CN108875746B - License plate recognition method, device and system and storage medium - Google Patents
License plate recognition method, device and system and storage medium Download PDFInfo
- Publication number
- CN108875746B CN108875746B CN201810472844.4A CN201810472844A CN108875746B CN 108875746 B CN108875746 B CN 108875746B CN 201810472844 A CN201810472844 A CN 201810472844A CN 108875746 B CN108875746 B CN 108875746B
- Authority
- CN
- China
- Prior art keywords
- license plate
- recognition result
- character
- initial
- recognition
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Abstract
The embodiment of the invention provides a license plate recognition method, a license plate recognition device, a license plate recognition system and a storage medium. The method comprises the following steps: acquiring a license plate image to be recognized; carrying out character recognition on the license plate image to be recognized to obtain a primary recognition result of the characters; and determining a final recognition result based on the prior information of the license plate and the preliminary recognition result. According to the technical scheme, the final recognition result is determined by utilizing the prior information of the license plate, so that the serious dependence of the license plate recognition technology on the image quality can be reduced. Even if the quality of the license plate image to be recognized is poor, a relatively ideal recognition result can be obtained based on the license plate prior information, so that the license plate recognition precision is remarkably improved.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a license plate recognition method, a license plate recognition device, a license plate recognition system and a storage medium.
Background
The license plate recognition technology is an application of computer image recognition technology in vehicle license plate recognition. License plate recognition has been widely used in various vehicle management systems, such as an Electronic Toll Collection (ETC) system for highways and a parking lot management system, and the like.
The license plate recognition technology requires that the license plate of the vehicle can be extracted and recognized from the complex background of an image (such as a video frame), and then the information such as the specific license plate of the vehicle can be recognized through the technologies of license plate extraction, image preprocessing, feature extraction, license plate character recognition and the like.
The license plate recognition comprises recognition of characters such as Chinese characters, letters and numbers. The existing license plate recognition technology adopts a segmentation recognition method or a compaction recognition method and the like. But these recognition methods are limited by the quality of the image. When the quality of the collected image is poor, the accuracy of license plate recognition can be seriously and negatively affected.
Therefore, a new license plate recognition technology is urgently needed to solve the above problems.
Disclosure of Invention
The present invention has been made in view of the above problems. The invention provides a license plate recognition method, a license plate recognition device, a license plate recognition system and a storage medium.
According to an aspect of the present invention, there is provided a license plate recognition method, including:
acquiring a license plate image to be recognized;
carrying out character recognition on the license plate image to be recognized to obtain a primary recognition result of the characters; and
and determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result.
Illustratively, the method further comprises: and updating the prior information of the license plate according to the preliminary identification result.
Exemplarily, the method further comprises: selecting the character with the maximum confidence coefficient from the preliminary recognition result as a preliminary recognition result character;
the step of updating the license plate prior information according to the initial identification result comprises the following steps:
determining whether the confidence of the initial recognition result character is higher than a first threshold value; and
and updating the license plate prior information by using the initial recognition result characters under the condition that the confidence coefficient of the initial recognition result characters is higher than the first threshold value.
Illustratively, the determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result includes:
determining whether the confidence of the initial recognition result character is lower than a second threshold; and
and determining the final recognition result based on the license plate prior information and the preliminary recognition result when the confidence coefficient of the characters of the preliminary recognition result is lower than the second threshold value.
Exemplarily, the method further comprises: and receiving a parameter for controlling the action degree of the license plate prior information.
Exemplarily, the preliminary recognition result includes a set of first recognized characters of the character and a probability distribution (p) corresponding to the set of first recognized characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and is 0<i<n +1, n is the number of elements of the initial character set,
the determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result includes:
determining the index number C of the final recognition result of the character in the initial character set according to the following formula:
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )，
wherein β represents the parameter for controlling the degree of action of the license plate prior information, q i Representing the probability corresponding to the ith initial character in the initial character set obtained according to the license plate prior information;
and determining the final recognition result in the initial character recognition set according to the index number C.
Exemplarily, the method further comprises: and obtaining the license plate prior information by counting the probability distribution of characters representing the vehicle attribution in the license plate image.
According to another aspect of the present invention, there is also provided a license plate recognition apparatus including:
the acquisition module is used for acquiring a license plate image to be recognized;
the recognition module is used for carrying out character recognition on the license plate image to be recognized so as to obtain a primary recognition result of the characters; and
and the determining module is used for determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result.
According to another aspect of the present invention, there is also provided a license plate recognition system, comprising a processor and a memory, wherein the memory has stored therein computer program instructions, which when executed by the processor, are adapted to perform the above license plate recognition method.
According to still another aspect of the present invention, a storage medium is further provided, on which program instructions are stored, and when executed, the program instructions are used for executing the license plate recognition method.
According to the license plate recognition method, the license plate recognition device, the license plate recognition system and the storage medium, the final recognition result is determined by utilizing the license plate prior information, and the serious dependence of a license plate recognition technology on the image quality can be reduced. Even if the quality of the image to be recognized is poor, a relatively ideal recognition result can be obtained based on the license plate prior information. Therefore, the technical scheme of the application reduces the requirement on image quality and obviously improves the license plate recognition precision.
The above description is only an overview of the technical solutions of the present invention, and the present invention can be implemented in accordance with the content of the description so as to make the technical means of the present invention more clearly understood, and the above and other objects, features, and advantages of the present invention will be more clearly understood.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail embodiments of the present invention with reference to the attached drawings. The accompanying drawings, which are included to provide a further understanding of the embodiments 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, like reference numbers generally represent like parts or steps.
FIG. 1 is a schematic block diagram of an example electronic device for implementing a license plate recognition method and apparatus in accordance with embodiments of the present invention;
FIG. 2 shows a schematic flow diagram of a license plate recognition method according to one embodiment of the invention;
FIG. 3 shows a schematic flow diagram of a license plate recognition method according to another embodiment of the present invention;
FIG. 4 shows a schematic block diagram of a license plate recognition device 400 according to one embodiment of the present invention; and
FIG. 5 shows a schematic block diagram of a license plate recognition system 500 according to one embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of embodiments of the invention and not all embodiments of the invention, with the understanding that the invention is not limited to the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the invention described in the present application without inventive step, shall fall within the scope of protection of the present invention.
The embodiment of the invention provides a license plate identification method. The license plate is a short name for a vehicle number plate, and the upper surface of the license plate comprises a plurality of characters. Characters on the license plate can comprise Chinese characters, numbers, letters and the like, and can express information such as the attribution of the vehicle, registration numbers and the like. The license plate recognition method provided by the embodiment of the invention determines the final recognition result of the license plate by utilizing the prior information of the license plate, and can obtain a more reliable recognition result no matter the quality of the license plate image to be recognized is better or worse.
First, an example electronic device 100 for implementing a license plate recognition method and apparatus according to an embodiment of the present invention is described with reference to fig. 1.
As shown in FIG. 1, electronic device 100 includes one or more processors 102, one or more memory devices 104. Optionally, the electronic device 100 may also include an input device 106, an output device 108, and a data acquisition device 110, which are interconnected via a bus system 112 and/or other form of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.
The processor 102 may be a Central Processing Unit (CPU), a Graphics Processor (GPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by processor 102 to implement the license plate recognition functionality of the embodiments of the invention described below (implemented by the processor) and/or other desired functionality. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 108 may output various information (e.g., images and/or sounds) to an external (e.g., user), and may include one or more of a display, a speaker, etc.
The data acquisition device 110 may capture various forms of data, such as images, and store the captured data in the storage device 104 for use by other components. The data acquisition device 110 may be a camera or the like. It should be understood that the data acquisition device 110 is merely an example, and the electronic device 100 may not include the data acquisition device 110. In this case, data may be acquired by other data acquisition means and the acquired data may be transmitted to the electronic apparatus 100.
Exemplary electronic devices for implementing the license plate recognition method and apparatus according to embodiments of the present invention may be implemented on devices such as a personal computer or a remote server.
Hereinafter, a license plate recognition method according to an embodiment of the present invention will be described with reference to fig. 2. FIG. 2 shows a schematic flow diagram of a license plate recognition method 200 according to one embodiment of the invention. As shown in fig. 2, the method 200 includes the following steps.
And step S210, acquiring a license plate image to be recognized.
The license plate image to be recognized may be any suitable image that needs to be subjected to license plate recognition, for example, an image collected for a monitored area. It is to be understood that the image may be a video frame in a video. The license plate image to be recognized can be an original image acquired by an image acquisition device such as a camera and the like, and can also be an image acquired after the original image is preprocessed.
The license plate image to be recognized may be sent to the electronic device 100 by a client device (such as a parking management device including a camera) to be processed by the processor 102 of the electronic device 100, or may be collected by an image collecting device 110 (e.g., a camera) included in the electronic device 100 and transmitted to the processor 102 for processing.
Step S220, character recognition is carried out on the license plate image to be recognized, which is obtained in the step S210, so that a primary recognition result of characters in the license plate is obtained.
As previously mentioned, license plates typically include a plurality of characters. For example, the license plate of China includes the first Chinese character, the second English letter and the subsequent number. Step S220 may be implemented using any conventional or future-developed character recognition method, such as a traditional edge and/or color-based recognition algorithm under fixed angles and environments, a compact recognition method, or a segmentation recognition method. The character recognition methods are used for obtaining a preliminary recognition result of characters in the license plate.
The preliminary recognition result may include a set of initial characters of the character, each element of which is an initial character of the character. The initial character indicates the specific character that the character may be. In one example, the initial character set of the first Chinese character in a certain license plate of China is { Jing, qiong }, i.e., the first Chinese character may be two initial characters, namely "Jing" and "Qiong".
The preliminary recognition result may also include a confidence level corresponding to each of the first recognized characters, which indicates a confidence level of the corresponding first recognized character. As described above, for each character on the license plate, a plurality of possible initial characters can be obtained by character recognition. Each initial character corresponds to a confidence level. The probability distribution of all initial characters can be determined according to the proportional relation between the confidences corresponding to the initial characters and each other. For example, a vector composed of the confidences corresponding to all the initial characters is used as the probability distribution corresponding to the initial character set. It will be appreciated that the elements in the set of initial characters have a one-to-one correspondence with the elements in the aforementioned vector used to express the probability distribution.
For example, the initial recognition result of the first Chinese character in a certain license plate may include n Chinese characters and the confidences p corresponding to the Chinese characters respectively 1 ,p 2 ,p 3 ……p n . The initial character set of the first Chinese character of the license plate is the n Chinese characters, and the corresponding probability distribution is (p) 1 ,p 2 ,p 3 ……p n ). Specifically, by taking the above example as an example, through the character recognition operation in step S220, the initial characters of the first Chinese character in one license plate include "jing" and "qiong", and the confidences thereof are 0.55 and 0.45, respectively. This indicates that the probability of the character being "Jing" is 55% and the probability of being "Qiong" is 45%. The initial character set of the character is { Jing, qiong }, and the corresponding probability distribution is (0.55, 0.45).
It is understood that in the prior art, the initial character with the highest confidence is usually selected as the final recognition result. For example, in the above example, the initial character "jing" is used as the final recognition result of the character.
Optionally, character recognition is performed on the license plate image to be recognized by using a neural network, so as to obtain a preliminary recognition result. The neural network may be a multi-layer perceptron. The multi-layer perceptron can more easily implement non-linear classification than a single-layer perceptron. Illustratively, the neural network may be a BP (back propagation) neural network, a convolutional neural network, a Hopfield neural network, or the like. The neural network models are more suitable for character recognition, so that the recognition result is more accurate.
In one example, a license plate of China is identified. As mentioned above, the typical civil license plate in China is composed of the first Chinese character, the second English letter, the last 5 English letters and Arabic numeral numbers. The first Chinese character is a character representing the attribution of the vehicle, namely the region of the vehicle. Thus, the first Chinese character of a license plate is one of the Chinese characters representing 34 regions across the country. The neural network can be used for carrying out character recognition on the license plate image to be recognized so as to obtain a preliminary recognition result of the first Chinese character in the license plate. The initial character set in the initial recognition result may include all the 34 Chinese characters. Correspondingly, the initial recognition result also comprises a probability distribution (p) corresponding to the initial character set 1 ,p 2 ,p 3 ……p 34 ). It can be understood that the vector (p) representing the probability distribution 1 ,p 2 ,p 3 ……p 34 ) May be 0 or close to 0.
The first character set of the second English letter can be a 26 English letter set. The last 5 characters of the license plate are also called the number of the license plate, and the initial character set can be a set of 36 characters which are 26 English letters and numbers 0-9. The recognition process of the characters of the license plate is similar to the processing process of the first Chinese characters, and is not repeated herein.
And step S230, determining a final recognition result of the characters in the license plate based on the license plate prior information and the preliminary recognition result obtained in the step S220. The final recognition result specifies what characters are in the license plate. For example, the first Chinese character in a certain license plate is 'Jing'. In this step, the license plate prior information is used to correct the preliminary recognition result obtained in step S220, so that the final recognition result is more accurate.
With respect to license plates, there is some license plate prior information. The method 200 may further include obtaining license plate prior information by counting a probability distribution of characters representing a home of the vehicle in the license plate image. In the number plate of China, the first Chinese character is a short name of the region (34 regions of the country) to which the vehicle belongs. The second English letter is the first-level code of the city where the vehicle is located, the rule is generally the same, A is province, B is the second major city of the province, C is the third major city of the province, and so on. When a license plate recognition system is arranged and controlled at a certain fixed place to perform license plate recognition, license plates belonging to the place are relatively concentrated. In other words, the characters in the license plate that identify the vehicle's home exhibit a particular probability distribution. For example, in the license plate recognition system distributed in Beijing City, the license plate of "Jing" plate appears most frequently, the probability of the license plate of its nearby province appears higher, and the probability of the license plate of the province far away from Beijing is lower. Similarly, in a license plate recognition system distributed by Hainan province, license plates of "John" cards appear relatively frequently. For another example, in a license plate recognition system distributed and controlled in Qinhuang island city in Hebei province, the frequency of the appearance of the license plate of the 'JiC' plate is relatively high; in the license plate recognition system controlled by Zhang Jiakou city in Hebei province, the frequency of the appearance of the license plate of the 'JiG' plate is relatively high. The license plate recognition system can count the license plate recognition result after the license plate recognition in a certain time, so as to obtain the probability distribution of characters representing the vehicle attribution in the local license plate, and the probability distribution is used as the prior information of the license plate. The characters are such as the first Chinese character and the second English letter in the license plate of China.
As another example, the first number character of a license plate (i.e., the third digit of the license plate) in some region has its predefined information. For example, guangzhou, shenzhen reserve all numeric numbers with all numbers having the first word "0" to government authority vehicles. For example, taxis in many cities have special first numbers, and most of them use the English letter T as the first number, and also use the English letter X as the first number. Therefore, the third characters of the license plates in certain regions have the prior information, and can be used for assisting in license plate recognition. For example, a license plate recognition system deployed at a government gate recognizes a license plate with a greater probability that the third digit of the character is "0".
The license plate prior information can be used for assisting in license plate recognition so as to improve the accuracy of license plate recognition.
Based on the preliminary recognition result obtained in step S220, a final recognition result of the characters in the license plate is obtained with the assistance of the license plate prior information. Therefore, the serious dependence of the license plate recognition technology on the image quality can be reduced. Even if the quality of the license plate image to be recognized is poor, a relatively ideal recognition result can be obtained based on the license plate prior information, so that the requirement on the image quality is reduced, and the license plate recognition precision is obviously improved.
Illustratively, the license plate recognition method according to the embodiment of the present invention can be implemented in a device, an apparatus or a system having a memory and a processor.
The license plate recognition method provided by the embodiment of the invention can be deployed at an image acquisition end, for example, the license plate recognition method can be deployed at an image acquisition end of a highway toll station, an image acquisition end of a community vehicle access control system or an image acquisition end of a parking lot system in public places such as stations, shopping malls, banks and the like. Alternatively, the license plate recognition method according to the embodiment of the invention may also be distributively deployed at the server side (or cloud side) and the client side. For example, an image may be collected at a client, and the client transmits the collected image to a server (or a cloud), so that the server (or the cloud) performs license plate recognition.
Optionally, the preliminary recognition result of the characters in the license plate is used for determining a final recognition result, and can also be used for updating the prior information of the license plate. In other words, the method 200 may further comprise the steps of: and updating the prior information of the license plate according to the initial identification result. For example, the initial character set of the first Chinese character in the current license plate is { Jing, qiong }, the corresponding probability distribution is (0.95, 0.05), namely the big probability of the first Chinese character is 'Jing'. Then, the prior information of the first Chinese character can be changed correspondingly, and specifically, the probability that the first Chinese character of the license plate in the license plate prior information is 'Jing' is increased.
Therefore, the license plate prior information can be closer to an actual application scene through iterative optimization, and the accuracy of license plate recognition is further improved.
It will be understood by those skilled in the art that the above steps for updating the license plate prior information and the specific implementation process are only examples and are not necessary. For example, in one example, step S230 is performed directly using pre-stored license plate prior information. For another example, a limiting condition such as the number of times of updating or the duration of updating the license plate prior information may be set, and when the limiting condition is reached, the preliminary identification result of step S220 is no longer used to update the license plate prior information, so as to save the calculation cost.
FIG. 3 shows a schematic flow diagram of a license plate recognition method 300 according to another embodiment of the invention. As shown in fig. 3, steps S310 and S320 of the method 300 are similar to the functions, processing methods and processes implemented in steps S210 and S220 of the method 200, respectively, and are not described herein again.
The preliminary recognition result of the characters in the license plate is obtained through step S320. The credibility of the initial characters in the initial recognition result is influenced by many factors, such as the quality of the license plate image to be recognized. As mentioned above, the preliminary recognition result indicates the credibility of the initial character through the confidence degree corresponding to the initial character.
In one example, the method 300 includes a step S330 of selecting a character with the highest confidence from the preliminary recognition result of the characters as a preliminary recognition result character. It is to be understood that in the prior art, the initial recognition result character is typically selected as the final recognition result.
The method 300 may further include a step S331 of determining whether a confidence of the initial recognition result character is higher than a first threshold. Here, the confidence of the initial recognition result character is used to determine whether the initial recognition result character can be used to update the license plate prior information, that is, whether to execute step S341. The first threshold represents a decision threshold for the confidence level, i.e., confidence, of the initial recognition result character. If the confidence coefficient of the initial recognition result characters is higher than the first threshold value, the credibility of the initial recognition result characters is high, and the initial recognition result characters can be used for updating the prior information of the license plate. And step S341 is further continued, the license plate prior information is updated by using the initial recognition result characters, so that the license plate prior information is closer to an actual application scene through iterative optimization, and the accuracy of license plate recognition is further improved. On the contrary, the possibility of indicating that the initial recognition result characters are correct is low, and the initial recognition result characters are not suitable for updating the license plate prior information so as to prevent the license plate prior information from deviating from the practical application scene and further influencing the accuracy of license plate recognition. The first threshold may be preset by a user, such as by the input device 106 of the electronic device 100.
In one example, the method 300 may further include step S340 of determining whether the confidence of the initial recognition result character is below a second threshold. Here, the confidence level of the initial recognition result character is used to determine whether the initial recognition result character needs to be corrected for correctness, i.e., whether step S350 is performed. The second threshold represents a decision threshold for the confidence level, i.e., confidence, that the initially recognized result character is correct. If the confidence of the initial recognition result character is lower than the second threshold, the possibility that the initial recognition result character is correct is low, the step S350 is further continued, the final recognition result of the character is determined based on the license plate prior information and the initial recognition result of the character, and a more accurate recognition result can be obtained. On the contrary, the initial recognition result character has high possibility of being correct, and the initial recognition result character can be directly determined as the final recognition result of the character. The second threshold may be preset by a user, such as by the input device 106 of the electronic device 100.
Through the steps, only the primary recognition results of part of license plates are confirmed again, thereby avoiding meaningless calculation, obviously improving the processing efficiency of the system,
in step S350, a final recognition result of the characters is determined based on the license plate prior information and the preliminary recognition result of the characters in the license plate. Before this step, the method 300 further includes a step of receiving a parameter β for controlling the degree of influence of the license plate prior information. Therefore, the user can control the action degree of the license plate prior information in the license plate identification process according to experience so as to obtain a more satisfactory license plate identification result. For example, the parameter may be received through the input device 106 of the electronic device 100, and the parameter may be preset by a user.
As mentioned above, the preliminary recognition result may include a set of initial characters of the character and a probability distribution (p) corresponding to the set of initial characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and is 0<i<n +1, n is the number of elements of the initial character set. Exemplarily, the step S350 may be embodied by the following sub-steps.
Firstly, the index number C of the final recognition result of the characters in the license plate in the initial character set is determined according to the following formula.
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )。
Where argmax () represents a function that returns the index of the maximum argument. q. q.s i And expressing the probability corresponding to the ith initial character in the initial character set obtained according to the license plate prior information.
And then, determining a final recognition result in the initial character set of the character according to the index number C.
It is understood that the above example shows a specific implementation of step S350, and the implementation process is only illustrative and not limiting.
It should be appreciated that in the method 300, the step S350 is independent of the step S341. The two can be executed successively or simultaneously. Determining that correctness correction is required based on the confidence of the character of the initial recognition result in step S340, step S350 of determining a final recognition result based on the initial recognition result may be performed. In other words, step S350 is not necessarily executed after the license plate prior information is updated in step S341. Therefore, the license plate recognition time can be shortened.
For a clearer understanding of the method 300, an implementation of the method 300 according to an embodiment of the present invention is given below. According to this embodiment, the method 300 is implemented by a license plate recognition system deployed in a location in Hainan province. The license plate prior information comprises probability distribution of characters representing the attribution of the vehicle in the license plate. For example, the probability distribution of the first Chinese character of the license plate is as follows: 85% of ' Qiong ', 10% of ' Yue ', 3% of ' Gui ', 0.7% of ' Jing ', 8230and ' 8230. After the license plate recognition system performs the processing of step S320 on a license plate image to be recognized, the initial character set of the first Chinese character of the license plate image to be recognized is obtained as { Jing, qiong }, and the corresponding probability distribution is (0.55, 0.45). In the license plate recognition system, the set first threshold =0.8, the set second threshold =0.9, and the parameter β =0.7 that controls the degree of action of the license plate prior information.
Step S330, selecting the character 'Jing' with the maximum confidence coefficient as the character of the initial recognition result in the initial recognition result of the Chinese character.
In step S331, the confidence corresponding to the initial recognition result character "jing" is 0.55 and is not higher than the first threshold value 0.8, which indicates that the confidence level of the initial recognition result character is low and is not suitable for optimizing and updating the license plate prior information, and the execution of step S341 is omitted.
Step S340, determining that the confidence 0.55 corresponding to the initial recognition result character "jing" is lower than a second threshold 0.9. The confidence coefficient of the initial recognition result character 'Jing' as the final recognition result of the Chinese character is low. Step S350 is further performed to assist in correction by using the license plate prior information, and a final recognition result is determined based on the preliminary recognition result of the chinese character. According to the prior information of the license plate, the corresponding probabilities of the initial recognition characters of Beijing and Qiong are 0.007 and 0.85 respectively.
The index number C1 of the final recognition result of the Chinese character in the initial character recognition set is determined by the following formula:
C1＝argmax(0.7×0.55+(1-0.7)×0.007,0.7×0.45+(1-0.7)×0.85)
＝argmax(0.3871,0.57)
＝2
therefore, the final recognition result of the first Chinese character in the license plate is determined to be the 2 nd character 'Qiong' of the initial character set.
According to the license plate recognition method provided by the embodiment of the invention, as the license plate prior information is introduced to participate in license plate determination, the serious dependence of the existing license plate recognition technology on the image quality can be reduced, and the license plate recognition precision is obviously improved. The method has very important value for application scenes with poor quality of shot images under poor weather conditions (such as rainy and snowy days, foggy days or sand-dust days) or poor illumination (such as evening and dark night).
According to another aspect of the invention, a license plate recognition device is also provided. Fig. 4 shows a schematic block diagram of a license plate recognition apparatus 400 according to an embodiment of the present invention.
As shown in fig. 4, the apparatus 400 includes an acquisition module 410, a recognition module 420, and a determination module 440. The modules may respectively perform the steps/functions of the license plate recognition method described above. Only the main functions of the components of the device 400 are described below, and details that have been described above are omitted.
The obtaining module 410 is used for obtaining a license plate image to be recognized. The obtaining module 410 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The recognition module 420 is configured to perform character recognition on the license plate image to be recognized to obtain a preliminary recognition result of characters in the license plate. Preferably, the recognition module 420 performs license plate recognition on the image to be recognized by using a neural network to obtain the preliminary recognition result. The identification module 420 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104. The determining module 440 is configured to determine a final recognition result of the character based on the license plate prior information and the preliminary recognition result of the character. The determination module 440 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
Optionally, the apparatus 400 may further include an update module 430. The updating module 430 is configured to update the license plate prior information according to the preliminary identification result. Illustratively, the license plate prior information is obtained by counting probability distribution of characters representing a vehicle attribution in a license plate image. The update module 430 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
According to the embodiment of the present invention, the apparatus 400 may further include a preliminary recognition module configured to select a character with the highest confidence from the preliminary recognition result as a character of the preliminary recognition result.
The update module 430 may include a first judgment unit and an update unit. The first judging unit is used for determining whether the confidence coefficient of the initial recognition result character is higher than a first threshold value. And if the confidence coefficient of the initial recognition result character is higher than the first threshold value, executing the updating unit. And the updating unit is used for updating the license plate prior information by using the initial recognition result characters under the condition that the confidence coefficient of the initial recognition result characters is higher than the first threshold value. It can be understood that, for the case that the confidence is not higher than the first threshold, the license plate prior information is not updated.
According to an embodiment of the present invention, the determining module 440 includes a second judging unit and a final identifying unit. The second judging unit is used for determining whether the confidence coefficient of the initial recognition result character is lower than a second threshold value. The final recognition unit is executed for a case where the confidence of the initial recognition result character is lower than a second threshold. And the final recognition unit is used for determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result of the character under the condition that the confidence coefficient of the character of the preliminary recognition result is lower than a second threshold value. For the case that the confidence coefficient is not lower than the second threshold, the probability that the character of the initial recognition result is correct is high, and the character of the initial recognition result can be directly determined as the final recognition result of the character.
The apparatus 400 may further comprise a receiving unit for receiving a parameter β for controlling the extent of the effect of the license plate prior information. The parameter β may be used in the final identification unit.
As mentioned above, the preliminary recognition result may include a set of initial characters of the character and a probability distribution (p) corresponding to the set of initial characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and is 0<i<n +1, n is the number of elements of the initial character set. For example, the final recognition unit may determine an index number C of a final recognition result of a character in the license plate in the initial character set according to the following formula, and then determine the final recognition result in the initial character set of the character according to the index number C.
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )。
Where argmax () represents a function that returns the index of the maximum argument. q. q.s i And representing the probability corresponding to the ith initial character in the initial character set obtained according to the prior information of the license plate.
It is understood that the above example gives a specific implementation of the final recognition unit, and the implementation example is only illustrative and not limiting to the invention.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
FIG. 5 shows a schematic block diagram of a license plate recognition system 500 according to one embodiment of the present invention. As shown in fig. 5, system 500 includes an input device 510, a storage device 520, a processor 530, and an output device 540.
The input device 510 is used for receiving an operation instruction input by a user and collecting data. The input device 510 may include one or more of a keyboard, a mouse, a microphone, a touch screen, an image capture device, and the like.
The storage device 520 stores computer program instructions for implementing the corresponding steps in the license plate recognition method according to the embodiment of the present invention.
The processor 530 is configured to run the computer program instructions stored in the storage device 520 to perform the corresponding steps of the license plate recognition method according to the embodiment of the present invention, and is configured to implement the obtaining module 410, the recognition module 420, and the determining module 440 in the license plate recognition device according to the embodiment of the present invention. The processor 530 can also be used for implementing the license plate prior information module 430 in the license plate recognition device according to the embodiment of the invention.
In one embodiment, the computer program instructions, when executed by the processor 530, cause the system 500 to perform the steps of:
acquiring a license plate image to be recognized;
carrying out character recognition on the license plate image to be recognized to obtain a primary recognition result of characters in the license plate; and
and determining a final recognition result of the characters based on the prior information of the license plate and the preliminary recognition result.
In one embodiment, the computer program instructions, when executed by the processor 530, cause the system 500 to further perform the steps of: and updating the license plate prior information according to the preliminary identification result.
Illustratively, the license plate prior information is obtained by counting probability distribution of characters representing a vehicle attribution in a license plate image.
In one embodiment, the computer program instructions, when executed by the processor 530, cause the system 500 to further perform the steps of: and selecting the character with the maximum confidence coefficient from the preliminary recognition result as a preliminary recognition result character.
Illustratively, updating the license plate priors according to the preliminary recognition result, which is executed by the system 500 when the computer program instructions are executed by the processor 530, further comprises the steps of:
determining whether the confidence of the initial recognition result character is higher than a first threshold value; and
and updating the license plate prior information by using the initial recognition result characters under the condition that the confidence degree of the initial recognition result characters is higher than the first threshold value.
For example, determining the final recognition result of the character based on the license plate prior information and the preliminary recognition result, which is executed by the system 500 when the computer program instructions are executed by the processor 530, further comprises the following steps:
determining whether the confidence of the initial recognition result character is lower than a second threshold; and
and determining the final recognition result based on the license plate prior information and the preliminary recognition result when the confidence coefficient of the characters of the preliminary recognition result is lower than the second threshold value.
Illustratively, the computer program instructions, when executed by the processor 530, cause the system 500 to receive a parameter β for controlling the extent of effect of the license plate priors.
As mentioned above, the preliminary recognition result may include a set of initial characters of the character and a probability distribution (p) corresponding to the set of initial characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and 0<i<n +1, n is the number of elements of the initial character set.
For example, in the step of determining the final recognition result of the character based on the license plate prior information and the preliminary recognition result, which is executed by the processor 530, the system 500 may determine an index number C of the final recognition result of the character in the license plate in the preliminary recognition character set according to the following formula, and then determine the final recognition result in the preliminary recognition character set of the character according to the index number C.
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )。
Where argmax () represents a function that returns the index of the maximum argument. q. q.s i Representation is obtained according to license plate prior informationThe probability corresponding to the ith initial character in the initial character set.
Furthermore, according to still another aspect of the present invention, there is also provided a storage medium on which program instructions are stored, which when executed by a computer or a processor cause the computer or the processor to execute the respective steps of the license plate recognition method according to the embodiment of the present invention and to implement the respective modules in the license plate recognition apparatus according to the embodiment of the present invention. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a portable compact disc read only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.
In one embodiment, the computer program instructions, when executed by a computer or processor, cause the computer or processor to perform the steps of:
acquiring a license plate image to be recognized;
carrying out character recognition on the license plate image to be recognized to obtain a primary recognition result of characters in the license plate; and
and determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result.
Illustratively, the computer program instructions, when executed by a computer or processor, cause the computer or processor to further perform the steps of: and updating the license plate prior information according to the preliminary identification result.
Illustratively, the license plate prior information is obtained by counting probability distribution of characters representing a vehicle attribution in a license plate image.
Illustratively, the computer program instructions, when executed by a computer or processor, cause the computer or processor to select a character with the highest confidence level from the preliminary recognition result as a preliminary recognition result character.
Illustratively, the computer program instructions, when executed by a computer or processor, cause the computer or processor to update the license plate priors according to the preliminary identification result, including:
determining whether the confidence of the initial recognition result character is higher than a first threshold value; and
and updating the license plate prior information by using the initial recognition result characters under the condition that the confidence degree of the initial recognition result characters is higher than the first threshold value.
Illustratively, the computer program instructions, when executed by a computer or processor, cause the computer or processor to perform the step of determining a final recognition result of the character based on the license plate prior information and the preliminary recognition result further comprises the steps of:
determining whether the confidence of the initial recognition result character is lower than a second threshold; and
and determining the final recognition result based on the license plate prior information and the preliminary recognition result when the confidence coefficient of the characters of the preliminary recognition result is lower than the second threshold value.
Illustratively, the computer program instructions, when executed by a computer or processor, cause the computer or processor to further perform the steps of: and receiving a parameter beta for controlling the action degree of the license plate prior information.
As mentioned above, the preliminary recognition result may include a set of initial characters of the character and a probability distribution (p) corresponding to the set of initial characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and is 0<i<n +1, n is the number of elements of the initial character set.
For example, in the step of determining the final recognition result of the character based on the license plate prior information and the preliminary recognition result, when the computer program instructions are executed by the computer or the processor, the index number C of the final recognition result of the character in the license plate in the preliminary recognition character set may be determined according to the following formula, and then the final recognition result may be determined in the preliminary recognition character set of the character according to the index number C.
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )。
Where argmax () represents a function that returns the index of the maximum argument. q. q.s i And expressing the probability corresponding to the ith initial character in the initial character set obtained according to the license plate prior information.
The modules in the license plate recognition system according to the embodiment of the present invention may be implemented by a processor of an electronic device that performs license plate recognition according to the embodiment of the present invention running computer program instructions stored in a memory, or may be implemented by a computer running computer instructions stored in a computer-readable storage medium of a computer program product according to the embodiment of the present invention.
According to the license plate recognition method, the license plate recognition device, the license plate recognition system and the storage medium, license plate prior information is introduced to participate in license plate determination, and even if the quality of an image to be recognized is poor, an ideal recognition result can be obtained based on the license plate prior information, so that the requirement on the image quality is reduced, and the license plate recognition precision is remarkably improved. The method has very important value for application scenes with poor quality of shot images under poor weather conditions (such as rainy and snowy days, foggy days or sand-dust days) or poor illumination (such as evening and dark night).
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the foregoing illustrative embodiments are merely exemplary and are not intended to limit the scope of the invention thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the scope or spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as set forth in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another device, or some features may be omitted, or not executed.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the method of the present invention should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where such features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Moreover, those skilled in the art will appreciate that although some embodiments described herein include some features included in other embodiments, not others, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some of the modules in a license plate recognition apparatus according to embodiments of the present invention. The present invention may also be embodied as apparatus programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the purpose of describing the embodiments of the present invention or the description thereof, and the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present invention, and shall cover the scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A license plate recognition method includes:
acquiring a license plate image to be recognized;
carrying out character recognition on the license plate image to be recognized to obtain a primary recognition result of the characters;
receiving a parameter for controlling the action degree of license plate prior information, wherein the license plate prior information is used for correcting the preliminary identification result; and
determining a final recognition result of the characters based on the license plate prior information, the parameters and the preliminary recognition result;
wherein the method further comprises:
selecting the character with the maximum confidence coefficient from the preliminary recognition result as a preliminary recognition result character;
determining whether a confidence of the initial recognition result character is higher than a first threshold; and
and updating the license plate prior information by using the initial recognition result characters under the condition that the confidence coefficient of the initial recognition result characters is higher than the first threshold value.
2. The method of claim 1, wherein the method further comprises:
selecting the character with the maximum confidence coefficient from the preliminary recognition result as a preliminary recognition result character;
the determining a final recognition result of the characters based on the license plate prior information, the parameters and the preliminary recognition result comprises:
determining whether the confidence of the initial recognition result character is lower than a second threshold; and
and determining the final recognition result based on the license plate prior information, the parameter and the preliminary recognition result when the confidence coefficient of the characters of the preliminary recognition result is lower than the second threshold value.
3. The method according to claim 1, wherein the preliminary recognition result comprises a set of first recognized characters of the character and a probability distribution (p) corresponding to the set of first recognized characters 1 ,p 2 ,……p i ……p n ) Wherein p is i Representing the confidence coefficient of the ith initial character in the initial character set, i belongs to N and is 0<i<n +1, n is the number of elements of the initial character set,
the determining a final recognition result of the character based on the license plate prior information, the parameter and the preliminary recognition result includes:
determining the index number C of the final recognition result of the character in the initial character set according to the following formula:
C＝argmax(βp 1 +(1-β)q 1 ,βp 2 +(1-β)q 2 ,……βp i +(1-β)q i ,……βp n +(1-β)q n )，
wherein β represents the parameter for controlling the degree of action of the license plate prior information, q i Representing the probability corresponding to the ith initial character in the initial character set obtained according to the license plate prior information;
and determining the final recognition result in the initial character set according to the index number C.
4. The method of any of claims 1 to 3, wherein the method further comprises: and obtaining the license plate prior information by counting the probability distribution of characters representing the vehicle attribution in the license plate image.
5. A license plate recognition device comprising:
the acquisition module is used for acquiring a license plate image to be recognized;
the recognition module is used for carrying out character recognition on the license plate image to be recognized so as to obtain a primary recognition result of the characters;
the receiving module is used for receiving parameters for controlling the action degree of license plate prior information, wherein the license plate prior information is used for correcting the preliminary recognition result;
the determining module is used for determining a final recognition result of the characters based on the license plate prior information, the parameters and the preliminary recognition result;
the selection module is used for selecting the character with the maximum confidence coefficient from the preliminary recognition result as a preliminary recognition result character;
the judging module is used for determining whether the confidence coefficient of the initial recognition result character is higher than a first threshold value; and
and the updating module is used for updating the license plate prior information by using the initial recognition result characters under the condition that the confidence coefficient of the initial recognition result characters is higher than the first threshold value.
6. A license plate recognition system comprising a processor and a memory, wherein the memory has stored therein computer program instructions for execution by the processor to perform the license plate recognition method of any of claims 1-4.
7. A storage medium on which program instructions are stored, which program instructions are adapted, when executed, to perform a license plate recognition method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810472844.4A CN108875746B (en) | 2018-05-17 | 2018-05-17 | License plate recognition method, device and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810472844.4A CN108875746B (en) | 2018-05-17 | 2018-05-17 | License plate recognition method, device and system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108875746A CN108875746A (en) | 2018-11-23 |
| CN108875746B true CN108875746B (en) | 2023-02-17 |
Family
ID=64334136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810472844.4A Active CN108875746B (en) | 2018-05-17 | 2018-05-17 | License plate recognition method, device and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875746B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109858339B (en) * | 2018-12-22 | 2023-06-09 | 深圳市珍爱捷云信息技术有限公司 | Information verification method, information verification device, computer equipment and computer readable storage medium |
| CN112581749B (en) * | 2019-09-12 | 2023-06-13 | 阿里巴巴集团控股有限公司 | Method, system, device and electronic equipment for obtaining vehicle resource occupation information |
| CN112926560A (en) * | 2019-12-05 | 2021-06-08 | 浙江宇视科技有限公司 | License plate recognition method, device, equipment and storage medium |
| CN111860512B (en) * | 2020-02-25 | 2023-12-05 | 北京嘀嘀无限科技发展有限公司 | Vehicle identification method, device, electronic equipment and computer readable storage medium |
| CN113077018A (en) * | 2021-06-07 | 2021-07-06 | 浙江大华技术股份有限公司 | Target object identification method and device, storage medium and electronic device |
| CN113343985B (en) * | 2021-06-28 | 2023-04-18 | 展讯通信（上海）有限公司 | License plate recognition method and device |
| CN114663878B (en) * | 2022-05-25 | 2022-09-16 | 成都飞机工业（集团）有限责任公司 | Finished product software version checking method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298696A (en) * | 2010-06-28 | 2011-12-28 | 方正国际软件(北京)有限公司 | Character recognition method and system |
| CN102509112A (en) * | 2011-11-02 | 2012-06-20 | 珠海逸迩科技有限公司 | Number plate identification method and identification system thereof |
| CN103390173A (en) * | 2013-07-24 | 2013-11-13 | 佳都新太科技股份有限公司 | Plate number character vote algorithm based on SVM (support vector machine) confidence |
| CN103413440A (en) * | 2013-04-11 | 2013-11-27 | 江苏省邮电规划设计院有限责任公司 | Fake-licensed vehicle identification method based on smart city data base and identification rule base |
| CN106295645A (en) * | 2016-08-17 | 2017-01-04 | 东方网力科技股份有限公司 | A kind of license plate character recognition method and device |
| CN106845478A (en) * | 2016-12-30 | 2017-06-13 | 同观科技（深圳）有限公司 | The secondary licence plate recognition method and device of a kind of character confidence level |
| CN107195069A (en) * | 2017-06-28 | 2017-09-22 | 浙江大学 | A kind of RMB crown word number automatic identifying method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006059246A2 (en) * | 2004-11-08 | 2006-06-08 | Dspv, Ltd. | System and method of enabling a cellular/wireless device with imaging capabilities to decode printed alphanumeric characters |
| US8781172B2 (en) * | 2012-03-30 | 2014-07-15 | Xerox Corporation | Methods and systems for enhancing the performance of automated license plate recognition applications utilizing multiple results |
| CN106650721B (en) * | 2016-12-28 | 2019-08-13 | 吴晓军 | A kind of industrial character identifying method based on convolutional neural networks |
| CN106980854A (en) * | 2017-03-29 | 2017-07-25 | 珠海习悦信息技术有限公司 | Number-plate number recognition methods, device, storage medium and processor |
-
2018
- 2018-05-17 CN CN201810472844.4A patent/CN108875746B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298696A (en) * | 2010-06-28 | 2011-12-28 | 方正国际软件(北京)有限公司 | Character recognition method and system |
| CN102509112A (en) * | 2011-11-02 | 2012-06-20 | 珠海逸迩科技有限公司 | Number plate identification method and identification system thereof |
| CN103413440A (en) * | 2013-04-11 | 2013-11-27 | 江苏省邮电规划设计院有限责任公司 | Fake-licensed vehicle identification method based on smart city data base and identification rule base |
| CN103390173A (en) * | 2013-07-24 | 2013-11-13 | 佳都新太科技股份有限公司 | Plate number character vote algorithm based on SVM (support vector machine) confidence |
| CN106295645A (en) * | 2016-08-17 | 2017-01-04 | 东方网力科技股份有限公司 | A kind of license plate character recognition method and device |
| CN106845478A (en) * | 2016-12-30 | 2017-06-13 | 同观科技（深圳）有限公司 | The secondary licence plate recognition method and device of a kind of character confidence level |
| CN107195069A (en) * | 2017-06-28 | 2017-09-22 | 浙江大学 | A kind of RMB crown word number automatic identifying method |
Non-Patent Citations (4)
| Title |
|---|
| Development of Intelligent Transportation System for Philippine License Plate Recognition;John Paolo D. Dalida 等;《 2016 IEEE Region 10 Conference (TENCON)》;20170209;第3762-3766页 * |
| 一种汽车牌照字符分割的新方法;齐林、张向东;《仪器仪表用户》;20080408;第15卷(第2期);第92-94页 * |
| 基于与或图的车牌检测与识别;聂潇寒;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20120715;第I138-1678页正文第40页最后1段、41页第1段和最后1段、42页第1段 * |
| 聂潇寒.基于与或图的车牌检测与识别.《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》.2012, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108875746A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875746B (en) | License plate recognition method, device and system and storage medium | |
| CN106997466B (en) | Method and device for detecting road | |
| CN110705583B (en) | Cell detection model training method, device, computer equipment and storage medium | |
| CN108268867B (en) | License plate positioning method and device | |
| CN111428875A (en) | Image recognition method and device and corresponding model training method and device | |
| CN106845352B (en) | Pedestrian detection method and device | |
| CN106202086B (en) | Picture processing and obtaining method, device and system | |
| CN116403094B (en) | Embedded image recognition method and system | |
| CN114332513B (en) | New energy automobile abnormal parking amplification data detection method for smart city | |
| WO2020258077A1 (en) | Pedestrian detection method and device | |
| CN110443350B (en) | Model quality detection method, device, terminal and medium based on data analysis | |
| CN114038004A (en) | Certificate information extraction method, device, equipment and storage medium | |
| CN111860496A (en) | License plate recognition method, device, equipment and computer readable storage medium | |
| CN112668640A (en) | Text image quality evaluation method, device, equipment and medium | |
| CN110119736B (en) | License plate position identification method and device and electronic equipment | |
| CN110414544B (en) | Target state classification method, device and system | |
| CN115083008A (en) | Moving object detection method, device, equipment and storage medium | |
| CN111178347B (en) | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image | |
| CN110084157B (en) | Data processing method and device for image re-recognition | |
| CN115984786A (en) | Vehicle damage detection method and device, terminal and storage medium | |
| CN115761698A (en) | Target detection method, device, equipment and storage medium | |
| CN114663731A (en) | Training method and system of license plate detection model, and license plate detection method and system | |
| CN112132216B (en) | Vehicle type recognition method and device, electronic equipment and storage medium | |
| CN113869317A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN114330542A (en) | Sample mining method and device based on target detection and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |