CN112017194B - Image segmentation method, device, equipment and storage medium - Google Patents
Image segmentation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112017194B CN112017194B CN202010866043.3A CN202010866043A CN112017194B CN 112017194 B CN112017194 B CN 112017194B CN 202010866043 A CN202010866043 A CN 202010866043A CN 112017194 B CN112017194 B CN 112017194B
- Authority
- CN
- China
- Prior art keywords
- image
- factor
- clustering
- local similarity
- iteration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003709 image segmentation Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06T7/90—Determination of colour characteristics
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention relates to the field of computer vision and discloses an image segmentation method, an image segmentation system, electronic equipment and a storage medium. The image segmentation method comprises the following steps: setting parameters of image segmentation, wherein the parameters comprise a clustering number, an iteration termination threshold, a fuzzy index, an initial membership matrix and an initial clustering center; calculating local similarity factors and space coordination factors according to the space information of the image and the parameters; performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter; and after the iteration is terminated, image segmentation is carried out. The method is applied to the image segmentation process, and the purpose that not only the color information of the image but also the spatial information of the image are considered during the image segmentation is achieved.
Description
Technical Field
The embodiment of the invention relates to the field of computer vision, in particular to an image segmentation method, an image segmentation system, electronic equipment and a storage medium.
Background
The Fuzzy C-Means clustering algorithm (FCM) is a commonly used image segmentation method for Fuzzy clustering. The FCM algorithm is implemented as follows: and continuously carrying out iterative clustering on the membership degree of the pixel points and the clustering center according to the color information of the pixel points in the image, optimizing the clustering result when the change before and after the iteration of the clustering center meets the iteration termination condition, and finally dividing the image according to the clustering result.
However, when the existing FCM algorithm performs image segmentation, only color information of an image is considered, so that the segmented image is sensitive to noise, and the segmented region is often discontinuous.
Disclosure of Invention
An object of an embodiment of the present invention is to provide an image segmentation method, apparatus, device, and storage medium, so that not only color information but also spatial information of an image are considered in image segmentation.
In order to solve the above technical problems, an embodiment of the present invention provides an image segmentation method, including the following steps: setting parameters of image segmentation, wherein the parameters comprise a clustering number, an iteration termination threshold, a fuzzy index, an initial membership matrix and an initial clustering center; calculating local similarity factors and space coordination factors according to the space information of the image and the parameters; performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter; and after the iteration is terminated, image segmentation is carried out.
The embodiment of the invention also provides an image segmentation device, which comprises: the iteration module is used for setting parameters of image segmentation, wherein the parameters comprise a cluster number, an iteration termination threshold, a fuzzy index, an initial membership matrix and an initial cluster center; calculating local similarity factors and space coordination factors according to the space information of the image and the parameters; performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter; and the segmentation module is used for carrying out image segmentation after the iteration module terminates the iteration.
The embodiment of the invention also provides electronic equipment, which comprises:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the image segmentation method described above.
Embodiments of the present invention also provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements the image segmentation method described above.
Compared with the prior art, when the image is segmented, the method and the device have the advantages that the parameters of iterative clustering are properly set when the image is segmented, so that iteration is quicker, the local similarity factor and the spatial coordination factor of the image are obtained according to the spatial information of the image and the preset parameters, the spatial information of the image is converted into numerical values, the spatial information of the image is visually represented, the pixel points in the image are subjected to iterative clustering according to the obtained local similarity factor, spatial coordination factor and parameters, the local similarity factor and the spatial coordination factor reflecting the spatial information are introduced in the iterative clustering process of the pixel points in the image, and after the iterative clustering is ended, the image is segmented according to the iterative clustering result. The spatial information of the image is considered in the process of obtaining the iterative clustering result, so that the spatial information of the image is also considered in the image segmentation based on the iterative clustering result, and the problem that only the color information of the image is considered in the existing local image segmentation technology is solved.
