CN104732562A - Method for comparing similarity of electric imaging logging images - Google Patents
Method for comparing similarity of electric imaging logging images Download PDFInfo
- Publication number
- CN104732562A CN104732562A CN201510129617.8A CN201510129617A CN104732562A CN 104732562 A CN104732562 A CN 104732562A CN 201510129617 A CN201510129617 A CN 201510129617A CN 104732562 A CN104732562 A CN 104732562A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- row
- formula
- scale
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003384 imaging method Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 5
- 208000035126 Facies Diseases 0.000 description 1
- 239000004990 Smectic liquid crystal Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an electrical imaging logging image similarity comparison method, and relates to the technical field of interpretation and evaluation of electrical imaging logging information. And calculating various texture characteristic values by utilizing dynamic image data of each polar plate of the electric imaging logging, and calculating Euclidean distances of various texture characteristic values between the electric imaging images, thereby realizing the similarity of comparing the two electric imaging logging images by a computer. The method solves the problem of calculating various texture characteristics by using the electrical imaging logging data; secondly, the problem of how to determine the similarity between the electric imaging images by utilizing the calculated various characteristic values is solved; thirdly, the problem of realizing the calculation method through the computer language is solved.
Description
Technical field
The present invention relates to electric imaging logging data interpretation assessment technique field.
Background technology
Publication number is CN101899971A, and publication date is recognition methods and the device thereof that the Chinese patent literature on Dec 1st, 2010 discloses a kind of carbonate formation electric imaging logging phase, and the method comprises: the electric imaging logging data obtaining carbonate formation; Electric imaging logging data are processed, obtains the image information of electric imaging logging data; Identify the image information of the electric imaging logging data of acquisition according to the electric imaging logging preset mutually, obtain the carbonate formation electric imaging logging phase that electric imaging logging data are corresponding; Electric imaging logging comprises mutually: massive phase, smectic phase and plaque-like phase.By the embodiment of the present invention, carbonate formation sedimentary facies can be identified, obtain carbonate formation electric imaging logging phase, better the regularity of distribution of research and predicting reservoir.
Above-mentioned patent document relates generally to the identification of carbonate strata electric imaging logging phase, but current electric imaging logging image, still mainly through artificial cognition comparison, exists artificial subjective factor, cause different people's comparison effects to differ, and efficiency is lower.Prior art shortcoming:
1, a set of image characteristic extracting method of Electrical imaging is not accurately had;
2, neither one Electrical imaging feature comparison method fast.
Summary of the invention
The present invention is intended to for the defect existing for above-mentioned prior art and deficiency, and provide a kind of electric imaging logging image similarity comparison method, the present invention one solves the problem utilizing electric imaging logging data to carry out multiple textural characteristics calculating; Two is the problems solving the similarity how utilized between calculated various features value determination Electrical imaging image; Three is solve problem computing method realized by computerese.
The present invention realizes by adopting following technical proposals:
A kind of electric imaging logging image similarity comparison method, it is characterized in that: utilize electric imaging logging each pole plate dynamic image data to calculate multiple textural characteristics value, and calculate the Euclidean distance of various textural characteristics value between Electrical imaging image, thus realize the similarity being contrasted two width electric imaging logging images by computing machine.
Described multiple textural characteristics value comprises: average, variance, anisotropic index, sorting coefficient, pseudo-sorting coefficient, image distribution intensity, gray level co-occurrence matrixes energy, gray level co-occurrence matrixes entropy, gray level co-occurrence matrixes contrast and gray level co-occurrence matrixes local homogeneity.
