CN111818269A - Identification method and identification system of vehicle-mounted certificate - Google Patents
Identification method and identification system of vehicle-mounted certificate Download PDFInfo
- Publication number
- CN111818269A CN111818269A CN202010832100.6A CN202010832100A CN111818269A CN 111818269 A CN111818269 A CN 111818269A CN 202010832100 A CN202010832100 A CN 202010832100A CN 111818269 A CN111818269 A CN 111818269A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- certificate
- data
- identification
- onboard
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/56—Cameras or camera modules comprising electronic image sensors; Control thereof provided with illuminating means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a vehicle-mounted certificate identification method and system, wherein the vehicle-mounted certificate identification system comprises a machine body, a plurality of detection windows, a plurality of cameras, a processor and a storage, wherein the detection windows are arranged at the top of the machine body; the camera is arranged in the machine body and corresponds to the detection windows one by one, and the camera collects images of the vehicle-mounted certificates on the detection windows; the processor extracts vehicle-mounted data from the image of the vehicle-mounted certificate and identifies and compares the vehicle-mounted data with the image of the vehicle-mounted certificate; the memory is used for storing the identification data and the comparison result. The identification system of the vehicle-mounted certificate can simultaneously detect all contents in a plurality of vehicle-mounted certificates, improves the detection efficiency and has high detection accuracy.
Description
Technical Field
The invention relates to the technical field of vehicle-mounted certificate identification, in particular to a vehicle-mounted certificate identification method and system.
Background
The vehicle-mounted certificate is an important identity and product certificate of the automobile and is the only certificate for leaving a factory. The vehicle-mounted certificate comprises four files, namely a vehicle certificate of pass, a COC consistency certificate, an energy consumption identifier and an environmental protection information list, and whether the content of the file is correct or not is judged by adopting a manual sampling inspection mode at present. Because the production capacity requirement only allows personnel to have short detection time, but many of the four kinds of file information can not be detected within the specified time, only a sampling detection method can be adopted, and therefore, the method has many defects, such as incapability of realizing full content detection, easiness in detection error and low detection efficiency.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an identification method and an identification system of an on-vehicle certificate.
One embodiment of the invention provides a method for identifying an onboard certificate, which comprises the following steps:
receiving images of a plurality of onboard certificates; the image of the vehicle-mounted certificate is acquired by the cameras on the vehicle-mounted certificates on the detection windows respectively;
respectively detecting the outer frame of the image of each vehicle-mounted certificate, and correspondingly extracting the content in the outer frame as vehicle-mounted data;
carrying out image preprocessing on the vehicle-mounted data;
adopting deep learning CNN to identify the content of the background complex area of the vehicle-mounted data; recognizing the content of a single background area of the vehicle-mounted data by adopting OCR (optical character recognition);
and collecting and comparing the identification data, and sending a result obtained by comparison to the display equipment.
Compared with the prior art, the identification method of the vehicle-mounted certificate can simultaneously detect all contents in a plurality of vehicle-mounted certificates, improves the detection efficiency and has high detection accuracy.
Furthermore, after the content in the outer frame is extracted to be used as vehicle-mounted data, the position of the title of the vehicle-mounted data is detected, and the position of the vehicle-mounted data is corrected and positioned according to the position of the title, so that the identification accuracy is improved.
Further, adopting deep learning CNN to identify the content of the background complex area of the vehicle-mounted data; recognizing the content of the background single area of the vehicle-mounted data by adopting an OCR (optical character recognition), specifically comprising the following steps of selecting the content of the background complex area from the vehicle-mounted data through a plurality of preset first recognition areas, and recognizing the content selected from the first recognition areas by adopting a deep learning CNN (content recognition network); recognizing contents which are not selected by the first recognition area in the vehicle-mounted data by adopting OCR;
the position and the selection range of the first identification area correspond to the content of the title of the vehicle-mounted material, and the position of the first identification area is relatively fixed with the position of the title. And the vehicle-mounted data is divided into identified areas so as to improve the accuracy of identification.
Further, the collecting identification data and comparing the identification data, and sending the result obtained by comparison to the display device specifically includes searching and comparing corresponding vehicle information in the mes system according to the identification data, and sending the result of comparison to the display device. The corresponding vehicle information is searched in the mes system and compared, so that the detection quality is improved.
Further, after the outer frame of the image of each vehicle-mounted certificate is detected, whether the vehicle-mounted certificate corresponds to the detection window is judged according to the size of the outer frame of the image of the vehicle-mounted certificate. And the vehicle-mounted certificate is prevented from being placed on the non-corresponding detection window.
An embodiment of the invention also provides an identification system of an onboard certificate, comprising:
a body;
the detection windows are arranged at the top of the machine body;
the cameras are arranged inside the machine body and correspond to the detection windows one by one, and the cameras collect images of the vehicle-mounted certificates on the detection windows;
a storage storing a computer program;
the processor realizes the steps of the identification method of the vehicle-mounted certificate when executing the computer program, and sends the collected identification data and the comparison result to the storage for storage;
the display screen, the display screen with the fuselage can be dismantled and be connected, the display screen is received and is shown the identification data of treater and the result of comparison.
Compared with the prior art, the identification system of the vehicle-mounted certificate can simultaneously detect all contents in a plurality of vehicle-mounted certificates, improves the detection efficiency and has high detection accuracy.
And further, the voice playing device is fixedly connected with the machine body, and receives and plays the comparison result of the processor. And informing the user of the comparison result in a voice broadcasting mode for looking up.
Further, the top of fuselage is equipped with a plurality of bracing piece, the display screen with the bracing piece can be dismantled and be connected. And supporting the display screen by using the supporting rod.
Furthermore, a sliding rod group is arranged inside the machine body, the cameras are movably connected with the sliding rod respectively, and the cameras can move along the sliding rod. The user can conveniently adjust the position of the camera.
Furthermore, the detection window is provided with a transparent support plate for placing the vehicle-mounted certificate, and the lens of the camera faces the transparent support plate. And ensuring that the camera can accurately collect the image of the vehicle-mounted certificate.
In order that the invention may be more clearly understood, specific embodiments thereof will be described hereinafter with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart of an identification method of an onboard certificate according to an embodiment of the present invention.
Fig. 2 is a flowchart of step S2 of the identification method of the onboard certificate according to an embodiment of the present invention.
Fig. 3 is a flowchart of step S3 of the identification method of the onboard certificate according to one embodiment of the present invention.
Fig. 4 is a schematic view of a first angle of an identification system of an onboard vehicle according to an embodiment of the present invention.
FIG. 5 is a schematic view of a second angle of the identification system of the onboard vehicle according to one embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a third angle of the identification system of the vehicle-mounted certificate according to the embodiment of the 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 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.
Please refer to fig. 1, which is a flowchart illustrating a method for identifying an onboard certificate according to an embodiment of the present invention, wherein the method can detect all contents of a plurality of onboard certificates at the same time, and comprises the following steps:
s1: receiving images of a plurality of onboard certificates; the image of the vehicle-mounted certificate is acquired by the cameras on the vehicle-mounted certificates on the detection windows respectively;
s2: respectively detecting the outer frame of the image of each vehicle-mounted certificate, and correspondingly extracting the content in the outer frame as vehicle-mounted data;
s3: carrying out image preprocessing on the vehicle-mounted data;
s4: adopting a deep learning CNN (Convolutional Neural Networks) to identify the content of the background complex region of the vehicle-mounted data; recognizing the content of a background single area of the vehicle-mounted data by adopting OCR (optical character recognition);
s5: and collecting and comparing the identification data, and sending a result obtained by comparison to the display equipment.
In this embodiment, the number of the vehicle-mounted certificates is 4, and the vehicle-mounted certificates include vehicle certificates, COC consistency certificates, energy consumption identifiers, and environmental protection information lists. The number of the detection windows is 4, and the detection windows comprise a first detection window, a second detection window, a third detection window and a fourth detection window. The first detection window is used for placing the vehicle certificate, the second detection window is used for placing the COC consistency certificate, the third detection window is used for placing the energy consumption identifier, and the fourth detection window is used for placing the environmental protection information list. Preferably, the first detection window, the second detection window, the third detection window and the fourth detection window are transversely arranged on one side of the top of the machine body in sequence, so that an operator, a vehicle owner or a third party can conveniently place the vehicle-mounted certificate on the detection windows.
