CN108846396B - Image content segmentation method and device and license plate recognition method - Google Patents

Image content segmentation method and device and license plate recognition method Download PDF

Info

Publication number
CN108846396B
CN108846396B CN201810515635.3A CN201810515635A CN108846396B CN 108846396 B CN108846396 B CN 108846396B CN 201810515635 A CN201810515635 A CN 201810515635A CN 108846396 B CN108846396 B CN 108846396B
Authority
CN
China
Prior art keywords
image
level set
degradation
set function
segmentation
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
Application number
CN201810515635.3A
Other languages
Chinese (zh)
Other versions
CN108846396A (en
Inventor
林凡
成杰
张秋镇
唐昌宇
杨峰
李盛阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GCI Science and Technology Co Ltd
Original Assignee
GCI Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by GCI Science and Technology Co Ltd filed Critical GCI Science and Technology Co Ltd
Priority to CN201810515635.3A priority Critical patent/CN108846396B/en
Publication of CN108846396A publication Critical patent/CN108846396A/en
Application granted granted Critical
Publication of CN108846396B publication Critical patent/CN108846396B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06V10/26—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)

Abstract

The application relates to an image content segmentation method, an image content segmentation device and a license plate identification method. The image content segmentation method comprises the following steps: acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function; constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional; and determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model. The image object information segmentation method can control the iteration times of the segmentation model, reduce the iteration times of the finally obtained accurate segmentation model and reduce the operation amount in the segmentation process.

Description

Image content segmentation method and device and license plate recognition method
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image content segmentation method, an image content segmentation device, and a license plate recognition method.
Background
Before the characters in the image are recognized, the image needs to be segmented in advance to obtain the characters in the image, and then the characters in the image are compared with the characters in the database to realize character recognition.
The traditional image character segmentation mode can segment characters of license plates according to the principle that pixels belonging to the same character form a connected domain and by combining the prior knowledge of fixed character spacing, fixed proportion relation and the like of the license plate standard. However, the conventional image character segmentation method has low accuracy.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an image content segmentation method, an image content segmentation device, and a license plate recognition method, which can improve the accuracy of image character segmentation.
A method of image content segmentation, the method comprising:
acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
and determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model.
In an embodiment, in the image content segmentation method, the partial differential equation is:
Figure BDA0001674040540000021
wherein φ is a level set function of the image,
Figure BDA0001674040540000022
is a time partial differential of a level set function of the image, (phi) is a one-dimensional dirac function of a level set function of the image, mu is a constant greater than 0,
Figure BDA0001674040540000023
for the gradient field of the level set function of the image, div is the divergence operator, c±As a degradation coefficient of said image, c+A degradation coefficient for segmenting a region for said image object, c-Sign is a sign function for the degradation coefficient of the image background area.
In one embodiment, the image content segmentation method for determining the degradation coefficient in the image degradation expression according to the level set function of the image and the energy functional of the image includes:
representing an expression of an energy functional by a level set function of the image, and determining a degradation coefficient of the image according to the expression of the energy functional and the expression of the energy functional infimum;
the image degradation expression is:
Figure BDA0001674040540000027
wherein x is the coordinate value of the image pixel point, I (x) is the image degradation expression, omega±For the segmentation region of the image, Ω+Is the target region of the image, Ω-And the background area of the image is a constant of the image to be segmented influenced by the environmental noise.
In an embodiment of the image content segmentation method, an expression of the energy functional is as follows:
Figure BDA0001674040540000024
wherein E (φ, c)+，c-) Is the energy functional of the image, μ is a constant greater than 0,
Figure BDA0001674040540000026
is a Hamiltonian, omega is the image, and H is the step function.
In an embodiment, in the image content segmentation method, the expression of the energy functional infinitive is as follows:
Figure BDA0001674040540000025
wherein inf is an infimum symbol,
Figure BDA0001674040540000031
is the lower part of the energy functionalThe boundary is determined according to the data of the boundary,
Figure BDA0001674040540000032
updating the infimum bound of the energy functional.
In one embodiment, the image content segmentation method includes:
Figure BDA0001674040540000033
wherein x is the coordinate value of the image pixel point,
Figure BDA0001674040540000034
a model is segmented for the image.
An image character segmentation apparatus, the apparatus comprising:
the acquisition module is used for acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
the solving module is used for constructing a degradation model of the image according to image content and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
and the segmentation module is used for determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model.
A license plate recognition method includes:
dividing characters in the license plate image to be recognized according to the image content division method; the image is a license plate image, and the content is characters;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
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 following steps when executing the computer program:
acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model;
or the processor, when executing the computer program, implements the steps of:
dividing characters in the license plate image to be recognized according to the image content division method;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model;
or the computer program when executed by a processor implements the steps of:
dividing characters in the license plate image to be recognized according to the image content division method;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
According to the image content segmentation method, the image content segmentation device and the license plate recognition method in the embodiment of the application, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
Drawings
FIG. 1 is a diagram of an embodiment of an application environment of a method for segmenting image content;
FIG. 2 is a flow chart illustrating a method for segmenting image content according to an embodiment;
FIG. 3 is a schematic flow chart of a license plate recognition method according to an embodiment;
FIG. 4 is a block diagram of an exemplary embodiment of an image character segmentation apparatus;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image content segmentation method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 and the server 104 communicate via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an image content segmentation method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
step 202, acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function.
For the above steps, the image may be subjected to graying preprocessing to obtain a grayed image of the image to be segmented. The graying processing of the image to be segmented can remove the color information in the image. In image processing, color information of an image does not reflect morphological features of the image, and after the image is subjected to graying processing, properties such as a histogram and a grayscale change of the image can be processed.
And 204, constructing a degradation model of the image according to the image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional.
Specifically, the basic idea of level set is to regard the interface as a zero level set of a certain function (level set function) in a high one-dimensional space, and simultaneously, the evolution of the interface is also extended into the high one-dimensional space. And (3) carrying out evolution or iteration on the level set function according to a development equation which is satisfied by the level set function, wherein the level set function is continuously evolved, so that the corresponding zero level set is continuously changed, and when the level set evolution tends to be stable, the evolution is stopped, and the interface shape is obtained. The degradation coefficient is a coefficient used for adjusting a degradation form (expression) of an image in the degradation form of the image.
And step 206, determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model.
Specifically, the step function may be a one-dimensional Heaviside (Heaviside) function. The Heaviside function is a special continuous time function, is a process of jumping from 0 to 1 and belongs to a singular function. The Heaviside function can be used for signal processing and integral transformation, and is found in various fields such as natural ecology, calculation, engineering and the like to different degrees. The content of the image may be character information of the image, and the content of the image is not limited herein.
In the embodiment, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
In one embodiment, the partial differential equation of the level set function is:
Figure BDA0001674040540000071
where φ is a level set function of the image,
Figure BDA0001674040540000072
is the time partial differential of the level set function of the image, (phi) is the one-dimensional dirac function of the level set function of the image, mu is a constant greater than 0,
Figure BDA0001674040540000073
is the gradient field of the level set function of the image, div is the divergence operator, c±As a degradation coefficient of the image, c+A degradation coefficient for segmenting a region for an image object, c-Is the degradation coefficient of the image background area, sign is a sign function,f(|c+-c-i) is f (| c)+-c-I) > kx and
Figure BDA0001674040540000074
as a function of (c).
In the above embodiment, the evolution of the level set function Φ is controlled by the above partial differential equation, the level set function may be introduced into the segmentation model of the image to be segmented, and the partial differential equation control function is added, so that the iteration number of the segmentation model may be controlled, and the computation amount in the segmentation process may be reduced. The sensitivity of the segmentation model to the iteration times is reduced, namely the segmentation times can obtain a segmentation result with higher accuracy without reaching a specified threshold value.
In the embodiment, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
In one embodiment, step 204 includes: expressing an expression of an energy functional by using a level set function of the image, and determining a degradation coefficient of the image according to the expression of the energy functional and an expression of an energy functional infimum;
the image degradation expression is:
Figure BDA0001674040540000075
wherein x is the coordinate value of the image pixel point, I (x) is the image degradation expression, omega±Is a divided region of the image, omega+Is the target region of the image, Ω-Is a background area of the image, is a constant of the image to be segmented influenced by environmental noise,
Figure BDA0001674040540000084
represents omega+Is determined by the characteristic function of (a),
Figure BDA0001674040540000085
represents omega-The characteristic function of (2).
In the above-described embodiment, the image to be segmented after the graying has the above-described degradation expression, and the image degradation refers to a decrease in image quality due to imperfections of the imaging system, the recording apparatus, the transmission medium, and the processing method during the formation, recording, processing, and transmission of the image. c. C+And c-The degradation coefficient may be a constant, and may be understood as a coefficient that adjusts a degradation form of an image. Omega-omega+∪Ω-The image to be segmented, for example,
Figure BDA0001674040540000083
in the embodiment, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
In one embodiment, the expression of the energy functional is:
Figure BDA0001674040540000081
wherein E (φ, c)+，c-) Is the energy functional of the image, mu is a constant greater than 0,
Figure BDA0001674040540000082
is Hamiltonian, omega is the image and H is the step function.
In the above embodiments, the functional is that the domain is a set of functions, and the value domain is a set of real functions or a subset of the set of real functions. That is, it is a mapping from the function space to the number domain. The energy functional (energy function) is the integral of the squared modular length of the derivative of the map.
In the embodiment, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
In one embodiment, the expression of the energy functional infinitive is:
Figure BDA0001674040540000091
wherein inf is an infimum symbol,
Figure BDA0001674040540000092
is the infimum bound of the energy functional,
Figure BDA0001674040540000093
is an update of the infimum of the energy functional.
In the above embodiment, the expression of the energy functional infimum represents the infimum of the updated energy functional. For example, given a set of numbers E, we call the largest lower bound of E the infimum bound of E, denoted inf. C can be determined by combining an expression of an energy functional infinitive and an expression of an energy functional±Value of (a) and omega±The value of (c).
In the embodiment, the degradation coefficient in the image degradation expression is determined according to the level set function and the energy functional of the image to be segmented, the segmentation model of the image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the content of the image is segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced.
In one embodiment, the segmentation model is:
Figure BDA0001674040540000094
wherein x is the coordinate value of the image pixel point,
Figure BDA0001674040540000095
an image segmentation model.
In the above segmentation model, the expression of the degradation coefficient is:
Figure BDA0001674040540000096
wherein the evolution of the level set function φ is governed by the following partial differential equations:
Figure BDA0001674040540000097
where, H' is the differential of the one-dimensional Heaviside function.
In an embodiment, as shown in fig. 3, there is further provided a license plate recognition method, including the steps of:
s302, segmenting characters in the license plate image to be recognized through the image object information segmentation method in each embodiment of the embodiment.
Specifically, the image to be segmented in the image object information segmentation method is a license plate image to be recognized, and the license plate image to be recognized can be acquired from a camera or a video stream.
S304, extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database.
S306, recognizing the license plate in the license plate image according to the recognition of each character.
The license plate recognition method is explained below with reference to examples. Defining the grayed license plate image to be recognized as a level set function, wherein the level set function has the following degradation form:
Figure BDA0001674040540000101
wherein x is the coordinate value of the gray image pixel, I (x) is the gray image degradation expression, omega±Is a divided region of a gray image, omega+Is the target region of the grayscale image, Ω-The background area of the gray level image is a constant of the image to be segmented influenced by the environmental noise.
Ω can be determined by the following formula+And Ω-：
Figure BDA0001674040540000102
Figure BDA0001674040540000103
Wherein E (φ, c)+，c-) Is the energy functional of the grayscale image, μ is a constant greater than 0,
Figure BDA0001674040540000104
is Hamiltonian, omega is gray image, H is step function, inf is infimum symbol,
Figure BDA0001674040540000105
is the infimum bound of the energy functional,
Figure BDA0001674040540000106
is an update of the infimum of the energy functional.
Figure BDA0001674040540000107
Is the zero level set { x: phi (x) ═ 0 }.
The segmentation result of the license plate image to be recognized after graying is obtained according to the data is as follows:
Figure BDA0001674040540000108
Figure BDA0001674040540000111
the evolution of the level set function φ is governed by the partial equation:
Figure BDA0001674040540000112
wherein x is the coordinate value of the gray image pixel point,
Figure BDA0001674040540000113
a grayscale image segmentation model, where H' is the differential of the one-dimensional Heaviside function.
f(|c+-c-I) is f (| c)+-c-|)＞＞k|c+-c-I and
Figure BDA0001674040540000114
Figure BDA0001674040540000115
as a function of (c).
And extracting each character in the segmented license plate image result one by one, comparing the extracted character with the characters which possibly appear on the license plate in the character library, and determining the result of the extracted character. And combining the results of the extracted characters, determining the license plate number, and realizing license plate identification.
In the above embodiment, the degradation coefficient in the degradation expression of the grayscale image is determined according to the level set function of the grayscale image after the image to be segmented is grayed and the energy functional of the grayscale image, the segmentation model of the grayscale image to be segmented is determined according to the degradation coefficient and the step function of the level set function, and the characters of the grayscale image are segmented according to the segmentation model. The evolution of the level set function in the segmentation model is controlled by a partial differential equation of the level set function, so that the iteration times of the segmentation model can be controlled, the iteration times of the accurate segmentation model which is finally obtained are reduced, and the operation amount in the segmentation process is reduced. Meanwhile, the speed and the accuracy of card inserting identification can be improved.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided an image character segmentation apparatus including:
an obtaining module 402, configured to obtain a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
a solving module 404, configured to construct a degradation model of the image according to image content, and determine a degradation coefficient of the degradation model according to the level set function and the energy functional;
a segmentation module 406, configured to determine a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segment the content of the image according to the segmentation model.
For the specific definition of the image character segmentation apparatus, reference may be made to the above definition of the image object information segmentation method, which is not described herein again. The modules in the image character segmentation device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The terms "comprises" and "comprising," and any variations thereof, of embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or (module) elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase 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 explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Reference herein to "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. 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 character data. 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 an image object information segmentation method or a license plate recognition method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 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 device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model;
or the processor, when executing the computer program, realizes the following steps:
segmenting characters in a license plate image to be recognized according to the image object information segmentation method;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
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 level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional;
determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model;
or the computer program when executed by a processor implements the steps of:
segmenting characters in a license plate image to be recognized according to the image object information segmentation method;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples 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 invention. 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 patent shall be subject to the appended claims.

Claims (10)

1. An image content segmentation method, comprising:
acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
constructing a degradation model of the image according to image content, and determining a degradation coefficient of the degradation model according to the level set function and the energy functional, wherein the step comprises the following steps: representing an expression of an energy functional by a level set function of the image, and determining a degradation coefficient of the image according to the expression of the energy functional and the expression of the energy functional infimum; the degradation coefficient is a coefficient used for adjusting an image degradation expression;
and determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model.
2. The image content segmentation method according to claim 1, characterized in that the partial differential equation is:
Figure FDA0002694510690000011
wherein φ is a level set function of the image,
Figure FDA0002694510690000012
is a time partial differential of a level set function of the image, (phi) is a one-dimensional dirac function of a level set function of the image, mu is a constant greater than 0,
Figure FDA0002694510690000013
is the gradient field of the level set function of the image, div is the divergence operator, I is the image degradation expression, c±As a degradation coefficient of said image, c+A degradation coefficient of the image target segmentation region, c _ is a degradation coefficient of the image background region, sign is a sign function, f (| c)+-c-I) is f (| c)+-c-|)＞＞k|c+-c-I and
Figure FDA0002694510690000014
as a function of (c).
3. The image content segmentation method according to claim 2, wherein the image degradation expression is:
Figure FDA0002694510690000015
wherein x is the coordinate value of the image pixel point, I (x) is the image degradation expression, omega±For the segmentation region of the image, Ω+Is the target region of the image, Ω-Is the background area of the image, is a constant of the image to be segmented influenced by the environmental noise,
Figure FDA0002694510690000028
represents omega+Is determined by the characteristic function of (a),
Figure FDA0002694510690000029
represents omega+The characteristic function of (2).
4. The image content segmentation method according to claim 3, wherein the expression of the energy functional is:
Figure FDA0002694510690000021
wherein E (φ, c)+，c-) Is the energy functional of the image, μ is a constant greater than 0,
Figure FDA0002694510690000027
is a Hamiltonian, omega is the image, and H is the step function.
5. The image content segmentation method according to claim 4, wherein the energy functional infinitive is expressed by:
Figure FDA0002694510690000022
wherein inf is an infimum symbol,
Figure FDA0002694510690000023
for the infimum bound of the energy functional,
Figure FDA0002694510690000024
updating the infimum bound of the energy functional.
6. The image content segmentation method according to claim 4, wherein the segmentation model is:
Figure FDA0002694510690000025
wherein x is the coordinate value of the image pixel point,
Figure FDA0002694510690000026
a model is segmented for the image.
7. An image content segmentation apparatus, comprising:
the acquisition module is used for acquiring a level set function and an energy functional of an image to be segmented; the evolution of the level set function is governed by the partial differential equation of the level set function;
a solving module, configured to construct a degradation model of the image according to image content, and determine a degradation coefficient of the degradation model according to the level set function and the energy functional, where the solving module is specifically configured to: representing an expression of an energy functional by a level set function of the image, and determining a degradation coefficient of the image according to the expression of the energy functional and the expression of the energy functional infimum; the degradation coefficient is a coefficient used for adjusting an image degradation expression;
and the segmentation module is used for determining a segmentation model of the image according to the degradation coefficient and the step function of the level set function, and segmenting the content of the image according to the segmentation model.
8. A license plate recognition method is characterized by comprising the following steps:
the image content segmentation method according to any one of claims 1 to 6, segmenting characters in a license plate image to be recognized; the image is a license plate image, and the content is characters;
extracting the segmented characters, and identifying each character in the license plate image by matching each extracted character with a character prestored in a database;
and identifying the license plate in the license plate image according to the identification of each character.
9. 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 processor implements the steps of the image content segmentation method according to any one of claims 1 to 6 or the license plate recognition method according to claim 8 when executing the computer program.
10. 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 image content segmentation method according to any one of claims 1 to 6 or the license plate recognition method according to claim 8.
CN201810515635.3A 2018-05-25 2018-05-25 Image content segmentation method and device and license plate recognition method Active CN108846396B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810515635.3A CN108846396B (en) 2018-05-25 2018-05-25 Image content segmentation method and device and license plate recognition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810515635.3A CN108846396B (en) 2018-05-25 2018-05-25 Image content segmentation method and device and license plate recognition method

