WO2023273017A1 - 测井图像清晰度的识别方法、装置、介质及电子设备 - Google Patents

测井图像清晰度的识别方法、装置、介质及电子设备 Download PDF

Info

Publication number
WO2023273017A1
WO2023273017A1 PCT/CN2021/124746 CN2021124746W WO2023273017A1 WO 2023273017 A1 WO2023273017 A1 WO 2023273017A1 CN 2021124746 W CN2021124746 W CN 2021124746W WO 2023273017 A1 WO2023273017 A1 WO 2023273017A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
sharpness
logging
target
vector
Prior art date
Application number
PCT/CN2021/124746
Other languages
English (en)
French (fr)
Inventor
黄琳
郭书生
侯振学
范川
徐大年
盛达
龙威
张国华
成家杰
李东
张璋
尹璐
张朝华
张贵斌
Original Assignee
中海油田服务股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中海油田服务股份有限公司 filed Critical 中海油田服务股份有限公司
Priority to EP21947944.1A priority Critical patent/EP4365755A1/en
Priority to US18/574,234 priority patent/US20240143651A1/en
Publication of WO2023273017A1 publication Critical patent/WO2023273017A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • 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
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Definitions

  • the present disclosure relates to the technical field of image clarity identification, and in particular to a method, device, medium and electronic equipment for identification of well logging image clarity.
  • the sharpness of its imaging reflects the focus state of the system.
  • the image is clearer, with rich information such as contour details, and different feature information is highlighted in the spatial domain or frequency domain.
  • the gray value of the image is used as the main feature information; in the frequency domain, the feature information is high-frequency components.
  • the image focus evaluation function (Focus Value) is usually used to measure whether the image is in focus.
  • the image focus state is relatively good, the image is clear, and the feature values of the adjacent pixels of the image, such as gray value, contrast, etc., change drastically in the spatial domain.
  • the image is out of focus, many details are lost, making the object image blurred.
  • different resolution recognition methods have differences in processing different blurred images, and there are conditional restrictions on the pictures to be recognized.
  • the main focus is on the uniform arrangement of points in the picture. If you compare a picture with only black and white bars with a picture that is blurred but has many black points on the picture, then through the entropy function this The clear picture obtained by the recognition method is a fuzzy picture, which is obviously contrary to the facts, and the correct recognition result cannot be obtained.
  • the purpose of the present disclosure is to provide a method, device, medium and electronic equipment for identification of well logging image clarity.
  • a method for identifying clarity of well logging images comprising:
  • the actual sharpness information is the actual sharpness sorting number or the actual normalized sharpness
  • the target weight corresponding to each target image clarity determination algorithm and each target image clarity determination algorithm are used to determine the clarity of the target logging image.
  • each target image sharpness determination algorithm determines the target weight corresponding to each target image sharpness determination algorithm, including:
  • a resolution vector corresponding to each logging image is established, and the resolution vector includes a normalized resolution corresponding to each target image resolution determination algorithm;
  • the weight vector includes the weight corresponding to each target image sharpness determination algorithm
  • a plurality of training units are constructed by using the weight vector and the sharpness vector corresponding to each well logging image, and the training unit includes the weight vector and the sharpness vector corresponding to the two well logging images respectively;
  • the weight adjustment step includes: for each training unit, comparing the elements in the resolution vector corresponding to each logging image in the training unit, and adjusting the weight of the weight vector in the training unit according to the comparison result;
  • the training unit includes a first sharpness vector and a second sharpness vector, for each training unit, compare the elements in the sharpness vector corresponding to each logging image in the training unit, and adjust the training according to the comparison result
  • the weights of the weight vector in the cell consisting of:
  • the number of elements in the first definition vector is greater than the corresponding elements in the second definition vector and exceeds half of the total number of elements in the first definition vector or the second definition vector, then increase the weight of each target in the weight vector or reduce the weight vector Each non-target weight in , until the sum of the product of the weight vector and the corresponding element in the first definition vector is greater than the sum of the product of the weight vector and the corresponding element in the second definition vector, wherein, greater than the corresponding element in the second definition vector
  • the elements in the first sharpness vector correspond to the target image sharpness determination algorithm corresponding to the target weight, and the non-target weights are weights in the weight vector except the target weights.
  • the actual sharpness information is the sequence number of the actual sharpness, and it is determined whether the final sharpness corresponding to each logging image matches the actual sharpness information corresponding to each logging image, including:
  • the sorting number corresponding to the logging image is consistent with the actual resolution sorting number corresponding to the logging image, then determine the final resolution corresponding to each logging image and the actual resolution corresponding to each logging image.
  • the sharpness information matches, otherwise, it is determined that the final sharpness corresponding to each logging image does not match the actual sharpness information corresponding to each logging image.
  • the method further includes:
  • multiple target image sharpness determination algorithms are selected from the multiple image sharpness determination algorithms.
  • a well logging image sample library comprising a plurality of well logging images, including:
  • the logging image sample library is established by using the unrepaired logging images and the repaired logging images.
  • a plurality of target image sharpness determination algorithms include one or more of the following algorithms: Brenner algorithm, Tenengrad algorithm, Laplacian algorithm, SMD algorithm, SMD2 algorithm, variance algorithm, energy algorithm, Vollath algorithm .
  • an identification device for logging image clarity comprising:
  • An establishment module configured to establish a well logging image sample library including a plurality of well logging images
  • the first acquisition module is configured to acquire the actual sharpness information corresponding to each logging image, where the actual sharpness information is the sorting number of the actual sharpness or the actual normalized sharpness;
  • the second acquiring module is configured to acquire multiple resolutions corresponding to each logging image, and the multiple resolutions are generated by calculating the resolutions of the logging images respectively by multiple target image resolution determination algorithms;
  • the target weight determination module is configured to determine the target weight corresponding to each target image clarity determination algorithm according to multiple sharpness and actual sharpness information corresponding to each logging image;
  • the sharpness determination module is configured to determine the sharpness of the target logging image by using the target weight corresponding to each target image sharpness determination algorithm and each target image sharpness determination algorithm.
  • an electronic device includes: a processor;
  • the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the following operations are implemented:
  • the actual sharpness information is the actual sharpness sorting number or the actual normalized sharpness
  • the target weight corresponding to each target image clarity determination algorithm and each target image clarity determination algorithm are used to determine the clarity of the target logging image.
  • a non-volatile computer-readable storage medium wherein at least one executable instruction is stored in the non-volatile computer-readable storage medium, and the executable instruction causes a processor to perform the following operations :
  • the actual sharpness information is the actual sharpness sorting number or the actual normalized sharpness
  • the target weight corresponding to each target image clarity determination algorithm and each target image clarity determination algorithm are used to determine the clarity of the target logging image.
  • a computer program product including the calculation program stored on the above-mentioned non-volatile computer-readable storage medium.
  • the method includes the following steps: establishing a well logging image sample library including multiple well logging images; obtaining the actual Sharpness information, the actual sharpness information is the actual sharpness sorting number or the actual normalized sharpness; multiple sharpnesses corresponding to each logging image are obtained, and the multiple sharpnesses are determined by multiple target image sharpness determination algorithms respectively
  • the definition calculation is performed on the logging image to generate; according to the plurality of definitions corresponding to each logging image and the actual definition information, determine the target weight corresponding to each target image definition algorithm; use each target image definition to determine The target weight corresponding to the algorithm and the clarity of each target image are determined by the algorithm to determine the clarity of the target logging image.
  • the target weights corresponding to each target image definition determination algorithm are determined according to the multiple resolutions and actual resolution information corresponding to each logging image, and then the target weights and target weights corresponding to each target image resolution determination algorithm are used.
  • Each target image clarity determination algorithm determines the clarity of the target logging image.
  • Fig. 1 is a schematic diagram of the system architecture of a method for identifying the definition of well logging images according to an exemplary embodiment
  • Fig. 2 is a flow chart of a method for identifying the clarity of well logging images according to an exemplary embodiment
  • FIG. 3 is a flowchart showing the details of step 210 according to an embodiment shown in the embodiment of FIG. 2;
  • Fig. 4 is a block diagram of an identification device for logging image clarity according to an exemplary embodiment
  • Fig. 5 is a block diagram showing an example of an electronic device for realizing the identification method of the above-mentioned logging image clarity according to an exemplary embodiment
  • Fig. 6 is a computer program product showing a method for realizing the above-mentioned recognition method of logging image clarity according to an exemplary embodiment.
  • the present disclosure firstly provides a method for identifying the clarity of well logging images.
  • Well logging images are image data generated by well logging techniques, for example, well logging images can be generated by acoustoelectric imaging techniques.
  • the identification of well logging image clarity refers to determining the corresponding clarity according to the well logging image. Different well logging images generally have different clarity; when the focus of a well logging image is poor, the clarity of the well logging image lower.
  • the implementation terminal of the present disclosure can be any device with computing, processing and communication functions, which can be connected to external devices for receiving or sending data, specifically portable mobile devices, such as smart phones, tablet computers, notebook computers, PDA (Personal Digital Assistant), etc., can also be fixed devices, such as computer equipment, field terminals, desktop computers, servers, workstations, etc., or a collection of multiple devices, such as the physical infrastructure of cloud computing or server clusters .
  • portable mobile devices such as smart phones, tablet computers, notebook computers, PDA (Personal Digital Assistant), etc.
  • PDA Personal Digital Assistant
  • the implementation terminal of the present disclosure may be a server or a physical infrastructure of cloud computing.
  • Fig. 1 is a schematic diagram of a system architecture of a method for identifying clarity of a logging image according to an exemplary embodiment.
  • the system architecture includes a personal computer 110, a server 120 and a database 130, and between the personal computer 110 and the server 120, and between the database 130 and the server 120, are connected by a communication link, which can be used to send or receive data .
  • the server 120 is the implementation terminal in this embodiment, the database 130 stores well logging images and corresponding actual resolution information, and the personal computer 110 stores well logging images to be identified.
  • a process may be as follows: the server 120 acquires well logging images and corresponding actual sharpness information from the database 130 Then use the image clarity determination algorithm and determine each target image clarity determination algorithm and corresponding target weight based on the logging image and the corresponding actual clarity information; finally, the server 120 obtains the measurement to be identified from the personal computer 110 After the well image is obtained, the clarity of the well logging image to be recognized is calculated by using the target image clarity determination algorithm and the corresponding target weight.
  • Fig. 2 is a flow chart of a method for identifying clarity of well logging images according to an exemplary embodiment.
  • the method for identifying the clarity of the logging image provided in this embodiment can be executed by the server, as shown in Figure 2, including the following steps:
  • Step 210 establishing a well logging image sample library including several well logging images.
  • step 210 includes the following steps:
  • Step 211 acquiring unrepaired well logging images and repaired well logging images corresponding to each unrepaired well logging image.
  • Step 212 using the unrepaired well logging image and the repaired well logging image to establish a well logging image sample library.
  • the well logging image sample library includes both unrepaired well logging images and repaired well logging images, thus enriching the number of well logging images in the well logging image sample library, thus providing data support for accurately identifying the clarity of well logging images.
  • Step 220 acquiring actual sharpness information corresponding to each logging image.
  • the actual sharpness information is the sorting number of the actual sharpness or the actual normalized sharpness.
  • the actual sharpness sorting number is the serial number marked after sorting each logging image according to the order of sharpness from large to small or from small to large after manually distinguishing the clarity of each logging image.
  • the actual normalized sharpness is the value obtained by manually quantizing each logging image in the same quantization interval, and the quantization interval is usually [0,1].
  • Step 230 acquiring multiple resolutions corresponding to each logging image.
  • the multiple resolutions are generated by calculating the resolutions of the logging images respectively by multiple target image resolution determination algorithms.
  • the multiple target image sharpness determination algorithms include one or more of the following algorithms: Brenner algorithm, Tenengrad algorithm, Laplacian algorithm, SMD algorithm, SMD2 algorithm, variance algorithm, energy algorithm, Vollath algorithm.
  • the method before acquiring the plurality of resolutions corresponding to each logging image, the method further includes:
  • multiple target image sharpness determination algorithms are selected from the multiple image sharpness determination algorithms.
  • the number of target image clarity determination algorithms is smaller than the number of image clarity determination algorithms, for example, the number of target image clarity determination algorithms may be 5, and the number of image clarity determination algorithms may be 8, for example, multiple target image clarity
  • the algorithm for determining the degree may be the eight algorithms in the above-mentioned embodiments.
  • multiple target image sharpness determination algorithms are selected from multiple image sharpness determination algorithms, including:
  • each image definition determination algorithm determines the number of resolution sequence numbers that are consistent with the actual definition sequence numbers in the definition sequence numbers of each logging image corresponding to the image definition determination algorithm and the image definition determination algorithm.
  • the ratio corresponding to each image definition determination algorithm at least one image definition determination algorithm among the plurality of image definition determination algorithms is eliminated to obtain a plurality of target image definition determination algorithms, wherein the eliminated image definition determination algorithm corresponds to The ratio of is smaller than the ratio corresponding to the target image sharpness determination algorithm.
  • the corresponding resolution of each logging image can be determined by using the same image resolution determination algorithm, therefore, an image resolution determination algorithm has a corresponding resolution ranking, and correspondingly has a resolution ranking sequence number of each logging image; Therefore, the well logging image has a corresponding resolution sorting number, and also has a corresponding actual sharpness sorting number. Compared with the sharpness sorting number corresponding to a well logging image and the actual sharpness sorting number corresponding to the logging image, two can be the same or different.
  • the ratio reflects the consistency between the sharpness ranking calculated by an image sharpness determination algorithm for each log image and the actual sharpness ranking corresponding to each log image.
  • Step 240 according to the plurality of sharpness and actual sharpness information corresponding to each logging image, determine the target weight corresponding to each target image sharpness determination algorithm.
  • each target image sharpness determination algorithm including:
  • a resolution vector corresponding to each logging image is established, and the resolution vector includes a normalized resolution corresponding to each target image resolution determination algorithm;
  • the weight vector includes the weight corresponding to each target image sharpness determination algorithm
  • a plurality of training units are constructed by using the weight vector and the sharpness vector corresponding to each well logging image, and the training unit includes the weight vector and the sharpness vector corresponding to the two well logging images respectively;
  • the weight adjustment step includes: for each training unit, comparing the elements in the resolution vector corresponding to each logging image in the training unit, and adjusting the weight of the weight vector in the training unit according to the comparison result;
  • the definition corresponding to a target image definition determination algorithm is normalized in the following way:
  • the training unit includes a first sharpness vector and a second sharpness vector, and for each training unit, the elements in the sharpness vector corresponding to each logging image in the training unit are compared, and according to the comparison result Adjust the weights of the weight vector in the training unit, including:
