CN104732522A - Image segmentation method based on polymorphic ant colony algorithm - Google Patents
Image segmentation method based on polymorphic ant colony algorithm Download PDFInfo
- Publication number
- CN104732522A CN104732522A CN201510060447.2A CN201510060447A CN104732522A CN 104732522 A CN104732522 A CN 104732522A CN 201510060447 A CN201510060447 A CN 201510060447A CN 104732522 A CN104732522 A CN 104732522A
- Authority
- CN
- China
- Prior art keywords
- ant
- colony algorithm
- polymorphic
- pixel
- method based
- 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.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses an image segmentation method based on the polymorphic ant colony algorithm. The image segmentation method based on the polymorphic ant colony algorithm comprises the steps that the image segmentation process is taken as a clustering and combinatorial optimization process according to image segmentation characteristics, various ant colonies are made to search for corresponding food sources by simulating the preying and routing processes of ants by means of the multiple ant colonies, overall sensing of a whole image is achieved through the local sensing capacity, and a classification task is completed cooperatively. The defects that according to an ant colony algorithm, searching time is too long and the overall calculated quantity is large are overcome, it is proved by establishing a mathematical model based on the polymorphic ant colony algorithm that the image segmentation method can be used for segmenting a target rapidly and accurately and is an effective image segmentation method.
Description
Technical field
The invention belongs to computerized algorithm field, more particularly, the present invention relates to a kind of image partition method based on polymorphic ant colony algorithm.
Background technology
Based on the image partition method of ant group algorithm, ant walking is Stochastic sum blindness.Regard each for image pixel as an ant, suppose that image size is m × n, in cyclic search process, each pixel will carry out the probability calculation of Distance geometry routing with all the other m × n-1 pixel, and system has to pass through repeatedly to circulate and just can complete cluster process, cause search time long, overall calculation amount is large.For above problem, according to the feature of Iamge Segmentation, now image segmentation process is regarded as a cluster and Combinatorial Optimization process.Utilize multiple ant group, by simulate ant predation, seek footpath process, utilize local sensing ability to realize overall perception to whole image, complete to collaborative the process of classification task.
Summary of the invention
Problem to be solved by this invention is to provide short a kind of image partition method based on polymorphic ant colony algorithm a kind of search time.
To achieve these goals, the technical scheme that the present invention takes is:
Based on an image partition method for polymorphic ant colony algorithm, it is characterized in that, comprise the steps:
(1) view data is converted into the matrix A of M × N, supposes that every class has m ant, be randomly dispersed on image;
(2) parameter initialization, makes time t=0 and cycle index NC=0, arranges maximum cycle NCmax, and initialization α, β, ph
ij, r, ρ parameter;
(3) cluster circulation is started, cycle index NC ← NC+1;
(4) ant number k ← k+1;
(5) according to formulae discovery ant A
ito pixel X
jdistance d
ij;
(6) laying of ant group pheromone: ant is according to the transition probability between transition probability formulae discovery pixel;
(7) the following of pheromone path: the distinctive biological nature of ant, they always follow the high path of pheromone concentration, and the pheromone concentration of this class pixel is often higher, realize the classification of this class pixel and non-class pixel according to the pheromone concentration power of pixel;
(8) if meet termination condition, if i.e. cycle index NC >=NCmax, then end loop, and upgrade the gray-scale value of this class pixel and written-out program result of calculation by formula, otherwise go to step (3).
Preferably, the optimum configurations of described step (2) is α=3, β=10, r=20, ρ=0.1.
Preferably, described step (5) comprises the steps: further if d
ijbe zero, then this pixel is 1 to such degree of membership, d else if
ij<r, calculates guidance function according to formula 1, and calculates X
jto the quantity of information in each path.
Preferably, described formula 1 is
, wherein, r is cluster radius, and m is the intrinsic dimensionality of ant, p
kfor weighting factor, ph
ijfor quantity of information
Preferably, the m value in described formula 1 is 12.
Preferably, described step (6) comprises the steps: to compare transition probability and λ further, if be greater than λ, then adjust the quantity of information on path, upgrades cluster centre.
Beneficial effect: the invention provides a kind of image partition method based on polymorphic ant colony algorithm, according to the feature of Iamge Segmentation, image segmentation process is regarded as a cluster and Combinatorial Optimization process, utilize multiple ant group, by simulating the predation of ant, seek footpath process, allow the corresponding food source of all kinds of ant group huntings, the overall perception to whole image is realized by local sensing ability, complete to collaborative the process of classification task, reduce ant group algorithm long for search time, the shortcoming that overall calculation amount is large, through setting up its mathematical model, prove that the method can be partitioned into target more rapidly and accurately, it is a kind of effective image partition method.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of image partition method based on polymorphic ant colony algorithm of the present invention.
Embodiment
Based on an image partition method for polymorphic ant colony algorithm, it is characterized in that, comprise the steps:
(1) view data is converted into the matrix A of M × N, supposes that every class has m ant, be randomly dispersed on image;
(2) parameter initialization, makes time t=0 and cycle index NC=0, arranges maximum cycle NCmax, and initialization α, β, ph
ij, r, ρ parameter, optimum configurations is α=3, β=10, r=20, ρ=0.1;
(3) cluster circulation is started, cycle index NC ← NC+1;
(4) ant number k ← k+1;
(5) according to formulae discovery ant A
ito pixel X
jdistance d
ijif, d
ijbe zero, then this pixel is 1 to such degree of membership, d else if
ij<r, calculates guidance function according to formula 1, and calculates X
jto the quantity of information in each path, formula 1 is
, wherein, r is cluster radius, and m is the intrinsic dimensionality of ant, p
kfor weighting factor, ph
ijfor quantity of information, and m=12;
(6) laying of ant group pheromone: ant, according to the transition probability between transition probability formulae discovery pixel, compares transition probability and λ, if be greater than λ, then adjust the quantity of information on path, upgrades cluster centre;
(7) the following of pheromone path: the distinctive biological nature of ant, they always follow the high path of pheromone concentration, and the pheromone concentration of this class pixel is often higher, realize the classification of this class pixel and non-class pixel according to the pheromone concentration power of pixel;
(8) if meet termination condition, if i.e. cycle index NC >=NCmax, then end loop, and upgrade the gray-scale value of this class pixel and written-out program result of calculation by formula, otherwise go to step (3).
The invention provides a kind of image partition method based on polymorphic ant colony algorithm, according to the feature of Iamge Segmentation, image segmentation process is regarded as a cluster and Combinatorial Optimization process, utilize multiple ant group, by simulating the predation of ant, seek footpath process, allow the corresponding food source of all kinds of ant group huntings, the overall perception to whole image is realized by local sensing ability, complete to collaborative the process of classification task, reduce ant group algorithm long for search time, the shortcoming that overall calculation amount is large, through setting up its mathematical model, prove that the method can be partitioned into target more rapidly and accurately, it is a kind of effective image partition method.
The foregoing is only embodiments of the invention; not thereby the scope of the claims of the present invention is limited; every utilize description of the present invention to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (6)
1. based on an image partition method for polymorphic ant colony algorithm, it is characterized in that, comprise the steps:
(1) view data is converted into the matrix A of M × N, supposes that every class has m ant, be randomly dispersed on image;
(2) parameter initialization, makes time t=0 and cycle index NC=0, arranges maximum cycle NCmax, and initialization α, β, ph
ij, r, ρ parameter;
(3) cluster circulation is started, cycle index NC ← NC+1;
(4) ant number k ← k+1;
(5) according to formulae discovery ant A
ito pixel X
jdistance d
ij;
(6) laying of ant group pheromone: ant is according to the transition probability between transition probability formulae discovery pixel;
(7) the following of pheromone path: the distinctive biological nature of ant, they always follow the high path of pheromone concentration, and the pheromone concentration of this class pixel is often higher, realize the classification of this class pixel and non-class pixel according to the pheromone concentration power of pixel;
(8) if meet termination condition, if i.e. cycle index NC >=NCmax, then end loop, and upgrade the gray-scale value of this class pixel and written-out program result of calculation by formula, otherwise go to step (3).
2. according to a kind of image partition method based on polymorphic ant colony algorithm according to claim 1, it is characterized in that: the optimum configurations of described step (2) is α=3, β=10, r=20, ρ=0.1.
3. according to a kind of image partition method based on polymorphic ant colony algorithm according to claim 1, it is characterized in that: described step (5) comprises the steps: further if d
ijbe zero, then this pixel is 1 to such degree of membership, d else if
ij<r, calculates guidance function according to formula 1, and calculates X
jto the quantity of information in each path.
4. according to a kind of image partition method based on polymorphic ant colony algorithm according to claim 3, it is characterized in that: described formula 1 is
, wherein, r is cluster radius, and m is the intrinsic dimensionality of ant, p
kfor weighting factor, ph
ijfor quantity of information.
5. according to a kind of image partition method based on polymorphic ant colony algorithm according to claim 4, it is characterized in that: the m value in described formula 1 is 12.
6. according to a kind of image partition method based on polymorphic ant colony algorithm according to claim 1, it is characterized in that: described step (6) comprises the steps: to compare transition probability and λ further, if be greater than λ, then adjust the quantity of information on path, upgrade cluster centre.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510060447.2A CN104732522A (en) | 2015-02-05 | 2015-02-05 | Image segmentation method based on polymorphic ant colony algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510060447.2A CN104732522A (en) | 2015-02-05 | 2015-02-05 | Image segmentation method based on polymorphic ant colony algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104732522A true CN104732522A (en) | 2015-06-24 |
Family
ID=53456390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510060447.2A Pending CN104732522A (en) | 2015-02-05 | 2015-02-05 | Image segmentation method based on polymorphic ant colony algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104732522A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250923A (en) * | 2016-07-27 | 2016-12-21 | 合肥高晶光电科技有限公司 | A kind of image processing method based on ant group algorithm |
CN106650916A (en) * | 2016-12-29 | 2017-05-10 | 西安思源学院 | Grid segmentation method based on ant colony optimization |
CN110319829A (en) * | 2019-07-08 | 2019-10-11 | 河北科技大学 | Unmanned aerial vehicle flight path planing method based on adaptive polymorphic fusion ant colony algorithm |
CN112947591A (en) * | 2021-03-19 | 2021-06-11 | 北京航空航天大学 | Path planning method, device, medium and unmanned aerial vehicle based on improved ant colony algorithm |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101377850A (en) * | 2008-09-27 | 2009-03-04 | 北京航空航天大学 | Method of multi-formwork image segmentation based on ant colony clustering |
-
2015
- 2015-02-05 CN CN201510060447.2A patent/CN104732522A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101377850A (en) * | 2008-09-27 | 2009-03-04 | 北京航空航天大学 | Method of multi-formwork image segmentation based on ant colony clustering |
Non-Patent Citations (2)
Title |
---|
吴闯: "基于蚁群算法的火焰图像分割方法应用研究", 《万方学位论文数据库》 * |
王振青: "基于蚁群算法的图像分割方法研究", 《万方学位论文数据库》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250923A (en) * | 2016-07-27 | 2016-12-21 | 合肥高晶光电科技有限公司 | A kind of image processing method based on ant group algorithm |
CN106650916A (en) * | 2016-12-29 | 2017-05-10 | 西安思源学院 | Grid segmentation method based on ant colony optimization |
CN106650916B (en) * | 2016-12-29 | 2019-02-01 | 西安思源学院 | A kind of mesh segmentation method based on ant group optimization |
CN110319829A (en) * | 2019-07-08 | 2019-10-11 | 河北科技大学 | Unmanned aerial vehicle flight path planing method based on adaptive polymorphic fusion ant colony algorithm |
CN110319829B (en) * | 2019-07-08 | 2022-11-18 | 河北科技大学 | Unmanned aerial vehicle flight path planning method based on self-adaptive polymorphic fusion ant colony algorithm |
CN112947591A (en) * | 2021-03-19 | 2021-06-11 | 北京航空航天大学 | Path planning method, device, medium and unmanned aerial vehicle based on improved ant colony algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | A return-cost-based binary firefly algorithm for feature selection | |
Xue et al. | A multi-objective particle swarm optimisation for filter-based feature selection in classification problems | |
Hassanzadeh et al. | A new hybrid approach for data clustering using firefly algorithm and K-means | |
Agbaje et al. | Automatic data clustering using hybrid firefly particle swarm optimization algorithm | |
Ozbay et al. | A novel approach for detection of fake news on social media using metaheuristic optimization algorithms | |
Zou et al. | A close neighbor mobility method using particle swarm optimizer for solving multimodal optimization problems | |
Guo et al. | A new improved krill herd algorithm for global numerical optimization | |
Nanda et al. | A survey on nature inspired metaheuristic algorithms for partitional clustering | |
Ahmadi et al. | A modified grey wolf optimizer based data clustering algorithm | |
Tong et al. | A density-peak-based clustering algorithm of automatically determining the number of clusters | |
Ma et al. | Decomposition-based multiobjective evolutionary algorithm for community detection in dynamic social networks | |
CN108197643A (en) | A kind of transfer learning method based on Unsupervised clustering and metric learning | |
CN104732522A (en) | Image segmentation method based on polymorphic ant colony algorithm | |
CN106991442A (en) | The self-adaptive kernel k means method and systems of shuffled frog leaping algorithm | |
CN109784405A (en) | Cross-module state search method and system based on pseudo label study and semantic consistency | |
CN108875896A (en) | A kind of disturbance chaos artificial bee colony algorithm certainly of global optimum's guidance | |
CN107045717A (en) | The detection method of leucocyte based on artificial bee colony algorithm | |
Yu et al. | Autonomous knowledge-oriented clustering using decision-theoretic rough set theory | |
Zhou et al. | A hybrid glowworm swarm optimization algorithm to solve constrained multimodal functions optimization | |
CN109657147A (en) | Microblogging abnormal user detection method based on firefly and weighting extreme learning machine | |
Fuentes et al. | Improving accuracy of tomato plant disease diagnosis based on deep learning with explicit control of hidden classes | |
CN116386899A (en) | Graph learning-based medicine disease association relation prediction method and related equipment | |
Chen et al. | Novel fruit fly algorithm for global optimisation and its application to short-term wind forecasting | |
Yan et al. | A novel clustering algorithm based on fitness proportionate sharing | |
CN105740949A (en) | Group global optimization method based on randomness best strategy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150624 |
|
WD01 | Invention patent application deemed withdrawn after publication |