In addition, the calculating the local similarity factor and the spatial coordination factor according to the spatial information of the image and the parameter includes: performing Census transformation to obtain CENTRIST spatial features F= { F 1,f2,…,fn } of the image, wherein n is the number of pixel points contained in the image; by the formula: Acquiring the local similarity factor, wherein N i represents an image block taking a pixel i as a center, the clustering number is C, M k = {1,2, …, C } \ { k }, the pixel point set of the image is { x 1,x2,…,xn }, and the clustering center is V= { V 1,v2,…,vC }; by the formula: acquiring the space coordination factor, wherein N is the number of pixels of the image block taking the pixel i as the center, N is the number of pixels contained in the image, N i represents the image block taking the pixel i as the center, the clustering number is C, M k = {1,2, …, C } \ { k }, and the membership degree matrix U = { mu ik |i=1, 2, …, N; k=1, 2, …, C }, Mu ik is the membership of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image. The spatial information of the image is converted into a numerical value, so that the spatial information of the image is intuitively represented.
In addition, the performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter includes: acquiring an objective function according to the local similarity factor, the spatial coordination factor and the parameter; and updating the membership matrix and the clustering center according to the local similarity factor, the spatial coordination factor and the parameter. And continuously iterating to obtain more accurate clustering results.
In addition, the obtaining the objective function according to the local similarity factor, the spatial coordination factor and the parameter includes: taking the local similarity factor as a weight, and adopting the formula: Obtaining an objective function, wherein N is the number of pixels contained in the image, the set of pixels of the image is { x 1,x2,…,xn }, the clustering center V= { V 1,v2,…,vC},ωi is the local similarity factor of the ith pixel,/> Is a spatial coordination factor, membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C }/>Mu ik is the membership of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image. In the process of obtaining the clustering result by the image, the spatial information of the image is considered, so that the sensitivity to noise is reduced, and the clustering effect is improved.
In addition, after the iterative calculation according to the local similarity factor, the spatial coordination factor and the parameter, the method includes: judgingSize relationship with ε; if less than ε, the iteration is terminated. And if the local similarity factor is not smaller than epsilon, returning to the step, and carrying out iterative computation according to the local similarity factor and the spatial coordination factor. The accuracy of the clustering result obtained by iteration meets the requirement, and the calculation consumption is small.
In addition, after the iteration is terminated, image segmentation is performed, including: by the formula: and determining the category to which each pixel belongs, and performing image segmentation according to the category to which each pixel belongs.
Drawings
One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which the figures of the drawings are not to be taken in a limiting sense, unless otherwise indicated.
Fig. 1 is a flowchart of an image segmentation method according to a first embodiment of the present invention;
FIG. 2 is a flowchart of step 102 in the image segmentation method provided by the first embodiment of the present invention shown in FIG. 1;
FIG. 3 is a flowchart of step 104 in the image segmentation method provided by the first embodiment of the present invention shown in FIG. 1;
Fig. 4 is a flowchart of an image segmentation method provided by a second embodiment of the present invention;
FIG. 5 is a flowchart of step 402 in the image segmentation method provided by the second embodiment of the present invention shown in FIG. 4;
Fig. 6 is a flowchart of an image segmentation method provided by a third embodiment of the present invention;
Fig. 7 is a schematic structural view of an image segmentation system according to a fourth embodiment of the present invention;
Fig. 8 is a schematic structural view of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings. However, those of ordinary skill in the art will understand that in various embodiments of the present application, numerous technical details have been set forth in order to provide a better understanding of the present application. The claimed application may be practiced without these specific details and with various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not be construed as limiting the specific implementation of the present application, and the embodiments can be mutually combined and referred to without contradiction.
A first embodiment of the present invention relates to an image segmentation method. The specific flow is shown in figure 1.
And step 101, setting parameters of image segmentation, wherein the parameters comprise a cluster number, an iteration termination threshold value, a fuzzy index m, an initial membership matrix and an initial cluster center.
The symbols of the parameters are as follows: cluster number C, iteration termination threshold epsilon, ambiguity index m, initial membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C } and the initial cluster center v= { V 1,v2,…,vC },Mu ik is the membership of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image. Unless otherwise indicated, the numerical designations of occurrences in the following calculations are the same as those described herein.
Step 102, calculating local similarity factors and space coordination factors according to the space information of the image and the parameters of image segmentation.
And step 103, performing iterative computation according to the local similarity factor, the spatial coordination factor and the image segmentation parameters.
And 104, after the iteration is terminated, image segmentation is performed.
Specifically, as shown in fig. 2, step 102 may include:
step 201, performing Census transformation to obtain CENTRIST spatial features f= { F 1,f2,…,fn } of the image, where n is the number of pixels included in the image.
Step 202, by the formula: obtaining a local similarity factor, wherein N i represents an image block taking a pixel i as a center, M k = {1,2, …, C } \ { k }, a pixel point set of the image is { x 1,x2,…,xn }, a cluster number C, a cluster center V= { V 1,v2,…,vC }, and/or > V k is a clustering prototype.
Step 203, by the formula: And acquiring a space coordination factor, wherein N is the number of pixels of the image block taking the pixel point i as the center, N is the number of pixels contained in the image, N i represents the image block taking the pixel i as the center, and M k = {1,2, …, C } \ { k }.
Specifically, as shown in fig. 3, step 104 may include:
Step 301, by the formula: the class to which each pixel belongs is determined.
In step 302, image segmentation is performed according to the category to which each pixel belongs.
Compared with the prior art, when the image is segmented, the method and the device have the advantages that the parameters of iterative clustering are properly set when the image is segmented, so that iteration is quicker, the local similarity factor and the spatial coordination factor of the image are obtained according to the spatial information of the image, the spatial information of the image is converted into numerical values, the spatial information of the image is visually represented, the iterative clustering is carried out on the pixel points in the image according to the local similarity factor and the spatial coordination factor of the image, the local similarity factor and the spatial coordination factor reflecting the spatial information are introduced in the iterative clustering process of the pixel points in the image, and after the iterative clustering is ended, the image segmentation is carried out according to the iterative clustering result. The spatial information of the image is considered in the process of obtaining the iterative clustering result, so that the spatial information of the image is also considered in the image segmentation based on the iterative clustering result, and the problem that only the color information of the image is considered in the existing local image segmentation technology is solved.
A second embodiment of the present invention relates to an image segmentation method. The second embodiment is substantially the same as the first embodiment, with the main difference that, as shown in fig. 4, step 103 includes:
step 401, obtaining an objective function according to the local similarity factor, the spatial coordination factor and the image segmentation parameters;
And step 402, updating a membership matrix and a clustering center according to the local similarity factor, the spatial coordination factor and the parameters of image segmentation.
Specifically, as shown in fig. 5, step 402 may include:
step 501, by the formula: And obtaining a membership function value, wherein t is an iteration count value.
Step 502, by the formula: and normalizing the membership function value.
Step 503, by the formula: The cluster center is updated, where t+1 is the iteration count value.
Compared with the prior art, the embodiment of the invention has the advantages that on the basis of realizing the beneficial effects brought by the first embodiment, particularly, the update iteration is carried out on the clustering center and the membership matrix, and the fuzzy clustering is effectively carried out on the pixel points.
A third embodiment of the present invention relates to an image segmentation method. The third embodiment is substantially the same as the first embodiment, and is mainly different in that it is necessary to determine whether the iteration is terminated, as shown in fig. 6, and further includes:
Step 601, judging If smaller than epsilon, go to step 104, otherwise return to step 103.
Compared with the prior art, the method and the device have the advantages that on the basis of the beneficial effects brought by the first embodiment, the condition judgment is carried out on the iterative process, so that the accuracy of the clustering result obtained by iteration meets the requirement, and the calculation consumption is small.
The above steps of the methods are divided, for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they include the same logic relationship, and they are all within the protection scope of this patent; it is within the scope of this patent to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.
A fourth embodiment of the present invention relates to an image segmentation system, as shown in fig. 7, including:
the iteration module 701 is configured to set a cluster number C of image segmentation, an iteration termination threshold epsilon, a fuzzy index m, and an initialized membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C } and cluster center v= { V 1,v2,…,vC }, where, Mu ik is the membership degree of the ith sample in the kth class, v k is a clustering prototype, n is the number of pixels contained in the image, a local similarity factor and a spatial coordination factor are calculated according to the spatial information of the image, iterative calculation is carried out according to the local similarity factor and the spatial coordination factor, and whether iteration is ended is judged;
The segmentation module 702 is configured to determine, after the iteration module terminates the iteration, a class to which each pixel belongs according to a maximum membership rule, and perform image segmentation.
It is to be noted that this embodiment is a system example corresponding to the first embodiment, and can be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, a detailed description is omitted here. Accordingly, the related art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module in this embodiment is a logic module, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, units that are not so close to solving the technical problem presented by the present invention are not introduced in the present embodiment, but this does not indicate that other units are not present in the present embodiment.
A fifth embodiment of the invention relates to an electronic device, as shown in fig. 8, comprising at least one processor 801; and
A memory 802 communicatively coupled to the at least one processor 801; wherein,
The memory 802 stores instructions executable by the at least one processor 801, so that the at least one processor 801 can execute the video color ring playing methods according to the first to third embodiments of the present invention.
Where the memory and the processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting the various circuits of the one or more processors and the memory together. The bus may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or may be a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over the wireless medium via the antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory may be used to store data used by the processor in performing operations.
A sixth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program implements the above-described method embodiments when executed by a processor.
That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the invention and that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (4)
1. An image segmentation method, comprising:
Setting parameters of image segmentation, wherein the parameters comprise a clustering number, an iteration termination threshold, a fuzzy index, an initial membership matrix and an initial clustering center;
Calculating local similarity factors and space coordination factors according to the space information of the image and the parameters;
performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter;
After the iteration is terminated, image segmentation is carried out;
Wherein the calculating the local similarity factor and the spatial coordination factor according to the spatial information of the image and the parameter comprises:
Performing Census transformation to obtain CENTRIST spatial features F= { F 1,f2,…,fn } of the image, wherein n is the number of pixel points contained in the image;
By the formula: Acquiring the local similarity factor, wherein N i represents an image block taking a pixel i as a center, the clustering number is C, M k = {1,2, …, C } \ { k }, the pixel point set of the image is { x 1,x2,…,xn }, and the clustering center is V= { V 1,v2,…,vC };
By the formula: Acquiring the space coordination factor, wherein N is the number of pixels of the image block taking the pixel i as the center, N is the number of pixels contained in the image, N i represents the image block taking the pixel i as the center, the cluster number C, M k = {1,2, …, C } \ { k }, and the membership matrix U = { mu ik |i=1, 2, …, N; k=1, 2, …, C }/> Mu ik is the membership degree of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image;
the performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter includes:
Acquiring an objective function according to the local similarity factor, the spatial coordination factor and the parameter;
updating the membership matrix and the clustering center according to the local similarity factor, the spatial coordination factor and the parameter;
the obtaining the objective function according to the local similarity factor, the spatial coordination factor and the parameter comprises:
taking the local similarity factor as a weight, and adopting the formula: obtaining an objective function, wherein N is the number of pixels contained in the image, the set of pixels in the image is { x 1,x2,…,xn }, the cluster center v= { V 1,v2,…,vC},ωi is the local similarity factor of the ith pixel,/> Is the spatial coordination factor, membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C }/>Mu ik is the membership degree of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image;
The updating the membership matrix and the clustering center according to the local similarity factor, the spatial coordination factor and the parameter comprises the following steps:
By the formula: obtaining membership function values, wherein t is an iteration count value, and m is the fuzzy index,/> The spatial coordination factor is { x 1,x2,…,xn } and the set of pixel points of the image is { x 1,x2,…,xn }, and the clustering center V= { V 1,v2,…,vC };
By the formula: normalizing the membership function value;
By the formula: updating the cluster center, wherein t+1 is an iteration count value;
After the iterative computation according to the local similarity factor, the spatial coordination factor and the parameter, the method comprises the following steps:
Judging Size relationship with ε, where/>And/>Respectively updating the clustering centers before and after updating, wherein epsilon is the iteration termination threshold;
if less than epsilon, terminating the iteration;
If not less than epsilon, returning to the step of carrying out iterative computation according to the local similarity factor and the space coordination factor;
after the iteration is terminated, image segmentation is carried out, and the method comprises the following steps:
By the formula: determining the category to which each pixel belongs, wherein the membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C }/> Mu ik is the membership degree of the ith sample in the kth class, v k is a clustering prototype, n is the number of pixels contained in the image, and C is the clustering number;
and carrying out image segmentation according to the category to which each pixel belongs.
