CN115984312A - Image segmentation method, electronic device and computer-readable storage medium - Google Patents

Image segmentation method, electronic device and computer-readable storage medium Download PDF

Info

Publication number
CN115984312A
CN115984312A CN202310247108.XA CN202310247108A CN115984312A CN 115984312 A CN115984312 A CN 115984312A CN 202310247108 A CN202310247108 A CN 202310247108A CN 115984312 A CN115984312 A CN 115984312A
Authority
CN
China
Prior art keywords
level set
image
iteration
set function
target image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310247108.XA
Other languages
Chinese (zh)
Other versions
CN115984312B (en
Inventor
董斌
倪锦根
翁桂荣
卜倩倩
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.)
Suzhou University
Original Assignee
Suzhou University
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 Suzhou University filed Critical Suzhou University
Priority to CN202310247108.XA priority Critical patent/CN115984312B/en
Publication of CN115984312A publication Critical patent/CN115984312A/en
Application granted granted Critical
Publication of CN115984312B publication Critical patent/CN115984312B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an image segmentation method, electronic equipment and a computer-readable storage medium. The method comprises the following steps: s1, setting an initial contour line in a target image, and representing the initial contour line by using an initial level set function; s2, updating and iterating the initial level set function; and S3, taking the level set function obtained by the last iteration as a segmentation curve of the target image. The image segmentation method of the invention replaces the length term in the traditional active contour model by the mean filter and is used for smoothing the segmentation curve; and (3) replacing a distance rule item in the traditional active contour model by an activation function, wherein the activation function is used for keeping the level set function to be a rule that the values on the contour line and inside the contour line are negative and the value outside the contour line is positive all the time in the iterative process. The image segmentation method has ideal segmentation effect on the image with uneven gray scale, and has advantages in both segmentation speed and segmentation accuracy.

