Crack identification method based on iris recognition principle

Abstract

The application provides a crack identification method based on an iris recognition principle, which comprises the following steps: step 1, inputting a three-dimensional seismic data body; step 2, carrying out seismic data fracture enhancement pretreatment based on an iris recognition related algorithm; step 3, carrying out seismic crack feature point analysis based on iris recognition related parameters; step 4, carrying out seismic crack feature extraction and coding based on an iris recognition algorithm; and step 5, carrying out predicted seismic crack and prior crack feature matching based on iris recognition, and completing the calculation when the matching relationship reaches a correlation threshold requirement. The crack identification method based on the iris recognition principle has the detail recognition advantage of the iris recognition technology, has strong sensitivity to micro crack identification, and has stability and uniqueness of the result of crack prediction through iris feature extraction and matching.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of petroleum exploration technology, in particular to a crack identification method based on iris recognition principle. BACKGROUND

[0002] There are many methods for predicting seismic cracks, such as coherence analysis, variance volume, and ant tracking. These fracture prediction methods have achieved good results, but due to the large calculation scale, the ability to react to details is relatively poor, the matching of the crack prediction results and the priori crack is general, resulting in strong multi-solution of the crack prediction results.

[0003] Iris recognition technology is a kind of human biometric technology. The appearance of human eyes is composed of three parts: sclera, iris and pupil. The sclera is the white part around the eyeball; the center of the eye is the pupil part; the iris is the annular part between the black pupil and the white sclera, which contains many interlaced spots, filaments, coronas, stripes, recesses and other detailed features, and is one of the unique structures of human body. The process of iris recognition technology is generally divided into four steps: iris image acquisition, image preprocessing, feature extraction and feature matching. The iris recognition technology has high accuracy in identifying the details of the target, and can be used in geophysical research for identifying cracks.

[0004] There are mainly eight categories of iris feature recognition methods based on image, phase, singular point, multi-channel texture filtering statistical feature, frequency domain decomposition coefficient, iris signal shape, direction feature and subspace. From the accuracy of iris feature recognition, the methods based on iris phase, singular point and multi-channel texture filtering statistical feature have good effect, and the corresponding iris feature recognition algorithms mainly include two categories: one is the iris texture phase feature recognition algorithm based on two-dimensional Gabor transform proposed by Daugman and its various improved algorithms, and the other is the local zero-crossing detection iris feature extraction algorithm proposed by Boles and its improved algorithm.

[0005] Multi-method, multi-angle and multi-scale seismic crack prediction based on iris recognition is carried out, two kinds of algorithms of three iris recognition methods are used, and the iris recognition parameters reflecting the strong sensitivity of seismic crack characteristics are preliminarily selected. The existing crack prediction method has weak ability to describe the details of the crack, and is affected by the dip angle of the stratum, the prediction result has multi-solution and is mostly low-order fracture, and cannot represent the true form of the crack.

[0006] Chinese patent application CN201911398558.9 discloses a method, apparatus, and system for fluid identification in fractured reservoirs. The method acquires frequency domain data of azimuth common reflection point angle gathers for a target area; it then uses a frequency-dependent inversion model to invert the frequency domain data of the azimuth common reflection point angle gathers to obtain dispersion attribute data of the target area. The dispersion attribute data includes at least background rock dispersion, fracture dispersion, P-wave dispersion, and fracture azimuth. The frequency-dependent inversion model is obtained by extending an anisotropic gradient inversion model to the frequency domain. Finally, it identifies reservoir fluids in the target area based on the dispersion attribute data. Using the various embodiments described in this specification, the accuracy of fluid identification in fractured reservoirs can be significantly improved.

[0007] Chinese patent application CN201611025040.7 discloses a seismic attribute identification system and method for fractures. The method includes: identifying and statistically analyzing fracture information (fracture density in a single well) based on acquired imaging logging data and core analysis data, and generating a single-well fracture model; extracting seismic attribute data of a specified type from the acquired seismic data, and selecting preferred seismic attributes that meet preset requirements for correlation with the reservoir; establishing a training model using the single-well fracture model as input and the preferred seismic attributes as output; training the training model using an artificial intelligence nonlinear neural network; and outputting preferred seismic attributes that meet the set screening conditions when the preferred seismic attributes in the training model meet the screening conditions. Using this application, the system can intelligently, quickly, and accurately distinguish the quality of numerous seismic attributes, effectively identifying well-detected fractures based on seismic attributes, and greatly improving the effectiveness and efficiency of actual operations.

