CN107239783B - Coal rock identification method based on extended local binary pattern and regression analysis - Google Patents
Coal rock identification method based on extended local binary pattern and regression analysis Download PDFInfo
- Publication number
- CN107239783B CN107239783B CN201710440697.8A CN201710440697A CN107239783B CN 107239783 B CN107239783 B CN 107239783B CN 201710440697 A CN201710440697 A CN 201710440697A CN 107239783 B CN107239783 B CN 107239783B
- Authority
- CN
- China
- Prior art keywords
- matrix
- column
- descriptor based
- characteristic
- coal
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
Abstract
The invention discloses a coal rock identification method based on an extended local binary pattern and regression analysis. In a sample training stage, obtaining a plurality of coal sample sub-images and rock sample sub-images through a series of processing such as camera shooting, sub-image interception, graying and the like, extracting expansion local binary pattern feature vectors of each sub-image, carrying out regression analysis on the feature vectors and class labels thereof to obtain a feature optimal combination, and obtaining a training sample optimal feature vector based on the feature optimal combination; in the coal rock identification stage, an unknown class sample sub-image is obtained through a series of processing, an extended local binary pattern feature vector of the unknown class sample sub-image is extracted, and an unknown class sample preferred feature vector is obtained based on a feature preferred combination in the sample training stage. And judging the coal rock category to which the unknown class sample belongs by comparing the preferred characteristic vectors between the unknown class sample and the training sample. The method has obvious advantages in the aspects of flexibility, reliability, instantaneity and the like.
Description
Technical Field
The invention relates to a coal rock identification method based on an extended local binary pattern and regression analysis, and belongs to the technical field of image identification.
Background
Coal and rock identification means that coal and rock are automatically distinguished by various technical means. In the process of coal resource mining and transportation, a plurality of production links need to distinguish coal and rock, such as height adjustment of a roller of a coal mining machine, control of a fully mechanized top coal caving process, selection of gangue from raw coal of a coal preparation plant and the like. Since the 50 s of the 20 th century, a series of researches on coal rock identification methods in major coal-producing countries in the world such as south africa, australia, germany, the united states and china are carried out, and some representative research results such as a natural gamma ray detection method, a radar detection method, an infrared detection method, an active power detection method, a vibration signal detection method, a sound signal detection method and the like are generated successively. However, these methods all have the following common problems: (1) various sensors need to be installed and deployed on the existing equipment, and related devices are complex in structure and high in manufacturing cost; (2) mechanical equipment such as a coal mining machine, a heading machine and the like is complex in stress, severe in vibration and severe in abrasion in the coal production process, a sensor is relatively difficult to deploy, an electronic circuit of the sensor is easy to damage, and the reliability of the device is poor; (3) for different types of mechanical carrier equipment, great differences exist between the type selection of the sensor and the selection of the installation position, and personalized customization is needed, so that the universality is poor.
Through observation of blocky coal and rock samples, the coal and the rock have great differences in color, luster, texture and the like. When the coal and the rock are imaged by the existing digital camera, the visual information of the coal and the rock is necessarily hidden in the acquired digital image, so that the coal and the rock are distinguished by mining the visual information in the digital image of the coal and the rock. The existing coal and rock identification method based on image processing has a larger promotion space in the aspects of robustness, identification rate and the like.
Disclosure of Invention
In order to overcome the defects of the existing coal rock identification method, the invention provides the coal rock identification method based on the extended local binary pattern and the regression analysis, and the method has the advantages of strong real-time performance, high identification rate, good robustness and the like, and is beneficial to improving the production efficiency and the safety degree of the modern coal mine.
The coal rock identification method is realized by adopting the following technical scheme, comprises a sample training stage and a coal rock identification stage, and specifically comprises the following steps:
RS1, in a sample training stage, acquiring m coal sample images and m rock sample images, intercepting subgraphs without non-coal rock background and carrying out gray processing on the subgraphs, and respectively recording the processed coal sample subgraphs and rock sample subgraphs as c1,c2,…,cmAnd s1,s2,…,sm;
Rs2. set sampling radius r 2, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 3 × 31,c2,…,cmAnd s1,s2,…,smWith median filtering and with rotationRobust extended local binary pattern 3-dimensional joint histogram with invariant characteristics and uniform characteristics and formed by combining 3 descriptors, namely descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
RS3. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector α1,α2,…,αm∈R1×200And β1,β2,…,βm∈R1×200;
Rs4. set sampling radius r 4, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 5 × 51,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
RS5. respectivelyAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector η1,η2,…,ηm∈R1×200And mu1,μ2,…,μm∈R1×200;
Rs6. set sampling radius r 6, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrC is counted as 7 × 71,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
RS7. respectively handleAndtransforming into 1-dimensional histogram, and normalizing them to obtain characteristic row vector theta1,θ2,…,θm∈R1×200And
rs8. set sampling radius r 8, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 9 × 91,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
RS9. respectivelyAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector k1,κ2,…,κm∈R1×200And upsilon1,υ2,…,υm∈R1×200;
RS10. construction of c separately1,c2,…,cmAnd s1,s2,…,smOriginal feature column vector x1=[α1,η1,θ1,κ1]T,x2=[α2,η2,θ2,κ2]T,…,xm=[αm,ηm,θm,κm]T∈R800×1And ,…,wherein T is a transposition operation;
RS11. constructing an original characteristic matrix X ═ X of the coal petrography training sample1,x2,…,xm,xm+1,xm+2,…,x2m]T∈R2m ×800And its category label matrix Y ∈ R2m×2Wherein T is a transpose operation, the first m rows and 1 st columns of data padding of Y is 1, the first m rows and 2 nd columns of data padding of Y is 0, the last m rows and 1 st columns of data padding of Y is 0, and the last m rows and 2 nd columns of data padding of Y is 1;
RS12, setting a regularization parameter lambda, iteration times K and an optimal feature number d, and performing regression analysis on X and Y to obtain d column marks j about X and beneficial to distinguishing coal rocks1,j2,…,jdWherein j is not less than 11,j2,…,jd≤800;
RS13. sequentially extracting j' th of X1,j2,…,jdArranging the columns, and then forming a final characteristic matrix of the coal rock training sample according to the arrangement of the columnsWherein X (col. j)1),X(col·j2),…,X(col·jd) J' th of X respectively1,j2,…,jdColumns;
in the coal rock identification stage, acquiring an unknown class sample image, intercepting a sub-image without a non-coal rock background and carrying out gray processing on the sub-image, wherein the processed unknown class sub-image is marked as q;
RS15, setting the sampling radius r to be 2, the radial interval to be 2, the sampling neighborhood number p to be 8 and filtering the medianSliding window size omega of waver3 × 3, the robust extended local binary pattern 3-dimensional joint histogram H with the combination of 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial difference, which adopts median filtering and has rotation invariant characteristic and uniform characteristicq;
RS16. A. HqTransforming into 1-dimensional histogram, and normalizing to obtain characteristic row vectorq∈R1 ×200;
Rs17. set sampling radius r 4, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr5 × 5, the robust extended local binary pattern 3-dimensional joint histogram Z with the rotation invariant characteristic and the uniform characteristic and adopting the median filtering is combined by 3 descriptors of a descriptor based on the central point intensity, a descriptor based on the neighborhood point intensity and a descriptor based on the radial differenceq;
RS18. handle ZqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector rhoq∈R1 ×200;
Rs19. set sampling radius r 6, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr7 × 7, the robust extended local binary pattern 3-dimensional joint histogram F with the combination of 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial difference, which adopts median filtering and has rotation invariant characteristic and uniform characteristic, of statistics qq;
RS20. A. FqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector sigmaq∈R1 ×200;
Rs21. set sampling radius r 8, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr9 × 9, statistical q center-based with median filtering and with rotation invariant and uniform propertiesPoint intensity descriptor, neighborhood point intensity-based descriptor and radial difference-based descriptor, namely 3 descriptors are combined to form robust extended local binary pattern 3-dimensional joint histogram Tq;
RS22. separately treating TqTransformed into a 1-dimensional histogram, which is then normalized to obtain a feature row vector ξq∈R1×200;
RS23. construction of the raw feature row vector x of qq=[q,ρq,σq,ξq]∈R1×800;
RS24. successively extracting xqJ (d) of1,j2,…,jdElements, then arranging the final feature row vector constituting q in orderWherein xq(j1),xq(j2),…,xq(jd) Are respectively xqJ (d) of1,j2,…,jdAn element;
RS25. by calculatingDetermining the coal rock class of q, if satisfiedThen judging q as coal; otherwise, q is determined to be rock, where i isI is 1,2, …,2m, j isColumn symbol ofThe element numbers of (1), (2), (…), (d),of the elements located in row i and column j,is composed ofThe jth element of (1).
The regression analysis described in step RS12 includes the following steps:
RS1201. construct symbol matrix U ∈ R2m×2Then initializing m elements positioned in the first m rows and the 1 st column in the U by using 1, initializing m elements positioned in the first m rows and the 2 nd column in the U by using-1, initializing m elements positioned in the second m rows and the 1 st column in the U by using-1, and initializing m elements positioned in the second m rows and the 2 nd column in the U by using 1;
RS1202. construct data matrix X0∈R2m×800Then byColumn by column initialization X0Wherein τ is X0And X, τ ═ 1,2, …,800,is X0Column τ of, xτColumn τ of X, mean (X)τ) Is xτMean of all elements in;
RS1203. respectively constructing weight matrix Wold,Wnew∈R800×2And an offset vector bold,bnew∈R2×1;
RS1204, first pass Wold=(X0)T{[X0(X0)T+λI2m]-1Y initialization WoldThen through Wnew=WoldInitializing WnewWhere T and-1 are the transposition and inversion operations, respectively, I2mIs an identity matrix of 2m order;
RS1206. first passInitialization boldThen through bnew=boldInitialization bnewWherein L isb(col. j) is LbJ is LbThe list of (1), (2), (…), (2 m);
RS1207, respectively constructing data matrixes A, B, G ∈ R2m×2Then initializing them to a zero matrix;
RS1208. constructing data matrix X1∈R2m×801Then initialize X with X1First 800 columns of (A), X1All elements of column 801 are initialized to 1000, i.e., X1=[X,1000e2m]∈R2m×801Wherein e is2m∈R2m×1A column vector with all elements 1;
RS1209. defining iteration number k1And is initialized to 0;
rs1211, first updating B by B ═ U ═ a, and then replacing the negative element in B with 0, where ≥ is a Hadamard product operation of the matrix;
rs1212. update G by G ═ B) + Y, wherein ═ Hadamard product operation of the matrix;
RS1213. describe mathematics as
The optimization problem (W) is recorded as KeyProblem, and the solution W of the KeyProblem is obtained0∈R801×2Wherein | · | purple light2,1Is a matrix of2,1Norm in matrix Ψ ∈ Ru0×v0For the purpose of example only,i0 is a row indicator of Ψ, i0 ═ 1,2, …, u0, j0 is a column indicator of Ψ, j0 ═ 1,2, …, v0, Ψ (i0, j0) is an element in Ψ located in the j0 th column of the i0 th row, and u0 and v0 are the row number and column number of Ψ, respectively;
RS1214. with W0Update W on the first 800 rowsnew;
RS1215. through bnew=1000×[W0(row·801)]TUpdate bnewWhere T is a transposition operation, W0(row 801) is W0Line 801;
RS1216. iteration number k1Self-increment by 1;
RS1217. if satisfied at the same timeAnd k1<K, then use WnewUpdate W of the value ofoldBy bnewUpdate of value boldThen, step RS 1210-RS 1217 is performed, where | · | | | ceilingFAnd | · | non-conducting phosphor2The Frobenius norm of the matrix and the 2-norm of the vector are respectively; otherwise, executing step RS 1218;
RS1218. constructing a weight square matrix W2∈R800×2Then through W2=Wnew⊙WnewInitializing W2Wherein ⊙ is a Hadamard product operation of the matrix;
RS1219. construction of weight vectorThen pass throughUpdatingWherein W2(col.1) and W2(col. 2) are each W2Column 1 and column 2;
RS1220. finish regression analysis, returnThe sequence number j of the first d elements in the sequence from big to small1,j2,…,jdAs d columns for X.
The solution of keypromlem in step RS1213 includes the following steps:
RS121301. construction of data matrix X+∈R2m×(801+2m)Then with X1Initialization of X+First 801 columns of (1), with 2m order identity matrix I2mInitialization of X+The last 2m column of (i.e. X)+=[X1,I2m]∈R2m×(801+2m)In which I2mIs an identity matrix of 2m order;
RS121302. construction of diagonal element vector φ ∈ R(801+2m)×1Then all elements of phi are initialized to 1;
RS121303. defining iteration number k2And initialized to 0, define and variable Sum and initialized to-1000.000;
RS121304. construction of diagonal matrix Λ∈ R(801+2m)×(801+2m);
Rs121305. via Λjj=φjJ is 1,2, …, (801+2m) sequentially updates the main diagonal element of Λ, where j is the element number of phi and the main diagonal element number of Λ, phijIs the jth element of phi, ΛjjThe jth main diagonal element of Λ, i.e., ΛjjΛ for the element located in row jth column jth;
RS121306. separately construct the data matrix W0∈R801×2And W3,W4∈R(801+2m)×2Then initializing them to a zero matrix;
RS121307. byUpdating W3Wherein T and-1 are transposition operation and inversion operation respectively;
RS121308. with W4=W3⊙W3Update W of the calculation result of (2)4Wherein ⊙ is a Hadamard product operation of the matrix;
rs121309. first pass through ═ W4(col·1)+W4(col.2) updating phi, if zero element exists in phi, replacing zero element with 0.000001, wherein W4(col.1) and W4(col. 2) are each W4Column 1 and column 2;
rs121310. iteration number k2Self-increment by 1;
RS121311. if satisfied at the same timeAnd k2<K, then passUpdate Sum and then perform steps RS 121305-RS 121311, where j is the element number of φ, φjThe jth element of phi; otherwise, go to step RS 121312;
RS121312. with W3The first 801 rows of update W0;
RS121313. complete the solution of KeyProblem, return the solution W of KeyProblem0。
Drawings
FIG. 1 is a basic flow diagram of a coal-rock identification method based on extended local binary patterns and regression analysis;
FIG. 2 is a basic flow diagram of the regression analysis of the present invention;
FIG. 3 is a solution W for KeyProblem according to the present invention0A basic flow diagram of (1);
Detailed Description
On the basis of carrying out experimental analysis on images of main coal types and rock types in Henan, Shanxi, Shaanxi and other places of China, the invention provides a coal and rock identification method based on an extended local binary pattern and regression analysis.
The invention is described in further detail below with reference to the figures and the detailed description.
Referring to fig. 1, the coal rock identification method based on the extended local binary pattern and the regression analysis specifically includes the following steps:
SS1, in a sample training stage, acquiring m coal sample images and m rock sample images, intercepting subgraphs not containing non-coal rock backgrounds and carrying out gray processing on the subgraphs, and respectively recording the processed coal sample subgraphs and rock sample subgraphs as c1,c2,…,cmAnd s1,s2,…,sm;
Ss2. set sampling radius r 2, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 3 × 31,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
SS3. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector α1,α2,…,αm∈R1×200And β1,β2,…,βm∈R1×200;
SS4. set sampling radius r 4, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 5 × 51,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
SS5. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector η1,η2,…,ηm∈R1×200And mu1,μ2,…,μm∈R1×200;
SS6. set sampling radius r 6, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrC is counted as 7 × 71,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
SS7. respectively handleAndtransforming into 1-dimensional histogram, and normalizing them to obtain characteristic row vector theta1,θ2,…,θm∈R1×200And
ss8. set sampling radius r 8, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringrCount c for 9 × 91,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
SS9. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector k1,κ2,…,κm∈R1×200And upsilon1,υ2,…,υm∈R1×200;
SS10. construction of c separately1,c2,…,cmAnd s1,s2,…,smOriginal feature column vector x1=[α1,η1,θ1,κ1]T,x2=[α2,η2,θ2,κ2]T,…,xm=[αm,ηm,θm,κm]T∈R800×1And ,…,wherein T is a transposition operation;
SS11. constructing an original characteristic matrix X ═ X of the coal rock training sample1,x2,…,xm,xm+1,xm+2,…,x2m]T∈R2m ×800And its category label matrix Y ∈ R2m×2Wherein T is a transpose operation, the first m rows and 1 st columns of data padding of Y is 1, the first m rows and 2 nd columns of data padding of Y is 0, the last m rows and 1 st columns of data padding of Y is 0, and the last m rows and 2 nd columns of data padding of Y is 1;
SS12, setting a regularization parameter lambda, iteration times K and an optimal feature number d, and performing regression analysis on X and Y to obtain d column marks j about X and beneficial to distinguishing coal rocks1,j2,…,jdWherein j is not less than 11,j2,…,jd≤800;
SS13. extract j of X in sequence1,j2,…,jdArranging the columns, and then forming a final characteristic matrix of the coal rock training sample according to the arrangement of the columnsX(col·j2),…,X(col·jd)]∈R2m×dWherein X (col. j)1),X(col·j2),…,X(col·jd) J' th of X respectively1,j2,…,jdColumns;
SS14, in the coal rock identification stage, collecting an unknown class sample image, intercepting a sub-image without a non-coal rock background and carrying out gray processing on the sub-image, wherein the processed unknown class sub-image is marked as q;
ss15. set sampling radius r 2, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr3 × 3, the robust extended local binary pattern 3-dimensional joint histogram H with the combination of 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial difference, which adopts median filtering and has rotation invariant characteristic and uniform characteristicq;
SS16. treating HqTransforming into 1-dimensional histogram, and normalizing to obtain characteristic row vectorq∈R1 ×200;
Ss17. set the sampling radius r 4, the radial spacing 2, the number of sampling neighborhoods p 8, and the sliding window size ω for median filteringr5 × 5, the robust extended local binary pattern 3-dimensional joint histogram Z with the rotation invariant characteristic and the uniform characteristic and adopting the median filtering is combined by 3 descriptors of a descriptor based on the central point intensity, a descriptor based on the neighborhood point intensity and a descriptor based on the radial differenceq;
SS18. handle ZqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector rhoq∈R1 ×200;
Ss19. set sampling radius r 6, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr7 × 7, statistics q using median filtering and having rotation invariant and uniform properties are based on central point intensity descriptors, neighborhood point intensity descriptors and radial differenceRobust extended local binary pattern 3-dimensional joint histogram F formed by combining 3 descriptors of sub-descriptorsq;
SS20. A. BqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector sigmaq∈R1 ×200;
Ss21. set sampling radius r 8, radial spacing 2, sampling neighborhood number p 8, and sliding window size ω for median filteringr9 × 9, the robust extended local binary pattern 3-dimensional joint histogram T with rotation invariant and uniform characteristics and adopting median filtering and with the rotation invariant characteristic and the uniform characteristic is formed by combining 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial differenceq;
SS22. separately treating TqTransformed into a 1-dimensional histogram, which is then normalized to obtain a feature row vector ξq∈R1×200;
SS23. construct the raw feature row vector x for qq=[q,ρq,σq,ξq]∈R1×800;
SS24. successively extract xqJ (d) of1,j2,…,jdElements, then arranging the final feature row vector constituting q in orderWherein xq(j1),xq(j2),…,xq(jd) Are respectively xqJ (d) of1,j2,…,jdAn element;
SS25. by calculationDetermining the coal rock class of q, if satisfiedThen judging q as coal; otherwise, q is determined to be rock, where i isI is 1,2, …,2m, j isColumn symbol ofThe element numbers of (1), (2), (…), (d),is composed ofOf the elements located in row i and column j,is composed ofThe jth element of (1).
Referring to FIG. 2, the regression analysis described in step SS12 includes the following steps:
SS1201. construct the symbol matrix U ∈ R2m×2Then initializing m elements positioned in the first m rows and the 1 st column in the U by using 1, initializing m elements positioned in the first m rows and the 2 nd column in the U by using-1, initializing m elements positioned in the second m rows and the 1 st column in the U by using-1, and initializing m elements positioned in the second m rows and the 2 nd column in the U by using 1;
SS1202. construct data matrix X0∈R2m×800Then byColumn by column initialization X0Wherein τ is X0And X, τ ═ 1,2, …,800,is X0Column τ of, xτColumn τ of X, mean (X)τ) Is xτMean of all elements in;
SS1203. respectively constructing weight matrices Wold,Wnew∈R800×2And an offset vector bold,bnew∈R2×1;
SS1204, first pass Wold=(X0)T{[X0(X0)T+λI2m]-1Y initialization WoldThen through Wnew=WoldInitializing WnewWhere T and-1 are the transposition and inversion operations, respectively, I2mIs an identity matrix of 2m order;
SS1206. first passInitialization boldThen through bnew=boldInitialization bnewWherein L isb(col. j) is LbJ is LbThe list of (1), (2), (…), (2 m);
SS1207. construction of data matrix A, B, G ∈ R separately2m×2Then initializing them to a zero matrix;
SS1208. construct data matrix X1∈R2m×801Then initialize X with X1First 800 columns of (A), X1All elements of column 801 are initialized to 1000, i.e., X1=[X,1000e2m]∈R2m×801Wherein e is2m∈R2m×1A column vector with all elements 1;
SS1209. define iteration number k1And is initialized to 0;
SS1211 updating B by first updating B by B ═ U ≧ A, and then replacing the negative element in B by 0, wherein | _ is Hadamard product operation of the matrix;
ss1212 updating G by G ═ B) + Y, wherein ═ Hadamard product operation of the matrix;
SS1213. describe mathematics as
The optimization problem (W) is recorded as KeyProblem, and the solution W of the KeyProblem is obtained0∈R801×2Wherein | · | purple light2,1Is a matrix of2,1Norm in matrix Ψ ∈ Ru0×v0For the purpose of example only,i0 is a row indicator of Ψ, i0 ═ 1,2, …, u0, j0 is a column indicator of Ψ, j0 ═ 1,2, …, v0, Ψ (i0, j0) is an element in Ψ located in the j0 th column of the i0 th row, and u0 and v0 are the row number and column number of Ψ, respectively;
SS1214 with W0Update W on the first 800 rowsnew;
SS1215. through bnew=1000×[W0(row·801)]TUpdate bnewWhere T is a transposition operation, W0(row 801) is W0Line 801;
SS1216. iteration number k1Self-increment by 1;
SS1217. if satisfied at the same timeAnd k1<K, then use WnewUpdate W of the value ofoldBy bnewUpdate of value boldThen, step SS 1210-SS 1217 is performed, in which | · | | | ceilingFAnd | · | non-conducting phosphor2The Frobenius norm of the matrix and the 2-norm of the vector are respectively; otherwise, go to step SS 1218;
SS1218. construct the weight-squared matrix W2∈R800×2Then through W2=Wnew⊙WnewInitializing W2Which isThe middle ⊙ is the Hadamard product operation of the matrix;
SS1219. construction of weight vectorsThen pass throughUpdatingWherein W2(col.1) and W2(col. 2) are each W2Column 1 and column 2;
SS1220. complete regression analysis, returnThe sequence number j of the first d elements in the sequence from big to small1,j2,…,jdAs d columns for X.
Referring to FIG. 3, the solution W of KeyProblem described in step SS1213 is obtained0The method comprises the following specific steps:
SS121301. construction of data matrix X+∈R2m×(801+2m)Then with X1Initialization of X+First 801 columns of (1), with 2m order identity matrix I2mInitialization of X+The last 2m column of (i.e. X)+=[X1,I2m]∈R2m×(801+2m)In which I2mIs an identity matrix of 2m order;
SS121302. construction of diagonal element vector φ ∈ R(801+2m)×1Then all elements of phi are initialized to 1;
SS121303. defining iteration number k2And initialized to 0, define and variable Sum and initialized to-1000.000;
SS121304. construction of diagonal matrix Λ∈ R(801+2m)×(801+2m);
SS121305. by Λjj=φjJ is 1,2, …, (801+2m) sequentially updates the main diagonal element of Λ, where j is the element number of phi and the main diagonal element number of Λ, phijIs the jth element of phi, ΛjjThe jth main diagonal element of Λ, i.e., ΛjjΛ for the element located in row jth column jth;
SS121306. separately construct the data matrix W0∈R801×2And W3,W4∈R(801+2m)×2Then initializing them to a zero matrix;
SS121307. byUpdating W3Wherein T and-1 are transposition operation and inversion operation respectively;
SS121308. with W4=W3⊙W3Update W of the calculation result of (2)4Wherein ⊙ is a Hadamard product operation of the matrix;
ss121309. first pass phi ═ W4(col·1)+W4(col.2) updating phi, if zero element exists in phi, replacing zero element with 0.000001, wherein W4(col.1) and W4(col. 2) are each W4Column 1 and column 2;
SS121310. iteration number k2Self-increment by 1;
SS121311. if satisfied at the same timeAnd k2<K, then passUpdate Sum and then perform steps SS 121305-SS 121311, where j is the element number of φ, φjThe jth element of phi; otherwise, go to step SS 121312;
SS121312. with W3The first 801 rows of update W0;
SS121313. the solution of KeyProblem is completed, and the solution W of KeyProblem is returned0。
It should be noted that the above-mentioned embodiment examples are used to further illustrate the present invention, and the embodiment examples should not be construed as limiting the scope of the present invention.
Claims (3)
1. The coal rock identification method based on the extended local binary pattern and the regression analysis is characterized by comprising the following steps of:
QS1, in the stage of sample training, acquiring m coal sample images and m rock sample images, intercepting subgraphs without non-coal rock background and carrying out gray processing on the subgraphs, and respectively recording the processed coal sample subgraphs and rock sample subgraphs as c1,c2,…,cmAnd s1,s2,…,sm;
Qs2. set the sampling radius r 2, the radial spacing 2, the number of sampling neighborhoods p 8, and the sliding window size ω for median filteringrCount c for 3 × 31,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
QS3. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector α1,α2,…,αm∈R1×200And β1,β2,…,βm∈R1×200;
QS4. set miningRadius of sample r 4, radial spacing 2, number of sampling neighborhoods p 8 and sliding window size ω for median filteringrCount c for 5 × 51,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
QS5. respectively handleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector η1,η2,…,ηm∈R1×200And mu1,μ2,…,μm∈R1×200;
Qs6. set the sampling radius r 6, the radial spacing 2, the number of sampling neighbours p 8, and the sliding window size ω for median filteringrC is counted as 7 × 71,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
QS7. respectively handleAndtransforming into 1-dimensional histogram, and normalizing them to obtain characteristic row vector theta1,θ2,…,θm∈R1×200And
qs8. set the sampling radius r 8, the radial spacing 2, the number of sampling neighborhoods p 8, and the sliding window size ω for median filteringrCount c for 9 × 91,c2,…,cmAnd s1,s2,…,smThe robust extended local binary pattern 3-dimensional joint histogram which adopts median filtering and has rotation invariant characteristic and uniform characteristic and is formed by combining 3 descriptors of descriptor based on central point intensity, descriptor based on neighborhood point intensity and descriptor based on radial differenceAnd
QS9. eachHandleAndtransformed into a 1-dimensional histogram, and then normalized to obtain a feature row vector k1,κ2,…,κm∈R1×200And upsilon1,υ2,…,υm∈R1×200;
QS10. construction of c separately1,c2,…,cmAnd s1,s2,…,smOriginal feature column vector x1=[α1,η1,θ1,κ1]T,x2=[α2,η2,θ2,κ2]T,…,xm=[αm,ηm,θm,κm]T∈R800×1And whereinTIs a transposition operation;
QS11. constructing an original characteristic matrix X ═ X of the coal rock training sample1,x2,…,xm,xm+1,xm+2,…,x2m]T∈R2m×800And its category label matrix Y ∈ R2m×2WhereinTFor the transpose operation, the first m rows and columns of data padding of Y are 1, the first m rows and columns of data padding of Y are 0, the last m rows and columns of data padding of Y are 0, and the last m rows and columns of data padding of Y are 1;
QS12, setting a regularization parameter lambda, an iteration number K and an optimal feature number d, and performing regression analysis on X and Y to obtain the advantageD columns j about X in discriminating coal petrography1,j2,…,jdWherein j is not less than 11,j2,…,jd≤800;
QS13. extract the j' th of X in sequence1,j2,…,jdThe columns are arranged into a final characteristic matrix of the coal rock training sample according to the columnsWherein X (col. j)1),X(col·j2),…,X(col·jd) J' th of X respectively1,j2,…,jdColumns;
QS14, in the stage of coal rock identification, collecting an unknown class sample image, intercepting a sub-image without a non-coal rock background and carrying out gray processing on the sub-image, and marking the processed unknown class sub-image as q;
qs15. set the sampling radius r 2, the radial spacing 2, the number of sampling neighborhoods p 8, and the sliding window size ω for median filteringr3 × 3, the robust extended local binary pattern 3-dimensional joint histogram H with the combination of 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial difference, which adopts median filtering and has rotation invariant characteristic and uniform characteristicq;
QS16. HqTransforming into 1-dimensional histogram, and normalizing to obtain characteristic row vectorq∈R1×200;
QS17. set the sampling radius r 4, radial spacing 2, sampling neighborhood number p 8 and sliding window size ω for median filteringr5 × 5, the robust extended local binary pattern 3-dimensional joint histogram Z with the rotation invariant characteristic and the uniform characteristic and adopting the median filtering is combined by 3 descriptors of a descriptor based on the central point intensity, a descriptor based on the neighborhood point intensity and a descriptor based on the radial differenceq;
QS18. a handle ZqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector rhoq∈R1×200;
Qs19. set the sampling radius r 6, the radial spacing 2, the number of sampling neighbours p 8, and the sliding window size ω for median filteringr7 × 7, the robust extended local binary pattern 3-dimensional joint histogram F with the combination of 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial difference, which adopts median filtering and has rotation invariant characteristic and uniform characteristic, of statistics qq;
QS20. a handle FqThe shape is changed into a 1-dimensional histogram, and then the histogram is normalized to obtain a characteristic row vector sigmaq∈R1×200;
Qs21. set the sampling radius r 8, the radial spacing 2, the number of sampling neighborhoods p 8, and the sliding window size ω for median filteringr9 × 9, the robust extended local binary pattern 3-dimensional joint histogram T with rotation invariant and uniform characteristics and adopting median filtering and with the rotation invariant characteristic and the uniform characteristic is formed by combining 3 descriptors, namely a descriptor based on central point intensity, a descriptor based on neighborhood point intensity and a descriptor based on radial differenceq;
QS22. respectively handle TqTransformed into a 1-dimensional histogram, which is then normalized to obtain a feature row vector ξq∈R1 ×200;
QS23. construct the raw feature row vector x of qq=[q,ρq,σq,ξq]∈R1×800;
QS24. successively extract xqJ (d) of1,j2,…,jdElements, then arranging the final feature row vector constituting q in orderWherein xq(j1),xq(j2),…,xq(jd) Are respectively xqJ (d) of1,j2,…,jdAn element;
QS25. by calculatingJudging the coal rock class of q, if the coal rock class satisfies qJudging q is coal; otherwise, q is determined to be rock, where i isI is 1,2, …,2m, j isColumn symbol ofThe element numbers of (1), (2), (…), (d),is composed ofOf the elements located in row i and column j,is composed ofThe jth element of (1).
2. The coal-rock identification method based on the extended local binary pattern and the regression analysis according to claim 1, wherein the regression analysis comprises the following steps:
QS1201. construct a symbol matrix U ∈ R2m×2Then initializing m elements positioned in the first m rows and the 1 st column in the U by using 1, initializing m elements positioned in the first m rows and the 2 nd column in the U by using-1, initializing m elements positioned in the second m rows and the 1 st column in the U by using-1, and initializing m elements positioned in the second m rows and the 2 nd column in the U by using 1;
QS1202. constructing a data matrix X0∈R2m×800Then byColumn by column initialization X0Wherein τ is X0And X, τ ═ 1,2, …,800,is X0Column τ of, xτColumn τ of X, mean (X)τ) Is xτMean of all elements in;
QS1203, respectively constructing weight matrix Wold,Wnew∈R800×2And an offset vector bold,bnew∈R2×1;
Qs1204. first pass Wold=(X0)T{[X0(X0)T+λI2m]-1Y initialization WoldThen through Wnew=WoldInitializing WnewWhereinTAnd-1respectively transpose operation and inversion operation, I2mIs a 2 m-order identity matrix, and lambda is a regularization parameter;
QS1206. first passInitialization boldThen through bnew=boldInitialization bnewWherein L isb(col. n) is LbN is LbWhere n is 1,2, …,2 m;
QS1207. respectively constructing data matrixes A, B, G ∈ R2m×2Then initializing them to a zero matrix;
QS1208. construct data matrix X1∈R2m×801Then initialize X with X1First 800 columns of (A), X1All elements of column 801 are initialized to 1000, i.e., X1=[X,1000e2m]∈R2m×801Wherein e is2m∈R2m×1A column vector with all elements 1;
QS1209. define iteration number k1And is initialized to 0;
QS1210. byUpdate A whereinTFor transposition operations, e2m∈R2m×1A column vector with all elements 1;
QS1211 updating B by replacing the negative element in B with 0, wherein ═ U is A for Hadamard product operation of the matrix;
QS1212, updating G by G ═ B) + Y, wherein &isHadamard product operation of the matrix;
QS1213. describe mathematics as
The optimization problem (W) is recorded as KeyProblem, and the solution W of the KeyProblem is obtained0∈R801×2Wherein | · | purple light2,1Is a matrix of2,1-a norm;
QS1214. with W0Update W on the first 800 rowsnew;
QS1215. through bnew=1000×[W0(row·801)]TUpdate bnewWhereinTFor transposition operations, W0(row 801) is W0Line 801;
QS1216. iteration number k1Self-increment by 1;
QS1217. if satisfied at the same timeAnd k1If < K, then W is usednewUpdate W of the value ofoldBy bnewUpdate of value boldThen, a step QS 1210-QS 1217 is performed, in which | · | |. aFAnd | · | non-conducting phosphor2The Frobenius norm of the matrix and the 2-norm of the vector are respectively; otherwise, executing step QS 1218;
QS1218. construct a weight square matrix W2∈R800×2Then through W2=Wnew⊙WnewInitializing W2Wherein ⊙ is a Hadamard product operation of the matrix;
QS1219. construction of weight vectorThen pass throughUpdatingWherein W2(col.1) and W2(col. 2) are each W2Column 1 and column 2;
3. The coal-rock identification method based on the extended local binary pattern and the regression analysis as claimed in claim 2, wherein the solution of the KeyProblem comprises the following steps:
QS121301. construction of data matrix X+∈R2m×(801+2m)Then with X1Initialization of X+First 801 columns of (1), with 2m order identity matrix I2mInitialization of X+The last 2m column of (i.e. X)+=[X1,I2m]∈R2m×(801+2m)In which I2mIs an identity matrix of 2m order;
QS121302. construction of diagonal element vector φ ∈ R(801+2m)×1Then all elements of phi are initialized to 1;
QS121303. define iteration number k2And initialized to 0, define and variable Sum and initialized to-1000.000;
QS121304. construction of diagonal matrix Λ∈ R(801+2m)×(801+2m);
Qs121305. through Λll=φl1,2, …, (801+2m) sequentially updates the main diagonal element of Λ, where l is the element number of phi and the main diagonal element number of Λ, philIs the l-th element of phi, ΛllThe first major diagonal element of Λ, i.e., ΛllΛ for the element in row l, column l;
QS121306. separately construct a data matrix W0∈R801×2And W3,W4∈R(801+2m)×2Then initializing them to a zero matrix;
QS121307. byUpdating W3WhereinTAnd-1respectively performing transposition operation and inversion operation;
QS121308. with W4=W3⊙W3Update W of the calculation result of (2)4Wherein ⊙ is a Hadamard product operation of the matrix;
qs121309. first pass phi ═ W4(col·1)+W4(col.2) updating phi, if zero element exists in phi, replacing zero element with 0.000001, wherein W4(col.1) and W4(col. 2) are each W4Column 1 and column 2;
QS121310. iteration number k2Self-increment by 1;
QS121311. if satisfied simultaneouslyAnd k2If < K, then passUpdate Sum, then execute stepQS 121305-QS 121311, where l is the element number of φlThe l-th element of phi; otherwise, step QS121312 is executed;
QS121312. with W3The first 801 rows of update W0;
QS121313. complete the solution of KeyProblem, return the solution W of KeyProblem0。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710440697.8A CN107239783B (en) | 2017-06-13 | 2017-06-13 | Coal rock identification method based on extended local binary pattern and regression analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710440697.8A CN107239783B (en) | 2017-06-13 | 2017-06-13 | Coal rock identification method based on extended local binary pattern and regression analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107239783A CN107239783A (en) | 2017-10-10 |
CN107239783B true CN107239783B (en) | 2020-09-18 |
Family
ID=59986964
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710440697.8A Active CN107239783B (en) | 2017-06-13 | 2017-06-13 | Coal rock identification method based on extended local binary pattern and regression analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107239783B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109447944B (en) * | 2018-09-21 | 2020-08-11 | 中国石油天然气股份有限公司 | Lithofacies identification method and system for carbonate rock |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184300A (en) * | 2015-09-01 | 2015-12-23 | 中国矿业大学(北京) | Coal-rock identification method based on image LBP |
CN106485223A (en) * | 2016-10-12 | 2017-03-08 | 南京大学 | The automatic identifying method of rock particles in a kind of sandstone microsection |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101656373B1 (en) * | 2014-10-15 | 2016-09-12 | 서울시립대학교 산학협력단 | Face identifying method, face identifying apparatus and computer program executing the method |
US9589323B1 (en) * | 2015-08-14 | 2017-03-07 | Sharp Laboratories Of America, Inc. | Super resolution image enhancement technique |
-
2017
- 2017-06-13 CN CN201710440697.8A patent/CN107239783B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184300A (en) * | 2015-09-01 | 2015-12-23 | 中国矿业大学(北京) | Coal-rock identification method based on image LBP |
CN106485223A (en) * | 2016-10-12 | 2017-03-08 | 南京大学 | The automatic identifying method of rock particles in a kind of sandstone microsection |
Non-Patent Citations (4)
Title |
---|
A new coal-rock interface recognition method based on Hilbert marginal spectrum distribution characteristics;B. Wang等;《Journal of Computational Information Systems》;20121031;第19卷(第8期);第8137-8142页 * |
Application of Hilbert Marginal Spectrum to Coal-Rock Interface Recognition;BaoPing Wang等;《Advanced Materials Research》;20120930;第569卷;第70-73页 * |
基于LBP-SR的复杂场景人脸识别算法;余天豪等;《杭州师范大学学报(自然科学版)》;20111130;第10卷(第6期);第552-555页 * |
基于图像识别的煤岩界面识别方法研究;孙继平;《煤炭科学技术》;20110228;第39卷(第2期);第77-79页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107239783A (en) | 2017-10-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Prakash et al. | Detection of leaf diseases and classification using digital image processing | |
CN105303198B (en) | A kind of remote sensing image semisupervised classification method learnt from fixed step size | |
Es-saady et al. | Automatic recognition of plant leaves diseases based on serial combination of two SVM classifiers | |
Sirmacek et al. | A probabilistic framework to detect buildings in aerial and satellite images | |
CN103927514B (en) | A kind of Coal-rock identification method based on random local image characteristics | |
Hong et al. | Comparative study on vision based rice seed varieties identification | |
CN104573744B (en) | Fine granulation classification identifies and the part of object positions and feature extracting method | |
CN104751192B (en) | Coal-rock identification method based on image block symbiosis feature | |
Poornima et al. | Detection and classification of diseases in plants using image processing and machine learning techniques | |
PUJARİ et al. | Statistical methods for quantitatively detecting fungal disease from fruits’ images | |
Rahamathunnisa et al. | Vegetable disease detection using k-means clustering and svm | |
Guerrero et al. | Automated system for classifying Hass avocados based on image processing techniques | |
Baghel et al. | K-means segmentation method for automatic leaf disease detection | |
Najeeb et al. | Dates maturity status and classification using image processing | |
Chandini | Improved quality detection technique for fruits using GLCM and multiclass SVM | |
Bukhari et al. | Assessing the impact of segmentation on wheat stripe rust disease classification using computer vision and deep learning | |
CN107239783B (en) | Coal rock identification method based on extended local binary pattern and regression analysis | |
CN111160389A (en) | Lithology identification method based on fusion of VGG | |
Palanikumar et al. | An effective two way classification of breast cancer images | |
CN113298137A (en) | Hyperspectral image classification method based on local similarity data gravitation | |
El Massi et al. | Automatic recognition of vegetable crops diseases based on neural network classifier | |
CN105350963B (en) | A kind of Coal-rock identification method learnt based on relativity measurement | |
CN104778461A (en) | Coal-rock recognition method based on similar measure learning | |
CN107169524B (en) | Coal rock identification method based on complete local binary pattern reconstruction residual error | |
CN106951924A (en) | Acceleration Algorithm in Seismic Coherence Cube image slices automatic identifying method and system based on AdaBoost algorithms |
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 |