Publications (2)

Publication Number Publication Date
CN108846396A CN108846396A (en) 2018-11-20
CN108846396B true CN108846396B (en) 2020-11-13

Family

ID=64213612

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810515635.3A Active CN108846396B (en) 2018-05-25 2018-05-25 Image content segmentation method and device and license plate recognition method

Country Status (1)

Country Link
CN (1) CN108846396B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105930831A (en) * 2016-05-19 2016-09-07 湖南博广信息科技有限公司 License plate intelligent identification method
CN106373097A (en) * 2016-08-29 2017-02-01 合肥康胜达智能科技有限公司 Image processing method
CN106447682A (en) * 2016-08-29 2017-02-22 天津大学 Automatic segmentation method for breast MRI focus based on Inter-frame correlation
CN106997596A (en) * 2017-04-01 2017-08-01 太原理工大学 A kind of Lung neoplasm dividing method of the LBF movable contour models based on comentropy and joint vector

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140071125A1 (en) * 2012-09-11 2014-03-13 The Johns Hopkins University Patient-Specific Segmentation, Analysis, and Modeling from 3-Dimensional Ultrasound Image Data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105930831A (en) * 2016-05-19 2016-09-07 湖南博广信息科技有限公司 License plate intelligent identification method
CN106373097A (en) * 2016-08-29 2017-02-01 合肥康胜达智能科技有限公司 Image processing method
CN106447682A (en) * 2016-08-29 2017-02-22 天津大学 Automatic segmentation method for breast MRI focus based on Inter-frame correlation
CN106997596A (en) * 2017-04-01 2017-08-01 太原理工大学 A kind of Lung neoplasm dividing method of the LBF movable contour models based on comentropy and joint vector

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
偏微分方程及其在图像去噪和分割中的应用;辛巧;《中国博士学位论文全文数据库信息科技辑》;20120428;全文 *

Also Published As

Publication number Publication date
CN108846396A (en) 2018-11-20

Similar Documents

Publication Publication Date Title
CN111860670B (en) Domain adaptive model training method, image detection method, device, equipment and medium
CN111192292B (en) Target tracking method and related equipment based on attention mechanism and twin network
US10713532B2 (en) Image recognition method and apparatus
CN110489951B (en) Risk identification method and device, computer equipment and storage medium
EP3971772A1 (en) Model training method and apparatus, and terminal and storage medium
US20180260664A1 (en) Deep-learning network architecture for object detection
CN111080628A (en) Image tampering detection method and device, computer equipment and storage medium
CN112419170B (en) Training method of shielding detection model and beautifying processing method of face image
CN112330685B (en) Image segmentation model training method, image segmentation device and electronic equipment
CN110163842B (en) Building crack detection method and device, computer equipment and storage medium
CN112270686B (en) Image segmentation model training method, image segmentation device and electronic equipment
KR20210060554A (en) Face landmark detection method and device, computer device, and storage medium
CN110046577B (en) Pedestrian attribute prediction method, device, computer equipment and storage medium
CN110633646B (en) Method and device for detecting image sensitive information, computer equipment and storage medium
CN110189341B (en) Image segmentation model training method, image segmentation method and device
CN111914908B (en) Image recognition model training method, image recognition method and related equipment
CN112966685B (en) Attack network training method and device for scene text recognition and related equipment
CN109711381B (en) Target identification method and device of remote sensing image and computer equipment
Lee et al. Facial landmarks detection using improved active shape model on android platform
CN113034514A (en) Sky region segmentation method and device, computer equipment and storage medium
CN111444807A (en) Target detection method, device, electronic equipment and computer readable medium
CN111860582B (en) Image classification model construction method and device, computer equipment and storage medium
CN113469092A (en) Character recognition model generation method and device, computer equipment and storage medium
CN110929730A (en) Image processing method, image processing device, computer equipment and storage medium
US20230342951A1 (en) Object tracking apparatus, object tracking 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