[0008] Chinese patent application number CN201910211333.1 relates to a fracture reservoir prediction method based on seismic frequency division coherence properties, belonging to the field of oil and gas geophysical reservoir prediction, aiming to provide a fracture reservoir analysis technology that can accurately identify fractures of different scales and predict their distribution patterns. The method includes the following steps: ① Extracting frequency-segregated coherence attributes of different frequencies in the target stratum and enhancing them; ② Calculating the average and variance of the four vertices of each grid for the gridded frequency-segregated coherence attribute data of the target stratum; ③ Statistically calculating the range of variance values, taking the median of the range, and calculating the average of all grids corresponding to that value. Based on the statistical results, setting the threshold for dividing into fracture and non-fracture units, thus quickly and effectively obtaining the distribution of fractures; ④ For grids that are fracture units in the frequency-segregated coherence attribute data of the target stratum at two different frequencies, assigning the average value of the vertex of the nearest non-fracture unit to the four vertices of the grid at the higher frequency, which can effectively remove the overlapping part of the fracture prediction results of the higher frequency with the fracture prediction results of the lower frequency; ⑤ Using the frequency-segregated coherence attribute data of different frequencies in the target stratum processed by the above steps, realizing fracture reservoir prediction through planar mapping. This invention, based on the frequency-segregated coherence attribute data of the target stratum, divides into fracture and non-fracture units, compares the distribution of fracture units in data of different frequencies, removes overlapping parts, and completes the accurate identification and accurate prediction of the distribution pattern of fractures at different scales.

[0009] The existing technologies described above are quite different from the present invention and have failed to solve the technical problem we want to solve. Therefore, we have invented a new crack recognition method based on the principle of iris recognition. Summary of the Invention

[0010] The purpose of this invention is to provide a crack recognition method based on the principle of iris recognition that leverages the detail recognition advantages of iris recognition technology and has strong sensitivity to the recognition of minute cracks.

[0011] The objective of this invention can be achieved through the following technical measures: a crack recognition method based on iris recognition principles, comprising:

[0012] Step 1: Input the 3D seismic data volume;

[0013] Step 2: Perform fault enhancement preprocessing on seismic data based on iris recognition-related algorithms;

[0014] Step 3: Analyze earthquake crack feature points based on iris recognition parameters;

[0015] Step 4: Extract and encode earthquake crack features based on iris recognition algorithm;

[0016] Step 5: Based on iris recognition, perform feature matching between predicted earthquake cracks and pre-existing cracks. The calculation is completed when the matching relationship reaches the correlation threshold.

[0017] The objective of this invention can also be achieved through the following technical measures:

[0018] In step 1, the input 3D seismic data volume is a standard segy format file.

[0019] The crack identification method based on iris recognition also includes, after step 1, performing an adaptability analysis of seismic crack prediction based on iris recognition for the three-dimensional seismic data volume; and performing an adaptability analysis of crack prediction for the original three-dimensional seismic data based on seismic data quality and iris recognition features.

[0020] In step 2, seismic data is used to perform seismic data fracture enhancement preprocessing based on iris recognition-related algorithms, so that the seismic data can reflect more fracture information.

[0021] In step 3, the correspondence between the relevant parameters of iris recognition, such as texture, spots, filaments, coronal patterns, stripes, and crypts, and the characteristics of earthquake cracks is analyzed so that the relevant iris recognition algorithms can be applied to earthquake crack prediction.

[0022] In step 4, seismic crack features are extracted and encoded based on iris recognition algorithms such as Gabor transform and local zero-crossing detection.

[0023] In step 4, a Gabor filter is applied to the two-dimensional image space to extract local texture phase information. The formula for the two-dimensional Gabor filter is as follows:

[0024] G(x,y)=exp(-π[(x-x0) 2 / α 2 +(y-y0) 2 / β 2 ]-2πi[μ(x-x0)+ν(y-y0)]) (1)

[0025] Where (x, y) represents the location of local texture in the image, (α, β) are the effective width and length of the Gaussian window, and (μ, ν) defines the spatial frequency ω = (μ0 + ν) / (μ0 + ν). 2 ) 1 / 2 The orientation angle θ = arctan(μ / ν) is used. By adjusting a series of parameters (x0, y0; μ0, ν0; α, β), different forms of filters can be obtained, where (x0, y0) represents the horizontal and vertical displacement of the image. This reflects the multi-scale and directional characteristics of the Gabor filter. The two-dimensional Fourier transform of the Gabor filter has the same functional form:

[0026] F(μ,ν)=exp(-π[(μ-μ0) 2 α 2 +(ν-ν0) 2 β 2 ]-2πi[x(μ-μ0)+y(ν-ν0)]) (2).

[0027] In step 5, if the matching relationship fails to meet the relevance threshold, return to step 5.

[0028] In step 5, the Hamming distance method is used to match the features of the predicted earthquake cracks and the prophetic cracks. If the two match well, it indicates that the prediction of cracks is highly reliable and the relevant calculation parameters are reasonably selected. Otherwise, return to step 5, optimize the relevant parameters, and re-extract and encode the earthquake crack features.

[0029] In step 5, the predicted fractures include core-described fractures, imaging logging fractures, and oil and water well production dynamics data. Only when the fractures predicted by seismic analysis match these known fractures can the predicted fractures be considered to have high reliability. The feature matching method between seismic fractures and predicted fractures uses Hamming distance as a classifier. The Hamming distance is calculated by statistically analyzing the proportion of the number of different corresponding bits on two templates relative to the total number of bits in the template. The smaller the distance, the better the two templates match.

[0030] In step 5, the features of the iris image are finally encoded into a 2048-bit vector. Vector A represents the iris feature vector to be identified, and vector B represents the iris feature vector in the iris feature database. A and B are denoted as:

[0031] A = (A1, A2, ..., A 2048 B = (B1, B2, ..., B) 2048 )

[0032] Where A i B i (i = 1, 2, ..., 2048) is either 1 or 0. The standard Hamming distance is defined as:

[0033]

[0034] Where A and B (i = 1, 2, ..., N) are the i-th codewords of the image to be recognized and the template image, respectively. It is an XOR operator. The result is 1 when the corresponding bits of A and B (i = 1, 2, ..., N) are different, and 0 when they are the same.

[0035] The crack identification method based on iris recognition principle also includes, after step 5, conducting a comprehensive evaluation of cracks and predicting the planar distribution of cracks using the data volume generated in step 5.

[0036] The crack identification method based on iris recognition principle in this invention, and the earthquake crack prediction system based on iris recognition principle, employ advanced iris recognition algorithms to predict cracks in seismic data. This leverages the detail-oriented advantages of iris recognition technology, exhibiting strong sensitivity to even minute cracks. Iris feature extraction and matching ensure the stability and uniqueness of the crack prediction results. Attached Figure Description

[0037] Figure 1 This is a flowchart of a specific embodiment of the crack recognition method based on the iris recognition principle of the present invention;

[0038] Figure 2 This is a preprocessed image of seismic data fracture enhancement based on an iris recognition-related algorithm in a specific embodiment of the present invention;

[0039] Figure 3 This is a profile of earthquake crack prediction based on the iris recognition principle in a specific embodiment of the present invention.

[0040] Figure 4 This is a crack prediction profile based on iris recognition principle from actual seismic data in a specific embodiment of the present invention. Detailed Implementation

[0041] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0042] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments of the present invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, and / or combinations thereof.

[0043] The following are several specific embodiments of the application of the present invention.

[0044] Example 1

[0045] In a specific embodiment 1 of the present invention, such as Figure 1 As shown, Figure 1 This is a flowchart of the crack recognition method based on iris recognition principle according to the present invention. The crack recognition method based on iris recognition principle includes:

[0046] Step 1: Input a 3D seismic data volume for a specific block;

[0047] Step 2: Fault enhancement preprocessing of seismic data based on iris recognition algorithms; this preprocessing serves as input for subsequent steps and improves fracture identification accuracy. The fault enhancement calculation results show that the fault boundaries are enhanced compared to the original seismic data. For example... Figure 2 .

[0048] Step 3: Seismic crack feature point analysis based on iris recognition parameters; analyze the correspondence between iris recognition parameters such as texture, spots, filaments, crowns, stripes, and crypts and seismic crack features, so as to facilitate the application of iris recognition algorithms to seismic crack prediction. Forward modeling based on iris recognition principles shows good results in micro-crack identification. For example... Figure 3 .

[0049] Step 4: Seismic crack feature extraction and encoding based on iris recognition algorithms such as Gabor transform and local zero-crossing detection; various iris recognition algorithms, including Gabor transform and local zero-crossing detection, are applied for seismic crack feature extraction and encoding. For example, Gabor transform:

[0050] The idea for the Gabor filter was originally proposed by Gabor. A Gabor filter can be viewed as a windowed Fourier transform, exhibiting good performance in both the time and frequency domains. Research has found that the Gabor operator's frequency and direction representations are similar to those of the human visual system, both decomposing the image and treating the entire image as a weighted sum of multiple filtered images with time-frequency domain characteristics. This makes it highly suitable for representing texture. Daugman et al. discovered this property and applied the Gabor filter to two-dimensional image space to extract local texture phase information. The formula for a two-dimensional Gabor filter is as follows:

[0051] G(x,y)=exp(-π[(x-x0) 2 / α 2 +(y-y0) 2 / β 2 ]-2πi[μ(x-x0)+ν(y-y0)]) (1)

[0052] Where (x, y) represents the location of local texture in the image, (α, β) are the effective width and length of the Gaussian window, and (μ, ν) defines the spatial frequency ω = (μ0 + ν) / (μ0 + ν). 2 ) 1 / 2The orientation angle θ = arctan(μ / ν) is used. By adjusting a series of parameters (x0, y0; μ0, ν0; α, β), different forms of filters can be obtained, where (x0, y0) represents the horizontal and vertical displacement of the image. This reflects the multi-scale and directional characteristics of the Gabor filter. The two-dimensional Fourier transform of the Gabor filter has the same functional form:

[0053] F(μ,ν)=exp(-π[(μ-μ0) 2 α 2 +(ν-ν0) 2 β 2 ]-2πi[x(μ-μ0)+y(ν-ν0)]) (2).

[0054] Gabor filters are suitable for texture segmentation because they have the following characteristics:

[0055] (l) It has adjustable direction and bandwidth;

[0056] (2) It has an adjustable center frequency;

[0057] (3) It can achieve the joint optimal resolution of the spatial domain and the frequency domain at the same time.

[0058] Therefore, 2D Gabor transform is particularly suitable for analyzing textures that contain a lot of specific resolution and orientation features.

[0059] Step 5: Match the predicted earthquake cracks and the pre-existing crack features based on iris recognition. If the matching relationship meets the correlation threshold, the calculation is complete; otherwise, return to step 5. Figure 4 As shown, the crack morphology can be clearly seen on the crack prediction profile of iris recognition, and the prediction effect is good.

[0060] Based on iris recognition algorithms, the matching of earthquake fractures and known fractures is performed, and the calculation is completed when the matching relationship reaches the correlation threshold. Known fractures include fractures described in core samples, fractures from imaging logging, and dynamic data from oil and water well production. Only when the earthquake-predicted fracture matches these known fractures can the predicted fracture be considered to have high reliability. The feature matching method for earthquake fractures and known fractures generally uses Hamming distance as a classifier. Hamming distance is calculated by statistically analyzing the proportion of different bits in corresponding codes between two templates out of the total number of bits in the template. The smaller the distance, the better the match between the two templates. Hamming distance is a relatively good classification method for solving template matching problems.

[0061] The features of an iris image are ultimately encoded into a 2048-bit vector. We use vector A to represent the iris feature vector to be identified, and vector B to represent the iris feature vector in the iris feature database. A and B are denoted as:

[0062] A = (A1, A2, ..., A 2048 B = (B1, B2, ..., B) 2048 )

[0063] Where A i B i (i = 1, 2, ..., 2048) is either 1 or 0. The standard Hamming distance is defined as:

[0064]

[0065] Where A and B (i = 1, 2, ..., N) are the i-th codewords of the image to be recognized and the template image, respectively. It is an XOR operator. The result is 1 when the corresponding bits of A and B (i = 1, 2, ..., N) are different, and 0 when they are the same.

[0066] Example 2

[0067] In a specific embodiment 2 of the present invention, the crack recognition method based on the iris recognition principle specifically includes:

[0068] In step 1, input the 3D seismic data volume; the input 3D seismic data volume is a standard segy format file.

[0069] In step 2, an adaptability analysis of seismic crack prediction based on iris recognition principle is performed on the 3D seismic data volume; and an adaptability analysis of crack prediction based on seismic data quality and iris recognition features is performed on the original 3D seismic data.

[0070] In step 3, seismic data fracture enhancement preprocessing based on iris recognition-related algorithms is performed. Using seismic data, seismic data fracture enhancement preprocessing based on iris recognition-related algorithms is performed to make the seismic data reflect more fracture information.

[0071] In step 4, the seismic crack feature points are analyzed based on iris recognition-related parameters; the correspondence between crack features and iris recognition-related parameters is established based on the seismic crack feature point analysis based on iris recognition-related parameters.

[0072] In step 5, seismic crack features are extracted and encoded based on iris recognition algorithms such as Gabor transform and local zero-crossing detection; seismic crack features are extracted and encoded using iris recognition algorithms such as Gabor transform and local zero-crossing detection, and crack data volume is calculated.

[0073] In step 6, the predicted seismic fractures and the known fracture features are matched based on iris recognition. If the matching relationship meets the correlation threshold, the calculation is completed; otherwise, return to step 5. Hamming distance and other methods are used to match the predicted seismic fractures with the features of known fractures from core samples and well logging. If the match is good, the predicted fractures are considered to have high reliability and the relevant calculation parameters are reasonably selected. Otherwise, return to step 5, optimize the relevant parameters, and re-extract and encode the seismic fracture features.

[0074] Example 3

[0075] In a specific embodiment 3 of the present invention, the crack recognition method based on the iris recognition principle specifically includes:

[0076] In step 101, input the 3D seismic data volume, i.e., a standard seismic format file. The process then proceeds to step 102.

[0077] In step 102, the adaptive analysis process for earthquake crack prediction based on iris recognition principle is carried out for the Ping-Nan 3D seismic data volume, and then proceeds to step 103.

[0078] In step 103, the seismic data fracture enhancement preprocessing based on iris recognition related algorithms is performed, and the process proceeds to step 104.

[0079] In step 104, the seismic crack feature point analysis is performed based on iris recognition-related parameters, and the process proceeds to step 105.

[0080] In step 105, the seismic crack features are extracted and encoded based on iris recognition algorithms such as Gabor transform and local zero-crossing detection, and the process proceeds to step 106.

[0081] In step 106, the matching degree between the predicted earthquake cracks and the prophetic cracks based on iris recognition is determined. When the matching relationship reaches the correlation threshold, the process proceeds to step 107. If the search parameter requirements are not met, the process returns to step 105 to reset the parameters.

[0082] In step 107, a comprehensive evaluation of the cracks is carried out using the data volume generated in step 105, and the planar distribution of the cracks is predicted.

[0083] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0084] Except for the technical features described in the specification, all other technologies are known to those skilled in the art.

Claims

1. A crack recognition method based on iris recognition principle, characterized in that, This crack recognition method based on iris recognition principles includes: Step 1: Input the 3D seismic data volume; Step 2: Perform fault enhancement preprocessing on seismic data based on iris recognition-related algorithms; Step 3: Analyze earthquake crack feature points based on iris recognition parameters; Step 4: Extract and encode earthquake crack features based on iris recognition algorithm; Step 5: Based on iris recognition, perform feature matching between predicted earthquake cracks and pre-existing cracks. The calculation is completed when the matching relationship reaches the correlation threshold.

2. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, In step 1, the input 3D seismic data volume is a standard seismic format file.

3. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, The crack identification method based on iris recognition principle also includes, after step 1, performing an adaptability analysis of seismic crack prediction based on iris recognition principle on the three-dimensional seismic data volume. We conduct crack prediction adaptability analysis on raw 3D seismic data based on seismic data quality and iris recognition features.

4. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, In step 2, seismic data is used to perform seismic data fracture enhancement preprocessing based on iris recognition-related algorithms, so that the seismic data can reflect more fracture information.

5. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, In step 3, the correspondence between the relevant parameters of iris recognition, such as texture, spots, filaments, coronal patterns, stripes, and crypts, and the characteristics of earthquake cracks is analyzed so that the relevant iris recognition algorithms can be applied to earthquake crack prediction.

6. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, In step 4, seismic crack features are extracted and encoded based on iris recognition algorithms such as Gabor transform and local zero-crossing detection.

7. The crack recognition method based on iris recognition principle according to claim 6, characterized in that, In step 4, a Gabor filter is applied to the two-dimensional image space to extract local texture phase information. The formula for the two-dimensional Gabor filter is as follows: G(x,y)=exp(-π[(x-x0) 2 / a 2 +(y-y0) 2 / b 2 ]-2πi[μ(x-x0)+ν(y-y0)]) (1) Where (x, y) represents the location of local texture in the image, (α, β) are the effective width and length of the Gaussian window, and (μ, ν) defines the spatial frequency ω = (μ0 + ν) / (μ0 + ν). 2 ) 1 / 2 The orientation angle θ = arctan(μ / ν) is used. By adjusting a series of parameters (x0, y0; μ0, ν0; α, β), different forms of filters can be obtained, where (x0, y0) represents the horizontal and vertical displacement of the image. This reflects the multi-scale and directional characteristics of the Gabor filter. The two-dimensional Fourier transform of the Gabor filter has the same functional form: F(μ,ν)=exp(-π[(μ-μ0) 2 a 2 +(n-n0) 2 b 2 ]-2πi[x(μ-μ0)+y(ν-ν0)]) (2).

8. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, In step 5, the Hamming distance method is used to match the features of the predicted earthquake cracks and the prophetic cracks. If the two match well, it indicates that the predicted cracks are highly reliable and the relevant calculation parameters are reasonably selected. Otherwise, return to step 3, optimize the relevant parameters, and re-extract and encode the earthquake crack features.

9. The crack recognition method based on iris recognition principle according to claim 8, characterized in that, In step 5, the predicted fractures include core-described fractures, imaging logging fractures, and oil and water well production dynamics data. Only when the fractures predicted by seismic analysis match these known fractures can the predicted fractures be considered to have high reliability. The feature matching method between seismic fractures and predicted fractures uses Hamming distance as a classifier. The Hamming distance is calculated by statistically analyzing the proportion of the number of different corresponding bits on two templates relative to the total number of bits in the template. The smaller the distance, the better the two templates match.

10. The crack recognition method based on iris recognition principle according to claim 9, characterized in that, In step 5, the features of the iris image are finally encoded into a 2048-bit vector. Vector A represents the iris feature vector to be identified, and vector B represents the iris feature vector in the iris feature database. A and B are denoted as: A=(A1,A2,...,A 2048 ),B=(B1,B2,...,B 2048 ) Where A i B i It can be either 1 or 0, where i = 1, 2, ..., 2048. The standard Hamming distance is defined as: Where A i B i Let i be the codeword of the image to be recognized and the template image. It is the XOR operator, when A i B i The result is either 1 or 0 when the corresponding bits are not the same, where i = 1, 2, ..., N.

11. The crack recognition method based on iris recognition principle according to claim 1, characterized in that, The crack identification method based on iris recognition principle also includes, after step 5, conducting a comprehensive evaluation of cracks and predicting the planar distribution of cracks using the data volume generated in step 5.

Images