CN113392839A - Method and device for recognizing license plate of non-motor vehicle, computer equipment and storage medium - Google Patents
Method and device for recognizing license plate of non-motor vehicle, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113392839A CN113392839A CN202110540159.2A CN202110540159A CN113392839A CN 113392839 A CN113392839 A CN 113392839A CN 202110540159 A CN202110540159 A CN 202110540159A CN 113392839 A CN113392839 A CN 113392839A
- Authority
- CN
- China
- Prior art keywords
- license plate
- character
- image
- area
- target
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Character Input (AREA)
Abstract
The application relates to a method, a device, a computer device and a storage medium for recognizing a license plate of a non-motor vehicle, which can increase the universality of the recognition of the license plate of the non-motor vehicle in different regions by acquiring the license plate image and the license plate type of a target license plate, segmenting the license plate image according to gray level jump information in the license plate image to obtain a character region of the license plate image, acquiring a first region and a second region which are positioned above and below the character region when the license plate type is a non-single-layer license plate, acquiring the character type of the first region, matching the registration information of the target license plate for the first region according to the license plate type of the target license plate under the condition that the character type of the first region is a configurable character, inputting a preset number recognition model into the second region to obtain the license plate number of the target license plate, and finally obtaining the recognition result of the target license plate according to the registration information and the license plate number, and the accuracy and efficiency of the license plate identification of the non-motor vehicle are improved.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a method and an apparatus for recognizing a license plate of a non-motor vehicle, a computer device, and a storage medium.
Background
With the development of deep learning in the traffic field, the application of deep learning in the non-motor vehicle management field has appeared. In the process of processing illegal snapshot of the non-motor vehicle by utilizing deep learning, the identification of the license plate information of the non-motor vehicle is very important. Because the license plates of the non-motor vehicles do not have a uniform license plate system, different regions have the license plates of the non-motor vehicles with specific systems, some license plates contain names of administrative regions or cities, and some license plates can add additional information which does not need to be identified, such as 'anti-theft record numbers'. The above information can increase the difficulty of identifying the license plate of the non-motor vehicle. Therefore, a general non-motor vehicle license plate recognition scheme which can be applied to different regions does not appear at present.
Aiming at the problem that the license plate recognition scheme of the non-motor vehicle in the related technology cannot be universally used in different regions, no effective solution is provided at present.
Disclosure of Invention
The embodiment provides a method and a device for recognizing a license plate of a non-motor vehicle, computer equipment and a storage medium, so as to solve the problem that the license plate recognition scheme of the non-motor vehicle in the related technology cannot be universally used in different regions.
In a first aspect, the present embodiment provides a method for recognizing a license plate of a non-motor vehicle, comprising the steps of:
acquiring a license plate image and a license plate type of a target license plate, wherein the license plate type comprises a single-layer license plate and a non-single-layer license plate;
segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
when the license plate type is a non-single-layer license plate, acquiring a first area above the character area and a second area below the character area; acquiring the character type of the first area, matching registration information of the target license plate for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is a configurable character, and inputting a preset number recognition model into the second area to obtain the license plate number of the target license plate;
and obtaining the identification result of the target license plate according to the registration information and the license plate number.
In some embodiments, the acquiring the license plate image and the license plate type of the target license plate includes the following steps:
acquiring a target non-motor vehicle image;
and inputting the target non-motor vehicle image into a preset detection model to obtain the license plate image and the license plate type.
In some embodiments, after obtaining a license plate image and a license plate type of a target license plate, before segmenting the license plate image according to gray jump information in the license plate image to obtain a character region of the license plate image, the method further includes the following steps:
carrying out graying processing on the license plate image;
inputting the grayed license plate image into a preset correction model, and correcting the form and angle of the license plate image.
In some embodiments, the segmenting the license plate image according to the gray jump information in the license plate image to obtain the character region of the license plate image includes the following steps:
acquiring a gray wave peak value, a gray wave valley value and a jumping frequency of a character area of the license plate image;
obtaining a gray adjacent combination according to the gray wave peak value, the gray wave valley value and the jumping times;
and determining a segmentation threshold value of the license plate image by utilizing the adjacent gray combination, and segmenting the license plate image according to the segmentation threshold value.
In some embodiments, the matching, according to the license plate system type of the target license plate, the registration information of the target license plate for the first region includes the following steps:
and if the license plate system type is one, acquiring preset license plate configuration information, and acquiring the registration information from the license plate configuration information.
In some embodiments, the matching, according to the license plate system type of the target license plate, the registration information of the target license plate for the first region further includes:
if the types of the license plate systems are more than one, inputting the first area into a first classification model with complete training, and determining the license plate system corresponding to the target license plate;
and acquiring preset license plate configuration information, and matching corresponding registration information for the first area according to the mapping relation between the license plate system and the license plate configuration information.
In some embodiments, when the license plate type is a non-single-layer license plate and the character category of the first area is recognizable characters, the method further includes the following steps:
and splicing the first area and the second area, and inputting a preset license plate recognition model to obtain a recognition result of the target license plate.
In some embodiments, when the license plate type is a single-layer license plate, the method comprises the following steps:
and inputting the character area into the number recognition model to obtain a recognition result of the target license plate.
In some embodiments, the obtaining the character category of the first region includes:
and inputting the first region into a second classification model which is completely trained to obtain the character classification of the first region.
In a second aspect, there is provided in this embodiment a license plate recognition apparatus for a non-motor vehicle, comprising: image acquisition module, segmentation module, identification module and result acquisition module, wherein:
the image acquisition module is used for acquiring a license plate image and a license plate type of a target license plate, wherein the license plate type comprises a single-layer license plate and a non-single-layer license plate;
the segmentation module is used for segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
the recognition module is used for acquiring a first area above and a second area below the character area when the license plate type is a non-single-layer license plate; under the condition that the character type of the first area is a configurable character, matching registration information for the first area according to the license plate system type of the target license plate, and inputting a preset number recognition model into the second area to obtain a license plate number;
and the result acquisition module is used for acquiring the identification result of the target license plate according to the registration information and the license plate number.
In a third aspect, there is provided in this embodiment a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of the first aspect when executing the computer program.
In a fourth aspect, in the present embodiment, a storage medium is provided, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method according to the first aspect.
The non-motor vehicle license plate recognition method, the device, the computer equipment and the storage medium acquire the license plate image and the license plate type of the target license plate, divide the license plate image according to the gray jump information in the license plate image to obtain the character area of the license plate image, acquire the first area of the character area positioned above and the second area positioned below when the license plate type is a non-single-layer license plate, acquire the character type of the first area, match the registration information of the target license plate for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is a configurable character, input the preset number recognition model into the second area to obtain the license plate number of the target license plate, and finally obtain the recognition result of the target license plate according to the registration information and the license plate number, thereby increasing the universality of the non-motor vehicle license plate recognition in different areas, and the accuracy and efficiency of the license plate identification of the non-motor vehicle are improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a diagram illustrating an application scenario of a license plate recognition method for a non-motor vehicle according to an embodiment of the present application;
FIG. 2 is a first flowchart of a method for identifying a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 3a is a schematic illustration of a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 3b is a schematic illustration of another license plate for a non-motor vehicle according to an embodiment of the present application;
FIG. 3c is a schematic illustration of a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 4a is a schematic illustration of a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 4b is a schematic illustration of a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 4c is a schematic illustration of a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 5 is a flow chart of a method for identifying a license plate of a non-motor vehicle according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a license plate recognition device for a non-motor vehicle according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.
Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of this application do not denote a limitation of quantity, either in the singular or the plural. The terms "comprises," "comprising," "has," "having," and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference throughout this application to "connected," "coupled," and the like is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.
Fig. 1 is a diagram illustrating an application scenario of the license plate recognition method for a non-motor vehicle according to an embodiment. As shown in fig. 1, both the server 101 and the monitoring terminal 102 may perform data transmission via a network. The monitoring terminal 102 is configured to obtain image information of the non-motor vehicle and transmit the image information to the server 101. After the server 101 receives the image information of the non-motor vehicle, a license plate image and a license plate type of a target license plate are obtained from the image information of the non-motor vehicle, the license plate image is segmented according to the gray level jump information in the license plate image to obtain a character area of the license plate image, and finally the license plate of the non-motor vehicle is identified according to the character area, so that the license plate information of the non-motor vehicle is obtained. The server 101 may be implemented by an independent server or a server cluster composed of a plurality of servers, and the monitoring terminal 102 may be any kind of camera.
Fig. 2 is a first flowchart of a remote access method according to this embodiment, and as shown in fig. 2, the process includes the following steps:
step S210, obtaining a license plate image and license plate types of a target license plate, wherein the license plate types comprise a single-layer license plate and a non-single-layer license plate.
Due to the diversity of the license plate systems of the non-motor vehicles, the same license plate identification scheme of the non-motor vehicles cannot be shared. When the license plate of the non-motor vehicle is identified, the license plate number of the license plate of the non-motor vehicle is obtained, and other license plate information of the license plate, such as the region to which the license plate belongs, can be further obtained by utilizing other character information on the license plate, so that the identification of the license plate of the non-motor vehicle is perfected. Therefore, the non-motor vehicle license plate can be classified according to the license plate content format in the target license plate, and a corresponding license plate recognition scheme is selected for the non-motor vehicle license plate according to different license plate types.
Specifically, the license plate image may be obtained by performing image processing on the target non-motor vehicle image after the target non-motor vehicle image is obtained, or may be directly provided by other processing devices. When the target non-motor vehicle image is processed, the non-motor vehicle license plate classification model can be used for analyzing the coordinates and the types of the license plates of the non-motor vehicles. And acquiring a license plate area from the target non-motor vehicle image through the license plate coordinate, and determining that the non-motor vehicle license plate belongs to a single-layer license plate or a non-single-layer license plate through the license plate type. The single-layer license plate is a license plate containing single-layer characters, the non-single-layer license plate is a license plate containing multi-layer characters, and the non-motor vehicle license plate detection model can be any one detection model of an SSD (Single Shot MultiBox Detector), a YOLO (You Only Look one) model and a facerCNN (face registers with CNN features).
Further, a license plate image and a license plate type of the target license plate are obtained through the non-motor vehicle license plate detection model and are used for providing parameters for subsequent license plate information identification. Specifically, the single-layer license plate may be a license plate that is recognized to contain no text but only a license plate number. The non-single-layer license plate can be a license plate containing characters and a license plate number, wherein the characters in the non-single-layer license plate can comprise Chinese character and letter information of provinces, cities and administrative districts to which the non-motor belongs, and can also comprise license plate additional information which does not need to be identified, such as 'anti-theft record number' and 'XX electric bicycle'. After the license plate type of the target license plate is obtained, a corresponding recognition scheme can be selected for the target license plate according to the license plate type so as to obtain license plate information. For example, for a single-layer license plate, the character region of the license plate can be directly recognized, while for a non-single-layer license plate, the character part and the number part of the license plate in the license plate need to be recognized respectively.
And step S220, segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character region of the license plate image.
In order to improve the robustness of the recognition of the license plate of the non-motor vehicle, the acquired license plate image of the target license plate is subjected to image preprocessing, so that the interference of noise is reduced. Therefore, the acquired target license plate can be an image subjected to graying processing. In the license plate image after the graying processing, the gray level change exists in the character region and the non-character region, so that the gray level jump information of the license plate image can be obtained, and the license plate image is segmented by utilizing the gray level jump information, so that the character region of the license plate image is obtained. Specifically, the grayscale jump information may include a peak value and a trough value of a pixel grayscale value in the license plate image, and a jump frequency between the peak value and the trough value, and the grayscale jump information may determine a segmentation threshold of the license plate image, so as to obtain a character region of the license plate image by using the segmentation threshold.
Further, the segmentation threshold may be a gray value, and the single-layer license plate and the non-single-layer license plate may be segmented by using the segmentation threshold to obtain the character region. When the single-layer license plate is segmented, projection segmentation and connected domain segmentation are carried out on the single-layer license plate by utilizing a segmentation threshold value, so that a character region is obtained. And obtaining the character area after obtaining the boundary of the character area. In addition, when a non-single-layer license plate is divided, a lower layer region of the non-single-layer license plate, which includes a license plate number, and an upper layer region of other character information may be divided respectively. Similarly, projection segmentation and connected domain segmentation are carried out by utilizing the segmentation threshold value to obtain character boundaries of the lower layer region of the non-single-layer license plate and character regions of the upper layer region of the non-single-layer license plate
By acquiring the character area of the license plate image, the efficiency of subsequently acquiring the license plate information of the non-motor vehicle can be improved. The character areas of the non-single-layer license plate are segmented, so that the license plate number areas and other character information in the non-single-layer license plate can be conveniently and respectively identified, and the accuracy of license plate identification is improved.
Step S230, when the license plate type is a non-single-layer license plate, acquiring a first area of a character area positioned above and a second area positioned below; and acquiring the character type of the first area, matching the registration information of the target license plate for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is the configurable character, and inputting a preset number recognition model into the second area to obtain the license plate number of the target license plate.
The first area is other text information, and specifically can be registration information of a license plate. The second area is the license plate number. The registration information of the license plate is often characters, the license plate number is a combination of numbers and letters, and the font formats in the two areas are different, so that the two areas can be identified differently.
Specifically, for the second area containing the license plate number information, the second area can be directly identified by using a preset number identification model. The number recognition model may be any text recognition model, such as a crnn (conditional recovery Neural network) recognition model. Additionally, for the first region containing the license plate registration information, after the character type of the first region is acquired, corresponding processing may be performed according to the character type of the first region. The character category of the first area can comprise recognizable characters, configurable characters and other characters. Specifically, the recognizable character may be registration information composed of a short form and a letter, as shown in fig. 3a, since the information contains a small amount of text, the information can be attributed to the recognizable character and recognized directly by using a recognition model. The configurable character may be registration information composed of place names, as shown in fig. 3b, the registration information includes full text information, and text fonts and spaces in different regions are different, so that the configurable character is not suitable for directly identifying the character, and the configurable character can be configured by means of external configuration information. Additionally, fig. 3c shows that the character type is a non-single-layer license plate with other characters, as shown in fig. 3c, the other characters are characters that do not need to be recognized in the license plate, that is, the characters do not represent the identity information of the non-motor vehicle, and therefore the characters do not need to be recognized.
Furthermore, the target license plate is designed according to a certain license plate system, and the registration information contained in the first area in the target license plate can be determined according to the license plate system. Therefore, when the character type of the first area is the configurable character, the license plate system type predetermined by the target license plate can be obtained. The license plate system type can be the license plate system type of the non-motor vehicle in the region to which the non-motor vehicle picture belongs. For example, when the non-motor vehicle in the area a is illegally captured, the license plate system type of the non-motor vehicle in the area a can be correspondingly acquired, so that the registration information of the corresponding target license plate is matched for the first area according to the license plate system type.
The registration information of the target license plate is matched with the first region by using the license plate system type as the first region, a character recognition mode for the first region is replaced, training of a recognition model and updating of a character library do not need to be carried out on characters in the first region, and meanwhile, the recognition error caused by pixel problems can be reduced, so that the accuracy and the efficiency of obtaining the license plate registration information can be improved.
And step S240, obtaining the identification result of the target license plate according to the registration information and the license plate number.
In the steps S210 to S240, by acquiring the license plate image and the license plate type of the target license plate, segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image, and when the license plate type is a non-single-layer license plate, a first area of the character area positioned above and a second area positioned below are obtained, matching the registration information of the target license plate for the first area according to the license plate system type of the target license plate under the condition that the character type of the first area is the configurable character, inputting the second area into a preset number recognition model to obtain the license plate number of the target license plate, finally obtaining the recognition result of the target license plate according to the registration information and the license plate number, therefore, the universality of the non-motor vehicle license plate recognition in different areas can be improved, and the accuracy and the efficiency of the non-motor vehicle license plate recognition are improved.
Further, based on the step S210, acquiring a license plate image and a license plate type of the target license plate includes the following steps:
and step S211, acquiring a target non-motor vehicle image.
Specifically, the target non-motor vehicle image can be obtained by video capture by a monitoring device arranged near a non-motor vehicle lane.
Step S212, inputting the target non-motor vehicle image into a preset detection model to obtain a license plate image and a license plate type.
For the target non-motor vehicle image, the license plate image contains the identity information of the target non-motor vehicle, and the license plate image usually occupies only a part of the area in the target non-motor vehicle image. Therefore, after the target non-motor vehicle image is acquired, processing is required to further acquire the license plate image of the target non-motor vehicle. Specifically, the detection model may be any image detection model, such as an SSD model, a YOLO model, and a fasterccnn model. The coordinates of the license plate image in the target non-motor vehicle image can be obtained through the detection model, and the license plate type can also be obtained.
Further, in an embodiment, after acquiring the license plate image and the license plate type of the target license plate, before segmenting the license plate image according to the gray jump information in the license plate image to obtain the character region of the license plate image, the method includes the following steps:
step S213, graying the license plate image.
And step S214, inputting the grayed license plate image into a preset correction model, and correcting the form and angle of the license plate image.
Due to the moving state of the non-motor vehicle, the license plate may have a plurality of different forms, such as a certain angle of inclination, in the non-motor vehicle image captured by the monitoring device. Therefore, in order to improve the accuracy and efficiency of the subsequent recognition of the license plate image, the license plate image can be corrected by using the correction model before the recognition. The correction model may be an STN model based on deep learning, or may be a processing method for problems such as image distortion and angular tilt in the field of image processing, and is not limited herein.
Additionally, in an embodiment, based on the step S220, the license plate image is segmented according to the grayscale jump information in the license plate image to obtain the character region end of the license plate image, including the following steps:
step S221, obtaining the gray wave peak value, the gray wave valley value and the jumping frequency of the character area of the license plate image.
And the license plate image can be cut in advance based on prior knowledge before the gray wave peak value, the gray wave valley value and the jumping times are obtained. For example, in the case of a non-single-layer license plate, since the upper region often contains only text characters and the lower region contains a license plate number, when the license plate number of the lower region is divided, the corrected license plate image may be cropped according to 1/2 corresponding to the height of the license plate image, and the cropped lower half image may be selected and processed.
In the license plate image after the graying processing, the character region and the background region have obvious difference in gray value, so that the gray jump information in the license plate image can be used for determining the segmentation threshold. Specifically, the gray level peak value may be a peak value generated when the gray level of the middle row of pixels in the clipping region jumps, and the gray level valley value may be a valley value generated when the gray level of the middle row of pixels in the clipping region jumps. The peak and trough values may be recorded as a set of arrays. The number of the gray level jumps can be determined by a preset jump threshold, that is, when the difference between the peak value and the valley value in a certain section of curve is higher than the preset jump threshold, the gray level change from the peak value to the valley value in the section of curve is recorded as one jump, otherwise, the section of curve is considered to have no jump. In addition, a threshold value of the number of hops may also be preset, and when the number of hops calculated under the preset threshold value is smaller than the threshold value of the number of hops, a threshold value of hops is additionally set to determine the peak value, the trough value, and the number of hops of the group of waves.
Further, a sequence of gray scale differences between the peak value and the trough value, such as a descending order of gray scale differences, below the preset transition threshold may also be recorded. And acquiring the minimum gray difference value in the sequence, such as the last bit in descending order, and updating the peak value and the trough value of the group of wave peaks according to the magnitude relation between the jump threshold and the minimum gray difference value. For example, when the transition threshold is greater than 3/4 times of the minimum gray scale difference value, the subsequent division threshold is calculated by using the peak value, the trough value and the transition number determined below the transition threshold. Otherwise, 3/4 times of the minimum gray difference value is used as a new jump threshold value, and the set of peak values and the set of valley values are updated by using the new jump threshold value.
For example, under the preset transition threshold T, a set of wave troughs is determined as an array of grada, a set of wave peaks is determined as an array of gradb, and the number of transitions is JmpNum. The pixel X-axis coordinate corresponding to each trough forms an array idxA, and the pixel X-axis coordinate corresponding to each peak forms an array idxB. The sequence obtained after descending order arrangement of the difference value between the wave crest and the wave trough is an array Maxdiff, if the length of the array is 7, the last bit is the array Maxdiff [6 ]. If T _ new is smaller than T, the calculation of the subsequent segmentation threshold is continued, otherwise, the T _ new is used as a new transition threshold T, and the set of peak value, valley value and transition number is updated until the current T _ new is smaller than the current T.
And step S222, obtaining the adjacent gray combination according to the peak value of the gray wave, the valley value of the gray wave and the jumping times.
Specifically, a current jump index is preset to be JmpIdx, and the initial value of the current jump index is 0, that is, JmpIdx is 0. And according to the jumping times JmpNum, a jumping index k is predetermined. For example, when the number of transitions JmpNum is 10, k is set to 4. And acquiring an array diffA ═ grayA [ JmpIdx ] -grayA [ k ] | formed by the difference value between the trough and the trough between the two jumps. And acquiring an array diffB ═ grayB [ JmpIdx ] -grayB [ k ] | formed by the difference value between the wave crest and the wave crest between the two jumps. And acquiring a difference value cHeight between the current jump peak and the current jump trough, namely grayB [ JmpIdx ] -grayA [ JmpIdx ]. And acquiring the difference value nHeight between the next jump peak and the trough, grayB [ k ] -grayA [ k ], and the difference value diffIdxB, idxB [ k ] -idxB [ JmIdx ] of the coordinates between the two peaks. Taking the larger of diffA and diffB as diffMax, taking the smaller of cpheight and nhight as HeightMin, setting a fixed comparison threshold, for example, the comparison threshold is 50, if diffMax 4< HeightMin and diffIdxB < > 50, determining the index of the adjacent combination of gray scales corresponding to the current jump index as nextFriend ═ JmpIdx + k, that is, when the current jump index is 0, the index of the adjacent combination of gray scales is 4. Then, let k be k-1, if diffMax 4< (HeightMin) and diffIdxB < (50) still holds at this time, update the nextFriend until k < 1. And after determining the index of the corresponding gray-scale adjacent combination when the JmpIdx is 0, making the JmpIdx equal to JmpIdx +1, and calculating the index of the corresponding gray-scale adjacent combination of the JmpIdx at the moment by using the same steps until the JmpIdx is equal to JmpNum.
After a group of current jump indexes JmpIdx and corresponding gray adjacent combination indexes nextFriend are obtained, the corresponding combination numbers slopeCnt of the current jump indexes JmpIdx from 0 to the jump times JmpNum are respectively calculated. Table 1 shows a set of corresponding relationships between JmpIdx and nextFriend, and the example in table 1 illustrates how to determine the number slopeCnt of combinations corresponding to each JmpIdx.
TABLE 1
| JmpIdx | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| nextFriend | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 0 |
As shown in table 1, first, the initial value of slopeCnt corresponding to each JmpIdx is set to 0. When the JmpIdx is 0, it is determined whether the nextFriend corresponding to this time is 0, and if not, the slopeCnt is made equal to slopeCnt + 1. Whether nextfield corresponding to the nextfield is 0 or not is continuously judged, namely when the JmpIdx is 0, the nextfield corresponding to the nextfield is 1, slopeCnt is 0+1, and when the nextfield is 1 and the nextfield corresponding to the nextfield is 2, the slopeCnt is 0+1+1, and the steps are sequentially accumulated until the nextfield corresponding to the nextfield is 0. Therefore, as can be determined from table 1, when JmpIdx is 0, its slopeCnt is 9. Finally, the corresponding relationship between all current jump indexes and the number of combinations can be obtained based on table 1, as shown in table 2. And finding a group of combinations with the maximum number of combinations in the corresponding relation, namely JmpIdx is 0 and slopeCnt is 9.
TABLE 2
| JmpIdx | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| slopeCnt | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 |
The value 9 with the maximum number of combinations at this time is used as the new hop number Num of the combination. And judging whether the new jump number Num is greater than a preset minimum jump frame number N, if so, calculating the segmentation threshold value at the moment according to a formula (1). Otherwise, let N be N-1 and recalculate the new segmentation threshold according to the above procedure.
And step S223, determining a segmentation threshold value of the license plate image by utilizing the adjacent combination of the gray levels, and segmenting the license plate image according to the segmentation threshold value.
Through the steps S221 to S223, the accuracy of segmentation can be improved under the condition that the license plate is unclear and the contrast is low due to interference factors, such as rain or muddy water shielding, existing in the target license plate, so that the robustness of character region segmentation is increased.
Additionally, in an embodiment, based on the step S230, matching the registration information of the target license plate for the first region according to the license plate system type of the target license plate includes the following steps:
step S231, if the type of the license plate system is one, acquiring preset license plate configuration information, and obtaining registration information from the license plate configuration information.
For example, when the license plate system of the target non-motor vehicle picture source area is one, for example, registration information of license plates other than the license plate number in all the non-motor vehicle license plates of the area a is "area a", the license plate configuration information preset in the area a, that is, a character string with the content of "area a" is directly acquired, and the content of the character string is used as the registration information corresponding to the first area of the target license plate.
Additionally, in an embodiment, based on the step S230, matching the registration information of the target license plate for the first area according to the license plate system type of the target license plate, further includes the following steps:
step S232, if the types of the license plate systems are more than one, inputting the first area into a first classification model with complete training, and determining the license plate system corresponding to the target license plate.
The license plate configuration information may be license plate systems configured correspondingly according to different regions, and includes registration information corresponding to various license plate systems in the region. When the types of the license plate systems are more than one, for example, three license plate systems with different character contents of a administrative district C, an administrative district D and an administrative district E exist in a city B. For example, the number plate of the non-motor vehicle in taizhou city includes a plurality of types, as shown in fig. 4a, 4b, and 4c, and the number plate system of the non-motor vehicle in taizhou city includes three types of greens, jiangjiang, and yuhuan, so that the number of types of the number plate system of the non-motor vehicle in the area can be set to three. When the type of the license plate system is more than one, inputting the first area into a first classification model, determining which of the three character contents the character content contained in the first area belongs to, and replacing direct recognition of the character content in the first area. The first classification model may be any classification model based on machine learning. Additionally, before the first classification model is used for classification, the first regions of a plurality of non-single-layer license plates can be used as a training set, and the first classification model is trained to obtain a first classification model with complete training.
Step S233, acquiring preset license plate configuration information, and matching corresponding registration information for the first area according to the mapping relation between the license plate system and the license plate configuration information.
And when the license plate system corresponding to the first area is determined, acquiring registration information corresponding to the license plate system from the pre-configured license plate configuration information.
In one embodiment, when the license plate type is a non-single-layer license plate and the character type of the first region is a recognizable character, the method further includes the following steps:
and S250, splicing the first area and the second area, and inputting a preset license plate recognition model to obtain a recognition result of the target license plate.
For example, if the character content of the first region is a combination of a short for a certain province and a letter of the city administration level, the character content can be directly recognized by a recognition model in an image processing field or a deep learning field, so that the first region and the second region containing the license plate number are spliced and then input into the license plate recognition model to determine the recognition result of the target license plate. Specifically, the license plate recognition model may be a pre-trained CRNN model.
In one embodiment, when the license plate type is a single-layer license plate, the method further comprises the following steps:
and step S260, inputting the character area into a number recognition model to obtain a recognition result of the target license plate.
Specifically, the number recognition model may be a pre-trained CRNN model.
In an embodiment, based on the step S230, the obtaining of the character type of the first area specifically includes the following steps:
and S231, inputting the first region into a second classification model with complete training to obtain the character classification of the first region.
In particular, due to the diversity of non-automotive license plates, the character classes of the first region may comprise a plurality of types for non-single-layer license plates. For example, the first region of the license plate of the non-motor vehicle in the first region is registration information consisting of the abbreviation and the letter of the province of the first region, and the information contains less text content, so that the identification of the detection model is facilitated, and the information can be classified into recognizable characters. The first region of the license plate of the non-motor vehicle in the second region is a full-text character region composed of the place names of the second region, and the condition that the recognition efficiency is low can be caused by inputting the characters into the detection model for character recognition, so that the characters can be configured by means of external configuration information. Additionally, other characters contained in the first region of a portion of the non-motor vehicle license plate that may not contain critical information for license plate registration are not recognized.
In order to determine the character class to which the first region belongs, detection may be performed using a second classification model. The second classification model may be any one of Alexnet, vggtet, Resnet, and the like, and is not limited in this embodiment.
Further, in one embodiment, as shown in fig. 5, a flowchart of a method for recognizing a license plate of a non-motor vehicle is provided, which includes the following steps:
and step S10, acquiring the non-motor vehicle picture.
And step S11, detecting the license plate of the non-motor vehicle by using the detection model to obtain the license plate image and the license plate type.
And step S12, correcting the license plate image.
And step S20, dividing character area according to the gray jump information.
Step S30, judging whether the license plate type is a single-layer license plate.
Step S31, if the license plate is a single-layer license plate, the texture boundary of the single-layer license plate is used for segmenting the character area.
In step S32, if the license plate is a non-single-layer license plate, a first region above the non-single-layer license plate and a second region below the non-single-layer license plate are respectively partitioned.
Step S321, the first area is sent to the second classification model, and the character type is judged.
In step S322, if the character type of the first area is an identifiable character of a combination of a province abbreviation and a letter, the first area and the second area are spliced.
In step S323, if the character type of the first area is other characters that do not need to be recognized, only the second area is selected.
In step S324, if the first area is a configurable character of a full text, the first area and the second area are selected respectively.
Step S325, judging whether the license plate system is one.
Step S3251, if the license plate system to which the target license plate belongs is one, acquiring registration information corresponding to the first area by using license plate configuration information.
Step S3252, if the number plate system to which the target number plate belongs is at least two, the first area is classified by using a first classification model, and the number plate system corresponding to the first area is matched with the registration information in the number plate configuration information.
In step S326, a second area is selected.
In step S40, the selected region is identified using the CRNN identification model.
The steps S210 to S260 are performed by processing the target non-motor vehicle image by using a preset detection model to obtain a license plate image and a license plate type, performing graying processing and correction processing on the license plate image to improve the accuracy of subsequent license plate image recognition, determining a grayscale neighboring combination according to a grayscale peak value, a grayscale valley value and a hopping number of the license plate image, determining a segmentation threshold of the license plate image by using the grayscale neighboring combination to improve the accuracy of segmentation of a character region in the license plate image, and reducing the influence of interference factors of the license plate image, determining registration information of a first region according to preset license plate configuration information when the license plate type is a non-single-layer license plate and the character type of the first region is a configurable character, and recognizing the spliced first region and a second region by using the license plate recognition model when the character type of the first region is a recognizable character, when the license plate type is a single-layer license plate, the number recognition model is used for recognizing the target license plate, the problems of low recognition model training efficiency and recognition accuracy caused by the fact that the target license plate contains more characters are solved, different processing modes can be selected according to different license plate types, and accordingly the universality of the non-motor vehicle license plate recognition in different regions is improved.
The embodiment also provides a license plate recognition device for a non-motor vehicle, which is used for realizing the above embodiments and preferred embodiments, and the description of the device is omitted. The terms "module," "unit," "subunit," and the like as used below may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 6 is a schematic structural diagram of a non-motor vehicle license plate recognition device 60 according to an embodiment of the present application, where as shown in fig. 6, the non-motor vehicle license plate recognition device 60 includes: an image acquisition module 62, a segmentation module 64, a recognition module 66, and a result acquisition module 68, wherein:
the image acquisition module 62 is configured to acquire a license plate image and a license plate type of a target license plate, where the license plate type includes a single-layer license plate and a non-single-layer license plate;
the segmentation module 64 is used for segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
the recognition module 66 is configured to, when the license plate type is a non-single-layer license plate, acquire a first region above the character region and a second region below the character region; acquiring the character type of the first area, matching registration information for the first area according to the license plate standard type of a target license plate under the condition that the character type of the first area is a configurable character, and inputting a preset number identification model into a second area to obtain a license plate number;
and the result acquisition module 68 is used for acquiring the identification result of the target license plate according to the registration information and the license plate number.
The above-mentioned license plate recognition device 60 for a non-motor vehicle obtains the license plate image and the license plate type of the target license plate, segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image, when the license plate type is a non-single-layer license plate, a first area of the character area positioned above and a second area positioned below are obtained, the character category of the first area is obtained, matching the registration information of the target license plate for the first area according to the license plate system type of the target license plate under the condition that the character type of the first area is the configurable character, inputting the second area into a preset number recognition model to obtain the license plate number of the target license plate, finally obtaining the recognition result of the target license plate according to the registration information and the license plate number, therefore, the universality of the non-motor vehicle license plate recognition in different areas can be improved, and the accuracy and the efficiency of the non-motor vehicle license plate recognition are improved.
In one embodiment, the image obtaining module 62 is further configured to obtain an image of the target non-motor vehicle, and input the image of the target non-motor vehicle into a preset detection model to obtain a license plate image and a license plate type.
In one embodiment, the non-motor vehicle license plate recognition device 60 further includes a correction module, and the correction module is configured to perform graying processing on the license plate image, input the grayed license plate image into a preset correction model, and correct the form and angle of the license plate image.
In one embodiment, the segmentation module 64 is further configured to obtain a gray peak value, a gray valley value, and a number of transitions of a character region of the license plate image, obtain a gray neighboring combination according to the gray peak value, the gray valley value, and the number of transitions, determine a segmentation threshold of the license plate image by using the gray neighboring combination, and segment the license plate image according to the segmentation threshold.
In one embodiment, the recognition module 66 is further configured to obtain preset license plate configuration information when the type of the license plate system is one, and obtain registration information from the license plate configuration information.
In one embodiment, the recognition module 66 is further configured to, when the type of the license plate system is greater than one, input the first region into a first classification model with complete training, determine a license plate system corresponding to the target license plate, acquire preset license plate configuration information, and match corresponding registration information for the first region according to a mapping relationship between the license plate system and the license plate configuration information.
In one embodiment, the recognition module 66 is further configured to splice the first region and the second region, and input the spliced first region and second region into a preset license plate recognition model, so as to obtain a recognition result of the target license plate.
In one embodiment, the recognition module 66 is further configured to input the character area into a number recognition model to obtain a recognition result of the target license plate.
In one embodiment, the recognition model 66 is further configured to input the first region into a second classification model that is well-trained, and obtain the character classification of the first region.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing a preset configuration information set. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize the non-motor vehicle license plate recognition method.
In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of identifying a license plate of a non-motor vehicle. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a license plate image and a license plate type of a target license plate, wherein the license plate type comprises a single-layer license plate and a non-single-layer license plate;
segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
when the license plate type is a non-single-layer license plate, acquiring a first area of a character area positioned above and a second area positioned below; acquiring the character type of the first area, matching registration information of a target license plate for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is a configurable character, and inputting a preset number recognition model into the second area to obtain the license plate number of the target license plate;
and obtaining the recognition result of the target license plate according to the registration information and the license plate number.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a target non-motor vehicle image;
and inputting the target non-motor vehicle image into a preset detection model to obtain a license plate image and a license plate type.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out graying processing on the license plate image;
inputting the grayed license plate image into a preset correction model, and correcting the form and angle of the license plate image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a gray wave peak value, a gray wave valley value and a jumping frequency of a character area of the license plate image;
obtaining adjacent gray combinations according to the gray wave peak value, the gray wave valley value and the jumping times;
and determining a segmentation threshold of the license plate image by utilizing the adjacent gray combination, and segmenting the license plate image according to the segmentation threshold.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and if the license plate system type is one, acquiring preset license plate configuration information and acquiring registration information from the license plate configuration information.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
if the type of the license plate system is more than one, inputting the first region into a first classification model with complete training, and determining the license plate system corresponding to the target license plate;
and acquiring preset license plate configuration information, and matching corresponding registration information for the first area according to the mapping relation between the license plate system and the license plate configuration information.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and splicing the first area and the second area, and inputting a preset license plate recognition model to obtain a recognition result of the target license plate.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and inputting the character area into a serial number recognition model to obtain a recognition result of the target license plate.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and inputting the first region into a second classification model which is completely trained to obtain the character classification of the first region.
The storage medium obtains the license plate image and the license plate type of the target license plate, segments the license plate image according to the gray jump information in the license plate image to obtain the character area of the license plate image, when the license plate type is a non-single-layer license plate, a first area of the character area positioned above and a second area positioned below are obtained, the character category of the first area is obtained, matching the registration information of the target license plate for the first area according to the license plate system type of the target license plate under the condition that the character type of the first area is the configurable character, inputting the second area into a preset number recognition model to obtain the license plate number of the target license plate, finally obtaining the recognition result of the target license plate according to the registration information and the license plate number, therefore, the universality of the non-motor vehicle license plate recognition in different areas can be improved, and the accuracy and the efficiency of the non-motor vehicle license plate recognition are improved.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly or implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (12)
1. A method for recognizing a license plate of a non-motor vehicle is characterized by comprising the following steps:
acquiring a license plate image and a license plate type of a target license plate, wherein the license plate type comprises a single-layer license plate and a non-single-layer license plate;
segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
when the license plate type is a non-single-layer license plate, acquiring a first area above the character area and a second area below the character area; acquiring the character type of the first area, matching registration information of the target license plate for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is a configurable character, and inputting a preset number recognition model into the second area to obtain the license plate number of the target license plate;
and obtaining the identification result of the target license plate according to the registration information and the license plate number.
2. The method of claim 1, wherein the obtaining of the license plate image and the license plate type of the target license plate comprises:
acquiring a target non-motor vehicle image;
and inputting the target non-motor vehicle image into a preset detection model to obtain the license plate image and the license plate type.
3. The method of claim 1, wherein after obtaining the license plate image and the license plate type of the target license plate, before segmenting the license plate image according to the gray jump information in the license plate image to obtain the character region of the license plate image, the method further comprises:
carrying out graying processing on the license plate image;
inputting the grayed license plate image into a preset correction model, and correcting the form and angle of the license plate image.
4. The method of claim 1, wherein the segmenting the license plate image according to the gray jump information in the license plate image to obtain the character region of the license plate image comprises:
acquiring a gray wave peak value, a gray wave valley value and a jumping frequency of a character area of the license plate image;
obtaining a gray adjacent combination according to the gray wave peak value, the gray wave valley value and the jumping times;
and determining a segmentation threshold value of the license plate image by utilizing the adjacent gray combination, and segmenting the license plate image according to the segmentation threshold value.
5. The method according to claim 1, wherein said matching registration information of the target license plate for the first region according to the license plate system type of the target license plate comprises:
and if the license plate system type is one, acquiring preset license plate configuration information, and acquiring the registration information from the license plate configuration information.
6. The method according to claim 1, wherein the matching of the registration information of the target license plate for the first region according to the license plate system type of the target license plate further comprises:
if the types of the license plate systems are more than one, inputting the first area into a first classification model with complete training, and determining the license plate system corresponding to the target license plate;
and acquiring preset license plate configuration information, and matching corresponding registration information for the first area according to the mapping relation between the license plate system and the license plate configuration information.
7. The method of claim 1, wherein when the license plate type is a non-single-layer license plate and the character class of the first region is an identifiable character, the method further comprises:
and splicing the first area and the second area, and inputting a preset license plate recognition model to obtain a recognition result of the target license plate.
8. The method of claim 1, wherein when the license plate type is a single-layer license plate, the method further comprises:
and inputting the character area into the number recognition model to obtain a recognition result of the target license plate.
9. The method of claim 1, wherein the obtaining the character classification of the first region comprises:
and inputting the first region into a second classification model which is completely trained to obtain the character classification of the first region.
10. A license plate recognition apparatus for a non-motor vehicle, comprising: image acquisition module, segmentation module, identification module and result acquisition module, wherein:
the image acquisition module is used for acquiring a license plate image and a license plate type of a target license plate, wherein the license plate type comprises a single-layer license plate and a non-single-layer license plate;
the segmentation module is used for segmenting the license plate image according to the gray level jump information in the license plate image to obtain a character area of the license plate image;
the recognition module is used for acquiring a first area above and a second area below the character area when the license plate type is a non-single-layer license plate; acquiring the character type of the first area, matching registration information for the first area according to the license plate standard type of the target license plate under the condition that the character type of the first area is a configurable character, and inputting a preset number recognition model into the second area to obtain a license plate number;
and the result acquisition module is used for acquiring the identification result of the target license plate according to the registration information and the license plate number.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 9 are implemented when the computer program is executed by the processor.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110540159.2A CN113392839B (en) | 2021-05-18 | 2021-05-18 | License plate recognition method and device for non-motor vehicle, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110540159.2A CN113392839B (en) | 2021-05-18 | 2021-05-18 | License plate recognition method and device for non-motor vehicle, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392839A true CN113392839A (en) | 2021-09-14 |
| CN113392839B CN113392839B (en) | 2023-07-28 |
Family
ID=77617200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110540159.2A Active CN113392839B (en) | 2021-05-18 | 2021-05-18 | License plate recognition method and device for non-motor vehicle, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392839B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114934467A (en) * | 2022-07-08 | 2022-08-23 | 江苏永达电力金具有限公司 | Parking space barrier gate control method, parking space barrier gate system and medium |
| CN115542362A (en) * | 2022-12-01 | 2022-12-30 | 成都信息工程大学 | High-precision space positioning method, system, equipment and medium for electric power operation site |
| WO2023169273A1 (en) * | 2022-03-11 | 2023-09-14 | 阿里巴巴（中国）有限公司 | Image recognition method and apparatus, device, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130294652A1 (en) * | 2012-05-04 | 2013-11-07 | Xerox Corporation | License plate character segmentation using likelihood maximization |
| CN106384113A (en) * | 2016-11-07 | 2017-02-08 | 湖南源信光电科技有限公司 | Odd-and-even-line license plate character dividing method based on projection and template matching |
| WO2018028306A1 (en) * | 2016-08-11 | 2018-02-15 | 杭州海康威视数字技术股份有限公司 | Method and device for recognizing license plate number |
-
2021
- 2021-05-18 CN CN202110540159.2A patent/CN113392839B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130294652A1 (en) * | 2012-05-04 | 2013-11-07 | Xerox Corporation | License plate character segmentation using likelihood maximization |
| WO2018028306A1 (en) * | 2016-08-11 | 2018-02-15 | 杭州海康威视数字技术股份有限公司 | Method and device for recognizing license plate number |
| CN106384113A (en) * | 2016-11-07 | 2017-02-08 | 湖南源信光电科技有限公司 | Odd-and-even-line license plate character dividing method based on projection and template matching |
Non-Patent Citations (2)
| Title |
|---|
| JINN-LI TAN；ET AL: "license plate localization based on edge-geometrical features using morphological approach", 2013 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING * |
| 马永杰，等: "基于自适应阈值投影的双行车牌分割方法", 计算机工程与科学 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023169273A1 (en) * | 2022-03-11 | 2023-09-14 | 阿里巴巴（中国）有限公司 | Image recognition method and apparatus, device, and storage medium |
| CN114934467A (en) * | 2022-07-08 | 2022-08-23 | 江苏永达电力金具有限公司 | Parking space barrier gate control method, parking space barrier gate system and medium |
| CN114934467B (en) * | 2022-07-08 | 2024-04-30 | 江苏永达电力金具有限公司 | Parking space barrier control method, parking space barrier system and medium |
| CN115542362A (en) * | 2022-12-01 | 2022-12-30 | 成都信息工程大学 | High-precision space positioning method, system, equipment and medium for electric power operation site |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392839B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392839A (en) | Method and device for recognizing license plate of non-motor vehicle, computer equipment and storage medium | |
| CN111027563B (en) | A text detection method, device and recognition system | |
| CN110866529B (en) | Character recognition method, device, electronic equipment and storage medium | |
| CN107944450B (en) | License plate recognition method and device | |
| CN110532866B (en) | Video data detection method, device, computer equipment and storage medium | |
| CN110751024B (en) | User identity recognition method and device based on handwritten signature and terminal equipment | |
| CN111104941B (en) | Image direction correction method and device and electronic equipment | |
| CN113033543B (en) | Curve text recognition method, device, equipment and medium | |
| CN113177409B (en) | Intelligent sensitive word recognition system | |
| CN109635805B (en) | Image text positioning method and device and image text identification method and device | |
| CN107545049B (en) | Picture processing method and related product | |
| CN111783767B (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| CN113095239A (en) | Key frame extraction method, terminal and computer readable storage medium | |
| CN103810488A (en) | Image feature extraction method, image searching method, server, terminal and system | |
| CN113987244A (en) | Human body image gathering method and device, computer equipment and storage medium | |
| EP0949580B1 (en) | Classification-driven thresholding of a normalized grayscale image | |
| US8913851B1 (en) | Fingerprinting image using points of interest for robust image identification | |
| CN116503596A (en) | Picture segmentation method, device, medium and electronic equipment | |
| JP2004118757A (en) | Detector for traveling lane on road surface | |
| CN112560856B (en) | License plate detection and identification method, device, equipment and storage medium | |
| CN111178340B (en) | Image recognition method and training method of image recognition model | |
| CN111860492B (en) | License plate inclination correction method and device, computer equipment and storage medium | |
| CN110059695A (en) | A kind of character segmentation method and terminal based on upright projection | |
| CN113807343B (en) | Character recognition method, character recognition device, computer equipment and storage medium | |
| KR100734857B1 (en) | Iris Recognition Method and Apparatus Using Cumulative Sum-based Change Point Analysis |
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 |