CN109102517A - A kind of method of Image Edge-Detection, system and associated component - Google Patents

A kind of method of Image Edge-Detection, system and associated component Download PDF

Info

Publication number
CN109102517A
CN109102517A CN201810908371.8A CN201810908371A CN109102517A CN 109102517 A CN109102517 A CN 109102517A CN 201810908371 A CN201810908371 A CN 201810908371A CN 109102517 A CN109102517 A CN 109102517A
Authority
CN
China
Prior art keywords
picture
image
seed
pixel
detected
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
Application number
CN201810908371.8A
Other languages
Chinese (zh)
Inventor
余荣
曾维亮
张浩川
钟德宝
陈广财
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.)
Guangdong University of Technology
Original Assignee
Guangdong University of Technology
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 Guangdong University of Technology filed Critical Guangdong University of Technology
Priority to CN201810908371.8A priority Critical patent/CN109102517A/en
Publication of CN109102517A publication Critical patent/CN109102517A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • 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
    • G06T7/10—Segmentation; Edge detection
    • G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

This application discloses a kind of methods of Image Edge-Detection, the method includes carrying out region growing according to the pixel in gray value sequence from big to small successively selection target picture, and picture to be detected is obtained according to the background that region growing result removes the Target Photo；Preset quantity ant is launched at random in the picture to be detected using Chaos Ant Colony Optimization, and image threshold is calculated according to the final Pheromone Matrix that all ants generate；The image border of the Target Photo is determined according to described image threshold value.This method can reduce the local interference of noise on image edge detection, promote the effect of edge detection.Disclosed herein as well is a kind of system of Image Edge-Detection, a kind of computer readable storage medium and a kind of image processing apparatus, have the above beneficial effect.

Description

A kind of method of Image Edge-Detection, system and associated component
Technical field
The present invention relates to technical field of image processing, in particular to a kind of method of Image Edge-Detection, system, one kind Computer readable storage medium and a kind of image processing apparatus.
Background technique
Edge is the most basic feature of image, it contains useful information for identification, and mesh is described or identified for people It is marked with and interpretation of images provides an important characteristic parameter.Edge detection is image procossing, image analysis and computer view One of most classic research contents in feel field is the basic means for carrying out pattern-recognition and image information extraction.It is mainly sharp Extract edge point set with edge detection operator, because of situations such as in detection there are noise, image is fuzzy and edge interruption.? In image, boundary shows the termination and the beginning of another characteristic area of a characteristic area, the inside of boundary institute separation region Feature or attribute are consistent, and the feature inside different zones is different, and edge detection exactly utilizes object and background at certain The difference on characteristics of image is planted to realize, these differences include gray scale, color or textural characteristics.
In the prior art, Image Edge-Detection usually is carried out merely with ant group algorithm, but ant group algorithm is easy to receive too early It holds back, easily sink into local optimum, to edge position inaccurate, interfered by ambient noise larger.
Therefore, the local interference for how reducing noise on image edge detection, the effect for promoting edge detection is this field The current technical issues that need to address of technical staff.
Summary of the invention
The purpose of the application is to provide the method, system, a kind of computer readable storage medium of a kind of Image Edge-Detection And a kind of image processing apparatus, it can reduce the local interference of noise on image edge detection, promote the effect of edge detection.
In order to solve the above technical problems, the application provides a kind of method of Image Edge-Detection, this method comprises:
Region growing, and root are carried out according to the pixel in the sequence of gray value from big to small successively selection target picture Picture to be detected is obtained according to the background that region growing result removes the Target Photo；
Preset quantity ant is launched at random in the picture to be detected using Chaos Ant Colony Optimization, and according to all The final Pheromone Matrix that the ant generates calculates image threshold；
The image border of the Target Photo is determined according to described image threshold value.
Optionally, launching preset quantity ant at random in the picture to be detected using Chaos Ant Colony Optimization includes:
The dimension of picture of the picture to be detected is obtained, and using the Chaos Ant Colony Optimization in the picture to be detected In launch preset quantity ant at random；Wherein, the preset quantity is determined according to the dimension of picture.
Optionally, calculating image threshold according to the final Pheromone Matrix that all ants generate includes:
The Pheromone Matrix that all ants are stopped obtaining after transfer is as the final Pheromone Matrix；
Image threshold primary is calculated according to the final Pheromone Matrix, and the image threshold primary is iterated It updates operation and obtains described image threshold value.
Optionally, to carry out region according to the pixel in gray value sequence from big to small successively selection target picture raw It is long, and picture to be detected is obtained according to the background that region growing result removes the Target Photo and includes:
Step 1: the corresponding relationship of the pixel and the gray value is stored into relationship table；
Step 2: the maximum pixel of the gray value is selected to carry out area as seed point from the relationship table Domain growth operation obtains seed region, and deletes pixel corresponding with the seed region in the relationship table；
Step 3: judge in the relationship table with the presence or absence of the pixel；If so, into the step 2； If it is not, then entering step four；
Step 4: setting background seed region for the corresponding seed region of the background of the Target Photo, and according to removing All seed regions except the background seed region obtain the picture to be detected.
Optionally, the maximum pixel of the gray value is selected to carry out area as seed point from the relationship table Domain growth operation obtains seed region
Select the maximum pixel of the gray value as the seed point from the relationship table；
It is operated and is planted according to seed point progress region growing using the method for eight neighborhood connection or the connection of four neighborhoods Subregion；Wherein, the gray value I of other pixels in the seed region in addition to the seed point meets target formula, The target formula is | Iseed- I | < λ | Imax-Imin|, IseedFor the gray value of the seed point, λ is adjustable parameter, ImaxFor The gray scale maximum value of the Target Photo, IminFor the minimum gray value of the Target Photo.
Present invention also provides a kind of system of Image Edge-Detection, which includes:
Region growing module, for according to the pixel in gray value sequence from big to small successively selection target picture Region growing is carried out, and picture to be detected is obtained according to the background that region growing result removes the Target Photo；
