CN110223249B - Fuzzy clustering-based soil pore three-dimensional segmentation method and system - Google Patents
Fuzzy clustering-based soil pore three-dimensional segmentation method and system Download PDFInfo
- Publication number
- CN110223249B CN110223249B CN201910470245.3A CN201910470245A CN110223249B CN 110223249 B CN110223249 B CN 110223249B CN 201910470245 A CN201910470245 A CN 201910470245A CN 110223249 B CN110223249 B CN 110223249B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- voxel
- fuzzy clustering
- soil
- dimensional image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002689 soil Substances 0.000 title claims abstract description 69
- 239000011148 porous material Substances 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000011218 segmentation Effects 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 2
- 239000004576 sand Substances 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011800 void material Substances 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a soil pore three-dimensional segmentation method and a system based on fuzzy clustering, wherein the method comprises the following steps: reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, and initializing a voxel matrix of the three-dimensional image by extracting a gray value of a voxel in the three-dimensional image; preprocessing the three-dimensional neighborhood information of the voxels, and automatically selecting the influence factors of the neighboring voxels based on the central voxel based on the three-dimensional neighborhood information; and constructing an objective function according to the three-dimensional neighborhood information and the influence factors, carrying out fuzzy clustering on the three-dimensional image based on the objective function, and obtaining a pore structure identification result after defuzzification processing. According to the soil pore three-dimensional segmentation method and system based on fuzzy clustering provided by the embodiment of the invention, the target function is constructed according to the three-dimensional neighborhood information and the influence factors to carry out fuzzy clustering and defuzzification, so that the universality is provided for the soil CT image, the problems of lack of space information and insufficient accuracy in two-dimensional image identification are solved, and the execution efficiency of soil pore identification is ensured.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a soil pore three-dimensional segmentation method and system based on fuzzy clustering.
Background
At present, soil pore identification based on soil CT images mostly adopts an FCM algorithm or an improved algorithm FCM _ S thereof to identify soil pores based on two-dimensional images or three-dimensional images.
When the identification is carried out based on the two-dimensional image, the two-dimensional image does not contain space information and is not added with three-dimensional neighborhood information for identification, the connectivity of a three-dimensional structure is lost, and the identification result based on the two-dimensional image cannot accurately describe the characteristics of the pore boundary of the complex soil, so that the identification is inaccurate.
When the three-dimensional image is used for identification, the traditional FCM algorithm identifies the pore structure, and the execution efficiency is low due to a large amount of data sets and iteration times, so that the method is not suitable for large-batch soil CT images. The traditional FCM _ S algorithm adds three-dimensional neighborhood information into an objective function, so that a large amount of calculation is required in each iteration, and the efficiency of the algorithm is greatly reduced. In addition, in the existing three-dimensional image identification method, all voxel points participate in calculation, so that the calculation amount is huge, and the calculation efficiency is low.
Therefore, it is an urgent need to solve the problem of developing a soil pore identification method with high execution efficiency while ensuring the accuracy of pore identification.
Disclosure of Invention
In order to solve the problem in the existing soil gap identification, the embodiment of the invention provides a soil gap three-dimensional segmentation method and a soil gap three-dimensional segmentation system based on fuzzy clustering.
In a first aspect, an embodiment of the present invention provides a fuzzy clustering-based soil pore three-dimensional segmentation method, including: reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image, and initializing a voxel matrix of the three-dimensional image based on the gray value of the voxel; preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix, and automatically selecting an influence factor of a neighboring voxel based on a central voxel based on the preprocessed three-dimensional neighborhood information; constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and carrying out fuzzy clustering on the three-dimensional image based on the objective function; and performing defuzzification processing on the three-dimensional image subjected to the fuzzy clustering to obtain a deblurred pore structure identification result.
In a second aspect, an embodiment of the present invention provides a soil pore three-dimensional segmentation system based on fuzzy clustering, including: the initialization module is used for reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image and initializing the voxel matrix of the three-dimensional image based on the gray value of the voxel; the preprocessing and influence factor selecting module is used for preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix and automatically selecting the influence factor of the adjacent voxel based on the central voxel based on the preprocessed three-dimensional neighborhood information; the fuzzy clustering module is used for constructing a target function according to the three-dimensional neighborhood information and the influence factors and carrying out fuzzy clustering on the three-dimensional image based on the target function; and the identification module is used for performing defuzzification processing on the three-dimensional image after the fuzzy clustering to obtain a deblurred pore structure identification result.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
According to the soil pore three-dimensional segmentation method and system based on fuzzy clustering provided by the embodiment of the invention, the voxel matrix is initialized through the gray value based on the three-dimensional image, the influence factor is automatically selected according to the three-dimensional neighborhood information, the target function is constructed according to the three-dimensional neighborhood information and the influence factor to carry out fuzzy clustering and defuzzification processing, the universality is provided for the soil CT image, the problems of missing space information and insufficient accuracy based on two-dimensional image identification are solved, and the execution efficiency of soil pore identification is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a soil pore three-dimensional segmentation method based on fuzzy clustering according to an embodiment of the present invention;
FIG. 2 is a schematic view of a processing effect in a fuzzy clustering-based soil pore three-dimensional segmentation method provided by an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a soil pore three-dimensional segmentation system based on fuzzy clustering according to an embodiment of the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flow chart of a soil pore three-dimensional segmentation method based on fuzzy clustering according to an embodiment of the present invention. As shown in fig. 1, the method includes:
soil porosity refers to the pores between and within the soil particles or aggregates. The pore structure includes the geometric forms of the number, the size and the like of pores. The CT scanning technique, i.e. computerized tomography, uses precisely collimated X-ray beam, gamma ray, ultrasonic wave, etc. and a detector with high sensitivity to scan the cross section of some part of the scanned object one by one, and features fast scanning time and clear image. The CT scanning technique is an effective means for pore quantification research, and before step 101, a two-dimensional soil CT image can be obtained by using the CT scanning technique. And then synthesizing the two-dimensional soil CT image into a three-dimensional image.
After the three-dimensional image is obtained, the gray values of all voxels in the three-dimensional image are extracted, and a voxel matrix of the three-dimensional image is initialized based on the gray values of the voxels.
The voxel matrix may be represented as:
wherein grey represents the voxel matrix, xr、xsAnd xtRepresenting a one-dimensional matrix on the r, s and t axes, respectively.
as can be seen from the object function of FCM, when performing image segmentation, the conventional FCM algorithm only uses the color information between voxels, i.e. the gray value, and does not use other information such as the spatial context, which may result in that the algorithm does not work well for image segmentation with strong noise. Therefore, when determining the class to which a certain voxel belongs, the influence of the voxels in the three-dimensional neighborhood of the voxel should be considered. In the traditional method, after the three-dimensional neighborhood information is added into the objective function, a large amount of calculation is needed in each iteration, so that the efficiency of the algorithm is greatly reduced, the three-dimensional neighborhood information of the voxel can be preprocessed, the same processing operation of each iteration is completed in advance, the preprocessed three-dimensional neighborhood information can be directly used in each iteration process, and the efficiency of the algorithm is improved.
The preprocessing may include a filtering process for removing image noise.
And after the preprocessed three-dimensional neighborhood information is obtained, automatically selecting an influence factor of a neighboring voxel based on a central voxel based on the three-dimensional neighborhood information.
103, constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and carrying out fuzzy clustering on the three-dimensional image based on the objective function;
in addition, after the three-dimensional neighborhood information is added in the traditional method, all voxels participate in calculation, so that the algorithm efficiency is low. Aiming at the problem, after the preprocessed three-dimensional neighborhood information is obtained, the embodiment of the invention automatically selects the influence factor of the adjacent voxel based on the central voxel based on the three-dimensional neighborhood information. Influence factors are automatically selected according to the neighborhood information, and the influence of the neighborhood information on the central voxel can be accurately calculated; and constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and ensuring the obvious improvement of algorithm efficiency on the basis of high identification precision. And carrying out fuzzy clustering on the three-dimensional image according to the target function to obtain a fuzzy clustering result. The fuzzy clustering result comprises a result of classifying the voxels according to the gray values of the voxels.
104, performing defuzzification processing on the three-dimensional image subjected to fuzzy clustering to obtain a deblurred pore structure identification result;
in order to obtain an accurate pore structure identification result, performing defuzzification processing on the three-dimensional image after fuzzy clustering, wherein the defuzzification processing comprises binarization processing, so as to obtain a pore structure identification result after defuzzification.
According to the embodiment of the invention, the voxel matrix is initialized based on the gray value of the three-dimensional image, the influence factor is automatically selected according to the three-dimensional neighborhood information, the objective function is constructed according to the three-dimensional neighborhood information and the influence factor to carry out fuzzy clustering and defuzzification processing, the universality is provided for the soil CT image, the problems of missing space information and insufficient accuracy based on two-dimensional image identification are solved, and the execution efficiency of soil pore identification is ensured.
Further, based on the above embodiment, the influence factors include a first influence factor and a second influence factor; for a target voxel, the first impact factor is represented as:
wherein α represents the first influence factor, P0 represents the gray-scale value of the target voxel, and P1, P2 … …, P6 represent the gray-scale values of voxels in 6 neighborhoods of the target voxel, right, left, front and back, and right, respectively;
the second impact factor is expressed as:
wherein β represents the second influence factor, and Q1 and Q2 … … Q20 represent the gray-scale values of the voxels in the three-dimensional 26 neighborhood of the target voxel, except for 6 neighborhoods immediately above, below, left, right, front and back thereof, respectively.
The three-dimensional 26 neighborhood is an adjacent region of three-dimensional space around the target voxel. The distances of 26 neighborhood voxels of a certain voxel relative to the voxel are different, and the corresponding influences on the voxel are different, so that the influence of neighborhood information on a central voxel can be calculated more accurately.
On the basis of the above embodiment, the embodiment of the present invention selects the first influence factor and the second influence factor, so that the influence of the neighborhood information on the central voxel can be more accurately calculated, and the identification accuracy and efficiency are further improved. Further, based on the above embodiment, the objective function is expressed as:
wherein J is an objective function, viRepresenting the ith clustering center, | | · | | is a vector of Euclidean distance, m is a constant for controlling ambiguity, c is the clustering number, i represents the ith clustering, R, S and T respectively represent the coordinates of the current R axis, S axis and T axis, R, S and T respectively represent the voxel number of three directions of the three-dimensional matrix, and x is the volume of the three-dimensional matrixr,s,tRepresenting the gray scale of a voxel with coordinates (r, s, t),
expressing the gray level median of the neighborhood of the voxel with the coordinate of (r, s, t), wherein alpha and beta respectively express a first influence factor and a second influence factor of the neighboring voxel based on the center point voxel; u. ofikRepresenting degree of membership, x, of the kth voxel to the ith cluster centerkRepresenting neighborhood information, NjA neighborhood set representing a kth voxel;
wherein:
wherein i represents the ith cluster, j represents the jth cluster, viDenotes the ith cluster center, vjRepresenting the jth cluster center;
cluster center viExpressed as:
wherein n represents viNumber of data points of a cluster, x, being the center of the clusterkThe information of the neighborhood is represented by a number of pixels,
representing the median of the neighborhood information.
On the basis of the above embodiment, the embodiment of the present invention provides a specific method for constructing an objective function according to three-dimensional neighborhood information and the first and second influence factors, and improves the practicability.
Further, based on the above embodiment, the performing fuzzy clustering on the three-dimensional image specifically includes: and classifying the voxels in the three-dimensional image according to preset color types, wherein the color types comprise four types of white-like, light gray, dark gray and black.
And carrying out fuzzy clustering on the three-dimensional image by utilizing the objective function according to the common color types in the soil, wherein the fuzzy clustering is used for classifying voxels in the three-dimensional image. Specifically, the voxels in the three-dimensional image are classified according to a preset gray value of a color type and a gray value of the voxel, and the voxels are corresponding to different color types, wherein the color types include four types of white-like, light gray, dark gray and black.
The fuzzy clustering problem solving range is wide, the problem can be converted into an optimization problem to be solved by means of a nonlinear programming theory of classical mathematics, and a computer is easy to realize.
On the basis of the embodiment, the embodiment of the invention is favorable for rapidly acquiring the pore structure identification result by classifying the voxels in the three-dimensional image according to the preset color type.
Further, based on the above embodiment, the deblurring processing is performed on the fuzzy clustering result to obtain a deblurred pore structure identification result, and the method specifically includes:
performing binarization processing on the three-dimensional image after fuzzy clustering according to a preset pore structure identification criterion so as to obtain a deblurred pore structure identification result;
the pore structure recognition criterion is expressed as:
wherein η represents the pore structure identification criterion, c is the number of clusters, g is a variable, and g ═ c-2, η is a decimal between 0 and 1;
the formula for performing binarization processing is as follows:
wherein G represents the gray value of each voxel in the three-dimensional image after fuzzy clustering, and f (x)r,s,t) Indicating the result of the binarization process.
After the voxels are classified, the purpose of the defuzzification process is to extract the pore structure in the three-dimensional image. The soil CT image is mainly classified into four types of white, light gray, dark gray and black, and the voxels of the pore structure are darker than other parts, so that the voxels of the type with the smallest gray value can be extracted as the pore structure identification result, and the soil CT image pore identification is completed.
The class of voxels in which the gray value is the smallest may be defined by the pore structure recognition criterion. Therefore, the void voxels and the non-void voxels can be divided by the above void structure identification criterion and the binarization processing formula, thereby realizing the soil void identification.
Fig. 2 is a schematic view of a processing effect in the soil pore three-dimensional segmentation method based on fuzzy clustering provided by the embodiment of the invention. Fig. 2(a) shows an original soil image, fig. 2(b) shows a soil image after the blurring process, and fig. 2(c) shows a soil image after the binarization process.
Fig. 3 is a schematic structural diagram of a soil pore three-dimensional segmentation system based on fuzzy clustering according to an embodiment of the present invention. As shown in fig. 3, the system includes an initialization module 10, a preprocessing and impact factor selection module 20, a fuzzy clustering module 30 and an identification module, wherein:
the initialization module 10 is configured to read a set of two-dimensional soil CT images and synthesize the two-dimensional soil CT images into a three-dimensional image, extract a gray value of a voxel in the three-dimensional image, and initialize a voxel matrix of the three-dimensional image based on the gray value of the voxel; the preprocessing and influence factor selecting module 20 is configured to preprocess the three-dimensional neighborhood information of the voxel according to the voxel matrix, and automatically select an influence factor of a neighboring voxel based on a central voxel based on the preprocessed three-dimensional neighborhood information; the fuzzy clustering module 30 is configured to construct an objective function according to the three-dimensional neighborhood information and the influence factor, and perform fuzzy clustering on the three-dimensional image based on the objective function; the identification module 40 is configured to perform defuzzification processing on the three-dimensional image after the fuzzy clustering, so as to obtain a deblurred pore structure identification result.
According to the embodiment of the invention, the voxel matrix is initialized based on the gray value of the three-dimensional image, the influence factor is automatically selected according to the three-dimensional neighborhood information, the objective function is constructed according to the three-dimensional neighborhood information and the influence factor to carry out fuzzy clustering and defuzzification processing, the universality is provided for the soil CT image, the problems of missing space information and insufficient accuracy based on two-dimensional image identification are solved, and the execution efficiency of soil pore identification is ensured.
The system provided by the embodiment of the invention is used for the method, and specific functions can refer to the method flow, which is not described herein again.
Fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, the electronic device may include: a processor (processor)810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call logic instructions in the memory 830 to perform the following method: reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image, and initializing a voxel matrix of the three-dimensional image based on the gray value of the voxel; preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix, and automatically selecting an influence factor of a neighboring voxel based on a central voxel based on the preprocessed three-dimensional neighborhood information; constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and carrying out fuzzy clustering on the three-dimensional image based on the objective function; and performing defuzzification processing on the three-dimensional image subjected to the fuzzy clustering to obtain a deblurred pore structure identification result.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image, and initializing a voxel matrix of the three-dimensional image based on the gray value of the voxel; preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix, and automatically selecting an influence factor of a neighboring voxel based on a central voxel based on the preprocessed three-dimensional neighborhood information; constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and carrying out fuzzy clustering on the three-dimensional image based on the objective function; and performing defuzzification processing on the three-dimensional image subjected to the fuzzy clustering to obtain a deblurred pore structure identification result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A soil pore three-dimensional segmentation method based on fuzzy clustering is characterized by comprising the following steps:
reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image, and initializing a voxel matrix of the three-dimensional image based on the gray value of the voxel;
preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix, and automatically selecting an influence factor of a neighboring voxel based on a central voxel based on the preprocessed three-dimensional neighborhood information;
constructing an objective function according to the three-dimensional neighborhood information and the influence factors, and carrying out fuzzy clustering on the three-dimensional image based on the objective function;
performing defuzzification processing on the three-dimensional image subjected to fuzzy clustering to obtain a deblurred pore structure identification result;
the influence factors include a first influence factor and a second influence factor; for a target voxel, the first impact factor is represented as:
wherein α represents the first influence factor, P0 represents the gray-scale value of the target voxel, and P1, P2 … …, P6 represent the gray-scale values of voxels in 6 neighborhoods of the target voxel, right, left, front and back, and right, respectively;
the second impact factor is expressed as:
wherein β represents the second influence factor, and Q1 and Q2 … … Q20 represent the gray-scale values of the voxels in the three-dimensional 26 neighborhood of the target voxel, except for 6 neighborhoods immediately above, below, left, right, front and back thereof, respectively.