Description

Image segmentation method, electronic device and computer-readable storage medium
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image segmentation method, an electronic device, and a computer-readable storage medium.
Background
Image segmentation is an important research topic in the field of image processing, and divides an image into a plurality of non-overlapping regions, extracts interested targets (such as foreground and background) from the regions, and lays a foundation for subsequent image target identification and feature analysis.
The active contour model is the most representative image segmentation method in recent decades, and is also a research hotspot of the current image segmentation method. The basic idea of the active contour model is to set an initial contour line on an image, drive the contour line evolution by using an energy function based on a level set method, make the contour line approximate to a target boundary and realize target segmentation. The algorithm can obtain the accuracy of the target boundary subpixel level and provide a smooth closed contour as a segmentation result.
The main existing active contour model mainly has the following technical problems: the segmentation effect on the gray scale unevenness of local areas is poor, and some false targets in the image cannot be distinguished. Therefore, a new image segmentation method is needed to solve the above problems.
Disclosure of Invention
Therefore, an object of the present invention is to provide an image segmentation method capable of effectively segmenting an image with non-uniform gray scale and having high segmentation accuracy.
In order to solve the above technical problem, the present invention provides an image segmentation method, which comprises the following steps:
s1, setting an initial contour line in a target image, and representing the initial contour line by using an initial level set function;
s2, updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure SMS_1
wherein is present>
Figure SMS_5
Is the window size is->
Figure SMS_7
The average filter of (1); softsign is a softsign activation function; />
Figure SMS_3
Is a constant; />
Figure SMS_4
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure SMS_6
Is the level set function at the n-1 th iteration; />
Figure SMS_8
Is a gradient descent equation in the (n-1) th iteration; />
Figure SMS_2
Is the time step;
and S3, taking the level set function obtained by the last iteration as a segmentation curve of the target image.
In one embodiment of the present invention, the gradient descent equation at the n-1 th iteration is:
Figure SMS_28
wherein is present>
Figure SMS_32
Is a constant; />
Figure SMS_35
The standard deviation of the gray scale of the target image is taken; function>
Figure SMS_10
Is a function->
Figure SMS_14
Is greater than or equal to>
Figure SMS_18
；
Figure SMS_23
For data-driven items, y is a vector pixel in the target image, and->
Figure SMS_25
Is based on y as the center point and side length as->
Figure SMS_27
The square neighborhood of (a) is,
Figure SMS_30
is a Gaussian kernel function>
Figure SMS_33
Is the standard deviation of a Gaussian kernel function>
Figure SMS_29
To make->
Figure SMS_31
A normalization constant of (d); />
Figure SMS_34
The real gray value of the target image is obtained; />
Figure SMS_36
For image shadow values fitted by calculation, <' >>
Figure SMS_16
Is window sized>
Figure SMS_20
Based on the mean value of>
Figure SMS_22
Is constant and is->
Figure SMS_26
Performing convolution operation;
Figure SMS_9
the value is the edge reflection structure information value in the (n-1) th iteration; when i =1, in>
Figure SMS_13
Is a region->
Figure SMS_19
The edge reflection structure information value of (1),
Figure SMS_24
(ii) a When i =2, in>
Figure SMS_11
Is a region->
Figure SMS_15
An edge reflection configuration information value of in->
Figure SMS_17
；/>
Figure SMS_21
Is an outer region of the contour line>
Figure SMS_12
The contour lines and the interior regions of the contour lines.
In one embodiment of the present invention, the standard deviation of the target image gray scale is:
Figure SMS_37
，
wherein the content of the first and second substances,
Figure SMS_38
an image domain of the target image; />
Figure SMS_39
The total number of pixel points in the target image is obtained; />
Figure SMS_40
Is the average gray value of the target image.
In one embodiment of the invention, the initial level set function is:
Figure SMS_41
。
in one embodiment of the present invention, step S3 comprises:
when in use
Figure SMS_42
Stopping iteration, and taking a level set function obtained by the last iteration as a segmentation curve of the target image; wherein +>
Figure SMS_43
Is a constant.
In one embodiment of the present invention,
Figure SMS_44
has a value range of [0.001, 0.0001 ]]。
In one embodiment of the present invention, the,
Figure SMS_45
has a value range of [0.5, 2 ]]。/>
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the program.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any of the above.
The invention also provides an image segmentation system, which comprises the following modules:
the initial level set module is used for setting an initial contour line in the target image and representing the initial contour line by using an initial level set function;
the iteration module is used for updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure SMS_48
wherein is present>
Figure SMS_50
Is the window size is->
Figure SMS_52
The average filter of (1); softsign is a softsign activation function; />
Figure SMS_46
Is a constant; />
Figure SMS_49
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure SMS_51
Is the level set function at the n-1 th iteration; />
Figure SMS_53
Is a gradient descent equation in the (n-1) th iteration; />
Figure SMS_47
Is the time step;
and the segmentation curve determination module is used for taking the level set function obtained by the last iteration as the segmentation curve of the target image.
Compared with the prior art, the technical scheme of the invention has the following advantages:
the image segmentation method provided by the invention adopts the optimized level set function to update the discrete level set function by setting the initial level set function during each iteration. Wherein, the length term in the traditional active contour model is replaced by an average filter for smoothing a segmentation curve; and (3) replacing a distance rule item in the traditional active contour model by an activation function, wherein the activation function is used for keeping the level set function always in the iterative process to keep the values on the contour line and inside the contour line to be negative and the value outside the contour line to be positive. Thereby realizing an ideal segmentation effect for an image with uneven gradation and having advantages in both segmentation speed and segmentation accuracy.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
In order that the present disclosure may be more readily understood, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings
FIG. 1 is a flow chart of a method of image segmentation in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an image segmentation method in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of the present invention for segmenting an image with non-uniform gray scale by using an image segmentation method;
FIG. 4 is a diagram illustrating the robustness of an image segmentation method to noise in an embodiment of the present invention;
FIG. 5 is a comparison diagram of segmentation of an image using different models according to an embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Example one
Referring to fig. 1, the present embodiment discloses an image segmentation method, which includes the following steps:
s1, setting an initial contour line in a target image, and representing the initial contour line by using an initial level set function;
specifically, referring to FIG. 2, for the target image I, the continuous image domain is
Figure SMS_67
X and y are image fields->
Figure SMS_57
Inner vector pixel point, setting initial contour line C 0 Based on the image field->
Figure SMS_63
Divided into two sub-areas->
Figure SMS_68
And &>
Figure SMS_71
，/>
Figure SMS_70
Represents the outer region of the initial contour, and>
Figure SMS_72
the initial contour line and the internal region of the initial contour line are shown. For an image field->
Figure SMS_65
At any point y in the interior, there is a point which takes y as the center point and has the side length->
Figure SMS_69
Is greater than or equal to>
Figure SMS_54
Wherein is present>
Figure SMS_60
Is a Gaussian kernel function>
Figure SMS_56
Is the standard deviation of a Gaussian kernel function>
Figure SMS_59
To make->
Figure SMS_62
Is calculated as a normalized constant. When point y is close to C 0 When, is greater or less>
Figure SMS_66
And sub-region/>
Figure SMS_55
And &>
Figure SMS_58
All have an intersection, i.e.>
Figure SMS_61
And &>
Figure SMS_64
。
Further, based on the level set method, an initial level set function is used
Figure SMS_73
To represent the initial contour line C 0 And is specified in the initial contour line C 0 Upper and initial contour C 0 In the interior of (2), an initial level set function>
Figure SMS_74
Are all-1, and in the initial contour line C 0 Outside of, the initial level set function>
Figure SMS_75
All have a value of 1. Level set function ^ based on nth iteration (n is greater than or equal to 1)>
Figure SMS_76
To represent a curve C n As the final segmentation result.
Specifically, the initial level set function is represented as:
Figure SMS_77
。
s2, updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure SMS_79
wherein is present>
Figure SMS_82
Is the window size is->
Figure SMS_84
The average filter of (1); softsign is a softsign activation function; />
Figure SMS_80
Is a constant; />
Figure SMS_83
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure SMS_85
Is the level set function at the n-1 th iteration; />
Figure SMS_87