Image threshold determining module, it is default for being launched at random in the picture to be detected using Chaos Ant Colony Optimization Quantity ant, and image threshold is calculated according to the final Pheromone Matrix that all ants generate；
Edge determining module, for determining the image border of the Target Photo according to described image threshold value.
Optionally, described image threshold determination module includes:
Ant launches unit, for obtaining the dimension of picture of the picture to be detected, and utilizes the Chaos Ant Colony Optimization Preset quantity ant is launched at random in the picture to be detected；Wherein, the preset quantity is true according to the dimension of picture It is fixed；
Threshold value determination unit, the final Pheromone Matrix for being generated according to all ants calculate image threshold.
Optionally, the threshold value determination unit includes；
Pheromone Matrix determines subelement, makees for all ants to be stopped the Pheromone Matrix obtaining after transfer For the final Pheromone Matrix；
Iteration subelement, for calculating image threshold primary according to the final Pheromone Matrix, and to the figure primary Described image threshold value is obtained as threshold value is iterated update operation.
Present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer The step of program realizes above-mentioned Image Edge-Detection method when executing executes.
Present invention also provides a kind of image processing apparatus, including memory and processor, it is stored in the memory Computer program, the processor realize the side of above-mentioned Image Edge-Detection when calling the computer program in the memory The step of method executes.
The present invention provides a kind of method of Image Edge-Detection, including according to gray value sequence from big to small successively Pixel in selection target picture carries out region growing, and the background of the Target Photo is removed according to region growing result Obtain picture to be detected；Preset quantity ant, and root are launched at random in the picture to be detected using Chaos Ant Colony Optimization Image threshold is calculated according to the final Pheromone Matrix that all ants generate；The target is determined according to described image threshold value The image border of picture.
Target Photo is carried out the seed region that preliminary division obtains by the application region growing technology, since region is raw Length can be effectively removed the background of Target Photo, reduce in background can influence, therefore the application only need to be to by region The pixel of picture to be detected after growth can quickly obtain image threshold, and then basis using Chaos Ant Colony Optimization detection Image threshold determines image border.Picture to be detected eliminates the background of original picture, therefore for Target Photo The application only detects the pixel of picture to be detected, effectively when carrying out edge detection using Chaos Ant Colony Optimization Reduce and avoid influence of the noise to edge detection effect, available marginal information is continuous, sharp-edged testing result. The application can reduce the local interference of noise on image edge detection, promote the effect of edge detection.The application is gone back simultaneously System, a kind of computer readable storage medium and a kind of image processing apparatus of a kind of Image Edge-Detection are provided, is had upper Beneficial effect is stated, details are not described herein.
Detailed description of the invention
In ord to more clearly illustrate embodiments of the present application, attached drawing needed in the embodiment will be done simply below Introduction, it should be apparent that, the drawings in the following description are only some examples of the present application, skill common for this field For art personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the method for Image Edge-Detection provided by the embodiment of the present application；
Fig. 2 is the flow chart of the method for another kind Image Edge-Detection provided by the embodiment of the present application；
Fig. 3 is the experimental result schematic diagram of the present embodiment；
Fig. 4 is a kind of structural schematic diagram of the system of Image Edge-Detection provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people Member's every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Below referring to Figure 1, Fig. 1 is a kind of process of the method for Image Edge-Detection provided by the embodiment of the present application Figure.
Specific steps may include:
S101: carrying out region growing according to the pixel in gray value sequence from big to small successively selection target picture, And picture to be detected is obtained according to the background that region growing result removes the Target Photo；
Wherein, Image Edge-Detection is a very important process, image segmentation, data scanning in image procossing The support of Image Edge-Detection is required with processes such as identifications.Noise is the interference signal being prevalent in image, image side Edge detection method needs that noise is overcome to reach efficient detection effect.
Region growing is first passed through treated picture, calculating cost is greatly saved in subsequent image processing, accelerates The speed of edge detection, it can be achieved that real-time online Image Edge-Detection；Relative to ant group algorithm, side provided in this embodiment Edge detection method introduces Chaos Ant Colony Optimization, and Chaos Ant Colony Optimization is with good performance in terms of searching for image border, from And improve ant group algorithm be easy Premature Convergence, easily sink into local optimum, to edge position inaccurate the problems such as.
Region growing refers to the process of groups of pixel or the region regional development Cheng Geng great.It is run jointly from the collection of seed point Begin, increasing from the region that these are put is by that there will be like attribute as intensity, gray level, texture color etc. with each seed point Adjacent pixel be merged into this region.
The purpose of this step is to carry out Target Photo into preliminary segmentation, that is, background and image distinguished, by It is the detection carried out for the edge of the image in Target Photo in carrying out Image Edge-Detection, therefore can be raw by region Long mode determines interested position when Chaos Ant Colony Optimization carries out edge detection.Image is carried out with region growing method Initial division is mainly handled using the continuity between image-region or pixel with adjacency.According to defining in advance Rule pixel or subregion are aggregated into bigger region.The basic ideas of region growing are from one or more seed points It sets out, continually adds and meet neighbours' point of similitude rule to grow image-region.The concrete operations of region growing will be It is introduced in next embodiment, the application carries out the mapping to be checked obtained after region growing processing to Target Photo in a word Piece is the picture after Target Photo removal background.It should be noted that successively selecting mesh according to the sequence of gray value from big to small The pixel marked on a map in piece carries out the concrete operations of region growing see the introduction in next embodiment.
S102: launching preset quantity ant using Chaos Ant Colony Optimization at random in the picture to be detected, and according to The final Pheromone Matrix that all ants generate calculates image threshold；
Wherein, Chaos Ant Colony Optimization is a kind of optimization algorithm based on nature, according to ant release pheromone on ground Upper searching optimal path, so that the action of subsequent ant tracks.Since edge is the important information in image, by chaos ant colony Algorithm is used for the edge detection of image, and exactly the edge extraction of characterization in the picture is come out.Side based on Chaos Ant Colony Optimization Edge detection is moved on picture to be detected using ant, and the edge of picture to be detected is found by establishing Pheromone Matrix. Marginal information at where each input representative image pixel of Pheromone Matrix.
Specifically, using mixed dynamic ant group algorithm determine image threshold operation the following steps are included:
Step 1: being launched at random in the picture to be detected of M × NAnt, utilizes ant random search path When, the situation of change of gray value of image is constantly updated Pheromone Matrix and is finally generated using the positive feedback of ant group algorithm Pheromone Matrix calculates the threshold value of image, so that it is determined that the marginal position of image.Initial Pheromone Matrix τi,jIt cannot be 0, Otherwise it can not start ant transfer, therefore generate a random matrix and initialized as Pheromone Matrix.Ant will walk in next step Position, by transition probabilityIt determines,
Wherein, (i, j) is a neighbor pixel of ant current location (l, m)；Ω (l, m) is all adjacent pixels The set of point；τi,jIt is Pheromone Matrix at pixel (i, j)；ηi,jIt is the inspiration guidance function at pixel (i, j)；α, β are Impact factor during the pheromones intensity accumulated at pixel (i, j) and heuristic guidance function selection pixel.
Heuristic guidance function ηi,jFor
Wherein, Ii,jIt is the gray value of pixel (i, j)；Function Vc(Ii,j) it is the edge for calculating ant place pixel The intensity value of information, value are determined by the value of place pixel peripheral region, shown as the following formula；Z is a standardization ginseng Number,
Wherein:
Var=| Ii-2,j-1-Ii+2,j+1|+|Ii-2,j+1-Ii+2,j-1|+|Ii-1,j-2-Ii+1,j+2|+ |Ii-1,j-1-Ii+1,j+1|+| Ii-1,j-Ii+1,j|+|Ii-1,j+1-Ii+1,j-1|+ |Ii-1,j+2-Ii+1,j-2|+|Ii,j-1-Ii,j+1|
Enable NC=0 (NC is the number of iterations), carry out chaos intialization, can choose typical chaos system --- Logistics mapping is used as Chaos Variable, is iterated as follows, Zi,j(t+1)=μ Zi,z(t)[1-Zi,j(t)]；
In formula, μ is control parameter, when μ=4,0≤Zi,j(0)≤1 when, Logistics mapping is completely in chaos shape State.Using fully intermeshing theory, each chaos amount corresponds to the pheromones value on a pixel, i.e., the letter on each pixel Plain initial value is ceased to be provided according to chaos amount.
Information is known as at two and updates in algorithm.Updating for the first time is the Pheromone Matrix after every ant covers a step Update according to formula:
(1- ρ) is the evaporation rate of pheromones, ρ ∈ (0,1)；Indicate the kth ant letter left in passing point Breath element, value is by heuristic matrix ηi,jIt is determined, i.e.,Zi,jIt (t) is Chaos Variable, by formula Zi,j(t+1)=μ Zi,z(t)[1-Zi,j(t)] iteration obtains, q1For coefficient.
It is after having carried out an iteration that second, which updates, and formula is as follows:
Wherein,For the attenuation coefficient of pheromones.
Step 2: after all ant transfers, can be initialized according to final Pheromone Matrix is obtained Image threshold T(l), l=0, l are the number of iterations, indicate that the threshold value is threshold value primary as l=0.
Wherein,For final Pheromone Matrix.
It should be noted that image threshold refers to the segmentation benchmark of image, the binaryzation based on this achievable image.
Further, according to threshold value T(l)It can be by Pheromone MatrixIt is divided into and is greater than T(l)Be less than T(l)Two Point, calculate separately this two-part average valueWith
Wherein:
Iteration coefficient l=l+1 is set and updates image threshold T(l):
Step 3: if | T(l)-T(l-1)| > ω then continues the iterative operation in step 2 to image threshold；If | T(l)-T(l-1)|≤ω then exports T(l), ω is the error range allowed, is typically set to 1.
In the above-mentioned operation for obtaining image threshold, make to be invested in picture to be detected at random first with Chaos Ant Colony Optimization Ant random movement, and according to the mobile obtained final Pheromone Matrix of ant.According to Pheromone Matrix to image primary Threshold value is iterated operation and finally obtains the image threshold for meeting preset condition.
S103: the image border of the Target Photo is determined according to described image threshold value.
Wherein, on the basis of S102 obtains image threshold, picture can be divided according to threshold value, that is, willPosition be set as 1,Position be set as 0, realize the division of picture to be detected, and be set as 1 The junction of part and the part for being set as 0 is exactly image border.
Target Photo is carried out the seed region that preliminary division obtains by the application region growing technology, since region is raw Length can be effectively removed the background of Target Photo, reduce in background can influence, therefore the application only need to be to by region The pixel of picture to be detected after growth can quickly obtain image threshold, and then basis using Chaos Ant Colony Optimization detection Image threshold determines image border.Picture to be detected eliminates the background of original picture, therefore for Target Photo The application only detects the pixel of picture to be detected, effectively when carrying out edge detection using Chaos Ant Colony Optimization Reduce and avoid influence of the noise to edge detection effect, available marginal information is continuous, sharp-edged testing result. The application can reduce the local interference of noise on image edge detection, promote the effect of edge detection.
Fig. 2 is referred to below, and Fig. 2 is the stream of the method for another kind Image Edge-Detection provided by the embodiment of the present application Cheng Tu；
Specific steps may include:
S201: the corresponding relationship of the pixel and the gray value is stored into relationship table；
S202: select the maximum pixel of the gray value as the seed point from the relationship table；
Wherein, the corresponding gray value of pixel and pixel all in Target Photo is store in relationship table Corresponding relationship.Region growing is the operation that region segmentation is carried out according to the gray value of pixel, specifically, can select every time The maximum pixel of gray value carries out region growing as seed point in relationship table.
S203: region growing operation is carried out according to the seed point using the method for eight neighborhood connection or the connection of four neighborhoods Obtain seed region；Wherein, the gray value I of other pixels in the seed region in addition to the seed point meets mesh Formula is marked, the target formula is | Iseed- I | < λ | Imax-Imin|, IseedFor the gray value of the seed point, λ is adjustable ginseng Number, ImaxFor the gray scale maximum value of the Target Photo, IminFor the minimum gray value of the Target Photo.
S204: pixel corresponding with the seed region in the relationship table is deleted；
It should be noted that multiple pixels can be corresponded in seed region, when determining that certain pixels " have belonged to " After some seed region, pixel inconvenience in subsequent region growing can be used as seed point and carry out region growing operation, Therefore the corresponding pixel of seed region in relationship table is deleted in this step, or can be understood as deleting relationship Pixel corresponding with the seed region and its gray value obtain corresponding relationship in the table of comparisons.
S205: judge in the relationship table with the presence or absence of the pixel；If so, into the S202；If It is no, then enter S206；
Specifically, this FOUR EASY STEPS of S202, S203, S204 and S205 can use following practical application in the present embodiment In embodiment be explained further:
Step 1: in the selection of seed point, selecting to carry out with the maximum pixel of gray value as seed point every time Region growing.
Step 2: spatially adjacent similar pixel being searched using eight neighborhood connection or four field connectivity schemes Rope.
Step 3: in the selection of similarity criterion, the formula being defined as follows is for selecting neighbouring pixel:
|Iseed- I | < λ | Imax-Imin| (1)
Wherein: the gray value of I expression pixel；IseedIndicate the gray value of seed point；ImaxWith IminIt respectively indicates in image Maximum gradation value and minimum gradation value；λ is adjustable parameter, for controlling the similarity thresholding between pixel, will be met The adjacent pixels point of this formula is added to seed region.
Step 4: during growth when there is no pixel to meet the condition that some seed region is added, in region growing Only.
In realization, it can recursively call the step 1 to the algorithm of 4 descriptions until all pixels are all drawn with program Subregion.When region growing is completed, output is a series of spatially continuous seed regions.The present embodiment is raw in region Some excessively trifling regions (for example, total pixel quantity is less than 10) are simply incorporated into the phase being adjacent after having grown Like spending in an immediate region, because the quantity in these regions is relatively more, doing so can be to avoid complicated calculation amount； The main information in image is nor affected on simultaneously.
S206: background seed region is set by the corresponding seed region of the background of the Target Photo, and according to except institute It states all seed regions except background seed region and obtains the picture to be detected.
S207: the dimension of picture of the picture to be detected is obtained, and using the Chaos Ant Colony Optimization described to be detected Preset quantity ant is launched in picture at random；Wherein, the preset quantity is determined according to the dimension of picture.
Wherein, the quantity of ant is to be stored to be arranged according to picture, such as dimension of picture is M × N, then can launchAnt.
S208: the Pheromone Matrix that all ants are stopped obtaining after transfer is as the final Pheromone Matrix；
S209: image threshold primary is calculated according to the final Pheromone Matrix, and the image threshold primary is carried out Iteration updates operation and obtains described image threshold value.
S210: the image border of the Target Photo is determined according to described image threshold value.
The present embodiment proposes a kind of edge detection algorithm combined based on region growing with Chaos Ant Colony Optimization (RGCAC).Relative to ant group algorithm, this embodiment introduces Chaos Ant Colony Optimization, which has in terms of searching for image border There is good performance, is easy Premature Convergence to improve ant group algorithm, easily sinks into local optimum, to edge position inaccurate etc. Problem, while region growing is first passed through treated picture, calculating cost is greatly saved in subsequent image processing, accelerates The speed of edge detection, and the marginal information of image is completely maintained, there is good noiseproof feature can realize in real time Online Image Edge-Detection.Fig. 3 is referred to, it is target picture in figure that Fig. 3, which is the experimental result schematic diagram of the present embodiment, Edge detection results, target picture are the common picture in edge detection example, and the network address of Target Photo is http: // breckon.eu/toby/fundipbook/materials/gallery/cameraman.jpg。
Fig. 4 is referred to, Fig. 4 is a kind of structural representation of the system of Image Edge-Detection provided by the embodiment of the present application Figure；
The system may include:
Region growing module 100, for according to the pixel in gray value sequence from big to small successively selection target picture Point carries out region growing, and obtains picture to be detected according to the background that region growing result removes the Target Photo；
Image threshold determining module 200, it is pre- for being launched at random in the picture to be detected using Chaos Ant Colony Optimization If quantity ant, and image threshold is calculated according to the final Pheromone Matrix that all ants generate；
Edge determining module 300, for determining the image border of the Target Photo according to described image threshold value.
Optionally, described image threshold determination module 200 includes:
Ant launches unit, for obtaining the dimension of picture of the picture to be detected, and utilizes the Chaos Ant Colony Optimization Preset quantity ant is launched at random in the picture to be detected；Wherein, the preset quantity is true according to the dimension of picture It is fixed；
Threshold value determination unit, the final Pheromone Matrix for being generated according to all ants calculate image threshold.
Optionally, the threshold value determination unit includes；
Pheromone Matrix determines subelement, makees for all ants to be stopped the Pheromone Matrix obtaining after transfer For the final Pheromone Matrix；
Iteration subelement, for calculating image threshold primary according to the final Pheromone Matrix, and to the figure primary Described image threshold value is obtained as threshold value is iterated update operation.
Since the embodiment of components of system as directed is corresponded to each other with the embodiment of method part, the embodiment of components of system as directed The description of the embodiment of method part is referred to, wouldn't be repeated here.
Present invention also provides a kind of computer readable storage mediums, have computer program thereon, the computer program It is performed and step provided by above-described embodiment may be implemented.The storage medium may include: USB flash disk, mobile hard disk, read-only Memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or The various media that can store program code such as person's CD.
Present invention also provides a kind of image processing apparatus, may include memory and processor, deposit in the memory There is computer program, when the processor calls the computer program in the memory, above-described embodiment may be implemented and mentioned For the step of.Certain described image processing unit can also include various network interfaces, the components such as power supply.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part Explanation.It should be pointed out that for those skilled in the art, in the premise for not departing from the application principle Under, can also to the application, some improvement and modification can also be carried out, these improvement and modification also fall into the protection of the claim of this application In range.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or behaviour There are any actual relationship or orders between work.Moreover, the terms "include", "comprise" or its any other change Body is intended to non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only It including those elements, but also including other elements that are not explicitly listed, or further include for this process, method, object Product or the intrinsic element of equipment.Under the situation not limited more, wanted by what sentence "including a ..." limited Element, it is not excluded that there is also other identical elements in the process, method, article or apparatus that includes the element.

Claims (10)

1. a kind of method of Image Edge-Detection characterized by comprising
Region growing is carried out according to the pixel in the sequence of gray value from big to small successively selection target picture, and according to region The background that growth result removes the Target Photo obtains picture to be detected；
Preset quantity ant is launched at random in the picture to be detected using Chaos Ant Colony Optimization, and according to all ants The final Pheromone Matrix that ant generates calculates image threshold；
The image border of the Target Photo is determined according to described image threshold value.
2. method according to claim 1, which is characterized in that random in the picture to be detected using Chaos Ant Colony Optimization Launching preset quantity ant includes:
The dimension of picture of the picture to be detected is obtained, and random in the picture to be detected using the Chaos Ant Colony Optimization Launch preset quantity ant；Wherein, the preset quantity is determined according to the dimension of picture.
3. method according to claim 1, which is characterized in that the final Pheromone Matrix meter generated according to all ants Calculating image threshold includes:
The Pheromone Matrix that all ants are stopped obtaining after transfer is as the final Pheromone Matrix；
Image threshold primary is calculated according to the final Pheromone Matrix, and update behaviour is iterated to the image threshold primary Obtain described image threshold value.
4. method according to claim 1, which is characterized in that according to gray value sequence from big to small successively selection target figure Pixel in piece carries out region growing, and obtains mapping to be checked according to the background that region growing result removes the Target Photo Piece includes:
Step 1: the corresponding relationship of the pixel and the gray value is stored into relationship table；
Step 2: the maximum pixel of the gray value is selected to carry out region growing as seed point from the relationship table Operation obtains seed region, and deletes pixel corresponding with the seed region in the relationship table；
Step 3: judge in the relationship table with the presence or absence of the pixel；If so, into the step 2；If it is not, Then enter step four；
Step 4: background seed region is set by the corresponding seed region of the background of the Target Photo, and according to except described All seed regions except background seed region obtain the picture to be detected.
5. method according to claim 4, which is characterized in that select the gray value maximum from the relationship table Pixel operates to obtain seed region as seed point progress region growing
Select the maximum pixel of the gray value as the seed point from the relationship table；
Region growing is carried out according to the seed point using the method for eight neighborhood connection or the connection of four neighborhoods to operate to obtain seed zone Domain；Wherein, the gray value I of other pixels in the seed region in addition to the seed point meets target formula, described Target formula is | Iseed- I | < λ | Imax-Imin|, IseedFor the gray value of the seed point, λ is adjustable parameter, ImaxIt is described The gray scale maximum value of Target Photo, IminFor the minimum gray value of the Target Photo.
6. a kind of system of Image Edge-Detection characterized by comprising
Region growing module, for carrying out area according to the pixel in gray value sequence from big to small successively selection target picture Domain growth, and picture to be detected is obtained according to the background that region growing result removes the Target Photo；
Image threshold determining module, for launching preset quantity at random in the picture to be detected only using Chaos Ant Colony Optimization Ant, and image threshold is calculated according to the final Pheromone Matrix that all ants generate；
Edge determining module, for determining the image border of the Target Photo according to described image threshold value.
7. system according to claim 6, which is characterized in that described image threshold determination module includes:
Ant launches unit, for obtaining the dimension of picture of the picture to be detected, and using the Chaos Ant Colony Optimization in institute It states and launches preset quantity ant in picture to be detected at random；Wherein, the preset quantity is determined according to the dimension of picture；
Threshold value determination unit, the final Pheromone Matrix for being generated according to all ants calculate image threshold.
8. system according to claim 7, which is characterized in that the threshold value determination unit includes；
Pheromone Matrix determines subelement, and the Pheromone Matrix for stopping obtaining after transfer using all ants is as described in Final Pheromone Matrix；
Iteration subelement, for calculating image threshold primary according to the final Pheromone Matrix, and to the image threshold primary Value is iterated update operation and obtains described image threshold value.
9. a kind of image processing apparatus characterized by comprising
Memory, for storing computer program；
Processor realizes such as Image Edge-Detection described in any one of claim 1 to 5 when for executing the computer program Method the step of.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium Program is realized when the computer program is executed by processor such as Image Edge-Detection described in any one of claim 1 to 5 The step of method.
CN201810908371.8A 2018-08-10 2018-08-10 A kind of method of Image Edge-Detection, system and associated component Pending CN109102517A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810908371.8A CN109102517A (en) 2018-08-10 2018-08-10 A kind of method of Image Edge-Detection, system and associated component

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810908371.8A CN109102517A (en) 2018-08-10 2018-08-10 A kind of method of Image Edge-Detection, system and associated component

Publications (1)

Publication Number Publication Date
CN109102517A true CN109102517A (en) 2018-12-28

Family

ID=64849236

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810908371.8A Pending CN109102517A (en) 2018-08-10 2018-08-10 A kind of method of Image Edge-Detection, system and associated component

Country Status (1)

Country Link
CN (1) CN109102517A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115131387A (en) * 2022-08-25 2022-09-30 山东鼎泰新能源有限公司 Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101286199A (en) * 2007-09-14 2008-10-15 西北工业大学 Method of image segmentation based on area upgrowth and ant colony clustering
CN106651872A (en) * 2016-11-23 2017-05-10 北京理工大学 Prewitt operator-based pavement crack recognition method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101286199A (en) * 2007-09-14 2008-10-15 西北工业大学 Method of image segmentation based on area upgrowth and ant colony clustering
CN106651872A (en) * 2016-11-23 2017-05-10 北京理工大学 Prewitt operator-based pavement crack recognition method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
姜雪瑶: "基于混沌蚁群算法的快速图像边缘检测", 《电子与信息科学》 *
耿艳香: "混沌蚁群算法在图像边缘检测中的应用", 《计算机工程与应用》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115131387A (en) * 2022-08-25 2022-09-30 山东鼎泰新能源有限公司 Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing
CN115131387B (en) * 2022-08-25 2023-01-24 山东鼎泰新能源有限公司 Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing

Similar Documents

Publication Publication Date Title
CN108961291A (en) A kind of method of Image Edge-Detection, system and associated component
Anjna et al. Review of image segmentation technique
CN106340016B (en) A kind of DNA quantitative analysis method based on microcytoscope image
CN108647577A (en) A kind of pedestrian&#39;s weight identification model that adaptive difficult example is excavated, method and system
CN109102518A (en) A kind of method of Image Edge-Detection, system and associated component
CN101286199A (en) Method of image segmentation based on area upgrowth and ant colony clustering
CN104376556B (en) A kind of rock CT images Target Segmentation method
CN106204646A (en) Multiple mobile object tracking based on BP neutral net
CN111639540B (en) Semi-supervised character re-recognition method based on camera style and human body posture adaptation
Verma et al. A novel fuzzy ant system for edge detection
CN109102514A (en) A kind of image partition method, device, equipment and computer readable storage medium
CN109685806B (en) Image significance detection method and device
CN105405136A (en) Self-adaptive spinal CT image segmentation method based on particle swarm optimization
CN110827299B (en) Image segmentation method based on Harris eagle optimization algorithm
CN111695640B (en) Foundation cloud picture identification model training method and foundation cloud picture identification method
CN106600965B (en) Traffic flow morning and evening peak period automatic identifying method based on sharpness
Park et al. Hierarchical data structure for real-time background subtraction
CN109323697A (en) A method of particle fast convergence when starting for Indoor Robot arbitrary point
CN112101428B (en) Image classification method and system based on convolutional neural network
CN106295639A (en) A kind of virtual reality terminal and the extracting method of target image and device
CN113689324A (en) Automatic adding and deleting method and device for portrait object based on two classification labels
Aydın et al. Extraction of flower regions in color images using ant colony optimization
Zhou et al. An efficient two-stage region merging method for interactive image segmentation
CN110009664A (en) A kind of infrared object tracking method and device based on response diagram fusion
Agrawal et al. Analysis and synthesis of an ant colony optimization technique for image edge detection

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20181228

RJ01 Rejection of invention patent application after publication