2. An image segmentation system, comprising:
The iteration module is used for setting parameters of image segmentation, wherein the parameters comprise a cluster number, an iteration termination threshold, a fuzzy index, an initial membership matrix and an initial cluster center; calculating local similarity factors and space coordination factors according to the space information of the image and the parameters; performing iterative computation according to the local similarity factor, the spatial coordination factor and the parameter;
The segmentation module is used for carrying out image segmentation after the iteration module terminates the iteration;
Wherein the iteration module is further configured to:
Performing Census transformation to obtain CENTRIST spatial features F= { F 1,f2,…,fn } of the image, wherein n is the number of pixel points contained in the image; by the formula: Acquiring the local similarity factor, wherein N i represents an image block taking a pixel i as a center, the clustering number is C, M k = {1,2, …, C } \ { k }, the pixel point set of the image is { x 1,x2,…,xn }, and the clustering center is V= { V 1,v2,…,vC }; by the formula: /(I) Acquiring the space coordination factor, wherein N is the number of pixels of the image block taking the pixel i as the center, N is the number of pixels contained in the image, N i represents the image block taking the pixel i as the center, the cluster number C, M k = {1,2, …, C } \ { k }, and the membership matrix U = { mu ik |i=1, 2, …, N; k=1, 2, …, C }/>Mu ik is the membership degree of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image;
Acquiring an objective function according to the local similarity factor, the spatial coordination factor and the parameter; updating the membership matrix and the clustering center according to the local similarity factor, the spatial coordination factor and the parameter; taking the local similarity factor as a weight, and adopting the formula: obtaining an objective function, wherein N is the number of pixels contained in the image, the set of pixels in the image is { x 1,x2,…,xn }, the cluster center v= { V 1,v2,…,vC},ωi is the local similarity factor of the ith pixel,/> Is the spatial coordination factor, membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C }/>Mu ik is the membership degree of the ith sample in the kth class, v k is the clustering prototype, and n is the number of pixels contained in the image; by the formula: /(I)Obtaining membership function values, wherein t is an iteration count value, and m is the fuzzy index,/>The spatial coordination factor is { x 1,x2,…,xn } and the set of pixel points of the image is { x 1,x2,…,xn }, and the clustering center V= { V 1,v2,…,vC }; by the formula: /(I)Normalizing the membership function value; by the formula: /(I)Updating the cluster center, wherein t+1 is an iteration count value;
Judging Size relationship with ε, where/>And/>Respectively updating the clustering centers before and after updating, wherein epsilon is the iteration termination threshold; if less than epsilon, terminating the iteration; if not less than epsilon, returning to the step of carrying out iterative computation according to the local similarity factor and the space coordination factor;
the segmentation module is further configured to calculate the segmentation result by: determining the category to which each pixel belongs, wherein the membership matrix u= { μ ik |i=1, 2, …, n; k=1, 2, …, C }/> Mu ik is the membership degree of the ith sample in the kth class, v k is a clustering prototype, n is the number of pixels contained in the image, and C is the clustering number; and carrying out image segmentation according to the category to which each pixel belongs.
3. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the image segmentation method of claim 1.
4. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the image segmentation method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010866043.3A CN112017194B (en) | 2020-08-25 | 2020-08-25 | Image segmentation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010866043.3A CN112017194B (en) | 2020-08-25 | 2020-08-25 | Image segmentation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112017194A CN112017194A (en) | 2020-12-01 |
| CN112017194B true CN112017194B (en) | 2024-05-10 |
Family
ID=73502198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010866043.3A Active CN112017194B (en) | 2020-08-25 | 2020-08-25 | Image segmentation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112017194B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741279A (en) * | 2016-01-27 | 2016-07-06 | 西安电子科技大学 | Rough set based image segmentation method for quickly inhibiting fuzzy clustering |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012096882A1 (en) * | 2011-01-11 | 2012-07-19 | Rutgers, The State University Of New Jersey | Method and apparatus for segmentation and registration of longitudinal images |
| US9401026B2 (en) * | 2014-03-12 | 2016-07-26 | Nokia Technologies Oy | Method and apparatus for image segmentation algorithm |
-
2020
- 2020-08-25 CN CN202010866043.3A patent/CN112017194B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741279A (en) * | 2016-01-27 | 2016-07-06 | 西安电子科技大学 | Rough set based image segmentation method for quickly inhibiting fuzzy clustering |
Non-Patent Citations (1)
| Title |
|---|
| 基于组合隶属度的快速模糊聚类算法;加小红;雷涛;伍忠东;张永芳;;兰州交通大学学报(01);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112017194A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280477B (en) | Method and apparatus for clustering images | |
| CN111079780B (en) | Training method for space diagram convolution network, electronic equipment and storage medium | |
| CN111028246A (en) | Medical image segmentation method and device, storage medium and electronic equipment | |
| Cong et al. | Image segmentation algorithm based on superpixel clustering | |
| CN111191786A (en) | Transfer learning algorithm based on active learning | |
| CN114969417B (en) | Image reordering method, related device and computer readable storage medium | |
| CN110276801B (en) | Object positioning method and device and storage medium | |
| CN113065593A (en) | Model training method and device, computer equipment and storage medium | |
| CN112949519B (en) | Target detection method, device, equipment and storage medium | |
| CN113469091B (en) | Face recognition method, training method, electronic device and storage medium | |
| CN112017194B (en) | Image segmentation method, device, equipment and storage medium | |
| CN112906517B (en) | Self-supervision power law distribution crowd counting method and device and electronic equipment | |
| CN110569915A (en) | automobile data clustering method and system based on intuitive fuzzy C-means | |
| US11388223B2 (en) | Management device, management method, and management program | |
| CN113642710A (en) | Network model quantification method, device, equipment and storage medium | |
| CN113822144A (en) | Target detection method and device, computer equipment and storage medium | |
| CN115795355B (en) | Classification model training method, device and equipment | |
| CN116128798B (en) | Finish forging method for bell-shaped shell forging face teeth | |
| CN114612757B (en) | Multi-source navigation image fusion method and system based on deep learning | |
| CN112926646B (en) | Data batch normalization method, computing device, and computer-readable storage medium | |
| CN115631370A (en) | Identification method and device of MRI (magnetic resonance imaging) sequence category based on convolutional neural network | |
| CN115620082A (en) | Model training method, head posture estimation method, electronic device, and storage medium | |
| CN112613415A (en) | Face nose type recognition method and device, electronic equipment and medium | |
| CN112950652A (en) | Robot and hand image segmentation method and device thereof | |
| CN112766380B (en) | Image classification method and system based on feature gain matrix incremental learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |