CN111582269A - License plate recognition method and device for protecting privacy - Google Patents
License plate recognition method and device for protecting privacy Download PDFInfo
- Publication number
- CN111582269A CN111582269A CN202010309947.6A CN202010309947A CN111582269A CN 111582269 A CN111582269 A CN 111582269A CN 202010309947 A CN202010309947 A CN 202010309947A CN 111582269 A CN111582269 A CN 111582269A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- registered
- license plate
- image
- features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of image recognition, in particular to a license plate recognition method and a license plate recognition device for protecting privacy, wherein the method comprises the following steps: firstly, acquiring a shot image of a vehicle to be registered, wherein a set area of the shot image contains a license plate image of the vehicle to be registered; then, extracting the registered license plate characteristics and the registered vehicle characteristics of the vehicle to be registered according to the shot image, and taking the registered license plate characteristics and the registered vehicle characteristics as registered characteristic information; when a vehicle image of a vehicle to be identified is acquired, extracting the characteristics of the vehicle to be identified according to the vehicle image; the similarity of the characteristics of the vehicle to be recognized and the registration characteristic information is compared, whether the vehicle to be recognized is registered or not is judged according to the similarity, and the license plate recognition device is correspondingly provided.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a license plate recognition method and device for protecting privacy.
Background
Under the trend of sharing economy, some places have already tried to share parking spaces in order to relieve the problem of difficult parking. Sharing parking spaces is not a new concept, but the implementation of sharing parking spaces faces many problems, such as parking space locks. The parking spot lock is the prerequisite of guaranteeing that the sharing parking spot is effectual, can not be occupied by unauthorized vehicle by the sharing parking spot that can be applied for promptly. The parking spot lock for sharing the parking spot comprises a real parking spot lock and a virtual parking spot lock, which is one of key technologies for realizing parking spot sharing, and a license plate recognition technology is the key of a parking spot authorization link (namely opening or closing the parking spot lock).
In modern society, license plate recognition technology is already common, and traditional license plate recognition recognizes specific license plate numbers through image recognition technology to serve as identification of each vehicle. At present, the accuracy of a license plate recognition technology is high, but only the number of a license plate is recognized, whether the license plate is consistent with a registered vehicle type or not cannot be judged, namely other illegal fake-licensed vehicles cannot be recognized, and the problem of information embezzlement when a shared parking lot is adopted is possibly caused. In addition, the shared parking space platform needs to register the private information of the user, and the private information of the vehicle is very sensitive.
The existing license plate recognition recognizes the specific license plate number through an image recognition technology and takes the specific license plate number as the identification of the vehicle, so that the following defects exist when the prior art is used for a shared parking space platform:
1) the illegal fake-licensed vehicle cannot be identified, and whether the vehicle is registered by the member in the shared parking space cannot be judged.
2) The parking space member needs to bind the license plate number, and the individual privacy of the user is revealed.
Disclosure of Invention
In order to solve the above problems, the present invention provides a license plate recognition method and apparatus for protecting privacy, so as to solve one or more technical problems in the prior art, and provide at least one useful choice or creation condition.
In order to achieve the purpose, the invention provides the following technical scheme:
according to a first aspect of the present invention, an embodiment of a license plate recognition method for protecting privacy includes:
acquiring a shot image of a vehicle to be registered, wherein a set area of the shot image contains a license plate image of the vehicle to be registered;
extracting the registered license plate characteristics and the registered vehicle characteristics of the vehicle to be registered according to the shot image;
taking the registered license plate characteristics and the registered vehicle characteristics as registered characteristic information;
acquiring a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified;
extracting the features of the vehicle to be identified according to the vehicle image;
and comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information, and judging whether the vehicle to be identified is registered according to the similarity.
Further, the extracting the registered license plate features and the registered vehicle features of the vehicle to be registered according to the shot image includes:
taking the license plate image of the vehicle to be registered as a registered license plate image, and taking the shot image without the license plate registered image as a registered vehicle image;
and respectively extracting visual features of the registered license plate image and the registered vehicle image to generate registered license plate features Fi and registered vehicle features Gi, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
Further, the using the registered license plate feature and the registered vehicle feature as registered feature information specifically includes:
the method comprises the steps of recording a set of registered license plate characteristics as F (F1, F2, … and Fn), recording a set of registered vehicle characteristics as G (G1, G2, … and Gn), and recording a set of registered characteristic information as D (D1, D2, … and Dn), wherein Di (Fi and Gi), i is larger than or equal to 1 and smaller than or equal to n, and i and n are positive integers.