In other embodiments, the order of the positions of the first detection window, the second detection window, the third detection window, and the fourth detection window is not limited, and those skilled in the art can freely change the order of the positions of the first detection window, the second detection window, the third detection window, and the fourth detection window.
In other possible embodiments, the number of the onboard documents and the detection windows can be set according to detection requirements, and is not limited to the 4.
The camera is 4, including the first camera that corresponds with first detection window, the second camera that corresponds with the second detection window, the third camera that corresponds with the third detection window and the fourth camera that corresponds with the fourth detection window. The specific steps of receiving the images of the plurality of onboard certificates are as follows: the first camera, the second camera, the third camera and the fourth camera are used for acquiring images of the vehicle-mounted certificate on the first detection window, the second detection window, the third detection window and the fourth detection window.
Referring to fig. 2, the step S2 specifically includes:
s201: respectively detecting the outer frame of the image of each vehicle-mounted certificate, and judging whether the vehicle-mounted certificates correspond to the detection windows according to the size of the outer frame for detecting the image of the vehicle-mounted certificates; and if the vehicle-mounted certificate corresponds to the detection window, executing the step S202, otherwise, informing a user that the vehicle-mounted certificate is abnormally placed.
The camera collects the image of the vehicle-mounted certificate and simultaneously collects the environmental content except the vehicle-mounted certificate, so that the edge of each vehicle-mounted certificate is used as the outer frame of the image of each vehicle-mounted certificate to detect, and whether the vehicle-mounted certificate corresponds to the detection window or not is judged. Taking the second detection window as an example, the second detection window is used for placing the COC consistency certificate, that is, the COC consistency certificate corresponds to the second detection window. If other vehicle-mounted certificates are placed in the second detection window, if the energy consumption identification exists, the size of the outer frame of the image of the energy consumption identification is different from that of the outer frame of the COC consistency certificate, and a result that the vehicle-mounted certificates are placed abnormally is obtained.
S202: correspondingly extracting the content in the outer frame as vehicle-mounted data.
Because the environmental content collected by the camera except the vehicle-mounted certificate can increase the identification difficulty, only the content within the outer frame of the vehicle-mounted certificate is extracted, and the image data only containing the vehicle-mounted certificate is obtained and used as vehicle-mounted data.
S203: and detecting the title position of the vehicle-mounted data, and correcting and positioning the position of the vehicle-mounted data according to the position of the title.
The correction positioning specifically comprises the following steps: if the vehicle-mounted data is a front image of the vehicle-mounted certificate in a turning or tilting mode, the direction of the image is confirmed by detecting the position of the title, and the direction of the image is used as a recognition reference direction, so that the recognition accuracy is improved.
In this embodiment, the step S2 may detect whether the onboard certificate is correctly placed, and whether the image of the onboard certificate is successfully collected and the onboard data is extracted. And correcting and positioning the vehicle-mounted data.
Referring to fig. 3, the step S3 specifically includes:
s301: carrying out image enhancement on the vehicle-mounted data; the image enhancement is: selectively highlighting textual content in the vehicle-mounted data, suppressing background features in the vehicle-mounted data.
S302: carrying out graying processing on the vehicle-mounted data; the graying treatment comprises the following steps: and setting the value of RGB of the vehicle-mounted data as R-G-B.
S303: carrying out binarization processing on the vehicle-mounted data; and selecting the gray value of the point on the vehicle-mounted data as 0 or 255, so that the vehicle-mounted data presents an obvious black-and-white effect, the vehicle-mounted data is simplified, and the data volume of the vehicle-mounted data is reduced.
The step S4 specifically includes: selecting contents of a background complex area from the vehicle-mounted data through a plurality of preset first identification areas, and identifying the contents selected from the first identification areas by adopting deep learning CNN; recognizing contents which are not selected by the first recognition area in the vehicle-mounted data by adopting OCR;
the background complex area refers to a part of the vehicle-mounted data, where the density of characters or graphics exceeds a preset density value, such as a background pattern in the vehicle-mounted data, characters close to or overlapped with the background pattern, and characters close to the edge of the vehicle-mounted data, where the characters close to the edge of the vehicle-mounted data are difficult to identify due to irregular tilting of the edge part when the vehicle-mounted certificate is captured. The background single area refers to a part of the vehicle-mounted data, of which the density of characters or the density of figures is lower than a preset density value, namely all other contents in the vehicle-mounted data, which are positioned in the area without the background complex area, comprise characters far away from the background pattern and characters positioned in the center of the vehicle-mounted data. The preset density value is initially set to be a default value, and a user can change the preset density value according to the actual use condition.
The position and the selection range of the first identification area are preset and correspond to the content of the title of the vehicle-mounted data, namely, the titles of the vehicle-mounted data are different due to different types of the vehicle-mounted data, so that the preset position and the preset selection range of the first identification area respectively correspond to each vehicle-mounted data. Preferably, the position of the first identification area is fixed relative to the position of the title. And the vehicle-mounted data is divided into identified areas so as to improve the accuracy of identification. The position and the selection range of the first identification area correspond to the content of the vehicle certificate of certification, the COC consistency certificate, the energy consumption identification and the title of the environmental protection information list.
The deep learning CNN is a convolutional neural network and has the capability of representing learning, and is also provided with a database which stores a large amount of data of characters, patterns, angles of the characters and tensile deformation of the characters. And the deep learning CNN calls data in the database to identify the content selected by the first identification area.
The OCR is optical character recognition, and the character shape in the vehicle-mounted data is translated into a computer character by using a character recognition method.
By dividing different identification areas for different vehicle-mounted data, the accuracy of identification is improved.
In an embodiment, the step S5 specifically includes: and searching corresponding vehicle information in a mes system (manufacturing execution system) according to the identification data, comparing the vehicle information, and sending a comparison result to the display device. Preferably, the result of the comparison can also be sent to the voice playing device. The mes system is a production informatization management system facing a workshop execution layer of a manufacturing enterprise, and stores the vehicle information, wherein the vehicle information comprises all or part of information in a vehicle certificate of certification, a COC (chip on control) consistency certificate, an energy consumption identifier and an environmental protection information list.
In this embodiment, taking the COC consistency certificate as an example, the embodiment searches for corresponding vehicle information in a mes system according to contents of one or more items of a vehicle consistency certificate number, a vehicle identification code, an engine number, and a vehicle model in the vehicle-mounted material of the COC consistency certificate, and then compares other contents in the vehicle-mounted material of the COC consistency certificate with the contents of the vehicle information. If the comparison results are completely consistent, the completely consistent comparison results are sent to the display device and the voice playing device, and if some item or some items of contents in the comparison results are inconsistent, the comparison results and the inconsistent contents are sent to the display device and the voice playing device.
Compared with the prior art, the identification method of the vehicle-mounted certificate can simultaneously detect all contents in a plurality of vehicle-mounted certificates, improves the detection efficiency and has high detection accuracy.
In the embodiment, the vehicle information can be searched and compared, the detection quality is improved, and the comparison result is visually displayed to a user for checking.
Referring to fig. 4 and 5, an identification system of an onboard certificate according to an embodiment of the present invention includes:
a body 1;
a plurality of detection windows 2, wherein the detection windows 2 are arranged at the top of the machine body 1;
the cameras 3 are arranged inside the machine body 1, the cameras 3 correspond to the detection windows 2 one by one, and the cameras 3 collect images of the vehicle-mounted certificates on the detection windows 2;
a storage storing a computer program;
the processor realizes the steps of the identification method of the vehicle-mounted certificate when executing the computer program, and sends the collected identification data and the comparison result to the storage for storage;
the display screen 6, the display screen 6 with the fuselage 1 can be dismantled and be connected, the display screen 6 receives and shows the identification data of treater and the result of comparison.
Preferably, a workbench extends from one side of the top of the machine body 1, so that an operator can conveniently place other office appliances.
The number of the vehicle-mounted certificates is 4, and the vehicle-mounted certificates comprise vehicle certificates, COC consistency certificates, energy consumption identifications and environment-friendly information lists. The number of the detection windows 2 is 4, and the detection windows comprise a first detection window, a second detection window, a third detection window and a fourth detection window. The first detection window is used for placing the vehicle certificate, the second detection window is used for placing the COC consistency certificate, the third detection window is used for placing the energy consumption identifier, and the fourth detection window is used for placing the environmental protection information list. Preferably, the first detection window, the second detection window, the third detection window and the fourth detection window are transversely arranged on one side of the top of the machine body in sequence, so that an operator, a vehicle owner or a third party can conveniently place the vehicle-mounted certificate on the detection windows.
In other embodiments, the order of the positions of the first detection window, the second detection window, the third detection window, and the fourth detection window is not limited, and those skilled in the art can freely change the order of the positions of the first detection window, the second detection window, the third detection window, and the fourth detection window.
In other possible embodiments, the number of the onboard documents and the detection windows 2 can be set according to detection requirements, and is not limited to 4.
The number of the cameras 3 is 4, and the cameras comprise a first camera corresponding to the first detection window, a second camera corresponding to the second detection window, a third camera corresponding to the third detection window and a fourth camera corresponding to the fourth detection window. The specific steps of receiving the images of the plurality of onboard certificates are as follows: the first camera, the second camera, the third camera and the fourth camera are used for acquiring images of the vehicle-mounted certificate on the first detection window, the second detection window, the third detection window and the fourth detection window.
Preferably, the quantity of display screen 6 is 2, 2 display screen 6 is located the both sides of fuselage 1, wherein one side display screen 6 shows to look for operating personnel, the opposite side display screen 6 shows to look for car owner or third party personnel.
In other possible embodiments, the number of the display screens 6 can be set according to the detection requirement, and is not limited to the 2.
In this embodiment, a user places the onboard certificate on the detection window 2, the camera 3 collects an image of the onboard certificate on the detection window 2 and sends the image of the onboard certificate to the processor, the processor detects an outer frame of the image of the onboard certificate, correspondingly extracts content within the outer frame as onboard data, performs image preprocessing on the onboard data, the processor identifies the onboard data to obtain identification data, and the processor compares the identification data; and the storage receives and stores the identification data and the comparison result. The user can directly view the identification data and the comparison result from the display screen 6, and can also call and view the identification data and the comparison result stored in the memory.
Compared with the prior art, the identification system of the vehicle-mounted certificate can simultaneously detect all contents in a plurality of vehicle-mounted certificates, improves the detection efficiency and has high detection accuracy.
In an embodiment, the mobile terminal further includes a voice playing device (not shown), the voice playing device is fixedly connected to the body, and the voice playing device receives and plays a comparison result of the processor. The voice playing device can inform nearby people of the comparison result at one time.
In one embodiment, a plurality of support rods 101 are arranged at the top of the body 1, and the display screen 6 is detachably connected with the support rods 101. Specifically, the number of the support rods 101 corresponds to the number of the display screens 6, and the support rods are connected to the corresponding display screens 6 by bolts. Preferably, the support bar 101 is pivoted on the top of the body 1 and can rotate around the pivoted position. Utilize the bracing piece 101 supports display screen 6 avoids display screen 6 occupies the position of fuselage 1 surface.
In one embodiment, a plurality of slide bars 103 corresponding to the cameras 3 one to one are arranged inside the body 1, each camera 3 is movably connected with each slide bar 103, and the camera 3 can move along the slide bars 103, so that a user can adjust the position of the camera 3 conveniently.
Optionally, a slide bar in the slide bar 103 is vertically arranged, and the camera 3 can move up and down along the slide bar 103, so that a user can adjust the height of the camera 3 conveniently. Specifically, after the camera 3 is adjusted to a proper height, the camera 3 and the sliding rod 103 can be relatively fixed through a bolt structure, so that the camera 3 is prevented from naturally sliding down due to gravity.
Optionally, the sliding rod 103 is arranged along a horizontal direction, and the camera 3 can move along the sliding rod 103 in the horizontal direction, so that a user can adjust the horizontal position of the camera 3 conveniently. Specifically, after the camera 3 is adjusted to a proper horizontal position, the camera 3 and the slide bar 103 can be relatively fixed through a bolt structure, so that the position of the camera 3 is prevented from shifting due to collision.
Preferably, the camera 3 is movably connected with the slide bar through a sliding part 7, the sliding part 7 can move along the slide bar 103, and the camera 3 is pivoted with the sliding part 7 and rotates around the pivoted position, so that a user can conveniently adjust the angle of the camera 3. Specifically, when the angle of the camera 3 is adjusted, the image effect of the camera 3 can be checked by means of a level meter or directly, and the camera 3 gradually rotates by taking the pivot joint with the sliding part 7 as a center, so that a better adjusting effect is achieved.
In one embodiment, still include a plurality of auxiliary lamps 8, auxiliary lamps 8 set up in the inside of fuselage 1, just auxiliary lamps 8 with detection window 2 one-to-one, auxiliary lamps 8 to detection window 2 shines light, improves camera 3 gathers the image accuracy of vehicle-mounted certificate. Preferably, the illumination intensity, color and illumination range of the auxiliary lamp 8 correspond to the type of the detection window 2, i.e. the illumination intensity, color and illumination range of the auxiliary lamp 8 are not necessarily the same, specifically, the auxiliary lamp 8 comprises a first auxiliary lamp, a second auxiliary lamp, a third auxiliary lamp and a fourth auxiliary lamp, and the illumination intensity, color and illumination range of the first auxiliary lamp, the second auxiliary lamp, the third auxiliary lamp and the fourth auxiliary lamp correspond to the first detection window, the second detection window, the third detection window and the fourth detection window respectively.
Referring to fig. 6, in an embodiment, the inspection window 2 is provided with a transparent support plate for placing the onboard certificate, and the lens of the camera 3 faces the transparent support plate. And the camera 3 can accurately collect the images of the vehicle-mounted certificates. The material of the transparent support plate can be transparent glass or a transparent composite material. The user will the vehicle-mounted certificate is placed in the transparent support plate, just the front orientation of vehicle-mounted certificate the transparent support plate, camera 3 passes through the transparent support plate can accurately gather the image of vehicle-mounted certificate.
In one embodiment, the bottom of the body 1 is provided with a support member 105 for preventing the bottom of the body 1 from being in direct contact with the ground, and protecting the bottom of the body 1. Wherein the support member 105 may be a set of legs 1051, a set of pulleys 1052, or a combination of both. Preferably, the support member 105 is a combination of a set of legs 1051 and a pulley block 1052, wherein the set of legs 1051 can be adjusted in height, when it is desired to move the fuselage 1, the set of legs 1051 can be adjusted away from the ground and then the fuselage 1 is moved by the pulley block 1052; when the body 1 needs to be fixed, the leg set 1051 can be adjusted to abut against the ground.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for identifying an on-board certificate is characterized by comprising the following steps:
receiving images of a plurality of onboard certificates; the image of the vehicle-mounted certificate is acquired by the cameras on the vehicle-mounted certificates on the detection windows respectively;
respectively detecting the outer frame of the image of each vehicle-mounted certificate, and correspondingly extracting the content in the outer frame as vehicle-mounted data;
carrying out image preprocessing on the vehicle-mounted data;
adopting deep learning CNN to identify the content of the background complex area of the vehicle-mounted data; recognizing the content of a single background area of the vehicle-mounted data by adopting OCR (optical character recognition);
and collecting and comparing the identification data, and sending a result obtained by comparison to the display equipment.
2. The method for identifying the onboard certificate of claim 1, wherein: and after the content in the outer frame is extracted to be used as vehicle-mounted data, detecting the position of the title of the vehicle-mounted data, and correcting and positioning the position of the vehicle-mounted data according to the position of the title.
3. The method for identifying the onboard certificate of claim 2, wherein: adopting deep learning CNN to identify the content of the background complex area of the vehicle-mounted data; recognizing the content of the background single area of the vehicle-mounted data by adopting an OCR (optical character recognition), specifically comprising the following steps of selecting the content of the background complex area from the vehicle-mounted data through a plurality of preset first recognition areas, and recognizing the content selected from the first recognition areas by adopting a deep learning CNN (content recognition network); recognizing contents which are not selected by the first recognition area in the vehicle-mounted data by adopting OCR;
the position and the selection range of the first identification area correspond to the content of the title of the vehicle-mounted material, and the position of the first identification area is relatively fixed with the position of the title.
4. The method for identifying the vehicle-mounted certificate as claimed in claim 3, wherein the collecting identification data and comparing the collected identification data, and sending the result of the comparison to a display device specifically comprises: and searching corresponding vehicle information in the mes system according to the identification data, comparing the vehicle information, and sending a comparison result to display equipment.
5. The method for identifying the onboard certificate of claim 1, wherein: after the outer frames of the images of the vehicle-mounted certificates are respectively detected, whether the vehicle-mounted certificates correspond to the detection windows or not is judged according to the sizes of the outer frames of the images of the vehicle-mounted certificates.
6. An identification system for an onboard certificate, comprising:
a body;
the detection windows are arranged at the top of the machine body;
the cameras are arranged inside the machine body and correspond to the detection windows one by one, and the cameras collect images of the vehicle-mounted certificates on the detection windows;
a storage storing a computer program;
a processor, which when executing the computer program implements the steps of the method according to any one of claims 1 to 6, sends the collected identification data and the comparison result to the storage for storage;
the display screen, the display screen with the fuselage can be dismantled and be connected, the display screen is received and is shown the identification data of treater and the result of comparison.
7. The identification system of an onboard certificate as recited in claim 6, further comprising: still include voice playback equipment, voice playback equipment with fuselage fixed connection, voice playback equipment receives and plays the result of the comparison of treater.
8. The identification system of an onboard certificate as recited in claim 6, further comprising: the top of fuselage is equipped with a plurality of bracing piece, the display screen with the bracing piece can be dismantled and be connected.
9. The identification system of an onboard certificate as recited in claim 6, further comprising: the inside of fuselage is equipped with slide bar group, a plurality of cameras respectively with slide bar swing joint, a plurality of cameras can be followed the slide bar removes.
10. The identification system of an onboard certificate as recited in claim 6, further comprising: the detection window is provided with a transparent support plate for placing the vehicle-mounted certificate, and the lens of the camera faces the transparent support plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010832100.6A CN111818269A (en) | 2020-08-18 | 2020-08-18 | Identification method and identification system of vehicle-mounted certificate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010832100.6A CN111818269A (en) | 2020-08-18 | 2020-08-18 | Identification method and identification system of vehicle-mounted certificate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111818269A true CN111818269A (en) | 2020-10-23 |
Family
ID=72859484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010832100.6A Pending CN111818269A (en) | 2020-08-18 | 2020-08-18 | Identification method and identification system of vehicle-mounted certificate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111818269A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991609A (en) * | 2021-02-23 | 2021-06-18 | 长久金孚企业管理咨询（深圳）有限公司 | Method, device and equipment for identifying authenticity of automobile certificate |
-
2020
- 2020-08-18 CN CN202010832100.6A patent/CN111818269A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991609A (en) * | 2021-02-23 | 2021-06-18 | 长久金孚企业管理咨询（深圳）有限公司 | Method, device and equipment for identifying authenticity of automobile certificate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111815630B (en) | Defect detection method and device for LCD screen | |
| TWI497422B (en) | A system and method for recognizing license plate image | |
| US20160148063A1 (en) | Traffic light detection | |
| KR101812953B1 (en) | Image detecting system and method for underbody of vehicle using recognizing a car type by identifying emblem image | |
| US20230005130A1 (en) | Method and device for detecting display panel defect | |
| CN104112153A (en) | Method for bar code recognition based on mobile terminal and system thereof | |
| CN108665458A (en) | Transparent body surface defect is extracted and recognition methods | |
| CN105184225B (en) | A kind of multinational banknote image recognition methods and device | |
| CN105303153A (en) | Vehicle license plate identification method and apparatus | |
| CN111524101A (en) | Electronic screen defect detection method based on machine vision technology | |
| CN110567965A (en) | Smartphone glass cover plate edge visual defect detection method | |
| CN114266773A (en) | Display panel defect positioning method, device, equipment and storage medium | |
| US20220164943A1 (en) | Circuit board detection method and electronic device | |
| EP2124194A1 (en) | Method of detecting objects | |
| CN106815830B (en) | Image defect detection method | |
| CN109191516B (en) | Rotation correction method and device of structured light module and readable storage medium | |
| CN111818269A (en) | Identification method and identification system of vehicle-mounted certificate | |
| CN114998217A (en) | Method for determining defect grade of glass substrate, computer device and storage medium | |
| CN113538603A (en) | Optical detection method and system based on array product and readable storage medium | |
| CN210775273U (en) | Battery image shooting system | |
| CN110596118A (en) | Print pattern detection method and print pattern detection device | |
| CN112585655A (en) | Unmanned electronic traffic police duty system based on 5G | |
| CN111353974B (en) | Method and device for detecting image boundary defects | |
| CN107948392B (en) | Terminal and display fault processing method | |
| CN112461846A (en) | Workpiece defect detection method and device |
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 |