  • the number of elements in the first definition vector is greater than the corresponding elements in the second definition vector and exceeds half of the total number of elements in the first definition vector or the second definition vector, then increase the weight of each target in the weight vector or reduce the weight vector Each non-target weight in , until the sum of the product of the weight vector and the corresponding element in the first definition vector is greater than the sum of the product of the weight vector and the corresponding element in the second definition vector, wherein, greater than the corresponding element in the second definition vector
  • the elements in the first sharpness vector correspond to the target image sharpness determination algorithm corresponding to the target weight, and the non-target weights are weights in the weight vector except the target weights.
  • the actual sharpness information is the sequence number of the actual sharpness, and it is determined whether the final sharpness corresponding to each logging image matches the actual sharpness information corresponding to each logging image, including:
  • the sorting number corresponding to the logging image is consistent with the actual resolution sorting number corresponding to the logging image, then determine the final resolution corresponding to each logging image and the actual resolution corresponding to each logging image.
  • the sharpness information matches, otherwise, it is determined that the final sharpness corresponding to each logging image does not match the actual sharpness information corresponding to each logging image.
  • the actual sharpness information is the actual normalized sharpness
  • determining whether the final sharpness corresponding to each logging image matches the actual sharpness information corresponding to each logging image includes:
  • the variance is less than the predetermined variance threshold, it is determined that the final resolution corresponding to each logging image matches the actual resolution information corresponding to each logging image; otherwise, determine that the final resolution corresponding to each logging image matches the corresponding The actual sharpness information does not match.
  • a resolution matrix X ⁇ X j ⁇ , j ⁇ [1,5], where X j is the normalized value of each logging image by the jth algorithm
  • the vector composed of the normalized sharpness is the column vector of the sharpness matrix X; the sharpness matrix X also includes a row vector, and a row vector includes the normalized sharpness of each algorithm for the same logging image, such as row Vectors can be:
  • X i ⁇ x i1 , x i2 , x i3 , x i4 , x i5 ⁇ , i ⁇ [1,N],
  • Xi is the normalized resolution of each algorithm on the i -th logging image
  • N is the number of logging images.
  • the sharpness ranking of each logging image reflects the sharpness change trend. If the final sharpness change trend of each logging image calculated by using the final weight vector is consistent with the actual sharpness change trend, it means that the final weight vector can be used for the final Calculate the sharpness of the well logging image, otherwise continue to perform the step of adjusting the weights, and finally obtain the weights corresponding to each algorithm that can be used to accurately calculate the sharpness of the well logging image.
  • Step 250 using the target weight corresponding to each target image clarity determination algorithm and each target image clarity determination algorithm to determine the clarity of the target logging image.
  • the target logging image is the logging image to be identified. Firstly, each target image resolution algorithm is used to identify the resolution of the target logging image respectively, and the corresponding resolutions of each target image resolution algorithm are normalized. Then, each normalized sharpness is multiplied by the target weight of the corresponding target image sharpness determination algorithm, and then the products are added together to finally obtain the sharpness of the target logging image.
  • the identification method of the definition of the well logging image provided by the embodiment in Fig. 2, firstly, according to the plurality of sharpness corresponding to each logging image and the actual sharpness information, determine the resolution corresponding to each target image sharpness determination algorithm. Target weight, and then use the target weight corresponding to each target image clarity determination algorithm and each target image clarity determination algorithm to determine the clarity of the target logging image.
  • the present disclosure also provides a device for identifying clarity of logging images, and the following are device embodiments of the present disclosure.
  • Fig. 4 is a block diagram of a device for identifying clarity of well logging images according to an exemplary embodiment. As shown in Figure 4, the device 400 includes:
  • Establishing module 410 configured to establish a well logging image sample library including several well logging images
  • the first acquisition module 420 is configured to acquire the actual sharpness information corresponding to each logging image, where the actual sharpness information is the sorting number of the actual sharpness or the actual normalized sharpness;
  • the second acquiring module 430 is configured to acquire multiple resolutions corresponding to each logging image, and the multiple resolutions are generated by calculating the resolutions of the logging images respectively by a plurality of target image resolution determination algorithms;
  • the target weight determination module 440 is configured to determine the target weight corresponding to each target image resolution determination algorithm according to multiple resolutions corresponding to each logging image and actual resolution information;
  • the sharpness determination module 450 is configured to determine the sharpness of the target logging image by using the target weight corresponding to each target image sharpness determination algorithm and each target image sharpness determination algorithm.
  • an electronic device capable of implementing the above method is also provided.
  • FIG. 5 An electronic device 500 according to this embodiment of the present invention is described below with reference to FIG. 5 .
  • the electronic device 500 shown in FIG. 5 is only an example, and should not limit the functions and scope of use of this embodiment of the present invention.
  • electronic device 500 takes the form of a general-purpose computing device.
  • Components of the electronic device 500 may include but not limited to: at least one processing unit 510 , at least one storage unit 520 , and a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510 ).
  • the storage unit stores program codes, and the program codes can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present invention described in the above-mentioned "embodiment method" section of this specification.
  • the storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 521 and/or a cache storage unit 522 , and may further include a read-only storage unit (ROM) 523 .
  • RAM random access storage unit
  • ROM read-only storage unit
  • Storage unit 520 may also include a program/utility tool 524 having a set (at least one) of program modules 525, such program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, Implementations of networked environments may be included in each or some combination of these examples.
  • program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, Implementations of networked environments may be included in each or some combination of these examples.
  • Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local area using any of a variety of bus structures. bus.
  • the electronic device 500 can also communicate with one or more external devices 700 (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable the user to interact with the electronic device 500, and/or communicate with Any device (eg, router, modem, etc.) that enables the electronic device 500 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 550 , such as communicating with display unit 540 . Moreover, the electronic device 500 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 560 .
  • LAN local area network
  • WAN wide area network
  • public network such as the Internet
  • the network adapter 560 communicates with other modules of the electronic device 500 through the bus 530 .
  • other hardware and/or software modules may be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.
  • the example implementations described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of software products, and the software products can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to make a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiments of the present disclosure.
  • a computing device which may be a personal computer, a server, a terminal device, or a network device, etc.
  • a computer-readable storage medium on which a program product capable of implementing the above-mentioned method in this specification is stored.
  • various aspects of the present invention can also be implemented in the form of a program product, which includes program code, and when the program product is run on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present invention described in the "Exemplary Method" section above in this specification.
  • a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus or device.
  • the computer program product may take the form of any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • a computer readable signal medium may include a data signal carrying readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Program code for carrying out the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language - such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.
  • the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider). business to connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider an Internet service provider

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Library & Information Science (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)

Abstract

本公开涉及图像清晰度识别领域，揭示了一种测井图像清晰度的识别方法、装置、介质及电子设备。该方法包括：建立包括多个测井图像的测井图像样本库；获取各测井图像对应的实际清晰度信息；获取与每一测井图像对应的多个清晰度；根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。

Description

测井图像清晰度的识别方法、装置、介质及电子设备
相关申请的交叉参考
本申请要求于2021年6月29日提交中国专利局、申请号为202110729473.5、名称为“测井图像清晰度的识别方法、装置、介质及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及图像清晰度识别技术领域，特别涉及一种测井图像清晰度的识别方法、装置、介质及电子设备。
背景技术
通常，对于一个特定的成像***，其成像的清晰度体现了***的聚焦状态。当聚焦效果比较好的时候，图像呈现较为清晰，轮廓细节等信息丰富，在空间域或频域上突出不同的特征信息。比如，在空间域上，图像的灰度值作为主要的特征信息；在频域上，特征信息为高频分量。通常使用图像聚焦评价函数(Focus Value)来衡量图像是否处于聚焦状态。
图像聚焦状态比较好时，图像清晰，在空域上表现为图像相邻的像素点的特征值，如灰度值、对比度等，变化比较剧烈。图像在离焦状态下，许多细节信息丢失，使得物体成像模糊。而不同的清晰度识别方法在处理不同模糊图像时存在差异，对于所要识别的图片有条件限制。例如使用熵函数进行识别时，主要侧重的图片中点的均匀排布，如果拿一张只有黑白条的图片来和一张模糊但是图上有很多黑色点的图片对比，那么通过熵函数这一识别方法得到的清晰图片就是模糊图，这显然有悖事实，得不到正确的识别结果。
发明内容
在图像清晰度识别技术领域，为了解决上述技术问题，本公开的目的在于提供一种测井图像清晰度的识别方法、装置、介质及电子设备。
根据本公开的一方面，提供了一种测井图像清晰度的识别方法，该方法包括：
建立包括多个测井图像的测井图像样本库；
获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成；
根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
可选地，根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重，包括：
利用各测井图像对应的多个清晰度，建立与各测井图像对应的清晰度向量，清晰度向量包括与各目标图像清晰度确定算法对应的归一化后的清晰度；
初始化权重向量，权重向量包括与各目标图像清晰度确定算法对应的权重；
利用权重向量和与各测井图像对应的清晰度向量构建多个训练单元，训练单元包括权重向量和与两个测井图像分别对应的清晰度向量；
执行权重调整步骤，权重调整步骤包括：针对每一训练单元，对训练单元中各测井图像对应的清晰度向量中的元素进行比较，并根据比较结果调整训练单元中权重向量的权重；
确定各训练单元中权重向量的平均值，得到最终权重向量；
利用最终权重向量与各测井图像对应的清晰度向量计算得到各测井图像对应的最终清晰度；
确定各测井图像对应的最终清晰度是否与各测井图像对应的实际清晰度信息匹配；
如果是，则将最终权重向量中的权重作为各目标图像清晰度确定算法对应的目标权重，否则执行权重调整步骤及之后的步骤，直至各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息匹配。
可选地，训练单元包括第一清晰度向量和第二清晰度向量，针对每一训练单元，对训练单元中各测井图像对应的清晰度向量中的元素进行比较，并根据比较结果调整训练单元中权重向量的权重，包括：
若第一清晰度向量中元素大于第二清晰度向量中相应元素的数量超过第一清晰度向量或第二清晰度向量中元素的总数的一半，则提高权重向量中各目标权重或降低权重向量中各非目标权重，直至权重向量与第一清晰度向量中相应元素的乘积之和大于权重向量与第二清晰度向量中相应元素的乘积之和，其中，大于第二清晰度向量中相应元素的第一清晰度向量中的元素和与目标权重对应的目标图像清晰度确定算法相对应，非目标权重为权重向量中除目标权重之外的权重。
可选地，实际清晰度信息为实际清晰度排序序号，确定各测井图像对应的最终清晰度是否与各测井图像对应的实际清晰度信息匹配，包括：
对各测井图像对应的最终清晰度进行排序，得到各测井图像对应的排序 序号；
若对于任一测井图像，与该测井图像对应的排序序号与该测井图像对应的实际清晰度排序序号一致，则确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息匹配，否则，确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息不匹配。
可选地，在获取与每一测井图像对应的多个清晰度之前，方法还包括：
针对测井图像样本库中的每一测井图像，利用多个图像清晰度确定算法分别确定该测井图像的清晰度；
根据各测井图像对应的清晰度和实际清晰度排序序号，在多个图像清晰度确定算法中筛选出多个目标图像清晰度确定算法。
可选地，建立包括多个测井图像的测井图像样本库，包括：
获取未修复测井图像和与各未修复测井图像对应的修复后测井图像；
利用未修复测井图像和修复后测井图像建立测井图像样本库。
可选地，其特征在于，多个目标图像清晰度确定算法包括下列算法中的一种或多种：Brenner算法、Tenengrad算法、Laplacian算法、SMD算法、SMD2算法、variance算法、energy算法、Vollath算法。
根据本公开的另一方面，提供了一种测井图像清晰度的识别装置，该装置包括：
建立模块，被配置为建立包括多个测井图像的测井图像样本库；
第一获取模块，被配置为获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
第二获取模块，被配置为获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成；
目标权重确定模块，被配置为根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
清晰度确定模块，被配置为利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
根据本公开的另一方面，提供了一种电子设备，该电子设备包括：处理器；
存储器，存储器上存储有计算机可读指令，计算机可读指令被处理器执行时，实现以下操作：
建立包括多个测井图像的测井图像样本库；
获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清 晰度确定算法分别对测井图像进行清晰度计算而生成；
根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
根据本公开的又一方面，提供了一种非易失性计算机可读存储介质，该非易失性计算机可读存储介质中存储有至少一可执行指令，可执行指令使处理器执行以下操作：
建立包括多个测井图像的测井图像样本库；
获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成；
根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
根据本公开的再一方面，还提供了一种计算机程序产品，该计算机程序产品包括存储在上述非易失性计算机可读存储介质上的计算程序。
本公开的实施例提供的技术方案可以包括以下有益效果：
对于本公开所提供的测井图像清晰度的识别方法、装置、介质及电子设备，该方法包括如下步骤：建立包括多个测井图像的测井图像样本库；获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成；根据各测井图像对应的所述多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
此方法下，通过先根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重，然后利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度，通过综合了多种图像清晰度确定算法的不同优势，形成了能够准确识别测井图像清晰度的方法，可以实现对测井图像清晰度的准确量化。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性的，并不能限制本发明。
附图概述
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本发明的实施例，并与说明书一起用于解释本发明的原理。
图1是根据一示例性实施例示出的一种测井图像清晰度的识别方法的***架构示意图；
图2是根据一示例性实施例示出的一种测井图像清晰度的识别方法的流程图；
图3是根据图2实施例示出的一实施例的步骤210的细节的流程图；
图4是根据一示例性实施例示出的一种测井图像清晰度的识别装置的框图；
图5是根据一示例性实施例示出的一种实现上述测井图像清晰度的识别方法的电子设备示例框图；
图6是根据一示例性实施例示出的一种实现上述测井图像清晰度的识别方法的计算机程序产品。
本公开的较佳实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本发明相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本发明的一些方面相一致的装置和方法的例子。
此外，附图仅为本公开的示意性图解，并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分，因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体，不一定必须与物理或逻辑上独立的实体相对应。
本公开首先提供了一种测井图像清晰度的识别方法。测井图像是通过测井技术生成的图像数据，比如可以声电成像技术生成测井图像。测井图像清晰度的识别是指根据测井图像确定出相应的清晰度，不同测井图像一般具有不同的清晰度；当一个测井图像的聚焦情况较差时，该测井图像的清晰度较低。
本公开的实施终端可以是任何具有运算、处理以及通信功能的设备，该设备可以与外部设备相连，用于接收或者发送数据，具体可以是便携移动设备，例如智能手机、平板电脑、笔记本电脑、PDA(Personal Digital Assistant)等，也可以是固定式设备，例如，计算机设备、现场终端、台式电脑、服务器、工作站等，还可以是多个设备的集合，比如云计算的物理基础设施或者服务器集群。
可选地，本公开的实施终端可以为服务器或者云计算的物理基础设施。
图1是根据一示例性实施例示出的一种测井图像清晰度的识别方法的***架构示意图。如图1所示，该***架构包括个人计算机110、服务器120及数据库130，个人计算机110和服务器120之间、数据库130和服务器120之间均通过通信链路相连，可以用于发送或接收数据。服务器120为本实施例中的实施终端，数据库130中存储有测井图像和对应的实际清晰度信息，个人计算机110上存有待识别的测井图像。
当本公开提供的一种测井图像清晰度的识别方法应用于图1所示的***架构中时，一个过程可以是这样的：服务器120从数据库130获取测井图像和对应的实际清晰度信息；然后利用图像清晰度确定算法并基于测井图像和对应的实际清晰度信息确定出各目标图像清晰度确定算法及对应的目标权重；最后，服务器120从个人计算机110在获取到待识别的测井图像之后，利用各目标图像清晰度确定算法及对应的目标权重计算出待识别的测井图像的清晰度。
图2是根据一示例性实施例示出的一种测井图像清晰度的识别方法的流程图。本实施例提供的测井图像清晰度的识别方法可以由服务器执行，如图2所示，包括以下步骤：
步骤210，建立包括若干测井图像的测井图像样本库。
在一个实施例中，步骤210的具体步骤如图3所示。图3是根据图2实施例示出的一实施例的步骤210的细节的流程图，如图3所示，步骤210包括以下步骤：
步骤211，获取未修复测井图像和与各未修复测井图像对应的修复后测井图像。
很多测井图像具有不完整的缺陷，由人工对未修复测井图像进行修复，可得到修复后测井图像。
步骤212，利用未修复测井图像和修复后测井图像建立测井图像样本库。
测井图像样本库中同时包括未修复测井图像和修复后测井图像，因而丰富了测井图像样本库中测井图像的数量，从而为准确识别测井图像的清晰度提供了数据支撑。
步骤220，获取各测井图像对应的实际清晰度信息。
实际清晰度信息为实际清晰度排序序号或实际归一化清晰度。
实际清晰度排序序号是由人工对各测井图像的清晰度进行辨别之后，按照清晰度由大到小或由小到大的顺序对各测井图像进行排序后标记的序号。
实际归一化清晰度是由人工在同一量化区间内对各测井图像进行量化后得到的数值，该量化区间通常为[0,1]。
步骤230，获取与每一测井图像对应的多个清晰度。
多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成。
在一个实施例中，多个目标图像清晰度确定算法包括下列算法中的一种或多种：Brenner算法、Tenengrad算法、Laplacian算法、SMD算法、SMD2算法、variance算法、energy算法、Vollath算法。
上述的每一种算法都能用于计算图像的清晰度。
在一个实施例中，在获取与每一测井图像对应的多个清晰度之前，该方法还包括：
针对测井图像样本库中的每一测井图像，利用多个图像清晰度确定算法分别确定该测井图像的清晰度；
根据各测井图像对应的清晰度和实际清晰度排序序号，在多个图像清晰度确定算法中筛选出多个目标图像清晰度确定算法。
目标图像清晰度确定算法的数量小于图像清晰度确定算法的数量，比如，目标图像清晰度确定算法的数量可以为5，而图像清晰度确定算法的数量可以为8，比如，多个目标图像清晰度确定算法可以为上述实施例中的8个算法。
在本实施例中，通过将一部分不适用于识别测井图像的清晰度的图像清晰度确定算法剔除，确保了后续的过程可以实现对测井图像清晰度的准确识别。
在一个实施例中，根据各测井图像对应的清晰度和实际清晰度排序序号，在多个图像清晰度确定算法中筛选出多个目标图像清晰度确定算法，包括：
针对每一图像清晰度确定算法，获取与该图像清晰度确定算法对应的各测井图像的清晰度排序序号；
针对每一图像清晰度确定算法，在与该图像清晰度确定算法对应的各测井图像的清晰度排序序号中确定与实际清晰度排序序号一致的清晰度排序序号的数量与该图像清晰度确定算法对应的所有测井图像的清晰度排序序号的数量的比值；
根据各图像清晰度确定算法对应的比值，将多个图像清晰度确定算法中至少一个图像清晰度确定算法剔除，得到多个目标图像清晰度确定算法，其中，被剔除的图像清晰度确定算法对应的比值小于目标图像清晰度确定算法对应的比值。
利用同一图像清晰度确定算法可以确定每一测井图像对应的清晰度，因而，一个图像清晰度确定算法具有对应的一个清晰度排序，相应地也就具有各测井图像的清晰度排序序号；因而，测井图像具有对应的清晰度排序序号，也具有对应的实际清晰度排序序号，一个测井图像对应的清晰度排序序号和与该测井图像对应的实际清晰度排序序号相比，两者可以相同也可以不同。
比值反映了一个图像清晰度确定算法对各测井图像计算出的清晰度的排名与各测井图像对应的实际清晰度排名的一致性。
一个图像清晰度确定算法对应的比值越低，说明该图像清晰度确定算法越不适用于计算测井图像的清晰度。
步骤240，根据各测井图像对应的所述多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重。
在一个实施例中，根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重，包括：
利用各测井图像对应的多个清晰度，建立与各测井图像对应的清晰度向量，清晰度向量包括与各目标图像清晰度确定算法对应的归一化后的清晰度；
初始化权重向量，权重向量包括与各目标图像清晰度确定算法对应的权重；
利用权重向量和与各测井图像对应的清晰度向量构建多个训练单元，训练单元包括权重向量和与两个测井图像分别对应的清晰度向量；
执行权重调整步骤，权重调整步骤包括：针对每一训练单元，对训练单元中各测井图像对应的清晰度向量中的元素进行比较，并根据比较结果调整训练单元中权重向量的权重；
确定各训练单元中权重向量的平均值，得到最终权重向量；
利用最终权重向量与各测井图像对应的清晰度向量计算得到各测井图像对应的最终清晰度；
确定各测井图像对应的最终清晰度是否与各测井图像对应的实际清晰度信息匹配；
如果是，则将最终权重向量中的权重作为各目标图像清晰度确定算法对应的目标权重，否则执行权重调整步骤及之后的步骤，直至各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息匹配。
通过如下的方式一个目标图像清晰度确定算法对应的清晰度进行归一化：
确定目标图像清晰度确定算法与各测井图像对应的清晰度中的最大值和最小值；针对同时与该目标图像清晰度确定算法与一个测井图像对应的清晰度，计算该清晰度与最小值之差跟该最大值与最小值之差的比值，作为归一化后的该清晰度。
在一个实施例中，训练单元包括第一清晰度向量和第二清晰度向量，针对每一训练单元，对训练单元中各测井图像对应的清晰度向量中的元素进行比较，并根据比较结果调整训练单元中权重向量的权重，包括：
若第一清晰度向量中元素大于第二清晰度向量中相应元素的数量超过第一清晰度向量或第二清晰度向量中元素的总数的一半，则提高权重向量中各 目标权重或降低权重向量中各非目标权重，直至权重向量与第一清晰度向量中相应元素的乘积之和大于权重向量与第二清晰度向量中相应元素的乘积之和，其中，大于第二清晰度向量中相应元素的第一清晰度向量中的元素和与目标权重对应的目标图像清晰度确定算法相对应，非目标权重为权重向量中除目标权重之外的权重。
在一个实施例中，实际清晰度信息为实际清晰度排序序号，确定各测井图像对应的最终清晰度是否与各测井图像对应的实际清晰度信息匹配，包括：
对各测井图像对应的最终清晰度进行排序，得到各测井图像对应的排序序号；
若对于任一测井图像，与该测井图像对应的排序序号与该测井图像对应的实际清晰度排序序号一致，则确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息匹配，否则，确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息不匹配。
在一个实施例中，实际清晰度信息为实际归一化清晰度，确定各测井图像对应的最终清晰度是否与各测井图像对应的实际清晰度信息匹配，包括：
针对每一测井图像，确定该测井图像对应的最终清晰度与该测井图像对应的实际归一化清晰度之差；
确定各测井图像对应的差的方差；
若方差小于预定方差阈值，则确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息匹配，否则，确定各测井图像对应的最终清晰度与各测井图像对应的实际清晰度信息不匹配。
下面通过一个具体的例子进一步说明上述实施例中的步骤。
首先，建立测井图像样本库；
接着，利用8种算法分别计算测井图像的清晰度，并判断各算法对各测井图像计算出的清晰度的排名与各测井图像对应的实际清晰度排名的一致性，并将该一致性较低的算法剔除，得到5种算法；
然后，利用各测井图像对应的多个清晰度，建立清晰度矩阵X＝{X j}，j∈[1，5]，其中，X j为由第j种算法对各测井图像的归一化后的清晰度组成的向量，为清晰度矩阵X的列向量；清晰度矩阵X还包括行向量，一个行向量包括各算法对同一测井图像的归一化后的清晰度，比如行向量可以为：
X i＝{x i1，x i2，x i3，x i4，x i5}，i∈[1，N]，
其中，X i为各算法对第i张测井图像的归一化后的清晰度，N为测井图像的数量。
接着，初始化权重向量：A＝{a 1，a 2，a 3，a 4，a 5}，其中，A为权重向量， A中的元素为各算法对应的权重，初始化的值为0.2；
接下来，利用N张测井图像对应的清晰度向量构建包括多个训练单元的集合U，每两个测井图像分别对应的所述清晰度向量生成一个训练单元，因而可生成
Figure PCTCN2021124746-appb-000001
个训练单元，每个训练单元为U i＝{X a，X b，A i}，其中a≠b,a∈[1,N]，b∈[1,N]，i∈[1,N(N-1)/2]，X a和X b分别为U i中A，B两张图像的清晰度行向量，A i为当前训练单元的权重系数向量，且
Figure PCTCN2021124746-appb-000002
即各算法对应的权重之和为1；
然后，以U i作为基本单元，通过比较X a和X b，确定本次训练得到的A i，具体为：比较X a和X b，如果多数算法认为A图像的清晰度更高，则提高相应几种算法的权重或降低其他几种算法的权重，权重调整后进行归一化，直至x am＞x bm，其中，x am为X a与A i中相应元素的乘积之和，x bm为X a与A i中相应元素的乘积之和；
完成全部训练单元的训练后共计产生N(N-1)/2个权重向量，然后对全部权重向量求平均得到最终权重向量A mean；
将最终权重向量代入下面的公式，也可以得到由所有测井图像的最终清晰度组成的如下矩阵：
X m＝XA；
各测井图像的清晰度排序情况反映了清晰度变化趋势，若利用最终权重向量计算得到的各测井图像的最终清晰度变化趋势与实际清晰度变化趋势相符，则说明最终权重向量可用于最终计算测井图像清晰度，否则继续执行对权重的调整步骤，最终能够得到能够用于准确计算测井图像清晰度的与各算法对应的权重。
步骤250，利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
目标测井图像即为待进行清晰度识别的测井图像，先利用各目标图像清晰度确定算法分别识别目标测井图像的清晰度，并将各目标图像清晰度确定算法对应的清晰度归一化，接着将各归一化后的清晰度分别与相应的目标图像清晰度确定算法的目标权重相乘，然后将各乘积相加，最终得到目标测井图像的清晰度。
综上所述，根据图2实施例提供的测井图像清晰度的识别方法，通过先根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重，然后利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度，通过综合了多种图像清晰度确定算法的不同优势，形成了能够准确识别测井图像清晰 度的方法，可以实现对测井图像清晰度的准确量化。
本公开还提供了一种测井图像清晰度的识别装置，以下是本公开的装置实施例。
图4是根据一示例性实施例示出的一种测井图像清晰度的识别装置的框图。如图4所示，装置400包括：
建立模块410，被配置为建立包括若干测井图像的测井图像样本库；
第一获取模块420，被配置为获取各测井图像对应的实际清晰度信息，实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
第二获取模块430，被配置为获取与每一测井图像对应的多个清晰度，多个清晰度由多个目标图像清晰度确定算法分别对测井图像进行清晰度计算而生成；
目标权重确定模块440，被配置为根据各测井图像对应的多个清晰度和实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
清晰度确定模块450，被配置为利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
根据本公开的第三方面，还提供了一种能够实现上述方法的电子设备。
所属技术领域的技术人员能够理解，本发明的各个方面可以实现为***、方法或程序产品。因此，本发明的各个方面可以具体实现为以下形式，即：完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等)，或硬件和软件方面结合的实施方式，这里可以统称为“电路”、“模块”或“***”。
下面参照图5来描述根据本发明的这种实施方式的电子设备500。图5显示的电子设备500仅仅是一个示例，不应对本发明实施例的功能和使用范围带来任何限制。
如图5所示，电子设备500以通用计算设备的形式表现。电子设备500的组件可以包括但不限于：上述至少一个处理单元510、上述至少一个存储单元520、连接不同***组件(包括存储单元520和处理单元510)的总线530。
其中，存储单元存储有程序代码，程序代码可以被处理单元510执行，使得处理单元510执行本说明书上述“实施例方法”部分中描述的根据本发明各种示例性实施方式的步骤。
存储单元520可以包括易失性存储单元形式的可读介质，例如随机存取存储单元(RAM)521和/或高速缓存存储单元522，还可以进一步包括只读存储单元(ROM)523。
存储单元520还可以包括具有一组(至少一个)程序模块525的程序/实用工具524，这样的程序模块525包括但不限于：操作***、一个或者多 个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。
总线530可以为表示几类总线结构中的一种或多种，包括存储单元总线或者存储单元控制器、***总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
电子设备500也可以与一个或多个外部设备700(例如键盘、指向设备、蓝牙设备等)通信，还可与一个或者多个使得用户能与该电子设备500交互的设备通信，和/或与使得该电子设备500能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口550进行，比如与显示单元540通信。并且，电子设备500还可以通过网络适配器560与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器560通过总线530与电子设备500的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备500使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID***、磁带驱动器以及数据备份存储***等。
通过以上的实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM，U盘，移动硬盘等)中或网络上，包括若干指令以使得一台计算设备(可以是个人计算机、服务器、终端装置、或者网络设备等)执行根据本公开实施方式的方法。
根据本公开的第四方面，还提供了一种计算机可读存储介质，其上存储有能够实现本说明书上述方法的程序产品。在一些可能的实施方式中，本发明的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当所述程序产品在终端设备上运行时，所述程序代码用于使所述终端设备执行本说明书上述“示例性方法”部分中描述的根据本发明各种示例性实施方式的步骤。
参考图6所示，描述了根据本发明的实施方式的用于实现上述方法的计算机程序产品600，其可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在终端设备，例如个人电脑上运行。然而，本发明的计算机程序产品不限于此，在本文件中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。
该计算机程序产品可以采用一个或多个可读介质的任意组合。可读介质 可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。
可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言的任意组合来编写用于执行本发明操作的程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
此外，上述附图仅是根据本发明示例性实施例的方法所包括的处理的示意性说明，而不是限制目的。易于理解，上述附图所示的处理并不表明或限制这些处理的时间顺序。另外，也易于理解，这些处理可以是例如在多个模块中同步或异步执行的。
应当理解的是，本发明并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围执行各种修改和改变。本发明的范围仅由所附的权利要求来限制。

Claims (11)

  1. 一种测井图像清晰度的识别方法，其特征在于，所述方法包括：
    建立包括多个测井图像的测井图像样本库；
    获取各测井图像对应的实际清晰度信息，所述实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
    获取与每一测井图像对应的多个清晰度，所述多个清晰度由多个目标图像清晰度确定算法分别对所述测井图像进行清晰度计算而生成；
    根据各测井图像对应的所述多个清晰度和所述实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
    利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
  2. 根据权利要求1所述的方法，其特征在于，所述根据各测井图像对应的所述多个清晰度和所述实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重，包括：
    利用各测井图像对应的所述多个清晰度，建立与各测井图像对应的清晰度向量，所述清晰度向量包括与各目标图像清晰度确定算法对应的归一化后的清晰度；
    初始化权重向量，所述权重向量包括与各目标图像清晰度确定算法对应的权重；
    利用所述权重向量和与各测井图像对应的所述清晰度向量构建多个训练单元，所述训练单元包括所述权重向量和与两个测井图像分别对应的所述清晰度向量；
    执行权重调整步骤，所述权重调整步骤包括：针对每一所述训练单元，对所述训练单元中各测井图像对应的所述清晰度向量中的元素进行比较，并根据比较结果调整所述训练单元中所述权重向量的权重；
    确定各所述训练单元中所述权重向量的平均值，得到最终权重向量；
    利用所述最终权重向量与各测井图像对应的清晰度向量计算得到各测井图像对应的最终清晰度；
    确定各测井图像对应的最终清晰度是否与各测井图像对应的所述实际清晰度信息匹配；
    如果是，则将所述最终权重向量中的权重作为各目标图像清晰度确定算法对应的目标权重，否则执行所述权重调整步骤及之后的步骤，直至各测井图像对应的最终清晰度与各测井图像对应的所述实际清晰度信息匹配。
  3. 根据权利要求2所述的方法，其特征在于，所述训练单元包括第一清 晰度向量和第二清晰度向量，所述针对每一所述训练单元，对所述训练单元中各测井图像对应的所述清晰度向量中的元素进行比较，并根据比较结果调整所述训练单元中所述权重向量的权重，包括：
    若所述第一清晰度向量中元素大于所述第二清晰度向量中相应元素的数量超过所述第一清晰度向量或所述第二清晰度向量中元素的总数的一半，则提高所述权重向量中各目标权重或降低所述权重向量中各非目标权重，直至所述权重向量与所述第一清晰度向量中相应元素的乘积之和大于所述权重向量与所述第二清晰度向量中相应元素的乘积之和，其中，大于所述第二清晰度向量中相应元素的所述第一清晰度向量中的元素和与所述目标权重对应的目标图像清晰度确定算法相对应，所述非目标权重为所述权重向量中除目标权重之外的权重。
  4. 根据权利要求2所述的方法，其特征在于，所述实际清晰度信息为实际清晰度排序序号，所述确定各测井图像对应的最终清晰度是否与各测井图像对应的所述实际清晰度信息匹配，包括：
    对各测井图像对应的最终清晰度进行排序，得到各测井图像对应的排序序号；
    若对于任一测井图像，与该测井图像对应的所述排序序号与该测井图像对应的所述实际清晰度排序序号一致，则确定各测井图像对应的最终清晰度与各测井图像对应的所述实际清晰度信息匹配，否则，确定各测井图像对应的最终清晰度与各测井图像对应的所述实际清晰度信息不匹配。
  5. 根据权利要求4所述的方法，其特征在于，在获取与每一测井图像对应的多个清晰度之前，所述方法还包括：
    针对所述测井图像样本库中的每一测井图像，利用多个图像清晰度确定算法分别确定该测井图像的清晰度；
    根据各测井图像对应的清晰度和实际清晰度排序序号，在所述多个图像清晰度确定算法中筛选出多个目标图像清晰度确定算法。
  6. 根据权利要求1-5任意一项所述的方法，其特征在于，所述建立包括多个测井图像的测井图像样本库，包括：
    获取未修复测井图像和与各未修复测井图像对应的修复后测井图像；
    利用所述未修复测井图像和所述修复后测井图像建立测井图像样本库。
  7. 根据权利要求1-5任意一项所述的方法，其特征在于，所述多个目标图像清晰度确定算法包括下列算法中的一种或多种：Brenner算法、Tenengrad算法、Laplacian算法、SMD算法、SMD2算法、variance算法、energy算法、Vollath算法。
  8. 一种测井图像清晰度的识别装置，其特征在于，所述装置包括：
    建立模块，被配置为建立包括多个测井图像的测井图像样本库；
    第一获取模块，被配置为获取各测井图像对应的实际清晰度信息，所述实际清晰度信息为实际清晰度排序序号或实际归一化清晰度；
    第二获取模块，被配置为获取与每一测井图像对应的多个清晰度，所述多个清晰度由多个目标图像清晰度确定算法分别对所述测井图像进行清晰度计算而生成；
    目标权重确定模块，被配置为根据各测井图像对应的所述多个清晰度和所述实际清晰度信息，确定各目标图像清晰度确定算法对应的目标权重；
    清晰度确定模块，被配置为利用各目标图像清晰度确定算法对应的目标权重和各目标图像清晰度确定算法确定目标测井图像的清晰度。
  9. 一种电子设备，其特征在于，所述电子设备包括：
    处理器；
    存储器，所述存储器上存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，实现如权利要求1至7任一项所述的测井图像清晰度的识别方法。
  10. 一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质中存储有至少一可执行指令，所述可执行指令用于使处理器执行前述任一权利要求1-7所述的测井图像清晰度的识别方法。
  11. 一种计算机程序产品，该计算机程序产品包括存储在非易失性计算机可读存储介质上的计算程序，该计算机程序包括程序指令，当该程序指令被处理器执行时，使该处理器执行前述任一权利要求1-7所述的测井图像清晰度的识别方法。
PCT/CN2021/124746 2021-06-29 2021-10-19 测井图像清晰度的识别方法、装置、介质及电子设备 WO2023273017A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21947944.1A EP4365755A1 (en) 2021-06-29 2021-10-19 Method for identifying clarity of well logging image, apparatus, medium, and electronic device
US18/574,234 US20240143651A1 (en) 2021-06-29 2021-10-19 Logging Image Definition Recognition Method and Device, Medium, and Electronic Equipment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110729473.5A CN113392241B (zh) 2021-06-29 2021-06-29 测井图像清晰度的识别方法、装置、介质及电子设备
CN202110729473.5 2021-06-29

Publications (1)

Publication Number Publication Date
WO2023273017A1 true WO2023273017A1 (zh) 2023-01-05

Family

ID=77624456

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124746 WO2023273017A1 (zh) 2021-06-29 2021-10-19 测井图像清晰度的识别方法、装置、介质及电子设备

Country Status (4)

Country Link
US (1) US20240143651A1 (zh)
EP (1) EP4365755A1 (zh)
CN (1) CN113392241B (zh)
WO (1) WO2023273017A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113392241B (zh) * 2021-06-29 2023-02-03 中海油田服务股份有限公司 测井图像清晰度的识别方法、装置、介质及电子设备
CN114820614A (zh) * 2022-06-29 2022-07-29 上海闪马智能科技有限公司 一种图像类型的确定方法、装置、存储介质及电子装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100100729A1 (en) * 2008-10-21 2010-04-22 Christopher Jensen Read Distribution medium for professional photography
CN110175980A (zh) * 2019-04-11 2019-08-27 平安科技（深圳）有限公司 图像清晰度识别方法、图像清晰度识别装置及终端设备
CN111754491A (zh) * 2020-06-28 2020-10-09 国网电子商务有限公司 一种图片清晰度判定方法及装置
CN112950626A (zh) * 2021-03-31 2021-06-11 网易传媒科技（北京）有限公司 清晰度的确定方法、介质、装置和计算设备
CN113392241A (zh) * 2021-06-29 2021-09-14 中海油田服务股份有限公司 测井图像清晰度的识别方法、装置、介质及电子设备

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615620B (zh) * 2018-11-30 2021-01-08 腾讯科技（深圳）有限公司 图像压缩度识别方法、装置、设备及计算机可读存储介质
CN109635800B (zh) * 2018-12-26 2024-01-19 深圳市捷顺科技实业股份有限公司 一种图像对焦方法及其相关设备
CN110080754B (zh) * 2019-04-25 2022-07-22 杭州迅美科技有限公司 一种电成像测井图像类周期性干扰处理方法
CN110378312A (zh) * 2019-07-26 2019-10-25 上海商汤智能科技有限公司 图像处理方法及装置、电子设备和存储介质
CN110866912B (zh) * 2019-11-15 2022-04-19 成都理工大学 基于成像测井图像纹理的页岩纹层非均质性数据处理方法
CN111080595A (zh) * 2019-12-09 2020-04-28 北京字节跳动网络技术有限公司 图像处理方法、装置、电子设备及计算机可读介质
CN111311543B (zh) * 2020-01-17 2022-09-02 苏州科达科技股份有限公司 图像清晰度检测方法、***、设备及存储介质
CN111314733B (zh) * 2020-01-20 2022-06-10 北京百度网讯科技有限公司 用于评估视频清晰度的方法和装置
CN111797733A (zh) * 2020-06-22 2020-10-20 浙江大华技术股份有限公司 一种基于图像的行为识别方法、装置、设备和存储介质
CN112135140B (zh) * 2020-09-17 2023-11-28 上海连尚网络科技有限公司 视频清晰度识别方法、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100100729A1 (en) * 2008-10-21 2010-04-22 Christopher Jensen Read Distribution medium for professional photography
CN110175980A (zh) * 2019-04-11 2019-08-27 平安科技（深圳）有限公司 图像清晰度识别方法、图像清晰度识别装置及终端设备
CN111754491A (zh) * 2020-06-28 2020-10-09 国网电子商务有限公司 一种图片清晰度判定方法及装置
CN112950626A (zh) * 2021-03-31 2021-06-11 网易传媒科技（北京）有限公司 清晰度的确定方法、介质、装置和计算设备
CN113392241A (zh) * 2021-06-29 2021-09-14 中海油田服务股份有限公司 测井图像清晰度的识别方法、装置、介质及电子设备

Also Published As

Publication number Publication date
US20240143651A1 (en) 2024-05-02
CN113392241B (zh) 2023-02-03
EP4365755A1 (en) 2024-05-08
CN113392241A (zh) 2021-09-14

Similar Documents

Publication Publication Date Title
WO2023005133A1 (zh) 联邦学习建模优化方法、设备、可读存储介质及程序产品
WO2021012526A1 (zh) 人脸识别模型的训练方法、人脸识别方法、装置、设备及存储介质
WO2023273017A1 (zh) 测井图像清晰度的识别方法、装置、介质及电子设备
CN113436100B (zh) 用于修复视频的方法、装置、设备、介质和产品
CN110211121B (zh) 用于推送模型的方法和装置
EP3852007A2 (en) Method, apparatus, electronic device, readable storage medium and program for classifying video
CN109145813B (zh) 一种图像匹配算法测试方法和装置
CN115359308B (zh) 模型训练、难例识别方法、装置、设备、存储介质及程序
CN110717405B (zh) 人脸特征点定位方法、装置、介质及电子设备
CN116935083B (zh) 一种图像聚类方法和装置
WO2020006962A1 (zh) 用于处理图片的方法和装置
CN117746125A (zh) 图像处理模型的训练方法、装置及电子设备
CN113516697A (zh) 图像配准的方法、装置、电子设备及计算机可读存储介质
CN113360683A (zh) 训练跨模态检索模型的方法以及跨模态检索方法和装置
WO2023005421A1 (zh) 作品封面显示方法、装置、介质和电子设备
KR102012564B1 (ko) 주식 정보 제공 방법
CN114741697B (zh) 恶意代码分类方法、装置、电子设备和介质
KR20230133808A (ko) Roi 검출 모델 훈련 방법, 검출 방법, 장치, 설비 및 매체
CN114419327B (zh) 图像检测方法和图像检测模型的训练方法、装置
CN116311298A (zh) 信息生成方法、信息处理方法、装置、电子设备以及介质
CN116030375A (zh) 视频特征提取、模型训练方法、装置、设备及存储介质
CN112542244B (zh) 辅助信息的生成方法、相关装置及计算机程序产品
CN111680754B (zh) 图像分类方法、装置、电子设备及计算机可读存储介质
CN114863162A (zh) 对象分类方法、深度学习模型的训练方法、装置和设备
CN112329708A (zh) 票据识别方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21947944

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18574234

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2021947944

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021947944

Country of ref document: EP

Effective date: 20240129