Further, the extracting the vehicle features to be identified according to the vehicle image specifically comprises:
and extracting visual features of the vehicle image to generate vehicle features H to be recognized, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
Further, the comparing the similarity between the features of the vehicle to be recognized and the registered feature information, and determining whether the vehicle to be recognized is registered according to the similarity includes:
step 1, obtaining a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified; extracting visual features of the vehicle image to generate a vehicle feature H to be identified;
step 2, selecting any registration license plate feature Fj from a registration license plate feature set F, and carrying out vector matching on the registration license plate feature F j and a vehicle feature H to be recognized to obtain a matching vector set MF;
and 3, judging whether | MF |/| Fj | is larger than u, if so, executing the next step, otherwise, skipping to the step 6, wherein the value range of u is as follows: 34.6% to 44.4%;
step 4, carrying out vector matching on the registered vehicle characteristics Gj and H-MF to obtain a matching vector set MG;
and 5, judging whether | MG |/| Gj | is larger than v, if so, judging that the vehicle to be identified is registered, otherwise, executing the next step, wherein the value range of v is as follows: 36% to 49.2%;
and 6, judging whether the unselected registered license plate features exist in the registered license plate feature set F, if so, selecting any registered license plate feature from the unselected registered license plate features, skipping to the step 1, and if not, judging that the vehicle to be identified is not registered.
According to a second aspect of the present invention, there is provided a license plate recognition apparatus for protecting privacy, including:
the system comprises a registered image acquisition module, a registration image acquisition module and a registration image acquisition module, wherein the registered image acquisition module is used for acquiring a shot image of a vehicle to be registered, and a set area of the shot image comprises a license plate image of the vehicle to be registered;
the registration feature extraction module is used for extracting registration license plate features and registration vehicle features of the vehicle to be registered according to the shot image;
the registration feature summarizing module is used for taking the registration license plate features and the registration vehicle features as registration feature information;
the identification image acquisition module is used for acquiring a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified;
the identification feature extraction module is used for extracting the features of the vehicle to be identified according to the vehicle image;
and the judging module is used for comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information and judging whether the vehicle to be identified is registered or not according to the similarity.
According to a third aspect of the present invention, there is provided a license plate recognition apparatus for protecting privacy, the apparatus including: memory, a processor and a computer program stored in the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method according to any of the embodiments of the first aspect.
The invention has the beneficial effects that: the invention discloses a license plate recognition method and a device for protecting privacy, wherein the method comprises the following steps: firstly, acquiring a shot image of a vehicle to be registered, wherein a set area of the shot image contains a license plate image of the vehicle to be registered; then, extracting the registered license plate characteristics and the registered vehicle characteristics of the vehicle to be registered according to the shot image, and taking the registered license plate characteristics and the registered vehicle characteristics as registered characteristic information; when a vehicle image of a vehicle to be identified is acquired, extracting the characteristics of the vehicle to be identified according to the vehicle image; and comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information, and judging whether the vehicle to be identified is registered according to the similarity. The registration characteristic information extracted from the vehicle image not only contains the information of the license plate, but also contains the vehicle information, thereby greatly reducing the possibility that the license plate is applied and ensuring the accuracy of license plate identification. In addition, the vehicle image is not directly used in registration and authentication or text information is extracted from the vehicle image, so that the privacy of the user is protected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating a license plate recognition method for protecting privacy according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a head image and a tail image taken when registering a vehicle in an embodiment of the present invention;
fig. 3 is a reference schematic diagram of photographing when registering a vehicle in the embodiment of the present invention;
FIG. 4 is a schematic diagram of an embodiment of the invention in which an intelligent camera captures images of a vehicle head and a vehicle tail;
fig. 5 is a schematic structural diagram of a license plate recognition device for protecting privacy according to an embodiment of the present invention.
