximum extent are fulfilled;
the angle extraction refers to identifying and extracting a handheld object in an acquired image, carrying out image acquisition on an image input device, a camera of an image scanning device and the extract in parallel, and processing an acquired image of the extract to obtain the processed imageStoring the standard picture in a standard object storage unit in a database, respectively endowing four vertexes with an ABCD sequence by taking the vertex at the upper left corner of the standard picture as a starting point according to a clockwise sequence, establishing a coordinate system by taking a point D as an origin, DC as the positive direction of an x axis and DA as the positive direction of a y axis, connecting the intersection point of AC and BD as a central point M, expressing the coordinates of the point M by (a and b), and expressing the coordinates of the point A by (x) A ，y A ) Expressed as C point coordinate (x) C ，y C ) Is shown with its center point
The central point M is used as a standard reference point, and the measured lengths of the DC and the DA are respectively L1 and L2;
marking the top point of the extract of the hand-held object in the collected image according to the corresponding position in the standard picture of the rectangular coordinate system, wherein A corresponds to E, B corresponds to F, C corresponds to G, D corresponds to H, the rectangular coordinate system is established by taking H as the origin, the horizontal direction is the x axis and the position vertical to the horizontal direction is the y axis, the lengths L1 and L2 of HE and HG are measured, L1 and L2 are compared with L1 and L2, if the lengths are not equal, the extracted image is amplified in the same proportion to cause L1= L1 and L2= L2, EG and FH are connected to take the intersection point as the central point Q, the coordinate of the Q point is expressed by (m, n), and the coordinate of the E point is expressed by (x, n) E ，y E ) The coordinates of the G point are expressed by (x) G ，y G ) Is shown with its center point
Putting the M and Q coordinates into the same rectangular coordinate system, wherein the origin is O, the & lt MOQ is the extracted inclination angle of the handheld object,
according to the technical scheme, the feature matching in the step S3 is region-based matching, the angle matching is used for comparing the angle information in the original database with the angle information extracted from the collected image, and the original database is provided with the angle information
Put into the set K = { theta = { [ theta ] 1 ,θ 2 ,……,θ n-1 And carrying out average calculation on the data in the K set to obtain an optimal angle delta, wherein the angle matching rate is as follows:
the above-mentioned
ε is the minimum maximum error in angle matching rate;
when the temperature is higher than the set temperature
Indicating that the angle matching is successful;
when other conditions occur, the angle matching is failed.
According to the technical scheme, the step S4 is used for carrying out real-time result notification on the matching result of the step S3, if the matching condition occurs, workers are reminded to carry out manual verification, and after the manual verification is passed, the step S5 is used for updating the database, and reminding can be carried out in a voice reminding mode, a pop-up window reminding mode and a warning lamp flashing mode.
Through the technical scheme, accurate and quick identity recognition can be carried out under a large-scale scene, other people can be identified effectively by faking, potential safety hazards are effectively reduced, and dangerous accidents are avoided.
Compared with the prior art, the invention has the following beneficial effects:
1. the information matching unit, the handheld object matching unit, the hand characteristic matching unit and the angle matching unit are arranged, and multiple kinds of characteristic information matching is carried out on the collected images, so that the matching result is more accurate, more convincing, more accurate in identity recognition, and capable of avoiding some major losses and potential safety hazards;
2. the verification notification module is arranged, so that the image feature matching result can be notified to field workers to take measures in time, meanwhile, the unmatched condition is reminded in time and verified in the field, and the occurrence of misjudgment can be avoided;
3. the database updating module is arranged to update the database in real time, so that the characteristic information in the database is richer and more detailed, and the characteristic matching is more accurate.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the module components of a data distribution management system in a large-scale scenario according to the present invention;
FIG. 2 is a schematic flow chart illustrating steps of a data distribution management method in a large-scale scenario according to the present invention;
fig. 3 is a schematic diagram of a connection structure of a data distribution management system in a large-scale scenario according to the present invention.
