CN112085705B - Image segmentation method and device based on improved goblet sea squirt swarm algorithm - Google Patents
Image segmentation method and device based on improved goblet sea squirt swarm algorithm Download PDFInfo
- Publication number
- CN112085705B CN112085705B CN202010802907.5A CN202010802907A CN112085705B CN 112085705 B CN112085705 B CN 112085705B CN 202010802907 A CN202010802907 A CN 202010802907A CN 112085705 B CN112085705 B CN 112085705B
- Authority
- CN
- China
- Prior art keywords
- image
- individual
- segmentation
- population
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000003709 image segmentation Methods 0.000 title claims abstract description 27
- 241000251555 Tunicata Species 0.000 title claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 38
- 240000005636 Dryobalanops aromatica Species 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000009827 uniform distribution Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 4
- 241000251557 Ascidiacea Species 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 241000282461 Canis lupus Species 0.000 description 2
- 241000283153 Cetacea Species 0.000 description 2
- 238000001793 Wilcoxon signed-rank test Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000003734 kidney Anatomy 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 241000798368 Ecteinascidia Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- 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
Abstract
The invention provides an image segmentation method based on an improved goblet-sea squirt swarm algorithm, which comprises the steps of inputting an image and initializing; generating a gray image by using the original image, and generating a non-local mean filtering image by combining a non-local mean filtering technology; constructing a corresponding two-dimensional histogram according to the gray level image and the non-local mean value filtering image, taking Kapur entropy as an objective function based on the constructed two-dimensional histogram, searching an optimal segmentation threshold by utilizing a goblet sea squirt swarm algorithm based on a skeleton random fractal search mechanism, segmenting the image based on the obtained optimal threshold, and outputting a segmentation result. By implementing the method and the device, the problems of the existing image segmentation algorithm, such as sinking into a local optimal solution, slow convergence speed, poor segmentation quality and the like, can be solved.
Description
Technical Field
The invention relates to the technical field of computer image processing, in particular to an image segmentation method and device based on an improved goblet sea squirt swarm algorithm.
Background
The image segmentation plays a role in assisting the medical diagnosis field, particularly the related diseases of the kidney, and the method with good segmentation effect can greatly promote the medical diagnosis accuracy and improve the diagnosis efficiency.
Multi-threshold segmentation is an efficient and simple segmentation method in the field of image segmentation, and is centered on the determination of the optimal threshold. The quality of the segmentation threshold can directly determine the segmentation quality of the image, and it is known that although the traditional gradient method can obtain the segmentation threshold, the method has larger calculation complexity and the obtained segmentation threshold has poorer quality. The group intelligent optimization algorithm is applied to multi-threshold image segmentation, and is an efficient method with good segmentation effect. However, due to the shortages of the group intelligent optimization method, the segmentation process is easily trapped in local optimization, so that the segmentation quality is poor.
Therefore, in order to avoid the local optimum in the segmentation process as much as possible and obtain better segmentation quality, it is necessary to provide an image segmentation method based on the improved goblet-sea squirt swarm algorithm, which can solve the problems of the existing image segmentation algorithm such as the local optimum solution, slow convergence speed, poor segmentation quality and the like.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide the image segmentation method and the device based on the improved goblet sea squirt swarm algorithm, which can solve the problems of the existing image segmentation algorithm such as sinking into a local optimal solution, slow convergence speed, poor segmentation quality and the like, and achieve the purposes of high operation efficiency and good segmentation effect.
In order to solve the technical problems, the embodiment of the invention provides an image segmentation method based on an improved goblet sea squirt swarm algorithm, which is characterized by comprising the following steps:
step S1: inputting an image to be segmented, and initializing a threshold segmentation level;
step S2: graying an input image to obtain a corresponding gray image, and obtaining a non-local mean value image by using a non-local mean value filtering mode;
step S3: constructing a corresponding two-dimensional histogram according to the gray level image and the non-local mean value filtering image, and taking Kapur entropy as an objective function based on the constructed two-dimensional histogram;
step S4: searching an optimal segmentation threshold by utilizing a goblet-sea squirt swarm algorithm based on a skeleton random fractal search mechanism, segmenting an image based on the obtained optimal threshold, and outputting a segmentation result.
The step S4 specifically includes:
step S41: initializing parameters including the population size pop ize of the sea squirt group, and the maximum Iteration number max_iteration;
step S42: calculating each individual P in the population i The fitness of (a), namely Kapur entropy, and finding the global optimum BP;
step S43: and performing a diffusion process: in the formula (1) and the formula (2), a Gaussian walk mode is selected to create the position of each new individual, and the optimal individual in the population is found out;
GW 1 =Gaussian(μ BP ,σ)+(ε×BP-ε′×P i ) (1)
GW 2 =Gaussian(μ P ,σ) (2)
wherein ε and ε' are in the interval [0, 1]]Random numbers obeying uniform distribution; BP and P i The positions of the optimal individual and the ith individual are respectively represented; mu (mu) BP 、μ P And sigma are both Gaussian parameters, and μ BP Equal to |BP|, μ P Equal to |P i I (I); the standard deviation sigma is calculated by the formula (3),step size used to reduce gaussian jump:
step S44: performing a first update operation: ranking all individuals according to the fitness value, and calculating each individual P according to formula (4) i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein for each individual (P i ) Judging Pa i <Whether epsilon is satisfied; if so, updating each individual P according to equation (5) i Is the j-th component of (2); otherwise, remain unchanged;
P′ i (j)=P r (j)-ε×(P t (j)-P i (j)) (5)
wherein Rank (P i ) For individual P i Ranking in a population; n is the size of the population; p'. i (j) For individual P i Updated position; p (P) r And P t Is a randomly selected individual from a population; epsilon is the interval 0,1]Random numbers obeying uniform distribution;
step S45: performing a second update operation: ranking the updated population of individuals according to the fitness value and calculating each individual P 'according to equation (4)' i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein, for each individual P' i Judging Pa i <Whether epsilon is satisfied; if so, updating P 'according to formula (6)' i And if P i Has a fitness higher than P' i For the adaptation degree of (1), P i Substitution P' i The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, remain unchanged;
wherein P' r And P' t Two individuals randomly selected from the population generated in step S42;is a random number generated by gaussian normal distribution; ε' is the interval [0, 1]]Random numbers obeying uniform distribution;
step S46: checking whether the iteration termination condition is reached, and executing step S47 if the iteration termination condition is reached; otherwise, returning to the step S43 to continue iteration;
step S47: returning the optimal sea squirt position and fitness value to the optimal threshold and the maximum Kapur entropy;
step S48: and dividing the image by using the obtained optimal threshold value.
The embodiment of the invention also provides an image segmentation device based on the improved goblet sea squirt swarm algorithm, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the image segmentation method based on the improved goblet sea squirt swarm algorithm when executing the computer program.
The embodiment of the invention has the following beneficial effects:
1. the invention integrates a Gaussian backbone mechanism and a fractal search mechanism and is used for improving the global search capability and the local search capability of the goblet-sea squirt swarm algorithm based on the skeleton random fractal search mechanism, so that the proposed global search capability and the local search capability of the goblet-sea squirt swarm algorithm based on the skeleton random fractal search mechanism reach a balanced state, thereby solving the problems of the existing image segmentation algorithm such as sinking into a local optimal solution, slow convergence speed, poor segmentation quality and the like, and achieving the purposes of high operation efficiency and good segmentation effect;
2. the segmentation quality of the invention is superior to the original sea Squirt Swarm Algorithm (SSA) and other similar methods, such as Whale Optimization Algorithm (WOA), bat Algorithm (BA), sine Cosine Algorithm (SCA) and gray wolf optimization algorithm (GWO).
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
FIG. 1 is a flowchart of an image segmentation method based on an improved sea squirt swarm algorithm according to an embodiment of the present invention;
fig. 2 is a plan view of a two-dimensional histogram in an image segmentation method based on the modified ecteinascidia group algorithm according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
As shown in fig. 1, in a first embodiment of the present invention, an image segmentation method based on an improved ecteinascidial group algorithm is provided, and the method includes the following steps:
step S1: inputting an image to be segmented, and initializing a threshold segmentation level;
specifically, an image to be segmented (e.g., a kidney pathological image) is input, and a threshold segmentation Level is initialized.
Step S2: graying an input image to obtain a corresponding gray image, and obtaining a non-local mean value image by using a non-local mean value filtering mode;
firstly, carrying out graying treatment on an input image to obtain a gray image; and secondly, obtaining a non-local mean value image by using a non-local mean value filtering mode.
The non-local mean value is a new denoising technology which is proposed by Buades and the like in recent years, fully utilizes redundant information in an image, and maximally reflects the detail characteristics of the image while denoising. The basic idea is that the estimate of the current pixel is obtained by a weighted average of the values of pixels in the image that have a similar neighborhood structure. Assuming that I (p) and I (q) are gray values of pixels p and q in the image I, a non-local average value of the image I can be calculated from formulas (7) to (10).
Where O (p) is a filtered value of a non-local average, μ (p) and μ (q) are local averages, σ is a standard deviation, ω (p, q) is the weights of pixel p and pixel q, and L (p) and L (q) are m×m pixel blocks centered on pixel p and pixel q, respectively.
Step S3: constructing a corresponding two-dimensional histogram according to the gray level image and the non-local mean value filtering image, and taking Kapur entropy as an objective function based on the constructed two-dimensional histogram;
specifically, through the non-local mean image and the gray level image, a corresponding non-local mean two-dimensional histogram can be generated.
Assuming that the gray value level of the original gray image I (x, y) is [0, l-1] and the image size is mxn, the gray value level of the generated non-local mean image g (x, y) is also [0, l-1] and the image size is mxn. Then, a preliminary two-dimensional histogram can be formed from I (x, y) and g (x, y).
If the point (I, j) is formed by I (x, y) and g (x, y), where I represents the pixel value of a certain pixel in I (x, y) and j represents the pixel value of a certain pixel in g (x, y). H (i, j) represents the number of times point (i, j) appears on the gray value vector (s, t). Therefore, after normalization processing is performed, a final two-dimensional histogram can be obtained.
According to the definition of the non-local mean two-dimensional histogram described above, a corresponding two-dimensional plane histogram is given in FIG. 2, where { t } 1 ,t 2 …, L-1} represents the value of the gray scale image, { s 1 ,s 2 …, L-1} represents the value of the non-local mean image. In the two-dimensional histogram, the main diagonal contains the largest amount of image information, so that only Kapur entropy of n sub-regions on the main diagonal is calculated, which can be defined as formula (11).
Wherein,
thus, if Kapur entropy is used as the objective function, then the improved algorithm finds the pairMaximized threshold set { t } 1 ,t 2 ,…,t n-1 Then consider the optimal segmentation threshold.
Step S4: searching an optimal segmentation threshold by utilizing a goblet-sea squirt swarm algorithm based on a skeleton random fractal search mechanism, segmenting an image based on the obtained optimal threshold, and outputting a segmentation result.
Specifically, step S41: initializing parameters including the population size pop ize of the sea squirt group, and the maximum Iteration number max_iteration;
step S42: calculating each individual P in the population i The fitness of (a), namely Kapur entropy, and finding the global optimum BP;
step S43: and performing a diffusion process: in the formula (1) and the formula (2), a Gaussian walk mode is selected to create the position of each new individual, and the optimal individual in the population is found out;
GW 1 =Gaussian(μ BP ,σ)+(ε×BP-ε′×P i ) (1)
GW 2 =Gaussian(μ P ,σ) (2)
wherein ε and ε' are in the interval [0, 1]]Random numbers obeying uniform distribution; BP and P i The positions of the optimal individual and the ith individual are respectively represented; mu (mu) BP 、μ P And sigma are both Gaussian parameters, and μ BP Equal to |BP|, μ P Equal to |P i I (I); the standard deviation sigma is calculated by the formula (3),step size used to reduce gaussian jump:
step S44: performing a first update operation: ranking all individuals according to the fitness value, and calculating each individual P according to formula (4) i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein for each individual (P i ) Judging Pa i <Whether epsilon is satisfied; if so, updating each individual P according to equation (5) i Is the j-th component of (2); otherwise, remain unchanged;
P′ i (j)=P r (j)-ε×(P t (j)-P i (j)) (5)
wherein Rank (P i ) For individual P i Ranking in a population; n is the size of the population; p'. i (j) For individual P i Updated position; p (P) r And P t Is a randomly selected individual from a population; epsilon is the interval 0,1]Random numbers obeying uniform distribution;
step S45: performing a second update operation: ranking the updated population of individuals according to the fitness value and calculating each individual P 'according to equation (4)' i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein, for each individual P' i Judging Pa i <Whether epsilon is satisfied; if so, updating P 'according to formula (6)' i And if P i Has a fitness higher than P' i For the adaptation degree of (1), P i Substitution P' i The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, remain unchanged;
wherein P' r And P' t Two individuals randomly selected from the population generated in step S42;is a random number generated by gaussian normal distribution; ε' is the interval [0, 1]]Random numbers obeying uniform distribution;
step S46: checking whether the iteration termination condition is reached, and executing step S47 if the iteration termination condition is reached; otherwise, returning to the step S43 to continue iteration;
step S47: returning the optimal sea squirt position and fitness value to the optimal threshold and the maximum Kapur entropy;
step S48: and dividing the image by using the obtained optimal threshold value.
Tables 1-3 show further analysis of peak signal to noise ratio (PSNR), structural Similarity (SSIM), feature Similarity (FSIM) evaluation results using Wilcoxon symbol Rank test, where "w" indicates that the segmentation effect of GBSFSSSA is superior to other methods, "t" indicates that the segmentation effect of GBSFSSSA is equal to other methods, "l" indicates that the segmentation effect of GBSFSSSA is inferior to other methods, "Mean" indicates the ranking average of each algorithm across all images, and "Rank" indicates the overall average ranking level of each algorithm. The GBSFSSSA is superior to other algorithms in the results of most images at different threshold levels, as observed by the analysis results of the Wilcoxon signed rank test. In addition, the sequencing mean value of the GBSFSSSA on all images under different threshold levels can be optimal, and the comprehensive mean value sequencing grade of the GBSFSSSA is No.1.
Wherein, the Wilcoxon sign rank test of PSNR evaluation results is shown in the following table 1:
wherein, wilcoxon sign rank test of SSIM evaluation result is shown in the following table 2:
wherein, wilcoxon signed rank test of FSIM evaluation results is shown in the following table 3:
in contrast to the image segmentation method based on the improved ascidian algorithm provided in the first embodiment of the present invention, the second embodiment of the present invention further provides an image segmentation device based on the improved ascidian algorithm, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the image segmentation method based on the improved ascidian algorithm in the first embodiment of the present invention when executing the computer program. It should be noted that, the process of executing the computer program by the processor in the second embodiment of the present invention is consistent with the execution process of each step in the image segmentation method based on the improved goblet-sea squirt swarm algorithm provided in the first embodiment of the present invention, and the description of the foregoing related content will be specifically referred to.
The embodiment of the invention has the following beneficial effects:
1. the invention integrates a Gaussian backbone mechanism and a fractal search mechanism and is used for improving the global search capability and the local search capability of the goblet-sea squirt swarm algorithm based on the skeleton random fractal search mechanism, so that the proposed global search capability and the local search capability of the goblet-sea squirt swarm algorithm based on the skeleton random fractal search mechanism reach a balanced state, thereby solving the problems of the existing image segmentation algorithm such as sinking into a local optimal solution, slow convergence speed, poor segmentation quality and the like, and achieving the purposes of high operation efficiency and good segmentation effect;
2. the segmentation quality of the invention is superior to the original sea Squirt Swarm Algorithm (SSA) and other similar methods, such as Whale Optimization Algorithm (WOA), bat Algorithm (BA), sine Cosine Algorithm (SCA) and gray wolf optimization algorithm (GWO).
Those of ordinary skill in the art will appreciate that all or a portion of the steps in implementing the methods of the above embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (2)
1. An image segmentation method based on an improved goblet sea squirt swarm algorithm is characterized by comprising the following steps:
step S1: inputting an image to be segmented, and initializing a threshold segmentation level;
step S2: graying an input image to obtain a corresponding gray image, and obtaining a non-local mean value image by using a non-local mean value filtering mode;
step S3: constructing a corresponding two-dimensional histogram according to the gray level image and the non-local mean value filtering image, and taking Kapur entropy as an objective function based on the constructed two-dimensional histogram;
step S4: searching an optimal segmentation threshold value by utilizing a goblet-sea squirt swarm algorithm based on a skeleton random fractal search mechanism, segmenting an image based on the obtained optimal threshold value, and outputting a segmentation result;
the step S4 specifically includes:
step S41: initializing parameters including the population size pop ize of the sea squirt group, and the maximum Iteration number max_iteration;
step S42: calculating each individual P in the population i The fitness of (a), namely Kapur entropy, and finding the global optimum BP;
step S43: and performing a diffusion process: in the formula (1) and the formula (2), a Gaussian walk mode is selected to create the position of each new individual, and the optimal individual in the population is found out;
GW 1 =Gaussian(μ BP ,σ)+(ε×BP-ε′×P i ) (1)
GW 2 =Gaussian(μ P ,σ) (2)
wherein ε and ε' are in the interval [0, 1]]Random numbers obeying uniform distribution; BP and P i The positions of the optimal individual and the ith individual are respectively represented; mu (mu) BP 、μ P And sigma are both Gaussian parameters, and μ BP Equal to |BP|, μ P Equal to |P i I (I); the standard deviation sigma is calculated by the formula (3),step size used to reduce gaussian jump:
step S44: performing a first update operation: ranking all individuals according to the fitness value, and calculating each individual P according to formula (4) i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein for each individual (P i ) Judging Pa i <Whether epsilon is satisfied; if so, updating each individual P according to equation (5) i Is the j-th component of (2); otherwise, remain unchanged;
P′ i (j)=P r (j)-ε×(P t (j)-P i (j) (5)
wherein Rank (P i ) For individual P i Ranking in a population; n is the size of the population; p'. i (j) For individual P i Updated position; p (P) r And P t Is a randomly selected individual from a population; epsilon is the interval 0,1]Random numbers obeying uniform distribution;
step S45: performing a second update operation: ranking the updated population of individuals according to the fitness value and calculating each individual P 'according to equation (4)' i Set performance level Pa of (1) i The method comprises the steps of carrying out a first treatment on the surface of the Wherein, for each individual P' i Judging Pa i <Whether epsilon is satisfied; if so, updating P 'according to formula (6)' i And if P i Has a fitness higher than P' i For the adaptation degree of (1), P i Substitution P' i The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, remain unchanged;
wherein P' r And P' t Two individuals randomly selected from the population generated in step S42;is a random number generated by gaussian normal distribution; ε' is the interval [0, 1]]Random numbers obeying uniform distribution;
step S46: checking whether the iteration termination condition is reached, and executing step S47 if the iteration termination condition is reached; otherwise, returning to the step S43 to continue iteration;
step S47: returning the optimal sea squirt position and fitness value to the optimal threshold and the maximum Kapur entropy;
step S48: and dividing the image by using the obtained optimal threshold value.
2. An image segmentation apparatus based on an improved ecteinascidity algorithm comprising a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, performs the steps of the image segmentation method based on an improved ecteinascidity algorithm as recited in claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010802907.5A CN112085705B (en) | 2020-08-11 | 2020-08-11 | Image segmentation method and device based on improved goblet sea squirt swarm algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010802907.5A CN112085705B (en) | 2020-08-11 | 2020-08-11 | Image segmentation method and device based on improved goblet sea squirt swarm algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112085705A CN112085705A (en) | 2020-12-15 |
CN112085705B true CN112085705B (en) | 2024-03-15 |
Family
ID=73736130
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010802907.5A Active CN112085705B (en) | 2020-08-11 | 2020-08-11 | Image segmentation method and device based on improved goblet sea squirt swarm algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112085705B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113177954B (en) * | 2021-04-28 | 2022-07-26 | 中南大学 | Image processing method and device |
CN113763409B (en) * | 2021-08-27 | 2023-05-02 | 南通大学 | Gaussian filtering-based multi-threshold segmentation method for high-dimensional brain nuclear magnetic image |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6445818B1 (en) * | 1998-05-28 | 2002-09-03 | Lg Electronics Inc. | Automatically determining an optimal content image search algorithm by choosing the algorithm based on color |
WO2014000663A1 (en) * | 2012-06-28 | 2014-01-03 | 中兴通讯股份有限公司 | Method and device for implementing stereo imaging |
CN105335960A (en) * | 2014-08-13 | 2016-02-17 | 温州大学 | Image segmentation method combining edge detection algorithm with watershed algorithm |
CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
CN111027663A (en) * | 2019-11-12 | 2020-04-17 | 天津大学 | Method for improving algorithm of goblet sea squirt group |
CN111047528A (en) * | 2019-11-27 | 2020-04-21 | 天津大学 | High-spectrum image unmixing method based on goblet sea squirt group |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107578178B (en) * | 2017-09-11 | 2018-08-28 | 合肥工业大学 | Based on the dispatching method and system for becoming neighborhood search and gravitation search hybrid algorithm |
-
2020
- 2020-08-11 CN CN202010802907.5A patent/CN112085705B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6445818B1 (en) * | 1998-05-28 | 2002-09-03 | Lg Electronics Inc. | Automatically determining an optimal content image search algorithm by choosing the algorithm based on color |
WO2014000663A1 (en) * | 2012-06-28 | 2014-01-03 | 中兴通讯股份有限公司 | Method and device for implementing stereo imaging |
CN105335960A (en) * | 2014-08-13 | 2016-02-17 | 温州大学 | Image segmentation method combining edge detection algorithm with watershed algorithm |
CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
CN111027663A (en) * | 2019-11-12 | 2020-04-17 | 天津大学 | Method for improving algorithm of goblet sea squirt group |
CN111047528A (en) * | 2019-11-27 | 2020-04-21 | 天津大学 | High-spectrum image unmixing method based on goblet sea squirt group |
Non-Patent Citations (2)
Title |
---|
基于天体运动更新机制的改进樽海鞘群算法;张文彬;;上海电力大学学报(02);全文 * |
基于混沌电磁场优化算法的多阈值彩色图像分割;马军;贾鹤鸣;;计算机应用与软件(03);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112085705A (en) | 2020-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Adcrowdnet: An attention-injective deformable convolutional network for crowd understanding | |
Fu et al. | Removing rain from single images via a deep detail network | |
CN110599401A (en) | Remote sensing image super-resolution reconstruction method, processing device and readable storage medium | |
CN112200812B (en) | Two-dimensional segmentation method for multi-threshold image | |
CN112085705B (en) | Image segmentation method and device based on improved goblet sea squirt swarm algorithm | |
Liu et al. | True wide convolutional neural network for image denoising | |
CN113221925A (en) | Target detection method and device based on multi-scale image | |
Gu et al. | A two-component deep learning network for SAR image denoising | |
CN114881861A (en) | Unbalanced image over-resolution method based on double-sampling texture perception distillation learning | |
CN114897694A (en) | Image super-resolution reconstruction method based on mixed attention and double-layer supervision | |
CN115293966A (en) | Face image reconstruction method and device and storage medium | |
CN113191968B (en) | Method for establishing three-dimensional ultrasonic image blind denoising model and application thereof | |
Shen et al. | Deeper super-resolution generative adversarial network with gradient penalty for sonar image enhancement | |
Gu et al. | Generative adversarial networks for robust cryo-EM image denoising | |
Jiang et al. | Lightweight semi-supervised network for single image rain removal | |
Irie et al. | Robust learning for deep monocular depth estimation | |
CN116452812A (en) | Camouflage object identification and semantic segmentation method | |
Wang et al. | Face super-resolution via hierarchical multi-scale residual fusion network | |
Chen et al. | Adaptive multi-modality residual network for compression distorted multi-view depth video enhancement | |
CN115761358A (en) | Method for classifying myocardial fibrosis based on residual capsule network | |
Li et al. | Super-resolution reconstruction of underwater image based on image sequence generative adversarial network | |
Shao et al. | Semantic segmentation method of 3D liver image based on contextual attention model | |
CN113570555B (en) | Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm | |
Chen et al. | Application of optimized convolution neural network model in mural segmentation | |
CN112734678B (en) | Image motion blur removing method based on depth residual shrinkage network and generation countermeasure network |
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 |