Detailed Description
The conception, specific structure and technical effects of the present disclosure will be described clearly and completely with reference to the accompanying drawings and embodiments, so that the purpose, scheme and effects of the present disclosure can be fully understood. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Referring to fig. 1, as shown in fig. 1, a license plate recognition method for protecting privacy provided by an embodiment includes the following steps:
step S100, acquiring a shot image of a vehicle to be registered, wherein a set area of the shot image contains a license plate image of the vehicle to be registered;
in the embodiment, the license plate image of the vehicle to be registered is located in the set area of the shot image by adjusting the shooting position of the vehicle to be registered.
S200, extracting the registered license plate characteristics and the registered vehicle characteristics of the vehicle to be registered according to the shot image;
step S300, using the registered license plate characteristics and the registered vehicle characteristics as registered characteristic information;
s400, obtaining a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified;
s500, extracting the features of the vehicle to be identified according to the vehicle image;
and S600, comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information, and judging whether the vehicle to be identified is registered or not according to the similarity.
Specifically, the license plate identification method provided by the invention is used for identifying the identity of the vehicle facing a membership parking lot and a shared parking space lock.
Firstly, a driver photographs a vehicle when registering in a parking lot management system to obtain a photographed image, and extracts a registration license plate feature and a registration vehicle feature of the vehicle to be registered from the photographed image as key image information.
Then, uploading the key image information to a cloud server in a digital sequence form to serve as registered feature information registered in a parking lot management system, wherein the registered feature information is stored in a vehicle information digital sequence form;
when a user successfully applies for a certain parking space, a camera mounted on an authentication device (e.g., a gate or parking lock, etc.) starts to authenticate a vehicle entering the parking lot. When a vehicle enters a parking lot, a camera at the front section of the gate machine shoots a vehicle picture, the characteristics of the vehicle to be identified are extracted from the picture and uploaded to a cloud server in a digital sequence mode, the cloud server retrieves and compares the vehicle picture from a database, and if the vehicle information digital sequence uploaded when a driver is registered is retrieved, the authentication is successful.
In the embodiment, the vehicle image is processed into the digital sequence which can not be directly read manually, so that the privacy of the vehicle owner and the driver is effectively protected.
It can be seen that embodiments of the present invention have the following advantages:
firstly, the registration feature information extracted from the vehicle image not only contains the information of the license plate, but also contains the vehicle information, thereby greatly reducing the possibility that the license plate is applied;
second, the vehicle image is not directly used in registration and authentication or text information is extracted from the vehicle image, so that the privacy of the user is protected.
As a further improvement of the above technical solution, the step S200 includes:
taking the license plate image of the vehicle to be registered as a registered license plate image, and taking the shot image without the license plate registered image as a registered vehicle image;
and respectively extracting visual features of the registered license plate image and the registered vehicle image to generate registered license plate features Fi and registered vehicle features Gi, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
In a specific embodiment, the photographing scenario is as shown in fig. 2 to 4, and the license plate position needs to be aligned when photographing. And extracting key point features of the 128-dimensional image as key image information by adopting an SIFT (Scale-invariant feature transform) algorithm at the mobile phone terminal. The SIFT is a description mode used in the field of image processing, the description mode has scale invariance, can detect key points in an image and is a local feature descriptor.
Therefore, in the embodiment of the invention, the information quantity of the visual characteristics is far less than that of the image, so that the transmission rate can be greatly improved, and the identification efficiency is obviously improved.
As a further improvement of the above technical solution, the step S300 specifically includes:
the method comprises the steps of recording a set of registered license plate characteristics as F (F1, F2, … and Fn), recording a set of registered vehicle characteristics as G (G1, G2, … and Gn), and recording a set of registered characteristic information as D (D1, D2, … and Dn), wherein Di (Fi and Gi), i is larger than or equal to 1 and smaller than or equal to n, and i and n are positive integers.
