CN104318575A - Multi-threshold image segmentation method based on comprehensive learning differential evolution algorithm - Google Patents

Abstract

The invention discloses a multi-threshold image segmentation method based on a comprehensive learning differential evolution algorithm. During the mutation operation process of the differential evolution algorithm, the invention uses a binary tournament selection method to randomly select an individual from the population, and compares it with the The optimal individual generates a comprehensive individual, and then performs mutation operations based on the comprehensive individual to generate mutant individuals, so as to speed up the search speed as much as possible while maintaining the diversity of the population, and then perform the hybridization and selection operations of the traditional differential evolution algorithm. At the same time, according to the current search feedback information, adaptively adjust the scaling factor and the value of hybridization probability, so as to enhance the robustness of the algorithm; repeat the above steps until the termination condition is met, the optimal individual obtained in the calculation process, That is, the final segmentation threshold of the image; the present invention can reduce the probability of falling into local optimum, improve the precision of image segmentation, accelerate the speed of segmentation, and improve the real-time performance of segmentation.

Description

A Multi-Threshold Image Segmentation Method Based on Comprehensive Learning Differential Evolutionary Algorithm

technical field

The invention relates to digital image segmentation technology, in particular to a multi-threshold image segmentation method based on comprehensive learning differential evolution algorithm.

Background technique

Multi-threshold image segmentation is a very important digital image processing method in modern digital image processing. In the process of multi-threshold image segmentation, usually according to the preset segmentation criteria, multiple thresholds are found to identify the interesting part in the image, so as to segment the image into several different parts. In the multi-threshold image segmentation process, the most critical step is how to quickly and effectively optimize each threshold. However, the traditional multi-threshold image segmentation methods based on exhaustive search often have the disadvantages of slow search speed and low real-time performance, especially when the number of thresholds is large, the time-consuming search is often unacceptable in practical engineering applications. For this reason, people apply intelligent optimization algorithms to multi-threshold image segmentation, so as to solve the segmentation threshold intelligently and quickly. For example, Dai Qionghai et al. invented a multi-threshold image segmentation method based on moderate random search behavior in 2010; Tong Xiaonian et al. proposed a dual-threshold image segmentation method based on quantum particle swarm optimization in 2010; Zhang Wei et al. In 2011, a fuzzy entropy coal dust image segmentation based on improved particle swarm optimization was proposed.

Differential evolution algorithm is an effective modern intelligent optimization algorithm for solving optimization problems. The structure of the differential evolution algorithm is very simple, easy to understand and implement, and has strong self-organization, self-learning and self-adaptability. It has become a very active research hotspot in the field of solving optimization problems. People have successfully used the differential evolution algorithm to solve the multi-threshold image segmentation problem. However, the traditional differential evolution algorithm often falls into local optimum when solving the multi-threshold image segmentation problem. The segmentation effect still needs to be improved, and the convergence speed is slow and real-time. Not strong disadvantages.

Contents of the invention

Aiming at the shortcomings of the traditional differential evolution algorithm for multi-threshold image segmentation, it is easy to fall into local optimum, the segmentation accuracy is not high, the segmentation speed is slow and the real-time performance is not strong, and a multi-threshold image based on comprehensive learning differential evolution algorithm is proposed. Segmentation method, in the process of mutation operation of differential evolution, a binary tournament selection method is used to randomly select an individual from the population, and generate an integrated individual with the optimal individual, and then execute based on the integrated individual The mutation operation generates mutated individuals, so as to speed up the search speed as much as possible while maintaining the diversity of the population, and then executes the hybridization and selection operation operators of the traditional differential evolution algorithm; at the same time, adaptively adjusts the scaling factor and The value of the hybridization probability, so as to enhance the robustness of the algorithm; repeat the above steps until the termination condition is met, and the optimal individual obtained in the calculation process is the final segmentation threshold of the image; compared with similar methods, the present invention can Reduce the probability of falling into local optimum, improve the accuracy of image segmentation, speed up the segmentation, and improve the real-time performance of segmentation.

Technical solution of the present invention: a multi-threshold image segmentation method based on comprehensive learning differential evolution algorithm, comprising the following steps:

Step 1, the user initializes parameters, and the initialization parameters include the number of segmentation thresholds D, the population size Popsize, and the maximum number of evaluations MAX_FEs;

Step 2, the current evolution algebra t=0, and set the comprehensive learning rate Pr _i ^t =0.5, the hybridization rate Cr _i ^t =0.9, the scaling factor F _i ^t =0.5, where the subscript i=1,...,Popsize, Current evaluation times FEs=0;

Step 3, randomly generate the initial population Wherein: subscript i=1,..., Popsize, and is the i-th individual in the population P _t , and its random initialization formula is:

${\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; 255.0</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; D.</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; rand</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 0,1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&Center\; Dot;</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 255.0</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; D.</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1.0</span>}<span\; class="notranslate">\; )</span>$

Wherein the subscript j=1,...,D, and D is the number of segmentation thresholds; For the i-th individual in the population P _t , D segmentation thresholds are stored; rand(0,1) is a random real number generation function that obeys a uniform distribution between [0,1];

Step 4, calculate the fitness value of each individual in the population _Pt , where the larger the fitness value is, the better the individual is, for any individual fitness value Calculated according to the following formula:

$\mathrm{<span\; class="notranslate">\; fit</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; D.</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; h</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ,</span>$

Where H _k is the entropy of the kth image gray value interval, calculated according to the following formula:

${\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; h</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; )</span>}{\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 255</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; h</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; ,</span>$

When k=0,

When the subscript k=1,2,...,D-1

when k=D

Where h(j) is the total number of pixels in the jth image gray value in the image, and p _j is the probability of the jth image gray value in the image; Down operator; w ₀ is interval The cumulative probability sum of the gray value of the image, H ₀ is the interval The entropy of the gray value of the image, w _k is the interval The cumulative probability sum of the gray value of the image, the subscript k=1,2,...D-1, H _k is the interval The entropy of the gray value of the image, w _D is the interval The cumulative probability sum of the gray value of the image, _HD is the interval The entropy of the gray value of the image; then the current evaluation times FEs=FEs+Popsize, and save the individual with the greatest fitness value in the population P ^t as the optimal individual Best ^t ;

Step 5, make the counter i=1;

Step 6, if the counter i is greater than the population size Popsize, go to step 15, otherwise go to step 7;

Step 7, calculate individual The current comprehensive learning rate NPr _i ^t , the calculation formula is as follows:

Where r1 is a real number randomly generated between [0,1];

Step 8, according to individual The current comprehensive learning rate NPr _i ^t for the individual Synthetic Learning Individual Its steps are as follows:

Step 8.1, let the counter j=1;

Step 8.2, if the counter j is greater than D, then go to step 9, otherwise go to step 8.3;

Step 8.3, generate a random real number r2 between [0, 1]; if r2 is less than the individual The current comprehensive learning rate NPr _i ^t then go to step 8.7, otherwise go to step 8.4;

Step 8.4, randomly generate two unequal positive integers RI1, RI2 between [1, Popsize];

Step 8.5, if the individual The fitness value is greater than the individual the fitness value of otherwise $B_{i,j}^t=A_{\mathrm{RI}2,j}^t;$

Step 8.6, make counter j=j+1, go to step 8.2;

Step 8.7, Make counter j=j+1, go to step 8.2;

Step 9, calculate the individual according to the following formula The current scaling factor NF _i ^t and the current hybridization rate NCr _i ^t :

Among them, r3 and r4 are real numbers randomly generated between [0,1]. randc(0.5,0.3) is a random real number function that uses 0.5 as a position parameter and 0.3 as a scale parameter to generate a Cauchy distribution. rand(0, 1) To generate a random real number function subject to uniform distribution between [0,1];

Step 10 to synthesize individual learning as the base individual, and with NF _i ^t as the individual The current scaling factor of , NCr _i ^t is the individual The current hybridization rate of , producing individuals test subjects and calculate the test individual fitness value Its steps are as follows:

Step 10.1, let the counter j=1;

Step 10.2, randomly generate a positive integer jRand between [1,D];

Step 10.3, randomly generate two unequal positive integers RI3, RI4 between [1, Popsize];

Step 10.4, if the counter j is greater than D, then go to step 10.9, otherwise go to step 10.5;

Step 10.5, generate a random real number r5 between [0, 1], if r5 is less than the individual The current hybridization rate NCr _i ^t or jRand is equal to the counter j, then go to step 10.6, otherwise go to step 10.7;

Step 10.6, $u_{i,j}^t=B_{i,j}^t+{{\mathrm{NF}}_i}^t\&CenterDot;(A_{\mathrm{RI}3,j}^t-A_{\mathrm{RI}4,j}^t);$ Go to step 10.8;

Step 10.7, $u_{i,j}^t=A_{i,j}^t;$

Step 10.8, make counter j=j+1, go to step 10.4;

Step 10.9, Computing Test Individuals fitness value Go to step 11;

Step 11, according to the following formula in the individual with test subjects Individuals are selected to enter the next generation population:

Step 12, update the individual according to the following formula Comprehensive learning rate Pr _i ^t , scaling factor F _i ^t , hybridization rate Cr _i ^t :

Step 13, make counter i=i+1;

Step 14, go to step 6;

Step 15, the current number of evaluations FEs=FEs+Popsize, the individual with the largest fitness value in the saved population P _t is the optimal individual Best ^t ; the current evolution algebra t=t+1;

Step 16, repeat step 5 to step 15 until the current evaluation times FEs reaches MAX_FEs and end, the optimal individual Best ^t obtained during the execution is the D segmentation thresholds of the segmented image, and the image is processed with the obtained D segmentation thresholds segmentation.

Therefore, the present invention has the following advantages: the present invention effectively utilizes the favorable comprehensive information of random individuals and optimal individuals to coordinate the balance between global search and local search, speed up the search as much as possible while maintaining population diversity, and reduce the risk of falling into local optimal probability, and speed up the convergence; on the other hand, the present invention adaptively adjusts the value of scaling factor and hybridization probability according to the current search feedback information, which enhances the robustness of the algorithm; compared with similar methods, the present invention The individual information of the differential evolution population is comprehensively utilized, which can reduce the probability of falling into a local optimum, improve the accuracy of image segmentation, accelerate the speed of segmentation, and improve the real-time performance of segmentation.

Description of drawings

Figure 1 is the Lena image;

Fig. 2 is the segmentation result of the present invention to the Lena image.

Detailed ways

The technical solutions of the present invention will be further specifically described below through the embodiments and in conjunction with the accompanying drawings.

Example:

The present embodiment is segmented based on the Lena image shown in Fig. 1, and the specific implementation steps of the present invention are as follows:

Step 1, the user initializes parameters, and the initialization parameters include the number of segmentation thresholds D=4, the population size Popsize=100, and the maximum number of evaluations MAX_FEs=60000;

Step 2, the current evolution algebra t=0, and set the comprehensive learning rate Pr _i ^t =0.5, the hybridization rate Cr _i ^t =0.9, the scaling factor F _i ^t =0.5, where the subscript i=1,...,Popsize, Current evaluation times FEs=0;

Step 3, randomly generate the initial population Wherein: subscript i=1,..., Popsize, and is the i-th individual in the population P _t , and its random initialization formula is:

${\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; 255.0</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; D.</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; rand</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 0,1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&CenterDot;</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 255.0</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; D.</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1.0</span>}<span\; class="notranslate">\; )</span>$

Wherein the subscript j=1,...,D, and D is the number of segmentation thresholds; For the i-th individual in the population P _t , D segmentation thresholds are stored; rand(0,1) is a random real number generation function that obeys a uniform distribution between [0,1];

Step 4, calculate the fitness value of each individual in the population _Pt , where the larger the fitness value is, the better the individual is, for any individual fitness value Calculated according to the following formula:

$\mathrm{<span\; class="notranslate">\; fit</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; D.</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; h</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; ,</span>$

Where H _k is the entropy of the kth image gray value interval, calculated according to the following formula:

${\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; h</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; )</span>}{\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 255</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; h</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; ,</span>$

When k=0,

When the subscript k=1,2,...,D-1

when k=D

Where h(j) is the total number of pixels of the jth image gray value in the Lena image, and p _j is the probability of the jth image gray value in the Lena image; It is the rounding down operator; w ₀ is the interval The cumulative probability sum of the gray value of the image, H ₀ is the interval The entropy of the gray value of the image, w _k is the interval The cumulative probability sum of the gray value of the image, the subscript k=1,2,...D-1, H _k is the interval The entropy of the gray value of the image, w _D is the interval The cumulative probability sum of the gray value of the image, _HD is the interval The entropy of the gray value of the image; then the current evaluation times FEs=FEs+Popsize, and save the individual with the greatest fitness value in the population P ^t as the optimal individual Best ^t ;

Step 5, make the counter i=1;

Step 6, if the counter i is greater than the population size Popsize, go to step 15, otherwise go to step 7;

Step 7, calculate individual The current comprehensive learning rate NPr _i ^t , the calculation formula is as follows:

Where r1 is a real number randomly generated between [0,1];

Step 8, according to individual The current comprehensive learning rate NPr _i ^t for the individual Synthetic Learning Individual Its steps are as follows:

Step 8.1, let the counter j=1;

Step 8.2, if the counter j is greater than D, then go to step 9, otherwise go to step 8.3;

Step 8.3, generate a random real number r2 between [0, 1]; if r2 is less than the individual The current comprehensive learning rate NPr _i ^t then go to step 8.7, otherwise go to step 8.4;

Step 8.4, randomly generate two unequal positive integers RI1, RI2 between [1, Popsize];

Step 8.5, if the individual The fitness value is greater than the individual the fitness value of otherwise $B_{i,j}^t=A_{\mathrm{RI}2,j}^t;$

Step 8.6, make counter j=j+1, go to step 8.2;

Step 8.7, Make counter j=j+1, go to step 8.2;

Step 9, calculate the individual according to the following formula The current scaling factor NF _i ^t and the current hybridization rate NCr _i ^t :

Among them, r3 and r4 are real numbers randomly generated between [0,1]. randc(0.5,0.3) is a random real number function that uses 0.5 as a position parameter and 0.3 as a scale parameter to generate a Cauchy distribution. rand(0, 1) To generate a random real number function subject to uniform distribution between [0,1];

Step 10 to synthesize individual learning as the base individual, and with NF _i ^t as the individual The current scaling factor of NCr _i ^t is the individual The current hybridization rate of , producing individuals test subjects and calculate the test individual fitness value Its steps are as follows:

Step 10.1, let the counter j=1;

Step 10.2, randomly generate a positive integer jRand between [1,D];

Step 10.3, randomly generate two unequal positive integers RI3, RI4 between [1, Popsize];

Step 10.4, if the counter j is greater than D, then go to step 10.9, otherwise go to step 10.5;

Step 10.5, generate a random real number r5 between [0, 1], if r5 is less than the individual The current hybridization rate NCr _i ^t or jRand is equal to the counter j, then go to step 10.6, otherwise go to step 10.7;

Step 10.6, $u_{i,j}^t=B_{i,j}^t+{{\mathrm{NF}}_i}^t\&Center\; Dot;(A_{\mathrm{RI}3,j}^t-A_{\mathrm{RI}4,j}^t);$ Go to step 10.8;

Step 10.7, $u_{i,j}^t=A_{i,j}^t;$

Step 10.8, make counter j=j+1, go to step 10.4;

Step 10.9, Computing Test Individuals fitness value Go to step 11;

Step 11, according to the following formula in the individual with test subjects Individuals are selected to enter the next generation population:

Step 12, update the individual according to the following formula Comprehensive learning rate Pr _i ^t , scaling factor F _i ^t , hybridization rate Cr _i ^t :

Step 13, make counter i=i+1;

Step 14, go to step 6;

Step 15, the current number of evaluations FEs=FEs+Popsize, the individual with the largest fitness value in the saved population P _t is the optimal individual Best ^t ; the current evolution algebra t=t+1;

Step 16, repeat steps 5 to 15 until the current number of evaluation times FEs reaches MAX_FEs and ends. The optimal individual Best ^t obtained during the execution is the D segmentation thresholds for segmenting the Lena image, and the obtained D segmentation thresholds are used to evaluate Lena The image is segmented.

The specific embodiments described herein are merely illustrative of the spirit of the invention. Those skilled in the art to which the present invention belongs can make various modifications or supplements to the described specific embodiments or adopt similar methods to replace them, but they will not deviate from the spirit of the present invention or go beyond the definition of the appended claims range.

Claims (1)

1. based on a multi-threshold image segmentation method for integrated learning Differential Evolution Algorithm, it is characterized in that, comprise the following steps:

Step 1, user's initiation parameter, described initiation parameter comprises segmentation threshold quantity D, Population Size Popsize, maximum evaluation number of times MAX_FEs;

Step 2, current evolution algebraically t=0, and integrated learning rate Pr is set _i ^t=0.5, hybrid rate Cr _i ^t=0.9, zoom factor F _i ^t=0.5, wherein subscript i=1 ..., Popsize, Evaluation: Current number of times FEs=0;

Step 3, produces initial population at random wherein: subscript i=1 ..., Popsize, and for population P _tin i-th individuality, its random initializtion formula is:

$A_{i,j}^t=(j-1)\&times;255.0/D+\mathrm{rand}\left(\mathrm{0,1}\right)\&CenterDot;(255.0/D-1.0)$

Wherein subscript j=1 ..., D, and D is segmentation threshold quantity; for at population P _tin i-th individuality, store D segmentation threshold; Rand (0,1) obeys equally distributed random real number to produce function between [0,1];

Step 4, calculates population P _tin the adaptive value of each individuality, wherein adaptive value is larger, shows that individuality is more outstanding, individual for any one adaptive value calculate as follows:

$\mathrm{Fit}\left(A_i^t\right)=\underset{k=0}{\overset{D}{\mathrm{\&Sigma;}}}{H}_k,$

Wherein H _kfor the entropy in a kth image intensity value interval, be calculated as follows:

$p_j=\frac{h\left(j\right)}{\underset{j=0}{\overset{255}{\mathrm{\&Sigma;}}}h\left(j\right)},$

as k=0,

as subscript k=1,2 ..., during D-1

as k=D

Wherein h (j) is jth image intensity value sum of all pixels in the picture, p _jfor jth image intensity value probability in the picture; for downward rounding operation accords with; w ₀for interval image intensity value accumulated probability and, H ₀for interval the entropy of image intensity value, w _kfor interval image intensity value accumulated probability and, subscript k=1,2 ... D-1, H _kfor interval the entropy of image intensity value, w _dfor interval image intensity value accumulated probability and, H _dfor interval the entropy of image intensity value; Then Evaluation: Current number of times FEs=FEs+Popsize, and preserve population P ^tthe maximum individuality of middle adaptive value is optimum individual Best ^t;

Step 5, makes counter i=1;

Step 6, if counter i is greater than Population Size Popsize, then forwards step 15 to, otherwise forwards step 7 to;

Step 7, calculates individual current composite learning rate NPr _i ^t, computing formula is as follows:

Wherein r1 is the random real number produced between [0,1];

Step 8, according to individuality current composite learning rate NPr _i ^t, to individuality produce an integrated learning individuality its step is as follows:

Step 8.1, makes counter j=1;

Step 8.2, if counter j is greater than D, then forwards step 9 to, otherwise forwards step 8.3 to;

Step 8.3, produces a random real number r2 between [0,1]; If r2 is less than individuality current composite learning rate NPr _i ^tthen forward step 8.7 to, otherwise forward step 8.4 to;

Step 8.4, random generation two unequal positive integer RI1, RI2 between [1, Popsize];

Step 8.5, if individual adaptive value be greater than individuality adaptive value, then otherwise $B_{i,j}^t=A_{\mathrm{RI}2,j}^t;$

Step 8.6, makes counter j=j+1, forwards step 8.2 to;

Step 8.7, make counter j=j+1, forward step 8.2 to;

Step 9, calculates individuality as follows current zoom factor NF _i ^twith current hybrid rate NCr _i ^t:

Wherein r3, r4 is [0,1] the random real number produced between, randc (0.5,0.3) be using 0.5 as location parameter, 0.3 produces the random real-number function of obeying Cauchy's distribution as scale parameter, rand (0,1) be produce to obey equally distributed random real-number function between [0,1];

Step 10, individual with integrated learning based on individual, and with NF _i ^tfor individuality current zoom factor, NCr _i ^tfor individuality current hybrid rate, produce individual test individual and it is individual to calculate test adaptive value its step is as follows:

Step 10.1, makes counter j=1;

Step 10.2, a random generation positive integer jRand between [1, D];

Step 10.3, random generation two unequal positive integer RI3, RI4 between [1, Popsize];

Step 10.4, if counter j is greater than D, then forwards step 10.9 to, otherwise forwards step 10.5 to;

Step 10.5, produces a random real number r5, if r5 is less than individuality between [0,1] current hybrid rate NCr _i ^tor jRand equals counter j, then forward step 10.6 to, otherwise forwards step 10.7 to;

Step 10.6, $U_{i,j}^t=B_{i,j}^t+{{\mathrm{NF}}_i}^t\&CenterDot;(A_{\mathrm{RI}3,j}^t-A_{\mathrm{RI}4,j}^t);$ Forward step 10.8 to;

Step 10.7, $U_{i,j}^t=A_{i,j}^t;$

Step 10.8, makes counter j=j+1, forwards step 10.4 to;

Step 10.9, calculates test individual adaptive value forward step 11 to;

Step 11, as follows at individuality individual with test between select individuality and enter population of future generation:

Step 12, upgrades individuality as follows integrated learning rate Pr _i ^t, zoom factor F _i ^t, hybrid rate Cr _i ^t:

Step 13, makes counter i=i+1;

Step 14, forwards step 6 to;

Step 15, Evaluation: Current number of times FEs=FEs+Popsize, preserves population P _tthe maximum individuality of middle adaptive value is optimum individual Best ^t; Current evolution algebraically t=t+1;

Step 16, repeats step 5 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, the optimum individual Best obtained in implementation ^tbe D segmentation threshold of segmentation image, and with the D an obtained segmentation threshold to Image Segmentation Using.