The computing method of each textural characteristics value are as follows:
Average: calculate its arithmetic average to target image gray scale array, adopts following formula to calculate:
In formula: AVE is average, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array;
Variance: calculate each pixel grey scale standard variance to target image, adopts following formula to calculate:
In formula: VAR is variance, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; U is average;
Anisotropic index:
The first step, the arithmetic mean of each row data of computed image gray scale array, gets its harmonic-mean as horizontal direction maximal value again to the arithmetic mean of each row, adopts following formula to calculate:
In formula: C
xMaxfor horizontal direction maximal value, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array;
Second step, calculates the harmonic-mean of each column data, then gets arithmetic mean to each row harmonic-mean and obtain horizontal direction minimum value, thus determines horizontal direction average conductivity, adopts following formula to calculate:
In formula: Cx is horizontal direction average conductivity, C
xMaxfor horizontal direction maximal value, C
xMinfor horizontal direction minimum value;
3rd step, exchanges row, column in upper two formulas and determines average conductivity in vertical direction
;
4th step, the ratio of horizontal direction and vertical direction average conductivity is exactly anisotropic index:
In formula: ANI is anisotropic index, Cx is horizontal direction average conductivity, and Cz is vertical direction average conductivity;
Sorting coefficient: for destination image data, make its frequency accumulative histogram, P1, P2 are frequency, and namely the ratio of the numerical value corresponding to P1 and P2 can be used as the tolerance of sorting coefficient, adopt following formula to calculate:
In formula: SORT is sorting coefficient, g(P1) be the gradation of image gray-scale value corresponding in P1 frequency place, g(P2) be the gradation of image gray-scale value corresponding in P2 frequency place;
Pseudo-sorting coefficient: for destination image data, make its frequency accumulative histogram, Pt, Pb, Pm are frequency, and the difference of the numerical value corresponding to Pt and Pb and the ratio of numerical value corresponding to Pm, namely can be used as the tolerance of pseudo-sorting coefficient, adopts following formula to calculate:
In formula: SORT_F is pseudo-sorting coefficient, g(Pb) be the gradation of image gray-scale value corresponding in Pb frequency place, g(Pt) be the gradation of image gray-scale value corresponding in Pt frequency place, g(Pm) be the gradation of image gray-scale value corresponding in Pm frequency place;
Image distribution intensity: K is exponent number, gets positive integer, and default value is 2, uses larger K value to be conducive to improving the resolution of result of calculation, adopts following formula to calculate:
In formula: CX is image distribution intensity, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; K is exponent number; U is average;
Gray level co-occurrence matrixes:
Texture is the comprehensive of a kind of image local feature of visually-perceptible, grey scale change rule around the textural characteristics of a certain position of image and this position is closely related, gray level co-occurrence matrixes reflects the integrated information of gradation of image about direction, adjacent spaces and changes in amplitude, can extract the series of features of Description Image texture from it further;
Definition direction is
, to be the gray level co-occurrence matrixes of d be pixel distance
, the dimension of matrix equals gradation of image progression,
representing matrix i-th row j column element, it is defined as a little
gray-scale value be i and point
gray-scale value be j occur frequency, wherein 2 position relationships are in a coordinate system as follows:
In formula: (k, l) is positioned at the point of the capable l row of k for gradation of image array is mapped in coordinate, (m, n) is positioned at the point of the capable n row of m for gradation of image array is mapped in coordinate, θ is four direction 0 °, 45 °, 90 °, 135 °, and d is pixel distance on θ direction;
The gray level co-occurrence matrixes of piece image reflects the integrated information of gradation of image about direction, adjacent spaces, amplitude of variation; It is the local mode of analysis chart picture and the basis of their queueing disciplines, can extract the series of features of Description Image texture from it further, and for expressing for simplicity, co-occurrence matrix below omits interval d and direction in expressing
;
Be extracted 4 reflection textural characteristics statistics by above gray level co-occurrence matrixes and have energy, entropy, contrast and local homogeneity;
Calculate gray level co-occurrence matrixes G (i, j) by different directions (0 degree, 45 degree, 90 degree, 135 degree) and different pixels distance, and extract the features such as its energy, entropy, contrast, local homogeneity, adopt following formula to calculate:
Energy
;
In formula: GM_ENE is gray level co-occurrence matrixes energy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Entropy
;
In formula: GM_ENT is gray level co-occurrence matrixes entropy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Contrast
;
In formula: GM_CON is gray level co-occurrence matrixes contrast, G(i, j) for gray level co-occurrence matrixes i-th row j arrange value;
Local homogeneity
;
In formula: GM_IDM is gray level co-occurrence matrixes local homogeneity, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Then the Euclidean distance between Euclidean distance formulae discovery two various eigenwerts of Electrical imaging image is utilized:
In formula: xi, yi are each textural characteristics values that two width Electrical imaging images are corresponding, calculate the Euclidean distance between the various textural characteristics value of two width Electrical imaging images, Euclidean distance is by the summed square then evolution of the difference of both each textural characteristics values, the less two width Electrical imaging images of Euclidean distance of the various textural characteristics values calculated are more similar, and that is when the Euclidean distance calculated is 0, two width Electrical imaging image similarities are 100%.
Compared with prior art, the beneficial effect that reaches of the present invention is as follows:
This method have employed Euclidean distance comparison method.Generally speaking, the Euclidean distance that these computing method accurately can calculate Electrical imaging image various features value and calculate between each eigenwert, realize the similarity being determined two Electrical imaging images by Euclidean distance size, and algorithm is easy to realize with computerese.One is solve the problem utilizing electric imaging logging data to carry out multiple textural characteristics calculating; Two is the problems solving the similarity how utilized between calculated various features value determination Electrical imaging image; Three is solve problem computing method realized by computerese.
Accompanying drawing explanation
Below in conjunction with specification drawings and specific embodiments, the present invention is described in further detail, wherein:
Fig. 1 is embodiment comparison result figure.
Embodiment
The invention discloses a kind of electric imaging logging image similarity comparison method, it is characterized in that: utilize electric imaging logging each pole plate dynamic image data to calculate multiple textural characteristics value, and calculate the Euclidean distance of various textural characteristics value between Electrical imaging image, thus realize the similarity being contrasted two width electric imaging logging images by computing machine.Described multiple textural characteristics value comprises: average, variance, anisotropic index, sorting coefficient, pseudo-sorting coefficient, image distribution intensity, gray level co-occurrence matrixes energy, gray level co-occurrence matrixes entropy, gray level co-occurrence matrixes contrast and gray level co-occurrence matrixes local homogeneity.
The computing method of each textural characteristics value are as follows:
Average: calculate conductivity arithmetic average to destination image data, adopts following formula to calculate:
In formula: AVE is average, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array.
Variance: calculate conductivity standard variance to destination image data, adopts following formula to calculate:
In formula: VAR is variance, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; U is average.
Anisotropic index:
The first step, calculates the arithmetic mean of each row data, gets its harmonic-mean again as horizontal direction maximal value to the arithmetic mean of each row, adopts following formula to calculate:
In formula: C
xMaxfor horizontal direction maximal value, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array.
Second step, calculates the harmonic-mean of each column data, then gets arithmetic mean to each row harmonic-mean and obtain horizontal direction minimum value, thus determines horizontal direction average conductivity, adopts following formula to calculate:
In formula: Cx is horizontal direction average conductivity, C
xMaxfor horizontal direction maximal value, C
xMinfor horizontal direction minimum value.
3rd step, exchanges row, column in upper two formulas and determines average conductivity in vertical direction
;
4th step, the ratio of horizontal direction and vertical direction average conductivity is exactly anisotropic index:
In formula: ANI is anisotropic index, Cx is horizontal direction average conductivity, and Cz is vertical direction average conductivity.
Sorting coefficient: for destination image data, make its frequency accumulative histogram, P1, P2 are frequency, and namely the ratio of the numerical value corresponding to P1 and P2 can be used as the tolerance of sorting coefficient, adopt following formula to calculate:
In formula: SORT is sorting coefficient, g(P1) be the gradation of image gray-scale value corresponding in P1 frequency place, g(P2) be the gradation of image gray-scale value corresponding in P2 frequency place.
Pseudo-sorting coefficient: for destination image data, make its frequency accumulative histogram, Pt, Pb, Pm are frequency, and the difference of the numerical value corresponding to Pt and Pb and the ratio of numerical value corresponding to Pm, namely can be used as the tolerance of pseudo-sorting coefficient, adopts following formula to calculate:
In formula: SORT_F is pseudo-sorting coefficient, g(Pb) be the gradation of image gray-scale value corresponding in Pb frequency place, g(Pt) be the gradation of image gray-scale value corresponding in Pt frequency place, g(Pm) be the gradation of image gray-scale value corresponding in Pm frequency place.
Image distribution intensity: K is exponent number, gets positive integer, and default value is 2, uses larger K value to be conducive to improving the resolution of result of calculation, adopts following formula to calculate:
In formula: CX is image distribution intensity, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; K is exponent number; U is average.
Gray level co-occurrence matrixes:
Texture is the comprehensive of a kind of image local feature of visually-perceptible, and the grey scale change rule around the textural characteristics of a certain position of image and this position is closely related.Gray level co-occurrence matrixes reflects the integrated information of gradation of image about direction, adjacent spaces and changes in amplitude.The series of features of Description Image texture can be extracted further from it.
Definition direction is
, to be the gray level co-occurrence matrixes of d be pixel distance
, the dimension of matrix equals gradation of image progression,
representing matrix i-th row j column element, it is defined as a little
gray-scale value be i and point
gray-scale value be j occur frequency.Wherein 2 position relationships are in a coordinate system as follows:
In formula: (k, l) is positioned at the point of the capable l row of k for gradation of image array is mapped in coordinate, (m, n) is positioned at the point of the capable n row of m for gradation of image array is mapped in coordinate, θ is four direction 0 °, 45 °, 90 °, 135 °, and d is pixel distance on θ direction.
The gray level co-occurrence matrixes of piece image reflects the integrated information of gradation of image about direction, adjacent spaces, amplitude of variation.It is the local mode of analysis chart picture and the basis of their queueing disciplines, can extract the series of features of Description Image texture from it further.For expressing for simplicity, co-occurrence matrix below omits interval d and direction in expressing
.
Be extracted 4 reflection textural characteristics statistics by above gray level co-occurrence matrixes and have energy, entropy, contrast and local homogeneity.
Calculate gray level co-occurrence matrixes G (i, j) by different directions (0 degree, 45 degree, 90 degree, 135 degree) and different pixels distance, and extract the features such as its energy, entropy, contrast, local homogeneity, adopt following formula to calculate:
Energy
;
In formula: GM_ENE is gray level co-occurrence matrixes energy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale.
Entropy
;
In formula: GM_ENT is gray level co-occurrence matrixes entropy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale.
Contrast
;
In formula: GM_CON is gray level co-occurrence matrixes contrast, G(i, j) for gray level co-occurrence matrixes i-th row j arrange value.
Local homogeneity
;
In formula: GM_IDM is gray level co-occurrence matrixes local homogeneity, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale.
Then the Euclidean distance between Euclidean distance formulae discovery two various eigenwerts of Electrical imaging image is utilized:
In formula: xi, yi are each textural characteristics values that two width Electrical imaging images are corresponding, calculate the Euclidean distance between the various textural characteristics value of two width Electrical imaging images, Euclidean distance is by the summed square then evolution of the difference of both each textural characteristics values, the less two width Electrical imaging images of Euclidean distance of the various textural characteristics values calculated are more similar, and that is when the Euclidean distance calculated is 0, two width Electrical imaging image similarities are 100%.
As shown in Figure 1, in comparison result figure, upper left-hand image is image to be compared, and below 5 width figure is target image.Calculate image to be compared and 5 width target images, 10 kinds of textural characteristics respectively.Then the Euclidean distance between the various textural characteristics of image to be compared and every various textural characteristics of width target image is calculated, draw the Euclidean distance of image to be compared respectively and between 5 width target images (as upper right side in figure), Euclidean distance represents the similarity of two width figure, and the less similarity of Euclidean distance is higher.Image to be compared and target image 1 comparison result Euclidean distance are 0, therefore this two width figure is same width figure.
Claims (3)
1. an electric imaging logging image similarity comparison method, it is characterized in that: utilize electric imaging logging each pole plate dynamic image data to calculate multiple textural characteristics value, and calculate the Euclidean distance of various textural characteristics value between Electrical imaging image, thus realize the similarity being contrasted two width electric imaging logging images by computing machine.
2. a kind of electric imaging logging image similarity comparison method according to claim 1, is characterized in that: described multiple textural characteristics value comprises: average, variance, anisotropic index, sorting coefficient, pseudo-sorting coefficient, image distribution intensity, gray level co-occurrence matrixes energy, gray level co-occurrence matrixes entropy, gray level co-occurrence matrixes contrast and gray level co-occurrence matrixes local homogeneity.
3. a kind of electric imaging logging image similarity comparison method according to claim 1, is characterized in that: the computing method of each textural characteristics value are as follows:
Average: calculate its arithmetic average to target image gray scale array, adopts following formula to calculate:
In formula: AVE is average, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array;
Variance: calculate each pixel grey scale standard variance to target image, adopts following formula to calculate:
In formula: VAR is variance, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; U is average;
Anisotropic index:
The first step, the arithmetic mean of each row data of computed image gray scale array, gets its harmonic-mean as horizontal direction maximal value again to the arithmetic mean of each row, adopts following formula to calculate:
In formula: C
xMaxfor horizontal direction maximal value, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array;
Second step, calculates the harmonic-mean of each column data, then gets arithmetic mean to each row harmonic-mean and obtain horizontal direction minimum value, thus determines horizontal direction average conductivity, adopts following formula to calculate:
In formula: Cx is horizontal direction average conductivity, C
xMaxfor horizontal direction maximal value, C
xMinfor horizontal direction minimum value;
3rd step, exchanges row, column in upper two formulas and determines average conductivity in vertical direction
;
4th step, the ratio of horizontal direction and vertical direction average conductivity is exactly anisotropic index:
In formula: ANI is anisotropic index, Cx is horizontal direction average conductivity, and Cz is vertical direction average conductivity;
Sorting coefficient: for destination image data, make its frequency accumulative histogram, P1, P2 are frequency, and namely the ratio of the numerical value corresponding to P1 and P2 can be used as the tolerance of sorting coefficient, adopt following formula to calculate:
In formula: SORT is sorting coefficient, g(P1) be the gradation of image gray-scale value corresponding in P1 frequency place, g(P2) be the gradation of image gray-scale value corresponding in P2 frequency place;
Pseudo-sorting coefficient: for destination image data, make its frequency accumulative histogram, Pt, Pb, Pm are frequency, and the difference of the numerical value corresponding to Pt and Pb and the ratio of numerical value corresponding to Pm, namely can be used as the tolerance of pseudo-sorting coefficient, adopts following formula to calculate:
In formula: SORT_F is pseudo-sorting coefficient, g(Pb) be the gradation of image gray-scale value corresponding in Pb frequency place, g(Pt) be the gradation of image gray-scale value corresponding in Pt frequency place, g(Pm) be the gradation of image gray-scale value corresponding in Pm frequency place;
Image distribution intensity: K is exponent number, gets positive integer, and default value is 2, uses larger K value to be conducive to improving the resolution of result of calculation, adopts following formula to calculate:
In formula: CX is image distribution intensity, X(i, j) be gray-scale value corresponding to gradation of image array i-th row j row; M is gray scale array head office number, and N is the total columns of gray scale array; K is exponent number; U is average;
Gray level co-occurrence matrixes:
Definition direction is
, to be the gray level co-occurrence matrixes of d be pixel distance
, the dimension of matrix equals gradation of image progression,
representing matrix i-th row j column element, it is defined as a little
gray-scale value be i and point
gray-scale value be j occur frequency, wherein 2 position relationships are in a coordinate system as follows:
In formula: (k, l) is positioned at the point of the capable l row of k for gradation of image array is mapped in coordinate, (m, n) is positioned at the point of the capable n row of m for gradation of image array is mapped in coordinate, θ is four direction 0 °, 45 °, 90 °, 135 °, and d is pixel distance on θ direction;
The gray level co-occurrence matrixes of piece image reflects the integrated information of gradation of image about direction, adjacent spaces, amplitude of variation; It is the local mode of analysis chart picture and the basis of their queueing disciplines, can extract the series of features of Description Image texture from it further, and for expressing for simplicity, co-occurrence matrix below omits interval d and direction in expressing
;
Be extracted 4 reflection textural characteristics statistics by above gray level co-occurrence matrixes and have energy, entropy, contrast and local homogeneity;
Calculate gray level co-occurrence matrixes G (i, j) by different directions (0 degree, 45 degree, 90 degree, 135 degree) and different pixels distance, and extract the features such as its energy, entropy, contrast, local homogeneity, adopt following formula to calculate:
Energy
;
In formula: GM_ENE is gray level co-occurrence matrixes energy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Entropy
;
In formula: GM_ENT is gray level co-occurrence matrixes entropy, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Contrast
;
In formula: GM_CON is gray level co-occurrence matrixes contrast, G(i, j) for gray level co-occurrence matrixes i-th row j arrange value;
Local homogeneity
;
In formula: GM_IDM is gray level co-occurrence matrixes local homogeneity, G(i, j) be the value that gray level co-occurrence matrixes i-th row j arranges, k is gray shade scale;
Then the Euclidean distance between Euclidean distance formulae discovery two various eigenwerts of Electrical imaging image is utilized:
In formula: xi, yi are each textural characteristics values that two width Electrical imaging images are corresponding, calculate the Euclidean distance between the various textural characteristics value of two width Electrical imaging images, Euclidean distance is by the summed square then evolution of the difference of both each textural characteristics values, the less two width Electrical imaging images of Euclidean distance of the various textural characteristics values calculated are more similar, and that is when the Euclidean distance calculated is 0, two width Electrical imaging image similarities are 100%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510129617.8A CN104732562A (en) | 2015-03-24 | 2015-03-24 | Method for comparing similarity of electric imaging logging images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510129617.8A CN104732562A (en) | 2015-03-24 | 2015-03-24 | Method for comparing similarity of electric imaging logging images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104732562A true CN104732562A (en) | 2015-06-24 |
Family
ID=53456430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510129617.8A Pending CN104732562A (en) | 2015-03-24 | 2015-03-24 | Method for comparing similarity of electric imaging logging images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104732562A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105626058A (en) * | 2015-12-30 | 2016-06-01 | 中国石油天然气股份有限公司 | Method and device for determining development degree of reservoir karst |
| CN110866912A (en) * | 2019-11-15 | 2020-03-06 | 成都理工大学 | Shale streak layer heterogeneity data processing method based on imaging logging image texture |
| CN110966000A (en) * | 2020-01-02 | 2020-04-07 | 中国石油集团测井有限公司华北分公司 | Method and system for representing glutenite reservoir stratiform index |
| CN112182415A (en) * | 2020-09-04 | 2021-01-05 | 上海松鼠课堂人工智能科技有限公司 | Intelligent learning guiding method and system |
| US11003952B2 (en) | 2018-08-24 | 2021-05-11 | Petrochina Company Limited | Method and apparatus for automatically recognizing electrical imaging well logging facies |
| US11010629B2 (en) | 2018-08-24 | 2021-05-18 | Petrochina Company Limited | Method for automatically extracting image features of electrical imaging well logging, computer equipment and non-transitory computer readable medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6229308B1 (en) * | 1998-11-19 | 2001-05-08 | Schlumberger Technology Corporation | Formation evaluation using magnetic resonance logging measurements |
| CN1573013A (en) * | 2003-05-22 | 2005-02-02 | 施卢默格海外有限公司 | Directional electromagnetic resistivity apparatus and method |
-
2015
- 2015-03-24 CN CN201510129617.8A patent/CN104732562A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6229308B1 (en) * | 1998-11-19 | 2001-05-08 | Schlumberger Technology Corporation | Formation evaluation using magnetic resonance logging measurements |
| CN1573013A (en) * | 2003-05-22 | 2005-02-02 | 施卢默格海外有限公司 | Directional electromagnetic resistivity apparatus and method |
Non-Patent Citations (5)
| Title |
|---|
| 李潮流 等: "碎屑岩储集层层内非均质性测井定量评价方法", 《石油勘探与开发》 * |
| 滕俊: "利用成像测井资料提高常规测井薄层分辨率的方法研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
| 王华锋 等: "基于纹理特征的测井图像分类算法的研究", 《计算机研究与发展》 * |
| 王满 等: "FMI图像纹理统计方法识别火成岩岩性", 《测井技术》 * |
| 王熊 等: "成像测井图像纹理特征提取的统计方法研究", 《石油天然气学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105626058A (en) * | 2015-12-30 | 2016-06-01 | 中国石油天然气股份有限公司 | Method and device for determining development degree of reservoir karst |
| US10641088B2 (en) | 2015-12-30 | 2020-05-05 | Petrochina Company Limited | Method and device for determining karst development degree of reservoir, computer readable storage medium and device |
| US11003952B2 (en) | 2018-08-24 | 2021-05-11 | Petrochina Company Limited | Method and apparatus for automatically recognizing electrical imaging well logging facies |
| US11010629B2 (en) | 2018-08-24 | 2021-05-18 | Petrochina Company Limited | Method for automatically extracting image features of electrical imaging well logging, computer equipment and non-transitory computer readable medium |
| CN110866912A (en) * | 2019-11-15 | 2020-03-06 | 成都理工大学 | Shale streak layer heterogeneity data processing method based on imaging logging image texture |
| CN110866912B (en) * | 2019-11-15 | 2022-04-19 | 成都理工大学 | Shale streak layer heterogeneity data processing method based on imaging logging image texture |
| CN110966000A (en) * | 2020-01-02 | 2020-04-07 | 中国石油集团测井有限公司华北分公司 | Method and system for representing glutenite reservoir stratiform index |
| CN112182415A (en) * | 2020-09-04 | 2021-01-05 | 上海松鼠课堂人工智能科技有限公司 | Intelligent learning guiding method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104732562A (en) | Method for comparing similarity of electric imaging logging images | |
| Li et al. | A cloud image detection method based on SVM vector machine | |
| CN107909039B (en) | High-resolution remote sensing image earth surface coverage classification method based on parallel algorithm | |
| CN102663391B (en) | Image multifeature extraction and fusion method and system | |
| WO2018023734A1 (en) | Significance testing method for 3d image | |
| CN112766184B (en) | Remote sensing target detection method based on multi-level feature selection convolutional neural network | |
| CN109472267A (en) | Picture similarity alignment algorithm | |
| CN108596975A (en) | A kind of Stereo Matching Algorithm for weak texture region | |
| CN107180436A (en) | A kind of improved KAZE image matching algorithms | |
| CN103714349A (en) | Image recognition method based on color and texture features | |
| Su et al. | Analysis of wavelet packet and statistical textures for object-oriented classification of forest-agriculture ecotones using SPOT 5 imagery | |
| CN108470338A (en) | A kind of water level monitoring method | |
| CN102446356A (en) | Parallel and adaptive matching method for acquiring remote sensing images with homogeneously-distributed matched points | |
| Huang et al. | A multiscale urban complexity index based on 3D wavelet transform for spectral–spatial feature extraction and classification: an evaluation on the 8-channel WorldView-2 imagery | |
| CN109215003B (en) | Image fusion method and device | |
| Wang et al. | A new Gabor based approach for wood recognition | |
| CN108985346A (en) | Fusion low layer pictures feature and showing for CNN feature survey image search method | |
| CN109271864A (en) | A kind of crowd density estimation method based on wavelet transformation and support vector machines | |
| Wan et al. | Remote sensing image segmentation using mean shift method | |
| Xiao et al. | Automatic recognition for striped woven fabric pattern | |
| Deshpande et al. | Image Retrieval with the use of different color spaces and the texture feature | |
| CN112232249A (en) | Remote sensing image change detection method and device based on depth features | |
| KR20110019117A (en) | Semantic based image retrieval method | |
| CN103955936B (en) | Significant object detection method based on stack-typed denoising self-coding machine | |
| CN109859145A (en) | It is a kind of that texture method is gone with respect to the image of total variance based on multistage weight |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150624 |
|
| RJ01 | Rejection of invention patent application after publication |