As a further improvement of the above technical solution, the step S500 specifically includes:
and extracting visual features of the vehicle image to generate vehicle features H to be recognized, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
As a further improvement of the above technical solution, the step S600 includes:
step 1, obtaining a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified; extracting visual features of the vehicle image to generate a vehicle feature H to be identified;
step 2, selecting any registration license plate feature Fj from a registration license plate feature set F, and carrying out vector matching on the registration license plate feature F j and a vehicle feature H to be recognized to obtain a matching vector set MF;
and 3, judging whether | MF |/| Fj | is larger than u, if so, executing the next step, otherwise, skipping to the step 6, wherein the value range of u is as follows: 34.6% to 44.4%;
it can be seen that when | MF |/| Fj | is greater than u, it is determined that the registered license plate feature Fj matches the feature H of the vehicle to be recognized, that is, the license plate of the vehicle to be recognized passes verification.
Step 4, carrying out vector matching on the registered vehicle characteristics Gj and H-MF to obtain a matching vector set MG;
and H-MF represents the vehicle features to be identified which are left after the matching direction quantity set is removed from the vehicle features to be identified.
And 5, judging whether | MG |/| Gj | is larger than v, if so, judging that the vehicle to be identified is registered, otherwise, executing the next step, wherein the value range of v is as follows: 36% to 49.2%;
it can be seen that when | MG |/| Gj | is greater than v, it is determined that the registered vehicle feature Gj matches the vehicle feature H to be identified, i.e., the vehicle verification of the vehicle to be identified is also passed.
And 6, judging whether the unselected registered license plate features exist in the registered license plate feature set F, if so, selecting any registered license plate feature from the unselected registered license plate features, skipping to the step 1, and if not, judging that the vehicle to be identified is not registered.
As understood by those skilled in the art, the vehicle image includes at least one of a nose image and a tail image; when the vehicle is registered, if only one of the head image and the tail image is acquired, the acquired image is naturally authenticated during vehicle authentication, if both the head image and the tail image are acquired, one of the images can be selected for identification, or both the images are selected for identification, and when both the images are identified, the vehicle to be identified is judged to be registered under the condition that both the images are successfully identified.
Referring to fig. 5, a second embodiment of the present invention further provides a license plate recognition apparatus for protecting privacy, including:
a registered image obtaining module 100, configured to obtain a captured image of a vehicle to be registered, where a set area of the captured image includes a license plate image of the vehicle to be registered;
a registered feature extraction module 200, configured to extract a registered license plate feature and a registered vehicle feature of a vehicle to be registered according to the captured image;
a registration feature summarizing module 300, configured to use the registration license plate features and the registration vehicle features as registration feature information;
the recognition image obtaining module 400 is configured to obtain a vehicle image of a vehicle to be recognized, where the vehicle image includes a license plate image of the vehicle to be recognized;
the identification feature extraction module 500 is used for extracting the features of the vehicle to be identified according to the vehicle image;
the determining module 600 is configured to compare similarity between the features of the vehicle to be identified and the registered feature information, and determine whether the vehicle to be identified is registered according to the similarity.
The embodiment of the third aspect of the invention also provides a license plate recognition device for protecting privacy, which comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method as claimed in any one of the above.
It can be seen that the contents in the foregoing method embodiments are all applicable to this apparatus embodiment, the functions specifically implemented by this apparatus embodiment are the same as those in the foregoing method embodiment, and the advantageous effects achieved by this apparatus embodiment are also the same as those achieved by the foregoing method embodiment.
Through the above description of the embodiments, it is clear to those skilled in the art that the method of the above embodiments may be implemented by software, and loaded into a processor in the form of software, so as to perform license plate recognition for protecting privacy. Based on this understanding, the technical solutions of the present invention may be embodied in the form of software products, which essentially or partially contribute to the prior art.
The Processor may be a Central-Processing Unit (CPU), other general-purpose Processor, a Digital Signal Processor (DSP), an Application-Specific-Integrated-Circuit (ASIC), a Field-Programmable Gate array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center for the license plate recognition device, and various interfaces and lines connecting the various parts of the overall kiln yield statistics system.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the kiln yield statistics system by running or executing the computer programs and/or modules stored in the memory and invoking the data stored in the memory. The memory may primarily include a program storage area and a data storage area, which may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart-Media-Card (SMC), a Secure-Digital (SD) Card, a Flash-memory Card (Flash-Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
While the present invention has been described in considerable detail and with particular reference to a few illustrative embodiments thereof, it is not intended to be limited to any such details or embodiments or any particular embodiments, but rather it is to be construed that the invention effectively covers the intended scope of the invention by virtue of the prior art providing a broad interpretation of such claims in view of the appended claims. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (7)
1. A license plate recognition method for protecting privacy is characterized by comprising the following steps:
acquiring a shot image of a vehicle to be registered, wherein a set area of the shot image contains a license plate image of the vehicle to be registered;
extracting the registered license plate characteristics and the registered vehicle characteristics of the vehicle to be registered according to the shot image;
taking the registered license plate characteristics and the registered vehicle characteristics as registered characteristic information;
acquiring a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified;
extracting the features of the vehicle to be identified according to the vehicle image;
and comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information, and judging whether the vehicle to be identified is registered according to the similarity.
2. The method for recognizing the license plate for protecting the privacy of claim 1, wherein the extracting the registered license plate features and the registered vehicle features of the vehicle to be registered according to the shot image comprises:
taking the license plate image of the vehicle to be registered as a registered license plate image, and taking the shot image without the license plate registered image as a registered vehicle image;
and respectively extracting visual features of the registered license plate image and the registered vehicle image to generate registered license plate features Fi and registered vehicle features Gi, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
3. The privacy-preserving license plate recognition method of claim 2, wherein the registration license plate features and the registration vehicle features are used as registration feature information, and specifically:
the method comprises the steps of recording a set of registered license plate characteristics as F (F1, F2, … and Fn), recording a set of registered vehicle characteristics as G (G1, G2, … and Gn), and recording a set of registered characteristic information as D (D1, D2, … and Dn), wherein Di (Fi and Gi), i is larger than or equal to 1 and smaller than or equal to n, and i and n are positive integers.
4. The privacy-protecting license plate recognition method of claim 3, wherein the extracting features of the vehicle to be recognized according to the vehicle image specifically comprises:
and extracting visual features of the vehicle image to generate vehicle features H to be recognized, wherein the visual features are image feature vector sets extracted by adopting an SIFT algorithm.
5. The method for recognizing the license plate with the privacy protection function according to claim 4, wherein the comparing the similarity between the features of the vehicle to be recognized and the registered feature information and the determining whether the vehicle to be recognized is registered according to the similarity comprise:
step 1, obtaining a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified; extracting visual features of the vehicle image to generate a vehicle feature H to be identified;
step 2, selecting any registration license plate feature Fj from a registration license plate feature set F, and carrying out vector matching on the registration license plate feature Fj and a vehicle feature H to be recognized to obtain a matching vector set MF;
and 3, judging whether | MF |/| Fj | is larger than u, if so, executing the next step, otherwise, skipping to the step 6, wherein the value range of u is as follows: 34.6% to 44.4%;
step 4, carrying out vector matching on the registered vehicle characteristics Gj and H-MF to obtain a matching vector set MG;
and 5, judging whether | MG |/| Gj | is larger than v, if so, judging that the vehicle to be identified is registered, otherwise, executing the next step, wherein the value range of v is as follows: 36% to 49.2%;
and 6, judging whether the unselected registered license plate features exist in the registered license plate feature set F, if so, selecting any registered license plate feature from the unselected registered license plate features, skipping to the step 1, and if not, judging that the vehicle to be identified is not registered.
6. A license plate recognition device for protecting privacy, comprising:
the system comprises a registered image acquisition module, a registration image acquisition module and a registration image acquisition module, wherein the registered image acquisition module is used for acquiring a shot image of a vehicle to be registered, and a set area of the shot image comprises a license plate image of the vehicle to be registered;
the registration feature extraction module is used for extracting registration license plate features and registration vehicle features of the vehicle to be registered according to the shot image;
the registration feature summarizing module is used for taking the registration license plate features and the registration vehicle features as registration feature information;
the identification image acquisition module is used for acquiring a vehicle image of a vehicle to be identified, wherein the vehicle image comprises a license plate image of the vehicle to be identified;
the identification feature extraction module is used for extracting the features of the vehicle to be identified according to the vehicle image;
and the judging module is used for comparing the similarity of the characteristics of the vehicle to be identified and the registered characteristic information and judging whether the vehicle to be identified is registered or not according to the similarity.
7. A privacy preserving license plate recognition device, the device comprising: memory, a processor and a computer program stored in the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010309947.6A CN111582269B (en) | 2020-04-20 | 2020-04-20 | License plate recognition method and device for protecting privacy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010309947.6A CN111582269B (en) | 2020-04-20 | 2020-04-20 | License plate recognition method and device for protecting privacy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111582269A true CN111582269A (en) | 2020-08-25 |
CN111582269B CN111582269B (en) | 2023-04-25 |
Family
ID=72124413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010309947.6A Active CN111582269B (en) | 2020-04-20 | 2020-04-20 | License plate recognition method and device for protecting privacy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111582269B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112633281A (en) * | 2020-12-30 | 2021-04-09 | 广东赛诺科技股份有限公司 | Vehicle identity authentication method and system based on Hash algorithm |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180268238A1 (en) * | 2017-03-14 | 2018-09-20 | Mohammad Ayub Khan | System and methods for enhancing license plate and vehicle recognition |
CN110263864A (en) * | 2019-06-24 | 2019-09-20 | 北京精英路通科技有限公司 | Matching process, device, computer equipment and the storage medium of vehicle |
US20190340423A1 (en) * | 2018-05-04 | 2019-11-07 | Hyundai Motor Company | Terminal for vehicle and method for authenticating face |
-
2020
- 2020-04-20 CN CN202010309947.6A patent/CN111582269B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180268238A1 (en) * | 2017-03-14 | 2018-09-20 | Mohammad Ayub Khan | System and methods for enhancing license plate and vehicle recognition |
US20190340423A1 (en) * | 2018-05-04 | 2019-11-07 | Hyundai Motor Company | Terminal for vehicle and method for authenticating face |
CN110263864A (en) * | 2019-06-24 | 2019-09-20 | 北京精英路通科技有限公司 | Matching process, device, computer equipment and the storage medium of vehicle |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112633281A (en) * | 2020-12-30 | 2021-04-09 | 广东赛诺科技股份有限公司 | Vehicle identity authentication method and system based on Hash algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN111582269B (en) | 2023-04-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7162058B2 (en) | Authentication system by fingerprint | |
US10552698B2 (en) | System for multiple algorithm processing of biometric data | |
CN104756135B (en) | System and method for biological characteristic validation relevant to the equipment equipped with camera | |
Kraetzer et al. | Modeling attacks on photo-ID documents and applying media forensics for the detection of facial morphing | |
US7366328B2 (en) | Method and device for preventing false acceptance of latent fingerprint images | |
US8103050B2 (en) | Method for computing a fingerprint of a video sequence | |
US11615176B2 (en) | Registration and verification of biometric modalities using encryption techniques in a deep neural network | |
KR101987618B1 (en) | Vehicle license plate specific system applying deep learning-based license plate image matching technique | |
US10216786B2 (en) | Automatic identity enrolment | |
US20190332878A1 (en) | Biological characteristic recognition device and method and biological characteristic template registration method | |
US9519824B2 (en) | Method for enabling authentication or identification, and related verification system | |
CN112633281B (en) | Vehicle identity authentication method and system based on Hash algorithm | |
CN111582269A (en) | License plate recognition method and device for protecting privacy | |
Jwaid et al. | Study and analysis of copy-move & splicing image forgery detection techniques | |
EP3264329B1 (en) | A method and a device for detecting fraud by examination using two different focal lengths during automatic face recognition | |
EP3107034B1 (en) | Biometric identification method | |
CN111860272B (en) | Image processing method, chip and electronic device | |
Hsiao et al. | More accurate and robust PRNU-based source camera identification with 3-step 3-class approach | |
Maser et al. | Identifying the origin of finger vein samples using texture descriptors | |
JP2592091B2 (en) | Vehicle number check device | |
AU2005100275A4 (en) | User authentication appratus using human body movement detection biometrics system | |
CN116541814B (en) | Unified login authentication method and system | |
JP2004355377A (en) | Face image collation system and its method for distributing face image data | |
Shehu et al. | Detecting an alteration in biometric fingerprint databases | |
KR102523598B1 (en) | Unmaned entrance system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |