CN113570555B - Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm - Google Patents

Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm Download PDF

Info

Publication number
CN113570555B
CN113570555B CN202110767492.7A CN202110767492A CN113570555B CN 113570555 B CN113570555 B CN 113570555B CN 202110767492 A CN202110767492 A CN 202110767492A CN 113570555 B CN113570555 B CN 113570555B
Authority
CN
China
Prior art keywords
grasshopper
population
position updating
iteration
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.)
Active
Application number
CN202110767492.7A
Other languages
Chinese (zh)
Other versions
CN113570555A (en
Inventor
陈慧灵
赵松伟
李成业
汪鹏君
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.)
Wenzhou University
Original Assignee
Wenzhou 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 Wenzhou University filed Critical Wenzhou University
Priority to CN202110767492.7A priority Critical patent/CN113570555B/en
Publication of CN113570555A publication Critical patent/CN113570555A/en
Application granted granted Critical
Publication of CN113570555B publication Critical patent/CN113570555B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/004Artificial life, i.e. computing arrangements simulating life
    • G06N3/006Artificial 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]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20021Dividing image into blocks, subimages or windows
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

A two-dimensional segmentation method of a multi-threshold medical image based on an improved grasshopper algorithm comprises the following steps: step 8: based on the first position updating of grasshoppers, the position updating of each grasshopper is performed again according to the position updating method of the triangle replacement strategy; step 9: based on the updated grasshopper population, the cauchy variation is carried out on the population individuals, and the local development is increased; step 10: checking whether the iteration termination condition is met, if so, executing the step 11, otherwise, returning to the step 5 to continue iteration; step 11: returning the optimal grasshopper position and the fitness value as an optimal threshold value and a maximum Kapur entropy; step 12: and dividing the medical image by using the obtained optimal threshold value. According to the invention, the triangular substitution strategy and the cauchy variation are adopted, so that the grasshopper algorithm searching capability and optimization precision can be improved, the situation that local optimization is involved in the segmentation process is avoided, and the segmentation quality of medical images can be improved.

Description

Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm
Technical Field
The invention relates to the technical field of image processing, in particular to a two-dimensional segmentation method of a multi-threshold medical image based on an improved grasshopper algorithm.
Background
The recognition and understanding of images are core technologies of modern medical imaging equipment, wherein the recognition and understanding of images are mostly dependent on the quality of image segmentation. Image segmentation, which is a classical problem in computer vision research and has become a focus of attention in the field of image understanding, is the first step of image analysis, is the basis of computer vision, is an important component of image understanding, and is one of the most difficult problems in image processing. Therefore, a segmentation method capable of obtaining a high quality segmentation result is particularly important.
In recent years, various image segmentation techniques have been proposed, in which a multi-threshold image segmentation technique is a very simple and efficient method, the core of which is the selection of a threshold value, which enables a more outstanding segmentation effect to be obtained. It is well known that the conventional gradient method can obtain a segmentation threshold, but the method has large computational complexity and the quality of the obtained segmentation threshold is poor.
Among various multi-threshold image segmentation methods, a histogram-based image segmentation method is one of the most commonly used methods. Image segmentation based on a histogram is mainly divided into a one-dimensional histogram and a two-dimensional histogram, wherein the one-dimensional histogram cannot effectively utilize spatial information of an image, and the segmentation is easy to be interfered by noise. Accordingly, abutaleb proposes a multi-threshold image segmentation method based on a two-dimensional histogram, which combines the original gray values with the local average of the pixels. However, when a two-dimensional histogram is applied to multi-threshold image segmentation, if the exhaustion method is directly adopted to find the optimal threshold, the computational complexity of the segmentation is very high. To effectively avoid this phenomenon, many researchers apply swarm intelligence algorithms to assist in finding the optimal threshold and achieve significant results. However, the method proposed by Abutaleb for image segmentation is a way of using local means, which does not take into account certain details of the picture, such as certain points and edges.
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 for pixels p and q in image I, a non-local average of image I can be calculated from Eq. (1) -Eq. (4).
Where O (p) is a filtered value of the 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 pixel blocks centered on pixel p and pixel q, respectively.
As shown in fig. 1, by the non-local mean image and the gray scale image, a corresponding non-local mean two-dimensional histogram may 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). Thus, the joint probability density of the point (i, j) is obtained by Eq. (5), and 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. 1, where { t } 1 ,t 2 …, L-1} represents a gray scale imageOf { s }, a value of 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, and therefore only Kapur entropy of n sub-regions on the main diagonal is calculated, which can be defined as Eq. (6).
Wherein,
taking the entropy of Kapur as an objective function, then find the cause based on grasshopper optimization algorithmMaximized threshold set { t } 1 ,t 2 ,...,t n-1 ]Then the optimal segmentation threshold is considered.
However, in the process of searching the optimal segmentation threshold, the grasshopper optimization algorithm is unbalanced in exploration and development, so that the situation of local optimization is easy to occur and fall into, and the segmentation quality of the final medical image is low.
Therefore, there is an urgent need to study a two-dimensional segmentation method of multi-threshold medical images based on an improved grasshopper algorithm to obtain better image segmentation quality.
Disclosure of Invention
In order to solve one or more problems in the prior art, the applicant finds that, through research, the search capability and optimization accuracy of grasshopper algorithm can be improved by adopting a triangular replacement strategy and cauchy variation, wherein grasshopper firstly completes the position update of the first round according to an original search mechanism, then completes the position update of a population by utilizing a position update mechanism of the triangular replacement strategy, so as to balance the search and development capability of the algorithm, then mutates the population by utilizing cauchy variation, and improves the possibility of searching the optimal solution of the population, so as to avoid trapping local optimization in the segmentation process and improve the segmentation quality of medical images.
Specifically, according to an aspect of the present invention, there is provided a two-dimensional segmentation method of a multi-threshold medical image based on an improved grasshopper algorithm, including the steps of:
step 1: inputting a medical image to be segmented, and initializing a threshold segmentation Level;
step 2: initializing parameters, namely, the size of grasshopper population is pop, and the maximum Iteration number max_iteration is equal to that of grasshopper population;
step 3: 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 4: initializing grasshopper population X i (i=1,2,...,n);
Step 5: calculating the fitness value of all grasshoppers, namely Kapur entropy;
step 6: determining the optimal grasshopper position and fitness value;
step 7: according to the position updating mode of the grasshopper, finishing the first position updating of the grasshopper population;
step 8: based on the first position updating of grasshoppers, the position updating of each grasshopper is performed again according to the position updating method of the triangle replacement strategy;
step 9: based on the updated grasshopper population, the cauchy variation is carried out on the population individuals, and the local development is increased;
step 10: checking whether the iteration termination condition is met, if so, executing the step 11, otherwise, returning to the step 5 to continue iteration;
step 11: returning the optimal grasshopper position and the fitness value as an optimal threshold value and a maximum Kapur entropy;
step 12: and dividing the medical image by using the obtained optimal threshold value.
According to yet another aspect of the present invention, step 8 specifically includes: based on the first position updating of grasshoppers, the position updating method of the triangle replacement strategy according to the formula (7) carries out the position updating of each grasshopper again;
wherein t is the current iteration number, i represents the ith individual in the population, bp t Is the optimal solution of the t-th iteration, r 2 ,r 3 And r 4 Are all random numbers, r 2 In the range of 0-2 pi, r 3 In the range of 0-2, r 4 Is in the range of 0-1; a is a constant set to 2.
According to yet another aspect of the present invention, step 9 specifically includes: based on the updated grasshopper population, carrying out local development on population individuals according to the cauchy variation of formulas (9) - (11), and increasing the possibility of finding an optimal solution;
wherein f of formula (9) t (x) Representing the Cauchy density function, θ being a proportional parameter and θ > 0, F of equation (10) t (x) Representing the cauchy distribution function,representing the ith individual in the population of the t-th iteration, r is a random number between 0 and 1, and C represents a random number subject to the Coxie distribution.
The invention has the beneficial effects that:
1. according to the invention, the grasshopper algorithm searching capability and optimization accuracy can be improved by adopting a triangle replacement strategy and the cauchy variation;
2. grasshoppers firstly finish the position updating of the first round according to the original searching mechanism, and then finish the position updating of the population by utilizing the position updating mechanism of the triangle replacement strategy so as to balance the searching and developing capabilities of the algorithm;
3. the method has the advantages that the Kexi variation is utilized to carry out variation on the population, the possibility of searching the optimal solution by the population is improved, so that the situation that local optimization is involved in the segmentation process is avoided, and the segmentation quality of medical images is improved.
Drawings
The invention will be described in further detail with reference to the drawings and the detailed description.
FIG. 1 is a plan view of a two-dimensional histogram;
FIGS. 2-4 are three example medical images to be segmented;
fig. 5-7 are the results of the segmentation of the three medical images of fig. 2-4, respectively, according to the two-dimensional segmentation method of the multi-threshold medical image based on the modified grasshopper algorithm of the present invention.
Detailed Description
The present invention is described in its best mode by the following preferred embodiments with reference to the accompanying drawings, and the detailed description herein is to be construed as limiting the invention, since various changes and modifications can be made without departing from the spirit and scope of the invention.
Example 1
The applicant finds that the search capability and the optimization precision of the grasshopper algorithm can be improved by adopting a triangular replacement strategy and the cauchy variation, wherein the grasshopper firstly completes the position update of the first round according to an original search mechanism, then completes the position update of the population by utilizing the position update mechanism of the triangular replacement strategy, so as to balance the search and development capability of the algorithm, then mutates the population by utilizing the cauchy variation, and improves the possibility of searching the optimal solution of the population, so as to avoid the local optimization and improve the segmentation quality of medical images in the segmentation process.
According to a preferred embodiment of the present invention, there is provided a two-dimensional segmentation method of multi-threshold medical images based on an improved grasshopper algorithm, comprising the steps of:
step 1: inputting a medical image to be segmented, and initializing a threshold segmentation Level;
step 2: initializing parameters, namely, the size of grasshopper population is pop, and the maximum Iteration number max_iteration is equal to that of grasshopper population;
step 3: 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 4: initializing grasshopper population X i (i=1,2,...,n);
Step 5: calculating the fitness value of all grasshoppers, namely Kapur entropy;
step 6: determining the optimal grasshopper position and fitness value;
step 7: according to the position updating mode of the grasshopper, finishing the first position updating of the grasshopper population;
step 8: based on the first position updating of grasshoppers, the position updating of each grasshopper is performed again according to the position updating method of the triangle replacement strategy;
step 9: based on the updated grasshopper population, the cauchy variation is carried out on the population individuals, and the local development is increased;
step 10: checking whether the iteration termination condition is met, if so, executing the step 11, otherwise, returning to the step 5 to continue iteration;
step 11: returning the optimal grasshopper position and the fitness value as an optimal threshold value and a maximum Kapur entropy;
step 12: and dividing the medical image by using the obtained optimal threshold value.
According to a further preferred embodiment of the present invention, step 8 specifically comprises: based on the first position updating of grasshoppers, the position updating method of the triangle replacement strategy according to the formula (7) carries out the position updating of each grasshopper again;
wherein t is the current iteration number, i represents the ith individual in the population, bp t Is the optimal solution of the t-th iteration, r 2 ,r 3 And r 4 Are all random numbers, r 2 In the range of 0-2 pi, r 3 In the range of 0-2, r 4 Is in the range of 0-l; a is a constant set to 2.
According to a further preferred embodiment of the present invention, step 9 specifically comprises: based on the updated grasshopper population, carrying out local development on population individuals according to the cauchy variation of formulas (9) - (11), and increasing the possibility of finding an optimal solution;
wherein f of formula (9) t (x) Representing the Cauchy density function, θ being a proportional parameter and θ > 0, F of equation (10) t (x) Representing the cauchy distribution function,representing the ith individual in the population of the t-th iteration, r is a random number between 0 and 1, and C represents a random number subject to the Coxie distribution.
It will be appreciated that the number of components,new individuals who are cauchy residual; x in equations (9) and (10) is the argument in the cauchy function. Preferably, if->And if the global optimal solution is larger than the current global optimal solution, replacing the global optimal solution, otherwise, discarding the global optimal solution.
Example 2
According to a preferred embodiment of the present invention, there is provided a two-dimensional segmentation method of multi-threshold medical images based on an improved grasshopper algorithm, comprising the steps of:
step 1: inputting an image to be segmented, and initializing a threshold segmentation Level;
step 2: user initialization parameters, grasshopper population size pop, maximum Iteration number Max_iteration, setting a global optimal fitness value best, initializing and assigning best to minus infinity, and setting a global optimal individual to be bp;
step 3: and graying the 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 4: initializing grasshopper population X i (i=1,2,...,n)
Step 5: calculating the fitness value of all grasshoppers, namely Kapur entropy;
step 6: updating an optimal grasshopper position bp and an optimal fitness value best;
step 7: and according to the position updating mode of the grasshopper, completing the first position updating of the grasshopper population.
Step 8: based on the first position updating of grasshoppers, the position updating method of the triangle replacement strategy according to the formula (7) carries out the position updating of each grasshopper again;
wherein t is the current iteration number, i represents the ith individual in the population, bp t Is the optimal solution of the t-th iteration, r 2 ,r 3 And r 4 Are all random numbers, r 2 In the range of 0-2 pi, r 3 In the range of 0-2, r 4 Is in the range of 0-1.a is a constant set to 2.
According to the trigonometric function, updating individuals of the population, wherein the exploration and development of the original grasshopper optimization algorithm are unbalanced, the trigonometric transformation strategy utilizes the fluctuation of the trigonometric function, so that the exploration and development can be well balanced in the iterative process, the updated population calculates the fitness value, and the fitness value is compared with the fitness value before updating, and the individuals with large fitness values are selected to be reserved.
Step 9: based on the updated grasshopper population, the individuals in the population are locally developed according to the cauchy variation of formulas (9) - (11), so that the possibility of finding the optimal solution is increased.
Wherein, the formula (9) represents the cauchy density function, θ > 0 is a proportional parameter, the formula (10) represents the cauchy distribution function,representing the ith individual in the population of the t-th iteration, r is a random number between 0 and 1, and C represents a random number subject to the Coxie distribution.
The Cauchy variation is wider in the horizontal direction than the Gaussian, which means that the local development capacity of the population individuals can be increased, and the possibility that the population finds the optimal solution is increased. And the individual calculates the fitness value according to the new neighborhood generated by the cauchy variation, compares the fitness value with the current global optimal solution, updates the global optimal solution if the fitness value is larger than the global optimal solution, and otherwise, the global optimal solution and population individual information are unchanged.
Step 10: checking whether the iteration termination condition is met, if so, executing the step 11, otherwise, returning to the step 5 to continue iteration;
step 11: returning the optimal grasshopper position and the fitness value as an optimal threshold value and a maximum Kapur entropy;
step 12: and dividing the medical image by using the obtained optimal threshold value.
5-7, which illustrate the results of segmenting the three example medical images of FIGS. 2-4 according to the two-dimensional segmentation method of the multi-threshold medical image based on the modified grasshopper algorithm of the present invention.
According to the invention, an improved grasshopper optimization algorithm is adopted, and first, grasshoppers finish updating own positions in an original mode to finish preliminary foraging behaviors; and then, the position updating mechanism of the triangle replacement strategy is utilized to complete the position updating of the population, so that the searching and developing capability of an algorithm is balanced, the Kexi variation is utilized to mutate the population, the possibility of searching an optimal solution of the population is improved, and the situation that the population is trapped into local optimal in the segmentation process is avoided, and the segmentation quality of medical images is improved. Grasshoppers will obtain better quality foods through triangle replacement strategies and cauchy variations, which can improve the quality of multi-threshold medical image segmentation.
Taking three medical images (hereinafter, respectively represented by image 1, image 2 and image 3) of fig. 2-4 as an example, the comparison analysis is performed by using the method of the present invention and using the grasshopper optimization algorithm, respectively, and the following results are obtained:
with the entropy of Kapur as the objective function, SCGOA (method of the present invention) is compared with the results of the objective function values obtained by GOA (grasshopper optimization algorithm) respectively (threshold=8):
when the objective function value is the largest, comparing the obtained results of the optimal segmentation threshold values:
the overall ranking Mean level of the 'Mean' representation and the ranking rating of the method are represented by the friedman 'using analysis results of 20 evaluations of Feature Similarity (FSIM), peak signal-to-noise ratio (PSNR), and Structural Similarity (SSIM) by friedman' test. According to the result of Friedman test analysis, in the 20 evaluations of PSNR, SSIM, FSIM, the SCGOA-based multi-threshold medical image segmentation method is obviously superior to the GOA-based multi-threshold medical image segmentation method, and the performance is greatly improved. This also fully demonstrates that the SCGOA-based multi-threshold image segmentation method is a multi-threshold image segmentation method that can obtain high quality segmentation results and is quite stable.
Friedman test of FSIM:
friedman test for PSNR:
friedman test of SSIM:
the invention has the beneficial effects that:
1. according to the invention, the grasshopper algorithm searching capability and optimization accuracy can be improved by adopting a triangle replacement strategy and the cauchy variation;
2. grasshoppers firstly finish the position updating of the first round according to the original searching mechanism, and then finish the position updating of the population by utilizing the position updating mechanism of the triangle replacement strategy so as to balance the searching and developing capabilities of the algorithm;
3. the method has the advantages that the Kexi variation is utilized to carry out variation on the population, the possibility of searching the optimal solution by the population is improved, so that the situation that local optimization is involved in the segmentation process is avoided, and the segmentation quality of medical images is improved.
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 (1)

1.A method for two-dimensional segmentation of a multi-threshold medical image based on an improved grasshopper algorithm, comprising the steps of:
step 1: inputting a medical image to be segmented, and initializing a threshold segmentation Level;
step 2: initializing parameters, namely, the size of grasshopper population is pop, and the maximum Iteration number max_iteration is equal to that of grasshopper population;
step 3: 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 4: initializing grasshopper population X i (i=1,2,…,n);
Step 5: calculating the fitness value of all grasshoppers, namely Kapur entropy;
step 6: determining the optimal grasshopper position and fitness value;
step 7: according to the position updating mode of the grasshopper, finishing the first position updating of the grasshopper population;
step 8: based on the first position updating of grasshoppers, the position updating of each grasshopper is performed again according to the position updating method of the triangle replacement strategy;
step 9: based on the updated grasshopper population, the cauchy variation is carried out on the population individuals, and the local development is increased;
step 10: checking whether the iteration termination condition is met, if so, executing the step 11, otherwise, returning to the step 5 to continue iteration;
step 11: returning the optimal grasshopper position and the fitness value as an optimal threshold value and a maximum Kapur entropy;
step 12: dividing the medical image by using the obtained optimal threshold;
the step 8 specifically includes: based on the first position updating of grasshoppers, the position updating method of the triangle replacement strategy according to the formula (7) carries out the position updating of each grasshopper again;
wherein t is the current iteration number, i represents the ith individual in the population, bp t Is the optimal solution of the t-th iteration, r 2 ,r 3 And r 4 Are all random numbers, r 2 In the range of 0-2 pi, r 3 In the range of 0-2, r 4 Is in the range of 0-1; a is a constant, set to 2;
the step 9 specifically comprises the following steps: based on the updated grasshopper population, carrying out local development on population individuals according to the cauchy variation of formulas (9) - (11), and increasing the possibility of finding an optimal solution;
wherein f of formula (9) t (x) Represents a cauchy density function, θ is a scale parameter and θ>0, F of formula (10) t (x) Representing the cauchy distribution function,representing the ith individual in the population of the t-th iteration, r is a random number between 0 and 1, and C represents a random number subject to the Coxie distribution.
CN202110767492.7A 2021-07-07 2021-07-07 Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm Active CN113570555B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110767492.7A CN113570555B (en) 2021-07-07 2021-07-07 Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110767492.7A CN113570555B (en) 2021-07-07 2021-07-07 Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm

Publications (2)

Publication Number Publication Date
CN113570555A CN113570555A (en) 2021-10-29
CN113570555B true CN113570555B (en) 2024-02-09

Family

ID=78163945

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110767492.7A Active CN113570555B (en) 2021-07-07 2021-07-07 Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm

Country Status (1)

Country Link
CN (1) CN113570555B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106570873A (en) * 2016-11-08 2017-04-19 江苏大学 Medical image segmentation method
CN106682682A (en) * 2016-10-20 2017-05-17 北京工业大学 Method for optimizing support vector machine based on Particle Swarm Optimization
CN109711097A (en) * 2019-01-22 2019-05-03 福州大学 A kind of Design of Cantilever Beam method based on sine and cosine mechanism chaos grasshopper algorithm
CN110880192A (en) * 2019-07-29 2020-03-13 辽宁师范大学 Image DCT coefficient distribution fitting method based on probability density function dictionary
CN111832838A (en) * 2020-07-24 2020-10-27 河北工业大学 Method for predicting short-term wind power generation output power
CN112085059A (en) * 2020-08-06 2020-12-15 温州大学 Breast cancer image feature selection method based on improved sine and cosine optimization algorithm
CN112232119A (en) * 2020-09-09 2021-01-15 自然资源部第四地形测量队 Remote sensing texture image segmentation method and device
AU2020103709A4 (en) * 2020-11-26 2021-02-11 Daqing Oilfield Design Institute Co., Ltd A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8046200B2 (en) * 2006-09-05 2011-10-25 Colorado State University Research Foundation Nonlinear function approximation over high-dimensional domains

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106682682A (en) * 2016-10-20 2017-05-17 北京工业大学 Method for optimizing support vector machine based on Particle Swarm Optimization
CN106570873A (en) * 2016-11-08 2017-04-19 江苏大学 Medical image segmentation method
CN109711097A (en) * 2019-01-22 2019-05-03 福州大学 A kind of Design of Cantilever Beam method based on sine and cosine mechanism chaos grasshopper algorithm
CN110880192A (en) * 2019-07-29 2020-03-13 辽宁师范大学 Image DCT coefficient distribution fitting method based on probability density function dictionary
CN111832838A (en) * 2020-07-24 2020-10-27 河北工业大学 Method for predicting short-term wind power generation output power
CN112085059A (en) * 2020-08-06 2020-12-15 温州大学 Breast cancer image feature selection method based on improved sine and cosine optimization algorithm
CN112232119A (en) * 2020-09-09 2021-01-15 自然资源部第四地形测量队 Remote sensing texture image segmentation method and device
AU2020103709A4 (en) * 2020-11-26 2021-02-11 Daqing Oilfield Design Institute Co., Ltd A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于柯西变异的多策略协同进化粒子群算法;王永骥;苏婷婷;刘磊;;系统仿真学报(第08期);全文 *
改进蚱蜢算法在电动汽车充换电站调度中的应用;王生生;张伟;董如意;李文辉;;东北大学学报(自然科学版)(第02期);全文 *

Also Published As

Publication number Publication date
CN113570555A (en) 2021-10-29

Similar Documents

Publication Publication Date Title
CN109360156B (en) Single image rain removing method based on image block generation countermeasure network
CN112150493B (en) Semantic guidance-based screen area detection method in natural scene
Li et al. Blind image deconvolution through support vector regression
EP1026631A2 (en) Method for inferring scenes from test images and training data using probability propagation in a markov network
CN111091503A (en) Image out-of-focus blur removing method based on deep learning
CN112200812B (en) Two-dimensional segmentation method for multi-threshold image
CN111127504A (en) Heart medical image segmentation method and system for atrial septal occlusion patient
Min et al. Blind deblurring via a novel recursive deep CNN improved by wavelet transform
CN109658378B (en) Pore identification method and system based on soil CT image
CN113781517A (en) System and method for motion estimation
CN114897728A (en) Image enhancement method and device, terminal equipment and storage medium
CN112329784A (en) Correlation filtering tracking method based on space-time perception and multimodal response
CN112085705B (en) Image segmentation method and device based on improved goblet sea squirt swarm algorithm
Dou et al. Image fusion based on wavelet transform with genetic algorithms and human visual system
Roy et al. Removal of ‘salt & pepper’noise from color images using adaptive fuzzy technique based on histogram estimation
CN113570555B (en) Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm
Bhuvaneswari et al. Contrast enhancement of retinal images using green plan masking and whale optimization algorithm
CN110176029B (en) Image restoration and matching integrated method and system based on level sparse representation
CN116543259A (en) Deep classification network noise label modeling and correcting method, system and storage medium
CN115761358A (en) Method for classifying myocardial fibrosis based on residual capsule network
Ollion et al. Joint self-supervised blind denoising and noise estimation
WO2004052016A2 (en) Improvements in image velocity estimation
CN113378620B (en) Cross-camera pedestrian re-identification method in surveillance video noise environment
Li et al. Super‐Resolution Reconstruction of Underwater Image Based on Image Sequence Generative Adversarial Network
Yousaf et al. Closed-loop restoration approach to blurry images based on machine learning and feedback optimization

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