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 obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in fig. 1 to fig. 3, the present invention provides the following technical solutions, in a large-scale scene, a data distribution management system, which includes a data acquisition module, a data analysis processing module, a feature comparison and judgment module, a verification notification module, and a database update module;
identity recognition can be accurately carried out in a large-scale scene;
the data acquisition module is used for transmitting the data acquired in the large-scale scene to the data analysis processing module;
the data analysis processing module is used for analyzing and processing the acquired data;
the characteristic comparison and judgment module is used for comparing and matching the characteristic information of the acquired information with the corresponding characteristic information in the original database;
the verification notification module is used for notifying the comparison and matching result of the characteristic information to a worker in real time and carrying out on-site verification on the unmatched condition;
the database updating module is used for storing the acquired data into an original database;
the output end of the data acquisition module is connected with the input end of the data analysis processing module; the output end of the data analysis processing module is connected with the input end of the characteristic comparison judging module; the output end of the characteristic comparison module is connected with the input end of the verification notification module, and the output end of the verification notification module is connected with the input end of the database updating module.
The data acquisition module acquires data through image input equipment and image scanning equipment; the image input equipment and the image scanning equipment refer to scanning equipment with a camera, such as a mobile phone, and transmit the acquired data to the data analysis processing module.
The data analysis processing module comprises an information extraction unit, a feature extraction unit and a data storage unit;
the information extraction unit is used for extracting useful personal information from the acquired data, wherein the personal information comprises name, gender, home address, identity card number, head portrait, telephone and two-dimensional code information, so that the personal identity information is more perfect, and the extracted personal information is transmitted to the data storage unit;
the characteristic extraction unit is used for extracting characteristics of the acquired data and transmitting the extracted characteristic information to the data storage unit;
the data storage unit is used for storing the extracted personal information and the extracted characteristic information, for example, the acquired data is subjected to personal information extraction and characteristic information extraction, and the extracted characteristic information is stored in the personal information storage unit;
the output end of the information extraction unit is connected with the input end of the characteristic extraction unit; the output end of the feature extraction unit is connected with the input end of the data storage unit.
The characteristic comparison judging module comprises an information matching unit, a handheld object matching unit, a hand characteristic matching unit and an angle matching unit;
the information matching unit is used for matching the acquired personal information with the personal information in the original database; the original database refers to a database in which the acquired data is not stored in the database, for example, after the acquired image passes through feature comparison and is notified to a worker, the system automatically stores the data in a personal information storage unit which is in neutral matching with the original database;
the handheld object matching unit is used for matching the handheld object information in the acquired picture with the corresponding handheld object information in the original database; the handheld object refers to an identity card and a mobile phone, for example, in large-scale health detection activities, the mobile phone is simultaneously handheld to perform two-dimensional code scanning or identify the identity by handheld identity card;
the hand feature matching unit is used for matching the collected hand features of the pictures with corresponding feature information in an original database; the corresponding characteristic information refers to characteristic information under the condition that the user information in the acquired image is matched with the personal information in the original database;
the angle matching unit is used for matching the angle of the hand-held object with the angle of the corresponding hand-held object in the original database; the angle of the hand-held object refers to the angle of the hand-held object in the acquired image;
the feature comparison judging module carries out feature matching for four times, so that the judging result of the feature comparison judging module is more accurate and convincing;
and the output end of the personal information matching unit is connected with the input ends of the handheld object matching unit, the hand characteristic matching unit and the angle matching unit.
The verification notification module is used for notifying the staff of the result of the feature matching in real time and carrying out on-site verification on the mismatch condition so that the staff can carry out processing before the first time.
The database updating module is used for finishing the updating of the database by storing the collected correct information to the corresponding position of the original database; the corresponding position of the original database refers to that the characteristic information in the collected image is stored in a storage unit matched with the personal information box in the collected image, wherein the personal user information in the collected image is stored in the original database.
A data distribution management method under a large-scale scene comprises the following steps:
s1, acquiring image information by using an image input device and an image scanning device and transmitting the image information to a data analysis processing module in real time;
s2, extracting the personal information in the collected image by using an information extraction unit; performing feature extraction on the acquired picture information by using a feature extraction unit; storing the extracted personal information and the extracted characteristic information by using a data storage unit;
s3, matching the personal information in the original database by using the information matching unit, and matching the personal information with the corresponding characteristic information of the original database through the handheld object matching unit, the hand characteristic matching unit and the angle matching unit after the personal information is successfully matched;
s4, notifying in real time according to the personal information and the feature matching result in the S3, and prompting manual verification for the unmatched condition;
and S5, intelligently updating the database according to the result of passing verification in the S4.
The step S2 of extracting the personal information in the collected image is divided into two types, one is that the personal information in the two-dimensional code is automatically identified and read through an image input device and an image scanning device, the other is that the image is preprocessed, then the face of the image is identified through a dlib library, eye characteristic points are found, the inclination angle of the eye is calculated, the image is rotated, a head image is extracted, the image is converted into a binary image, then the character information on the image is identified through a pytesseract library, and the personal information is extracted through a print function; the feature extraction comprises hand feature extraction, hand feature extraction and angle extraction, wherein the hand feature extraction and the hand feature extraction are carried out by utilizing a convolutional neural network; the binary image is a special gray image, namely the gray value of any pixel point is 0 or 255, and represents black and white respectively; the dlib library, the pytesseract library, the print function and the convolutional neural network are known technologies, and are not specifically described herein; the pre-processed character image is picked out and sent to an identification module for identification, so that the aims of eliminating useless information in the image, retaining useful information and simplifying data to the maximum extent are fulfilled;
the angle extraction refers to identifying and extracting a handheld object in an acquired image, parallelly acquiring the image by using a camera of image input equipment and image scanning equipment and the extract, processing the acquired image of the extract, storing the processed image as a standard image in a standard object storage unit in a database, respectively endowing four vertexes as ABCD by using the vertex of the upper left corner of the standard image as a starting point according to a clockwise sequence, establishing a coordinate system by using a point D as an original point, DC as an x-axis positive direction and DA as a y-axis positive direction, connecting AC and BD intersection points as a central point M, expressing the coordinates of the M point as (a and b), and expressing the coordinates of the A point as (x) and (DA) as central points A ，y A ) Expressed as the C point coordinate of (x) C ，y C ) Is shown with its center point
The central point M is used as a standard reference point, and the measured lengths of the DC and the DA are respectively L1 and L2;
performing corresponding position vertex labeling on an extract of a handheld object in an acquired image according to a standard picture of a rectangular coordinate system, wherein A corresponds to E, B corresponds to F, C corresponds to G, and D corresponds to H, H is taken as an original point, the horizontal direction is taken as an x axis, the position vertical to the horizontal direction is taken as a y axis, the rectangular coordinate system is established, the lengths L1 and L2 of HE and HG are measured, L1 and L2 are compared with L1 and L2, if the lengths are not equal, the extracted image is amplified in the same proportion so that L1= L1 and L2=:2, EG and FH are connected to take an intersection point as a central point Q, the coordinates of the Q point are expressed by (m, n), and the coordinates of the E point are expressed by (x, n) E ，y E ) Indicating that the G point coordinate is (x) G ，y G ) It is shown that, its center point
Putting the M and Q coordinates into the same rectangular coordinate system, wherein the origin is O, the & lt MOQ is the extracted inclination angle of the handheld object,
the step S3, the characteristic matching is based on region matching, the angle matching is used for comparing the angle information in the original database with the angle information extracted from the collected image, and the angle information in the original database
Put into the set K = { theta = { [ theta ] 1 ,θ 2 ,……,θ n-1 And calculating the average of the data in the K set to obtain an optimal angle delta, wherein the angle matching rate is as follows:
the above-mentioned
ε is the minimum maximum error of the angle matching rate;
when in use
Indicating that the angle matching is successful;
when other conditions occur, the angle matching is failed.
And S4, carrying out real-time result notification on the matching result of S3, if the matching condition occurs, reminding workers to carry out manual verification, and after the manual verification is passed, carrying out database updating in the step S5, for example, reminding can be carried out in a voice reminding mode, a pop-up window reminding mode and a warning lamp flashing mode.
Can carry out accurate quick identification under extensive scene to can effectively distinguish other people masquerading, the effectual potential safety hazard that has reduced avoids dangerous accident to take place.
Example (b):
the data acquisition module acquires images of the identity card held by the person to be detected through a mobile phone in large-scale health detection and transmits the acquired data to the data analysis and processing module;
the data analysis processing module is used for preprocessing the acquired image through the feature extraction unit, recognizing a face on the identity card by using a dlib library, finding out eye feature points, calculating an inclination angle of the eye, rotating the picture, extracting a head image, converting the image into a binary image, recognizing character information on the image by using a pytesseract library, extracting name, gender, address, birth year and month and identity card number information on the identity card by using a print function, and extracting hand-held object features and hand features by using a convolutional neural network;
giving four vertexes as ABCD according to clockwise sequence decibels by taking the vertex at the upper left corner as a starting point for an acquired standard picture, establishing a coordinate system by taking a point D as an origin point, DC as an x-axis positive direction and DA as a y-axis positive direction, connecting an AC intersection point and a BD intersection point as a central point M, expressing the coordinates of the point M by (a and b), expressing the coordinates of the point A by (0 and 2), expressing the coordinates of the point C by (4 and 0), and expressing the coordinates of the central point by (4 and 0)
The center point M is used as a standard reference point, and the lengths of the DC and the DA are respectively measured to be L1=4 and L2=2;
marking the corresponding position vertexes of an extract in a handheld object in a collected image according to a standard picture of a rectangular coordinate system, wherein A corresponds to E, B corresponds to F, C corresponds to G, and D corresponds to H, the rectangular coordinate system is established by taking H as an origin, the horizontal direction is an x axis, and the position vertical to the horizontal direction is a y axis, measuring the lengths L1=1 and L2=2 of HE and HG, comparing L1 and L2 with L1 and L2, carrying out equal-scale amplification on the extracted image to ensure that L1= L1=2 and L2= L2=4, connecting EG and FH to obtain an intersection point as a central point Q, expressing the coordinate of the point Q as (m, n), and measuring the coordinate of the point E as
For G point coordinates
Is shown with its center point
Putting the M and Q coordinates into the same rectangular coordinate system, wherein the origin is O, the & lt MOQ is the extracted inclination angle of the handheld object,
the set K = { -13.331 °, -13.332 °, -13.333 ° } in the original database, and the data in the K set is averaged to obtain the optimal angle
The angle matching rate is as follows:
when in use
Indicating that the angle matching was successful.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A data distribution management system under a large-scale scene is characterized in that: the data distribution management system comprises a data acquisition module, a data analysis processing module, a characteristic comparison judging module, a verification notification module and a database updating module;
the data acquisition module is used for transmitting the data acquired in the large-scale scene to the data analysis processing module;
the data analysis processing module is used for analyzing and processing the acquired data;
the characteristic comparison and judgment module is used for comparing and matching the characteristic information of the acquired information with the corresponding characteristic information in the original database;
the verification informing module is used for informing the comparison and matching result of the characteristic information to the staff in real time and carrying out field verification on the unmatched condition;
the database updating module is used for storing the acquired data into an original database;
the output end of the data acquisition module is connected with the input end of the data analysis processing module; the output end of the data analysis processing module is connected with the input end of the characteristic comparison judging module; the output end of the characteristic comparison module is connected with the input end of the verification notification module, and the output end of the verification notification module is connected with the input end of the database updating module.
2. The data distribution management system in the large-scale scene according to claim 1, wherein: the data acquisition module acquires data through image input equipment and image scanning equipment.
3. The data distribution management system in the large-scale scene according to claim 2, wherein: the data analysis processing module comprises an information extraction unit, a feature extraction unit and a data storage unit;
the information extraction unit is used for extracting useful personal information from the acquired data, wherein the personal information comprises name, gender, home address, identity card number, head portrait, telephone and two-dimensional code information;
the feature extraction unit is used for extracting features of the acquired data;
the data storage unit is used for storing the extracted personal information and the extracted characteristic information;
the output end of the information extraction unit is connected with the input end of the characteristic extraction unit; the output end of the characteristic extraction unit is connected with the input end of the data storage unit.
4. The data distribution management system in the large-scale scene according to claim 3, wherein: the characteristic comparison judging module comprises an information matching unit, a handheld object matching unit, a hand characteristic matching unit and an angle matching unit;
the information matching unit is used for matching the acquired personal information with the personal information in the original database;
the handheld object matching unit is used for matching the handheld object information in the acquired picture with the corresponding handheld object information in the original database;
the hand characteristic matching unit is used for matching the collected hand characteristics of the picture with corresponding characteristic information in the original database;
the angle matching unit is used for matching the angle of the hand-held object with the angle of the corresponding hand-held object in the original database;
the output end of the personal information matching unit is connected with the input ends of the handheld object matching unit, the hand characteristic matching unit and the angle matching unit.
5. The data distribution management system in the large-scale scene according to claim 4, wherein: and the verification notification module is used for notifying the working personnel of the result of the feature matching in real time and carrying out on-site verification on the unmatched condition.
6. The data distribution management system in the large-scale scene according to claim 5, wherein: the database updating module is used for finishing the updating of the database by storing the acquired correct information to the corresponding position of the original database.
7. A data distribution management method under a large-scale scene comprises the following steps:
s1, acquiring image information by using an image input device and an image scanning device and transmitting the image information to a data analysis processing module in real time;
s2, extracting personal information in the acquired image by using an information extraction unit; performing feature extraction on the acquired picture information by using a feature extraction unit; storing the extracted personal information and the extracted characteristic information by using a data storage unit;
s3, matching the personal information in the original database by using the information matching unit, and matching the personal information with the corresponding characteristic information of the original database through the handheld object matching unit, the hand characteristic matching unit and the angle matching unit after the personal information is successfully matched;
s4, notifying in real time according to the personal information and the feature matching result in the S3, and prompting manual verification for the unmatched condition;
and S5, intelligently updating the database according to the verification passing result in the S4.
8. The data distribution management method in the large-scale scene according to claim 7, wherein: the personal information in the collected image is extracted in the step S2, wherein the personal information in the two-dimensional code is automatically identified and read through the image input device and the image scanning device, the personal information in the two-dimensional code is automatically identified and read through the image scanning device, the personal information in the two-dimensional code is automatically identified through the image preprocessing, the image is automatically identified through the dlib library, the eye feature point is found, the inclination angle of the eye is calculated, the image is rotated, the head image is extracted and is converted into a binary image, the character information on the image is identified through the pytesseract library, and the personal information is extracted through the print function; the feature extraction comprises hand feature extraction, hand feature extraction and angle extraction; the hand feature extraction and the hand feature extraction are carried out by utilizing a convolutional neural network;
the angle extraction refers to identifying and extracting a handheld object in an acquired image, carrying out image acquisition on the image input device and a camera of an image scanning device in parallel with the extract, processing the acquired image of the extract, storing the processed image as a standard image in a standard object storage unit in a database, respectively giving four vertexes as ABCD by taking the vertex at the upper left corner of the standard image as a starting point according to a clockwise sequence, establishing a coordinate system by taking a point D as an origin, DC as an x-axis positive direction and DA as a y-axis positive direction, connecting AC and BD intersection points as a central point M, expressing M point coordinates as (a and b), and expressing A point coordinates as (x, DC) and (DA) point coordinates as (x, B) A ，y A ) Expressed as C point coordinate (x) C ，y C ) Is shown with its center point
The central point M is used as a standard reference point, and the measured lengths of the DC and the DA are respectively L1 and L2;
marking the extractive of the hand-held object in the collected image according to the vertex of the corresponding position in a standard picture of a rectangular coordinate system, wherein A corresponds to E, B corresponds to F, C corresponds to G, and D corresponds to H, H is used as the origin, the horizontal direction is used as the x axis, the position vertical to the horizontal direction is used as the y axis to establish the rectangular coordinate system, the lengths L1 and L2 of HE and HG are measured, L1 and L2 are compared with L1 and L2, if the lengths are not equal, the extracted image is amplified in the same proportion to cause L1= L1 and L2= L2, EG and FH are connected to take the intersection point as a central point Q, the coordinate of the Q point is expressed by (m, n), and the coordinate of the E point is expressed by (x, n) E ，y E ) The coordinates of the G point are expressed by (x) G ，y G ) Is shown with its center point
Putting the M and Q coordinates into the same rectangular coordinate system, wherein the origin is O, the & lt MOQ is the extracted inclination angle of the handheld object,
。
9. the data distribution management method in the large-scale scene according to claim 7, wherein: the feature matching in the step S3 is region-based matching, and the angle matching is used for comparing the angle information in the original database with the angle information extracted from the collected image, wherein the angle information in the original database is
Put into the set K = { theta = { [ theta ] 1 ,θ 2 ,……,θ n-1 And carrying out average calculation on the data in the K set to obtain an optimal angle delta, wherein the angle matching rate is as follows:
when the temperature is higher than the set temperature
Indicating that the angle matching is successful;
when other conditions occur, the angle matching is failed.
10. The data distribution management method in the large-scale scene according to claim 7, wherein: and S4, carrying out real-time result notification on the matching result of the S3, reminding workers to carry out manual verification if a mismatching condition occurs, and updating the database in the step S5 after the manual verification is passed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210794209.4A CN115147939A (en) | 2022-07-05 | 2022-07-05 | Data distribution management system and method in large-scale scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210794209.4A CN115147939A (en) | 2022-07-05 | 2022-07-05 | Data distribution management system and method in large-scale scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115147939A true CN115147939A (en) | 2022-10-04 |
Family
ID=83412084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210794209.4A Pending CN115147939A (en) | 2022-07-05 | 2022-07-05 | Data distribution management system and method in large-scale scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115147939A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115391431A (en) * | 2022-10-28 | 2022-11-25 | 山东蓝客信息科技有限公司 | Specimen information acquisition and verification system |
| CN115788848A (en) * | 2022-11-18 | 2023-03-14 | 珠海安诚电子科技有限公司 | Water pump fault monitoring system and method based on big data |
| CN116685033A (en) * | 2023-06-21 | 2023-09-01 | 惠州兴通成机电技术有限公司 | Intelligent control system for lamp |
-
2022
- 2022-07-05 CN CN202210794209.4A patent/CN115147939A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115391431A (en) * | 2022-10-28 | 2022-11-25 | 山东蓝客信息科技有限公司 | Specimen information acquisition and verification system |
| CN115391431B (en) * | 2022-10-28 | 2023-01-24 | 山东蓝客信息科技有限公司 | Specimen information acquisition and verification system |
| CN115788848A (en) * | 2022-11-18 | 2023-03-14 | 珠海安诚电子科技有限公司 | Water pump fault monitoring system and method based on big data |
| CN116685033A (en) * | 2023-06-21 | 2023-09-01 | 惠州兴通成机电技术有限公司 | Intelligent control system for lamp |
| CN116685033B (en) * | 2023-06-21 | 2024-01-12 | 惠州兴通成机电技术有限公司 | Intelligent control system for lamp |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115147939A (en) | Data distribution management system and method in large-scale scene | |
| CN102799850B (en) | A kind of barcode recognition method and device | |
| US9582728B2 (en) | System for determining alignment of a user-marked document and method thereof | |
| CN109409355B (en) | Novel transformer nameplate identification method and device | |
| CN109376604B (en) | Age identification method and device based on human body posture | |
| CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
| CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
| CN111639629B (en) | Pig weight measurement method and device based on image processing and storage medium | |
| CN112436477A (en) | Instrument is checked fast to relay protection device definite value of transformer substation | |
| CN107944344A (en) | Power supply enterprise's construction mobile security supervision platform | |
| CN114463567B (en) | Block chain-based intelligent education operation big data plagiarism prevention method and system | |
| CN110291527B (en) | Information processing method, system, cloud processing device and computer program product | |
| CN112365618A (en) | Attendance system and method based on face recognition and two-dimensional code temperature measurement | |
| CN111753608A (en) | Information processing method and device, electronic device and storage medium | |
| CN110991434B (en) | Self-service terminal certificate identification method and device | |
| CN115660627A (en) | Registration training method for attendance checking of personnel | |
| CN113592839A (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
| CN108960850A (en) | Method for anti-counterfeit and device, anti-fake traceability system | |
| CN114596618A (en) | Face recognition training method and device for mask wearing, electronic equipment and storage medium | |
| CN113111780B (en) | Regional alarm supervision system and method based on block chain | |
| CN108537990B (en) | All-in-one machine fraud judgment method, device, equipment and computer readable storage medium | |
| CN111079617B (en) | Poultry identification method and device, readable storage medium and electronic equipment | |
| JP3505713B2 (en) | Curve identification system | |
| CN113569594A (en) | Method and device for labeling key points of human face | |
| KR20200109977A (en) | Smartphone-based identity verification method using fingerprints and facial images |
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 |