2. The soil pore three-dimensional segmentation method based on fuzzy clustering according to claim 1, wherein the voxel matrix is represented as:
wherein grey represents the voxel matrix, xr、xsAnd xtRepresenting a one-dimensional matrix on the r, s and t axes, respectively.
3. The soil pore three-dimensional segmentation method based on fuzzy clustering as claimed in claim 1, wherein the preprocessing comprises filtering processing.
4. The fuzzy clustering-based soil pore three-dimensional segmentation method according to claim 1, wherein the objective function is expressed as:
wherein J is an objective function, viRepresenting the ith clustering center, | | · | | is a vector of Euclidean distance, m is a constant for controlling ambiguity, c is the clustering number, i represents the ith clustering, R, S and T respectively represent the coordinates of the current R axis, S axis and T axis, R, S and T respectively represent the voxel number of three directions of the three-dimensional matrix, and x is the volume of the three-dimensional matrixr,s,tRepresenting the gray scale of a voxel with coordinates (r, s, t),
expressing the gray level median of the neighborhood of the voxel with the coordinate of (r, s, t), wherein alpha and beta respectively express a first influence factor and a second influence factor of the neighboring voxel based on the center point voxel; u. ofikRepresenting degree of membership, x, of the kth voxel to the ith cluster centerkRepresenting neighborhood information, NkA neighborhood set representing a kth voxel;
wherein:
wherein i represents the ith cluster, j represents the jth cluster, viDenotes the ith cluster center, vjRepresenting the jth cluster center;
cluster center viExpressed as:
wherein n represents viNumber of data points of a cluster, x, being the center of the clusterkThe information of the neighborhood is represented by a number of pixels,
representing the median of the neighborhood information.
5. The soil pore three-dimensional segmentation method based on fuzzy clustering according to claim 1, wherein the fuzzy clustering of the three-dimensional image specifically comprises:
and classifying the voxels in the three-dimensional image according to preset color types, wherein the color types comprise four types of white-like, light gray, dark gray and black.
6. The soil pore three-dimensional segmentation method based on fuzzy clustering as claimed in claim 1, wherein the defuzzifying processing is performed on the fuzzy clustering result to obtain the deblurred pore structure identification result, specifically comprising:
performing binarization processing on the three-dimensional image after fuzzy clustering according to a preset pore structure identification criterion so as to obtain a deblurred pore structure identification result;
the pore structure recognition criterion is expressed as:
wherein η represents the pore structure identification criterion, c is the number of clusters, g is a variable, and g ═ c-2, η is a decimal between 0 and 1;
the formula for performing binarization processing is as follows:
wherein G represents the gray value of each voxel in the three-dimensional image after fuzzy clustering, and f (x)r,s,t) Indicating the result of the binarization process.
7. A soil pore three-dimensional segmentation system based on fuzzy clustering is characterized by comprising the following steps:
the initialization module is used for reading a group of two-dimensional soil CT images and synthesizing the two-dimensional soil CT images into a three-dimensional image, extracting the gray value of a voxel in the three-dimensional image and initializing the voxel matrix of the three-dimensional image based on the gray value of the voxel;
the preprocessing and influence factor selecting module is used for preprocessing the three-dimensional neighborhood information of the voxel according to the voxel matrix and automatically selecting the influence factor of the adjacent voxel based on the central voxel based on the preprocessed three-dimensional neighborhood information;
the fuzzy clustering module is used for constructing a target function according to the three-dimensional neighborhood information and the influence factors and carrying out fuzzy clustering on the three-dimensional image based on the target function;
the identification module is used for performing defuzzification processing on the three-dimensional image subjected to the fuzzy clustering to obtain a deblurred pore structure identification result;
the influence factors include a first influence factor and a second influence factor; for a target voxel, the first impact factor is represented as:
wherein α represents the first influence factor, P0 represents the gray-scale value of the target voxel, and P1, P2 … …, P6 represent the gray-scale values of voxels in 6 neighborhoods of the target voxel, right, left, front and back, and right, respectively;
the second impact factor is expressed as:
wherein β represents the second influence factor, and Q1 and Q2 … … Q20 represent the gray-scale values of the voxels in the three-dimensional 26 neighborhood of the target voxel, except for 6 neighborhoods immediately above, below, left, right, front and back thereof, respectively.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method for three-dimensional segmentation of soil pores based on fuzzy clustering according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for fuzzy clustering based three-dimensional segmentation of soil pores according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910470245.3A CN110223249B (en) | 2019-05-31 | 2019-05-31 | Fuzzy clustering-based soil pore three-dimensional segmentation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910470245.3A CN110223249B (en) | 2019-05-31 | 2019-05-31 | Fuzzy clustering-based soil pore three-dimensional segmentation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110223249A CN110223249A (en) | 2019-09-10 |
| CN110223249B true CN110223249B (en) | 2021-03-30 |
Family
ID=67819219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910470245.3A Active CN110223249B (en) | 2019-05-31 | 2019-05-31 | Fuzzy clustering-based soil pore three-dimensional segmentation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110223249B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064470A (en) * | 2018-08-28 | 2018-12-21 | 河南工业大学 | A kind of image partition method and device based on adaptive fuzzy clustering |
| CN109658378A (en) * | 2018-11-08 | 2019-04-19 | 北京林业大学 | Hole discrimination method and system based on soil CT image |
-
2019
- 2019-05-31 CN CN201910470245.3A patent/CN110223249B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064470A (en) * | 2018-08-28 | 2018-12-21 | 河南工业大学 | A kind of image partition method and device based on adaptive fuzzy clustering |
| CN109658378A (en) * | 2018-11-08 | 2019-04-19 | 北京林业大学 | Hole discrimination method and system based on soil CT image |
Non-Patent Citations (1)
| Title |
|---|
| 基于CT图像的土壤孔隙结构重构;赵玥等;《农业机械学报》;20181130;第49卷;第402-405页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110223249A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3449421B1 (en) | Classification and 3d modelling of 3d dento-maxillofacial structures using deep learning methods | |
| CN109685060B (en) | Image processing method and device | |
| US7512284B2 (en) | Volumetric image enhancement system and method | |
| Rahaman et al. | An efficient multilevel thresholding based satellite image segmentation approach using a new adaptive cuckoo search algorithm | |
| CN109712131B (en) | Method and device for quantifying lung nodule characteristics, electronic equipment and storage medium | |
| CN109658378B (en) | Pore identification method and system based on soil CT image | |
| CN110197206B (en) | Image processing method and device | |
| CN109685806B (en) | Image significance detection method and device | |
| CN105389821B (en) | It is a kind of that the medical image cutting method being combined is cut based on cloud model and figure | |
| CN113222964B (en) | Method and device for generating coronary artery central line extraction model | |
| CN109993753B (en) | Method and device for segmenting urban functional area in remote sensing image | |
| CN110956632A (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
| CN111951215A (en) | Image detection method and device and computer readable storage medium | |
| KR102473298B1 (en) | Method for obtaining 3D model data of multiple components of an object | |
| Yan et al. | Improved mask R-CNN for lung nodule segmentation | |
| He et al. | An automated three-dimensional detection and segmentation method for touching cells by integrating concave points clustering and random walker algorithm | |
| CN108986210B (en) | Method and device for reconstructing three-dimensional scene | |
| CN108597589B (en) | Model generation method, target detection method and medical imaging system | |
| Hosseini-Asl et al. | Lung segmentation based on nonnegative matrix factorization | |
| CN110223249B (en) | Fuzzy clustering-based soil pore three-dimensional segmentation method and system | |
| CN115439423B (en) | CT image-based identification method, device, equipment and storage medium | |
| JP6546385B2 (en) | IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND PROGRAM | |
| CN115393470A (en) | Cultural relic digital line graph drawing method, system and device | |
| Khudov et al. | The comparative assessment of the quality of cytological drugs image processing | |
| CN111784705A (en) | Method, device and equipment for delineating region of interest and storage medium |
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 |