CN108416346B - License plate character positioning method and device - Google Patents
License plate character positioning method and device Download PDFInfo
- Publication number
- CN108416346B CN108416346B CN201710071889.6A CN201710071889A CN108416346B CN 108416346 B CN108416346 B CN 108416346B CN 201710071889 A CN201710071889 A CN 201710071889A CN 108416346 B CN108416346 B CN 108416346B
- Authority
- CN
- China
- Prior art keywords
- region
- license plate
- characters
- character
- determining
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Input (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method and a device for positioning license plate characters, wherein the method is applied to a server and comprises the following steps: determining a license plate region in a target image; dividing the license plate region into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate; searching the middle position of the upper-row characters of the license plate region in the first region, and determining a candidate character region in the second region; and based on the middle positions of the characters in the upper row and the areas of the candidate characters, positioning the positions of all license plate characters in the first area and the second area. The method provided by the application can effectively improve the accuracy of license plate character positioning.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a method and an apparatus for positioning license plate characters.
Background
The license plate recognition system is an important component of an intelligent traffic system, generally introduces a digital shooting technology and a computer information management technology on the basis of traffic supervision, adopts advanced image processing, mode recognition and artificial intelligence technologies, and acquires more information by acquiring and processing vehicle images.
Generally, a license plate recognition system can comprise three parts of license plate positioning, license plate character positioning segmentation and license plate character recognition. The character positioning segmentation algorithm is used as a starting part and a starting part, and plays a vital role in the whole license plate recognition system.
However, in the existing license plate character positioning and segmentation technology, characters of a single-layer license plate are generally positioned and segmented, and the positioning and segmentation research on characters of a double-layer license plate in China is very little, so that how to position and segment characters of the double-layer license plate becomes a trend for the industry.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for positioning license plate characters, so as to improve the accuracy of positioning the double-layer license plate characters.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of the present application, a method for positioning license plate characters is provided, where the method is applied to a server; the license plate comprises an upper column and a lower column of characters, and the method comprises the following steps:
determining a license plate region in a target image;
dividing the license plate region into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate;
Searching the middle position of the upper-row characters of the license plate region in the first region, and determining a candidate character region in the second region;
and based on the middle positions of the characters in the upper row and the areas of the candidate characters, positioning the positions of all license plate characters in the first area and the second area.
According to a second aspect of the present application, a device for locating characters of a license plate is provided, wherein the device is applied to a server; the license plate includes two upper and lower columns of characters, the device includes:
the determining unit is used for determining a license plate area in the target image;
the license plate region is divided into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate;
the searching unit is used for searching the middle position of the upper-row characters of the license plate area in the first area and determining a candidate character area in the second area;
and the positioning unit is used for positioning the positions of all license plate characters in the first area and the second area based on the middle positions of the characters in the upper row and the areas of the candidate characters.
Because the server no longer locates the positions of the characters in the first region and the second region in isolation, the positions of all the characters on the license plate with the double-layer characters can be located based on the incidence relation of the positions of the characters in the first region and the second region. Therefore, the accuracy of license plate character positioning can be effectively improved.
Drawings
FIG. 1 is a flowchart illustrating a method for locating license plate characters according to an exemplary embodiment of the present disclosure;
FIG. 2 is a schematic illustration of a target image shown in an exemplary embodiment of the present application;
FIG. 3 is a schematic diagram illustrating an image of a target image in a two-dimensional coordinate system of CIE _ xyz color space according to an exemplary embodiment of the present application;
fig. 4(a) is a schematic diagram of an image of a color component region of a license plate background color according to an exemplary embodiment of the present application;
FIG. 4(b) is a diagram illustrating a morphologically processed image of a color component region according to an exemplary embodiment of the present application;
FIG. 5(a) is a schematic diagram of a license plate region image according to an exemplary embodiment of the present disclosure;
FIG. 5(b) is a schematic diagram of a license plate region image after tilt rectification according to an exemplary embodiment of the present application;
FIG. 6 is a schematic diagram illustrating a horizontal projection of a license plate region after horizontal gradient operation and binarization processing according to an exemplary embodiment of the present application;
FIG. 7 is a diagram illustrating a license plate region divided into a first region and a second region according to an exemplary embodiment of the present application;
FIG. 8 is a vertical projection of a first region shown in an exemplary embodiment of the present application;
FIG. 9 is a block diagram of a candidate character region of a second region in accordance with an exemplary embodiment of the present application;
FIG. 10 is a diagram illustrating a first area and a second area locating a character position in accordance with an exemplary embodiment of the present application;
FIG. 11 is a diagram illustrating the location of all characters on a license plate according to an exemplary embodiment of the present disclosure;
FIG. 12 is a block diagram of a hardware of a device for locating characters on a license plate according to an exemplary embodiment of the present disclosure;
fig. 13 is a block diagram of a device for locating characters on a license plate according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The license plate recognition system is an important component of an intelligent traffic system, generally introduces a digital shooting technology and a computer information management technology on the basis of traffic supervision, adopts advanced image processing, mode recognition and artificial intelligence technologies, and acquires more information by acquiring and processing vehicle images.
Generally, a license plate recognition system can comprise three parts of license plate positioning, license plate character positioning segmentation and license plate character recognition. The license plate character positioning and segmenting algorithm is used as a starting part and a starting part, and plays a vital role in the whole license plate recognition system. In the license plate character positioning and segmenting technology, the license plate character positioning technology plays a crucial role in license plate positioning and segmenting, so how to accurately position the position of each character on a license plate is a foundation for improving the license plate character positioning and segmenting accuracy.
However, in the related license plate character locating technology, characters of a single-layer license plate are mostly located. However, it is difficult to accurately locate the positions of all characters on the license plate with double-layer characters by using the single-layer license plate character locating method, and therefore how to accurately locate the positions of the double-layer characters on the license plate becomes an urgent problem in the industry.
The application provides a license plate character positioning method, which comprises the steps that a license plate area is divided into a first area and a second area through a server side; the first area corresponds to the characters listed above the license plate; the second region corresponds to the following characters of the license plate. The server side can search the middle position of the listed characters of the license plate area in the first area, determine a candidate character area in the second area, and position the positions of all license plate characters in the first area and the second area based on the middle position of the listed characters and the area of the candidate characters.
Because the server no longer locates the positions of the characters in the first region and the second region in isolation, the positions of all the characters on the license plate with the double-layer characters can be located based on the incidence relation of the positions of the characters in the first region and the second region. Therefore, the accuracy of license plate character positioning can be effectively improved.
Referring to fig. 1, fig. 1 is a flowchart of a license plate character positioning method according to an exemplary embodiment of the present application, where the method is applied to a server, and the method specifically includes the following steps:
step 101: and determining a license plate region in the target image.
The server can include a server, a server cluster, a cloud and the like. The server is mainly used for positioning license plate characters and the like.
The license plate can comprise a license plate with double-layer characters specified by national standards, and the license plate comprises an upper column of characters and a lower column of characters. The size and format of the license plate and the characters thereon are shown in FIG. 2.
In the embodiment of the application, the server can divide the license plate into a first area corresponding to the upper characters of the license plate and a second area corresponding to the lower characters of the license plate. Because the server no longer locates the positions of the characters in the first region and the second region in isolation, the positions of all the characters on the license plate with the double-layer characters can be located based on the incidence relation of the positions of the characters in the first region and the second region. Therefore, the license plate positioning method provided by the embodiment of the application can effectively improve the accuracy of license plate positioning.
The target image shot by the front-end camera includes a lot of information irrelevant to the license plate besides the license plate information, for example, the shot license plate image may include tail lights, a vehicle body and the like of the vehicle. When the license plate image contains a large amount of non-license plate information, the positioning difficulty of the license plate characters is increased, and the accuracy of the license plate character positioning is reduced.
Therefore, in order to improve the accuracy of license plate character positioning and improve the efficiency of license plate character positioning, in the embodiment of the application, when the server receives the target image shot by the front-end camera, the server may determine, in the target image, a license plate region only including license plate information based on the difference between the background color of the license plate and the colors of other objects in the target image.
When the method is realized, the server side can firstly convert the color space of the target image into the standard color space.
The standard color space may be a CIE _ xyz color space, or a HIS color space, and the standard color space is only exemplary and not particularly limited herein.
The conversion of the color space will be described in detail below, taking the CIE _ xyz color space as an example of the standard color space.
In general, the target image captured by the front-end camera is generally an RGB color space, and the server may convert the target image in the RGB color space into the target image in the CIE _ xyz color space through the following conversion formula.
x＝R*0.412453+G*0.357580+B*0.180423；
v＝R*0.212671+G*0.715160+B*0.072169；
z＝R*0.019334+G*0.119193+B*0.950227；
Where x, y, z are coordinates in the CIE _ xyz color space, and R, G, B are coordinates in the RGB color space.
In an alternative implementation manner, in order to reduce the amount of calculation for determining the color component region, the server may convert the xyz three-dimensional coordinates in the converted CIE _ xyz color space into xy two-dimensional coordinates, similar to performing xy plane horizontal projection on the CIE _ xyz color space.
The conversion of the xyz three-dimensional coordinate to the xy two-dimensional coordinate can be realized by the following formula:
sumxyz＝x+y+z；
x＝x/sumxyz；
y＝y/sumxyz；
the target image is converted from three-dimensional coordinates of the CIE _ xyz color space to an image of two-dimensional coordinates, as shown in fig. 3.
The server side can determine a color component region corresponding to the background color of the license plate in the standard color space.
For example, if the background color of the license plate is yellow, the server may determine a yellow component region and the like in the image shown in fig. 3. The image of the determined yellow component region is shown in fig. 4 (a).
It should be noted that, here, the license plate background color and the color component region determined by the server are only exemplified and not specifically limited.
In the standard color space, after determining the color component region corresponding to the license plate background color, the server may perform morphological processing on the determined color component region to obtain the boundary of the determined color component region.
In implementation, the server may perform opening and closing operations on the determined color component region based on a preset window, for example, a window with a window size of 5 × 5, and perform pixel merging processing on adjacent pixels in the color component region. The image of the morphologically processed color component region is shown in fig. 4 (b).
After the determined color component region is subjected to morphological processing, the server may perform horizontal and vertical projection operations on the boundary of the determined color component region, and may determine the boundary of the determined color component region based on the result of the horizontal and vertical projection operations, where the boundary of the determined color component region is the license plate region in the target image. The determined license plate region is shown in fig. 5 (a).
Step 102: dividing the license plate region into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second region corresponds to the following characters of the license plate.
In the embodiment of the application, in order to avoid that the determined license plate region influences the accuracy of license plate character positioning due to inclination, in an optional implementation manner, after the server determines the license plate region in the target image, the server may perform inclination correction operation on the license plate region.
When the method is realized, the server side can find out the inclination angle of the license plate region by using the existing HOUGH transformation, and rotate the license plate region based on the existing rotation algorithm so as to correct the inclination of the license plate region. The image of the license plate region after the tilt correction is shown in fig. 5 (b).
In the embodiment of the application, after the license plate region is subjected to tilt correction, the server may divide the license plate region into a first region corresponding to the upper characters of the license plate and a second region corresponding to the lower characters of the license plate.
In the related technology of dividing the license plate into the upper and lower regions, the license plate region is usually binarized, however, the photographed license plate is easily affected by factors such as illumination, so that the effect of binarizing the license plate is poor, and the difficulty of dividing the upper and lower characters of the license plate is greatly increased.
Therefore, in order to solve the above problem, in the embodiment of the present application, before the server performs the binarization processing on the license plate region, a horizontal gradient operation may be performed on the license plate region. On one hand, the edge of the image in the license plate region can be sharpened due to gradient operation; in another aspect. After the horizontal gradient operation, the obtained image of the license plate region is a vertical texture map, and the first region of the license plate and the first region are divided into horizontal divisions. Therefore, the error in determining the division boundary point of the first region and the second region can be effectively reduced.
When the method is realized, the server side can perform horizontal gradient operation on the license plate area. For example, the server may derive the license plate region with a lead kernel of [ -1, 0, 1 ]. And the horizontal gradient image obtained by the horizontal gradient operation may be subjected to binarization processing, for example, the background of the horizontal gradient image is 0, and the character is 1.
The server may perform horizontal projection on the horizontal gradient image after the binarization processing, and may divide the license plate region into a first region and a second region based on a valley position in the horizontal projection image obtained after the horizontal projection operation, for example, a position of a point a in fig. 6, where images of the divided first region and second region are shown in fig. 7.
Step 103: searching the middle position of the upper-row characters of the license plate region in the first region, and determining a candidate character region in the second region;
in this embodiment, after completing the segmentation of the first region and the second region, the server may process the segmented first region and second region respectively to obtain the middle position of the upper-listed character included in the first region and each candidate character region in the second region.
When the method is implemented, in order to enable the wave troughs of the image after the vertical projection of the first area not to be affected by the image detail information and not to fluctuate, the accuracy of determining the positions of the wave troughs is improved, and the server side can filter out the detail information in the image of the first area.
When the method is implemented, the server side can carry out smooth filtering on the first region of the license plate region. The server may use 5 × 5 gaussian operators to perform smoothing filtering on the first region, or may use other filters to perform smoothing filtering on the first region, which is not described herein again.
After the server performs smooth filtering on the first region, the server may perform vertical projection operation on the filtered first region. And the middle position of the upper-column character corresponding to the first region may be determined based on the middle trough position of the vertical projection diagram obtained after the vertical projection operation, as shown in fig. 8.
Meanwhile, the server may process the second region to determine all candidate character regions.
When the license plate is realized, the server side can carry out binarization processing on the second region of the license plate, carry out connected component marking processing on the binarized second region, and combine adjacent pixel points to form a plurality of combined pixel point groups.
The server can use the maximum value of the horizontal and vertical coordinates of the pixel points in each merged pixel point group as the horizontal and vertical coordinates of the area where each merged pixel point group is located, and form the area where a plurality of pixel point groups of each merged pixel point group are located.
The server side can screen the region where each merged pixel group is located based on the preset length and width value, and screen out the merged pixel group of which the length and width of the region where the merged pixel group is located accord with the preset length and width value.
During screening, the server may screen out that the aspect ratio of the region where the merged pixel point is located is within an error range of a preset aspect ratio, and the width of the region is greater than a preset width value, as each candidate character region in the second region. As shown in fig. 9, the regions in which "2", "7", "6", "8" and "5" of the white box city in fig. 9 are located are candidate character regions.
The preset aspect ratio is set by the developer according to actual conditions, and for example, the developer may use the aspect ratio of any one of the following characters of the license plate specified by the current national standard as the preset aspect ratio, that is, 110: 65 is 1.69. When the national standard is changed, the developer can change the preset length and width values based on actual conditions.
In addition, the error range of the preset aspect ratio may also be set by the developer based on actual conditions, for example, the developer may set the error range of the preset aspect ratio to [1.5, 1.9 ]. Of course, the error range of the preset aspect ratio is only exemplarily illustrated here, and is not particularly limited.
The preset width value can be set by a developer based on actual conditions. For example, the developer may set the preset width value as the height of the license plate multiplied by a certain weight value, which is not described herein again.
Step 104: and based on the middle positions of the characters in the upper row and the areas of the candidate characters, positioning the positions of all license plate characters in the first area and the second area.
In the embodiment of the application, the server does not separately position the characters of the first region and the second region, but positions all the characters of the first region and the second region based on the corresponding relationship of the character positions of the first region and the second region specified by the national standard, so that the accuracy of positioning each character of the license plate is effectively improved.
In practical application, the characters at the middle positions in the following characters of the license plate are relatively clean, so that when the characters on the license plate are positioned, the characters at the middle positions are used as a basis, and the positioning is relatively accurate.
In an alternative implementation manner, the server may determine, based on the determined middle position of the above-listed character, a position of a middle character of the following character corresponding to the second area. Then, the server may determine the positions of two characters on the left side of the middle character and the positions of two characters on the right side of the middle character based on the position of the middle character of the following characters and the following character widths specified by the national standard, and the spacing distances between the following characters, respectively, to the left and right.
The server may determine the position of each of the two characters listed above based on the position of one of the following characters that is adjacent to the middle character.
For example, as shown in fig. 10, fig. 10 is a schematic diagram illustrating a first area and a second area for locating the position of a character according to an exemplary embodiment of the present application.
The server may determine the middle position of the above-listed characters based on the above, i.e., the middle positions of the "Zhe" and "A" characters in FIG. 10. The character which is directly downward from the middle position is the position of the middle character in the following characters, namely the position of the character "6".
The server may determine the positions of two characters to the left of the middle character "6", i.e., the positions of the characters "2" and "7", to the left based on the position of the character "6", and the widths of the following characters and the length of the character interval of the following characters, which are specified by the national standard. Meanwhile, the server can determine the positions of two characters to the right of the middle character "6", namely the positions of the characters "8" and "5".
The server can respectively determine the position of each character in the above-listed characters based on the positions of characters adjacent to the middle character "6" left and right in the following characters, namely the positions of the character "7" and the character "6", namely, the position of the above-listed character "Zhe" is determined according to the position of the character "7", the position of the character "Zhe" is just above the position of the character "7", the position of the above-listed character "A" is determined according to the position of the character "8", and the position of the character "A" is just above the position of the character "8".
As shown in fig. 11, the positions of all the characters in the first area and the second area of the license plate are determined.
In the embodiment, the positions of all the characters on the license plate are determined by determining the positions of the middle characters in the following characters and then combining the corresponding relationship between the positions of the upper and lower characters based on the positions of the middle characters. Of course, the server may also locate the characters on the license plate in other manners, for example, the server may determine the positions of the above-listed characters, and then determine the positions of all the following characters based on the positions of the above-listed characters, and the like, so as to locate all the characters on the license plate, which is not described herein again.
The application provides a license plate character positioning method, which comprises the steps that a license plate area is divided into a first area and a second area through a server side; the first area corresponds to the characters listed above the license plate; the second region corresponds to the following characters of the license plate. The server side can search the middle position of the listed characters of the license plate area in the first area, determine a candidate character area in the second area, and position the positions of all license plate characters in the first area and the second area based on the middle position of the listed characters and the area of the candidate characters.
Because the server no longer locates the positions of the characters in the first region and the second region in isolation, the positions of all the characters on the license plate with the double-layer characters can be located based on the incidence relation of the positions of the characters in the first region and the second region. Therefore, the accuracy of license plate character positioning can be effectively improved.
Corresponding to the embodiment of the license plate character positioning method, the application also provides an embodiment of a license plate character positioning device.
The embodiment of the positioning device for the license plate characters can be applied to a server. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and as a device in a logical sense, a processor of a service end reads corresponding computer program instructions in a nonvolatile memory into a memory for operation. From a hardware aspect, as shown in fig. 12, the hardware structure diagram of the service end where the device for positioning license plate characters is located in the present application is shown, except for the processor, the memory, the network output interface, and the nonvolatile memory shown in fig. 12, the service end where the device is located in the embodiment may also include other hardware according to its actual functions, which is not described again.
Referring to fig. 13, fig. 13 is a block diagram of a license plate character locating device according to an exemplary embodiment of the present application. The device is applied to a server; the license plate includes two upper and lower columns of characters, the device includes:
a determining unit 1310, configured to determine a license plate region in the target image;
a dividing unit 1320, configured to divide the license plate region into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate;
a searching unit 1330, configured to search the first region for the middle position of the top-listed character of the license plate region, and determine a candidate character region in the second region;
a positioning unit 1340, configured to position the positions of all license plate characters in the first region and the second region based on the middle positions of the above-listed characters and the regions of the candidate characters.
In an alternative implementation manner, the determining unit 1310 is specifically configured to convert the color space of the target image into a standard color space; determining a color component region in the standard color space corresponding to a background color of the license plate; according to a preset window, carrying out pixel point merging processing on adjacent pixel points in the determined color component area; and respectively carrying out horizontal and vertical projection operation on the boundary of the color component region after the pixel point merging processing is executed, and determining the license plate region in the target image based on the results of the horizontal and vertical projection operation.
In another optional implementation manner, the segmentation unit 1320 is specifically configured to perform horizontal gradient operation on the license plate region, and perform binarization processing on a horizontal gradient image obtained through the horizontal gradient operation; and performing horizontal projection operation on the binarized horizontal gradient image, and dividing the license plate region into the first region and the second region based on the trough position in the horizontal projection image obtained by the horizontal projection operation.
In another optional implementation manner, the search unit 1330 is specifically configured to perform smooth filtering on the first region of the license plate region; performing vertical projection operation on the filtered first region, and determining the middle position of the upper-column character corresponding to the first region based on the middle trough position of the vertical projection graph obtained after the vertical projection operation; carrying out binarization processing on a second region of the license plate, carrying out connected component marking processing on the binarized second region to form a plurality of combined pixel point groups, and determining the region of each combined pixel point group based on the maximum value of the horizontal and vertical coordinates of the pixel points in each combined pixel point group; and screening the region where each merged pixel group is located based on a preset length and width value, and screening out the merged pixel groups of which the length and width of the region meet the preset length and width to serve as each candidate character region in the second region.
In another optional implementation manner, the positioning unit 1340 is specifically configured to determine, based on the middle position of the above-listed character, a position of a middle character of the following character corresponding to the second area; determining the position of each character in the following characters based on the position of the middle character of the following characters, the preset width of the following characters and the interval length between the following characters; determining a position of each character in the upper list of characters based on a position of a character adjacent to the middle character in the lower list of characters.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (8)
1. A method for positioning license plate characters is characterized in that the method is applied to a server side; the license plate comprises an upper column and a lower column of characters, and the method comprises the following steps:
determining a license plate region in a target image;
dividing the license plate region into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate;
searching the middle position of the upper-row characters of the license plate region in the first region, and determining a candidate character region in the second region;
based on the middle positions of the characters in the list and the areas of the candidate characters, locating the positions of all license plate characters in the first area and the second area, including:
determining the position of the middle character of the following characters corresponding to the second area based on the middle position of the above characters;
determining the position of each character in the following characters based on the position of the middle character of the following characters, the preset width of the following characters and the interval length between the following characters;
Determining a position of each character in the upper list of characters based on a position of a character adjacent to the middle character in the lower list of characters.
2. The method of claim 1, wherein determining the license plate region in the target image comprises:
converting the color space of the target image into a standard color space;
determining a color component region in the standard color space corresponding to a background color of the license plate;
according to a preset window, carrying out pixel point merging processing on adjacent pixel points in the determined color component area;
and respectively carrying out horizontal and vertical projection operation on the boundary of the color component region after the pixel point merging processing is executed, and determining the license plate region in the target image based on the results of the horizontal and vertical projection operation.
3. The method of claim 1, wherein the segmenting the license plate region into a first region and a second region comprises:
performing horizontal gradient operation on the license plate region, and performing binarization processing on a horizontal gradient image obtained by the horizontal gradient operation;
and performing horizontal projection operation on the binarized horizontal gradient image, and dividing the license plate region into the first region and the second region based on the trough position in the horizontal projection image obtained by the horizontal projection operation.
4. The method of claim 1, wherein the searching for the middle position of the top characters of the license plate region in the first region and the determining of the candidate character region in the second region comprise:
performing smooth filtering on a first region of the license plate region; performing vertical projection operation on the filtered first region;
determining the middle position of the upper-column character corresponding to the first region based on the middle trough position of the vertical projection graph obtained after vertical projection operation;
carrying out binarization processing on a second region of the license plate, and carrying out connected component marking processing on the binarized second region to form a plurality of combined pixel point groups;
determining the area of each merged pixel group based on the maximum value of the horizontal and vertical coordinates of the pixels in each merged pixel group;
and screening the region where each merged pixel group is located based on a preset length and width value, and screening out the merged pixel groups of which the length and width of the region meet the preset length and width to serve as each candidate character region in the second region.
5. The device for positioning the characters of the license plate is characterized in that the device is applied to a server side; the license plate includes two upper and lower columns of characters, the device includes:
The determining unit is used for determining a license plate area in the target image;
the license plate region is divided into a first region and a second region; the first area corresponds to the characters listed above the license plate; the second area corresponds to the following characters of the license plate;
the searching unit is used for searching the middle position of the upper-row characters of the license plate area in the first area and determining a candidate character area in the second area;
the positioning unit is used for positioning the positions of all license plate characters in the first area and the second area based on the middle positions of the characters in the list and the areas of the candidate characters, and comprises the following steps:
the positioning unit is specifically configured to determine, based on the middle position of the upper-column character, a position of a middle character of a lower-column character corresponding to the second area; determining the position of each character in the following characters based on the position of the middle character of the following characters, the preset width of the following characters and the interval length between the following characters; determining a position of each character in the upper list of characters based on a position of a character adjacent to the middle character in the lower list of characters.
6. The apparatus according to claim 5, wherein the determining unit is specifically configured to convert a color space of the target image into a standard color space; determining a color component region in the standard color space corresponding to a background color of the license plate; according to a preset window, carrying out pixel point merging processing on adjacent pixel points in the determined color component area; and respectively carrying out horizontal and vertical projection operation on the boundary of the color component region after the pixel point merging processing is executed, and determining the license plate region in the target image based on the results of the horizontal and vertical projection operation.
7. The device according to claim 5, wherein the segmentation unit is specifically configured to perform horizontal gradient operation on the license plate region, and perform binarization processing on a horizontal gradient image obtained by the horizontal gradient operation; and performing horizontal projection operation on the binarized horizontal gradient image, and dividing the license plate region into the first region and the second region based on the trough position in the horizontal projection image obtained by the horizontal projection operation.
8. The device according to claim 5, wherein the search unit is specifically configured to perform a smoothing filtering on a first region of the license plate region; performing vertical projection operation on the filtered first region, and determining the middle position of the upper-column character corresponding to the first region based on the middle trough position of the vertical projection graph obtained after the vertical projection operation; carrying out binarization processing on a second region of the license plate, carrying out connected component marking processing on the binarized second region to form a plurality of combined pixel point groups, and determining the region of each combined pixel point group based on the maximum value of the horizontal and vertical coordinates of the pixel points in each combined pixel point group; and screening the region where each merged pixel group is located based on a preset length and width value, and screening out the merged pixel groups of which the length and width of the region meet the preset length and width to serve as each candidate character region in the second region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710071889.6A CN108416346B (en) | 2017-02-09 | 2017-02-09 | License plate character positioning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710071889.6A CN108416346B (en) | 2017-02-09 | 2017-02-09 | License plate character positioning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108416346A CN108416346A (en) | 2018-08-17 |
| CN108416346B true CN108416346B (en) | 2021-11-16 |
Family
ID=63124812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710071889.6A Active CN108416346B (en) | 2017-02-09 | 2017-02-09 | License plate character positioning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416346B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110858303A (en) * | 2018-08-22 | 2020-03-03 | 西门子（中国）有限公司 | Method and device for detecting license plate number |
| CN111914845A (en) * | 2020-07-02 | 2020-11-10 | 浙江大华技术股份有限公司 | Character layering method and device in license plate and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN105528605A (en) * | 2014-09-28 | 2016-04-27 | 江苏省兴泽实业发展有限公司 | Double-layer license plate character segmentation method based on projection and recognition |
| CN106228136A (en) * | 2016-07-26 | 2016-12-14 | 厦门大学 | Panorama streetscape method for secret protection based on converging channels feature |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160232410A1 (en) * | 2015-02-06 | 2016-08-11 | Michael F. Kelly | Vehicle speed detection |
-
2017
- 2017-02-09 CN CN201710071889.6A patent/CN108416346B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN102375982B (en) * | 2011-10-18 | 2013-01-02 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN105528605A (en) * | 2014-09-28 | 2016-04-27 | 江苏省兴泽实业发展有限公司 | Double-layer license plate character segmentation method based on projection and recognition |
| CN106228136A (en) * | 2016-07-26 | 2016-12-14 | 厦门大学 | Panorama streetscape method for secret protection based on converging channels feature |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108416346A (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110919653B (en) | Stair climbing control method and device for robot, storage medium and robot | |
| CN107463918B (en) | Lane line extraction method based on fusion of laser point cloud and image data | |
| CN109726717B (en) | Vehicle comprehensive information detection system | |
| CN106296666B (en) | A kind of color image removes shadow method and application | |
| CN101334836B (en) | License plate positioning method incorporating color, size and texture characteristic | |
| WO2017041396A1 (en) | Driving lane data processing method, device, storage medium and apparatus | |
| WO2022134996A1 (en) | Lane line detection method based on deep learning, and apparatus | |
| CN109389163B (en) | Unmanned aerial vehicle image classification system and method based on topographic map | |
| CN104036262B (en) | A kind of method and system of LPR car plates screening identification | |
| CN105893949A (en) | Lane line detection method under complex road condition scene | |
| CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
| CN103324935B (en) | Vehicle is carried out the method and system of location and region segmentation by a kind of image | |
| CN102375982A (en) | Multi-character characteristic fused license plate positioning method | |
| CN109492525B (en) | Method for measuring engineering parameters of base station antenna | |
| CN107423735B (en) | License plate positioning method utilizing horizontal gradient and saturation | |
| CN112819895A (en) | Camera calibration method and device | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN114708208B (en) | Machine vision-based famous tea tender bud identification and picking point positioning method | |
| CN104182728A (en) | Vehicle logo automatic location and recognition method based on pattern recognition | |
| CN108765456B (en) | Target tracking method and system based on linear edge characteristics | |
| CN109461133A (en) | Bridge bolt dropping detection method and terminal device | |
| CN114511832B (en) | Lane line analysis method and device, electronic device and storage medium | |
| CN108416346B (en) | License plate character positioning method and device | |
| CN109187548A (en) | A kind of rock cranny recognition methods | |
| JP2008242508A (en) | Automatic specific area extraction system, automatic specific area extraction method and program |
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 |