Is a gradient descent equation in the (n-1) th iteration; />
Figure SMS_78
Is the time step; optionally, is selected>
Figure SMS_81
Has a value range of [0.5, 2 ]]In the present embodiment, is present>
Figure SMS_86
=1。
Specifically, the definition of the activation function softsign is:
Figure SMS_88
(ii) a And (3) replacing a distance rule item in the traditional active contour model by activating a softsign function, wherein the softsign function is used for keeping a rule that the values on the contour line and inside the contour line are negative and the value outside the contour line is positive all the time in the iteration process. />
Specifically, the gradient descent equation at the (n-1) th iteration is:
Figure SMS_106
in which>
Figure SMS_110
Is a constant; />
Figure SMS_113
The standard deviation of the gray scale of the target image is taken; function->
Figure SMS_90
Is a function->
Figure SMS_94
Is greater than or equal to>
Figure SMS_98
；
Figure SMS_102
For data-driven items, y is a vector pixel in the target image, and->
Figure SMS_105
Is based on y as the center point and side length as->
Figure SMS_108
The square neighborhood of (a) is,
Figure SMS_112
is a Gaussian kernel function>
Figure SMS_115
Is the standard deviation of a Gaussian kernel function>
Figure SMS_109
To make->
Figure SMS_111
A normalization constant of (d); />
Figure SMS_114
The real gray value of the target image is obtained; />
Figure SMS_116
For images fitted by calculationShadow value->
Figure SMS_92
Is the window size is->
Figure SMS_95
Based on the mean value of>
Figure SMS_99
Is constant->
Figure SMS_103
Performing convolution operation;
Figure SMS_89
the value is the edge reflection structure information value in the (n-1) th iteration; when i =1, is selected>
Figure SMS_93
Is a region->
Figure SMS_97
The edge reflection structure information value of (1),
Figure SMS_100
(ii) a When i =2, in>
Figure SMS_91
Is a region->
Figure SMS_96
An edge reflection configuration information value of in->
Figure SMS_101
；/>
Figure SMS_104
Is an outer region of the contour line>
Figure SMS_107
The contour lines and the interior regions of the contour lines.
Further, the standard deviation of the target image gray scale is:
Figure SMS_117
，
wherein the content of the first and second substances,
Figure SMS_118
an image domain of the target image; />
Figure SMS_119
The total number of pixel points in the target image is obtained; />
Figure SMS_120
Is the average gray value of the target image.
And S3, taking the level set function obtained by the last iteration as a segmentation curve of the target image.
In particular when
Figure SMS_121
Stopping iteration, and taking a level set function obtained by the last iteration as a segmentation curve of the target image; wherein it is present>
Figure SMS_122
Is constant, optionally, is selected>
Figure SMS_123
Has a value range of [0.001, 0.0001 ]]In the present embodiment, is present>
Figure SMS_124
Is 0.001./>
The image shading values proposed in the present embodiment
Figure SMS_125
The method is a comprehensive measurement of the intensity of the whole image, and the calculation result is one-time and does not need to be updated through iteration. Edge reflection configuration information value->
Figure SMS_126
The region with obvious change of brightness in the image is embodied, so that iteration of the level set function is guided, and the contour line evolves towards the target boundary.
In the optimized length term calculation method in the present embodiment,
Figure SMS_127
actually, filtering processing is carried out on the level set function after each iteration, and compared with the traditional method in which the length term needs to be updated through iteration, the method has higher calculation speed. At the same time, the activation function softsign is used to implement a distance rule term, in which the level-set function->
Figure SMS_128
Outside only one constant->
Figure SMS_129
And no parameter needing to be adjusted exists, so that the robustness of the method is improved.
In order to prove the effectiveness of the invention, the performance of the proposed method is verified by a computer experiment method, and a comparison experiment is carried out with two multiplicative bias field models.
A. The experimental conditions are as follows:
all experiments were carried out in MATLAB2015b on a 2.6-GHz Intel core i5 personal computer. Images used for the experiments were all from a standard gallery. The color image is converted to a grayscale image before segmentation. In all experiments, the solid rectangular line represents the initial contour and the dashed line represents the final segmentation curve.
B. The experimental steps are as follows:
the parameters were set as follows:
Figure SMS_130
，/>
Figure SMS_131
，
Figure SMS_132
and setting the maximum iteration number N and the initial contour line.
C. The experimental results are as follows:
(1) Segmentation experiment
Selecting 5 images with uneven gray levels from BSDS image library, and using the image of the inventionThe image segmentation method segments the five images. As shown in FIG. 3, the first column is the original image and the initial contour, the second column is the shadow of the image, and the third column is at the nth iteration
Figure SMS_133
In the figure, the fourth column shows the final segmentation result. Table 1 shows the number of iterations and the data averaged over 10 independent experiments for the segmentation.
TABLE 1 iteration number and time for five images by the image segmentation method of the present invention
Figure SMS_134
(2) Noise robustness experiment
In order to evaluate the robustness of the image segmentation method to noise, 5 gray images are selected from a BSDS image library, gaussian noise with the average value of 0 and the variance of 0.03 is artificially added, and the original image and the image added with the noise are respectively segmented by the image segmentation method. As shown in FIG. 4, the first column is the original image and the initial contour, the second column is the segmentation result of the image segmentation method according to the present invention on the original image, and the third column is the segmentation result of the image segmentation method according to the present invention on the image after noise addition. The segmentation results of the images without noise and with noise are close to each other, which shows that the image segmentation method has robustness to noise.
(3) Comparative experiment
7 complex color images are selected from a BSDS (binary active contour) image library, and the 7 complex color images are segmented by using a PBCACM (pre-fitting bias active contour model), a JDACM (Jeffreys differential active contour model) and an image segmentation method in the invention respectively. As shown in fig. 5, the first column is the original image and the initial contour, the second column is the segmentation result of the PBC model, the third column is the segmentation result of the JDACM model, and the fourth column is the segmentation result of the image segmentation method according to the present invention.
TABLE 2 time of segmentation of three models (seconds)
Figure SMS_135
TABLE 3 DSC and IOU of the three models (DSC/IOU)
Figure SMS_136
When the table 2 shows the division of the three models, the data in the table shows that the ERSI model is superior to other models in speed. The segmentation accuracy of each model was quantitatively compared with two reference standards, namely DSC (Dice similarity Coefficient) and IOU (interaction of Union). DSC is defined as
Figure SMS_137
IOU is defined as ^ 4>
Figure SMS_138
Wherein S is 1 Is the target region obtained experimentally, S 2 Is a standard target area provided in the BSDS gallery. The closer the DSC and IOU values are to 1, the better the splitting effect. Table 3 compares DSC and IOU values for the three models. As can be seen from the data in the table, the image segmentation method of the invention also has advantages in segmentation accuracy.
Example two
The embodiment discloses an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the method in the first embodiment.
EXAMPLE III
The present embodiment discloses a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method described in the first embodiment.
Example four
The embodiment discloses an image segmentation system, which comprises the following modules:
the initial level set module is used for setting an initial contour line in the target image and representing the initial contour line by using an initial level set function;
the iteration module is used for updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure SMS_140
wherein is present>
Figure SMS_142
Is the window size is->
Figure SMS_144
The average filter of (1); softsign is a softsign activation function; />
Figure SMS_141
Is a constant; />
Figure SMS_143
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure SMS_145
Is the level set function at the n-1 th iteration; />
Figure SMS_146
Is a gradient descent equation in the (n-1) th iteration; />
Figure SMS_139
Is the time step;
and the segmentation curve determination module is used for taking the level set function obtained by the last iteration as the segmentation curve of the target image.
The image segmentation system in the embodiment of the present invention is used to implement the foregoing image segmentation method, and therefore, the detailed implementation of the system can be seen in the foregoing embodiment of the image segmentation method, and therefore, the detailed implementation thereof can refer to the description of the corresponding respective partial embodiments, and is not further described herein.
In addition, since the image segmentation system of the present embodiment is used for implementing the aforementioned image segmentation method, the role thereof corresponds to that of the aforementioned method, and is not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of the invention may be made without departing from the spirit or scope of the invention.

Claims (10)

1. An image segmentation method, characterized by comprising the steps of:
s1, setting an initial contour line in a target image, and representing the initial contour line by using an initial level set function;
s2, updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure QLYQS_3
wherein is present>
Figure QLYQS_5
Is a window size of
Figure QLYQS_7
The average filter of (1); softsign is a softsign activation function; />
Figure QLYQS_2
Is a constant; />
Figure QLYQS_4
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure QLYQS_6
Is the level set function at the n-1 th iteration;
Figure QLYQS_8
is a gradient descent equation in the (n-1) th iteration; />
Figure QLYQS_1
Is the time step;
and S3, taking the level set function obtained by the last iteration as a segmentation curve of the target image.
2. The image segmentation method according to claim 1, wherein the gradient descent equation at the n-1 th iteration is:
Figure QLYQS_11
wherein is present>
Figure QLYQS_15
Is a constant; />
Figure QLYQS_17
The standard deviation of the gray scale of the target image is taken; function->
Figure QLYQS_10
Is a function>
Figure QLYQS_13
The derivative function of (a) is,
Figure QLYQS_18
；
Figure QLYQS_21
is a data driving item, y is a vector pixel point in the target image, and>
Figure QLYQS_12
is based on y as the center point and side length as->
Figure QLYQS_25
Of square adjacent toThe domain(s) is (are),
Figure QLYQS_29
in a Gaussian kernel function>
Figure QLYQS_34
Is the standard deviation of a Gaussian kernel function>
Figure QLYQS_28
To make->
Figure QLYQS_31
A normalization constant of (d); />
Figure QLYQS_35
The real gray value of the target image is obtained; />
Figure QLYQS_36
For the image shadow value fitted by calculation, <' >>
Figure QLYQS_22
Is the window size is->
Figure QLYQS_26
Based on the mean value of>
Figure QLYQS_30
Is constant and is->
Figure QLYQS_33
Performing convolution operation;
Figure QLYQS_9
the value is the edge reflection structure information value in the (n-1) th iteration; when i =1, is selected>
Figure QLYQS_14
Is a region->
Figure QLYQS_16
The edge reflection structure information value of (1),
Figure QLYQS_19
(ii) a When i =2, is selected>
Figure QLYQS_20
Is a region->
Figure QLYQS_23
An edge reflection configuration information value of in->
Figure QLYQS_27
；/>
Figure QLYQS_32
Is an outer region of the contour line>
Figure QLYQS_24
The contour lines and the interior regions of the contour lines.
3. The image segmentation method according to claim 2, wherein the standard deviation of the target image gray scale is:
Figure QLYQS_37
，
wherein the content of the first and second substances,
Figure QLYQS_38
an image domain of the target image; />
Figure QLYQS_39
The total number of pixel points in the target image is obtained; />
Figure QLYQS_40
Is the average gray value of the target image.
4. The image segmentation method according to claim 1, characterized in that the initial level set function is:
Figure QLYQS_41
。
5. the image segmentation method according to claim 1, wherein step S3 comprises:
when in use
Figure QLYQS_42
Stopping iteration, and taking a level set function obtained by the last iteration as a segmentation curve of the target image; wherein it is present>
Figure QLYQS_43
Is a constant.
6. The image segmentation method according to claim 5,
Figure QLYQS_44
has a value range of [0.001, 0.0001 ]]。
7. The image segmentation method according to claim 1,
Figure QLYQS_45
has a value range of [0.5, 2 ]]。
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any of claims 1 to 7 are implemented when the program is executed by the processor.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An image segmentation system, comprising the following modules:
the initial level set module is used for setting an initial contour line in the target image and representing the initial contour line by using an initial level set function;
the iteration module is used for updating and iterating the initial level set function; the level set function at the nth iteration is:
Figure QLYQS_47
wherein is present>
Figure QLYQS_50
Is a window size of
Figure QLYQS_52
The average filter of (1); softsign is a softsign activation function; />
Figure QLYQS_48
Is a constant; />
Figure QLYQS_49
Is the level set function at the nth iteration; x is a vector pixel point in the target image; />
Figure QLYQS_51
Is the level set function at the n-1 th iteration;
Figure QLYQS_53
is a gradient descent equation in the (n-1) th iteration; />
Figure QLYQS_46
Is the time step;
and the segmentation curve determination module is used for taking the level set function obtained by the last iteration as the segmentation curve of the target image.
CN202310247108.XA 2023-03-15 2023-03-15 Image segmentation method, electronic device and computer readable storage medium Active CN115984312B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310247108.XA CN115984312B (en) 2023-03-15 2023-03-15 Image segmentation method, electronic device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310247108.XA CN115984312B (en) 2023-03-15 2023-03-15 Image segmentation method, electronic device and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN115984312A true CN115984312A (en) 2023-04-18
CN115984312B CN115984312B (en) 2023-07-07

Family

ID=85968353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310247108.XA Active CN115984312B (en) 2023-03-15 2023-03-15 Image segmentation method, electronic device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN115984312B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117593323A (en) * 2024-01-19 2024-02-23 苏州大学 Image segmentation method, system, medium and device based on non-local features
CN117994277A (en) * 2024-04-02 2024-05-07 苏州大学 Target segmentation method, device, medium and system for non-uniform illumination image

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3327963A1 (en) * 2016-11-29 2018-05-30 Alcatel Lucent Optical multiplexing device and associated equipment and method
CN111462145A (en) * 2020-04-01 2020-07-28 重庆大学 Active contour image segmentation method based on double-weight symbol pressure function
US20210104023A1 (en) * 2020-05-18 2021-04-08 Shanghai United Imaging Healthcare Co., Ltd. Systems and methods for image reconstruction
CN114584870A (en) * 2022-02-28 2022-06-03 武汉光迅科技股份有限公司 Device and method for compensating originating signal frequency spectrum imbalance in optical module

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3327963A1 (en) * 2016-11-29 2018-05-30 Alcatel Lucent Optical multiplexing device and associated equipment and method
CN111462145A (en) * 2020-04-01 2020-07-28 重庆大学 Active contour image segmentation method based on double-weight symbol pressure function
US20210104023A1 (en) * 2020-05-18 2021-04-08 Shanghai United Imaging Healthcare Co., Ltd. Systems and methods for image reconstruction
CN114584870A (en) * 2022-02-28 2022-06-03 武汉光迅科技股份有限公司 Device and method for compensating originating signal frequency spectrum imbalance in optical module

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117593323A (en) * 2024-01-19 2024-02-23 苏州大学 Image segmentation method, system, medium and device based on non-local features
CN117593323B (en) * 2024-01-19 2024-03-29 苏州大学 Image segmentation method, system, medium and device based on non-local features
CN117994277A (en) * 2024-04-02 2024-05-07 苏州大学 Target segmentation method, device, medium and system for non-uniform illumination image
CN117994277B (en) * 2024-04-02 2024-06-07 苏州大学 Target segmentation method, device, medium and system for non-uniform illumination image

Also Published As

Publication number Publication date
CN115984312B (en) 2023-07-07

Similar Documents

Publication Publication Date Title
Weng et al. A level set method based on additive bias correction for image segmentation
CN115984312A (en) Image segmentation method, electronic device and computer-readable storage medium
US20090290795A1 (en) Geodesic Image and Video Processing
CN106709964B (en) Sketch generation method and device based on gradient correction and multidirectional texture extraction
CN117173201B (en) Second order differential image segmentation method, system, medium and device
CN110969046B (en) Face recognition method, face recognition device and computer-readable storage medium
CN111754538B (en) Threshold segmentation method for USB surface defect detection
Feng et al. URNet: A U-Net based residual network for image dehazing
CN111681198A (en) Morphological attribute filtering multimode fusion imaging method, system and medium
Graf et al. Robust segmentation of relevant regions in low depth of field images
CN113505702A (en) Pavement disease identification method and system based on double neural network optimization
CN113643302B (en) Active contour model-based unsupervised medical image segmentation method and system
Liu et al. Two‐stage image smoothing based on edge‐patch histogram equalisation and patch decomposition
CN117808835A (en) Image processing method based on deep learning and local pre-fitting
CN110176021B (en) Level set image segmentation method and system for saliency information combined with brightness correction
CN107945186A (en) Method, apparatus, computer-readable recording medium and the terminal device of segmentation figure picture
CN109241865B (en) Vehicle detection segmentation algorithm under weak contrast traffic scene
CN116739943A (en) Image smoothing method and target contour extraction method
CN113344935B (en) Image segmentation method and system based on multi-scale difficulty perception
CN115564727A (en) Method and system for detecting abnormal defects of exposure development
CN114596320A (en) Image segmentation method and device based on ALSLCV model
Lei et al. A robust hybrid active contour model based on pre-fitting bias field correction for fast image segmentation
CN113781515A (en) Cell image segmentation method, device and computer readable storage medium
Long et al. Spectrum decomposition in Gaussian scale space for uneven illumination image binarization
Li et al. Peach surface defect identification of complex background based on IDCNN and GWOABC-KM

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