CN113420768A - Core category determination method and device, electronic equipment and storage medium - Google Patents
Core category determination method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113420768A CN113420768A CN202110974902.5A CN202110974902A CN113420768A CN 113420768 A CN113420768 A CN 113420768A CN 202110974902 A CN202110974902 A CN 202110974902A CN 113420768 A CN113420768 A CN 113420768A
- Authority
- CN
- China
- Prior art keywords
- image
- core
- identified
- determining
- preset model
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention discloses a method and a device for determining core category, electronic equipment and a storage medium. The method comprises the following steps: acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule; carrying out segmentation processing on the image to be identified to obtain a segmented first image; carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface; performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified; and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image. By adopting the scheme provided by the invention, the automatic judgment of the core category can be realized, and the preparation rate and the judgment speed of the judgment are improved.
Description
Technical Field
The invention relates to the technical field of core judgment, in particular to a method and a device for determining core categories, electronic equipment and a storage medium.
Background
With the development of economy in China, the capital construction strength in China is continuously increased, and large-scale roads, buildings, tunnels and the like are put into construction. Before a building is built, geological conditions in an area range need to be surveyed, and geotechnical conditions and geological environments in the area are analyzed through surveying. Drilling is an important means for exploring geological conditions, and aims to find out the stratum structure and distribution characteristics of each hole through core analysis and judgment on drilling of a drilling machine.
At present, in the process of judging the outdoor drilling core, the judgment is mainly carried out based on the standard human eyes. The above determination method has low accuracy and low speed.
Disclosure of Invention
In order to solve the technical problems of low accuracy and low speed caused by the fact that traditional human eyes are used for judging rocks, the embodiment of the invention provides a method and a device for determining the rock core category, electronic equipment and a storage medium.
The technical scheme of the embodiment of the invention is realized as follows:
the embodiment of the invention provides a method for determining the category of a core, which comprises the following steps:
acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
carrying out segmentation processing on the image to be identified to obtain a segmented first image;
carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface;
performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified;
and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image.
In the above scheme, the extracting and identifying the features of the second image, and determining the core categories of the plurality of cores in the image to be identified includes:
extracting the features of the second image by using a feature extraction network in a preset model to obtain a plurality of first vectors;
and classifying and identifying each first vector by using a classifier in the preset model, and determining the core category corresponding to each first vector.
In the foregoing solution, the classifying and identifying each first vector by using the classifier in the preset model, and determining the core category corresponding to each first vector includes:
classifying and identifying each first vector by using a classifier in the preset model, and determining a first core class and a second core class corresponding to each first vector; wherein the first core category characterizes a degree of weathering of the core and the second core category characterizes a sample type of the core.
In the above scheme, for each core type, the core type is labeled at a corresponding core position in the image to be identified, and obtaining the labeled identification image includes:
and marking the first core type and the second core type corresponding to each first vector at the corresponding core position in the image to be identified to obtain a marked identification image.
In the foregoing scheme, the extracting features of the second image by using a feature extraction network in a preset model to obtain a plurality of first vectors includes:
extracting the features of the second image by using a feature extraction network in the preset model to obtain feature information;
generating a feature map according to the feature information;
and carrying out weighting processing on the characteristic diagram to obtain a plurality of first vectors.
In the above scheme, before the image to be identified is acquired, the method includes:
acquiring a training image set;
labeling the training image set to obtain a first image set after labeling;
and training a model by using the first image set to obtain a preset model.
In the foregoing scheme, the segmenting the image to be recognized to obtain a segmented first image includes:
equally dividing the image to be identified into three equal parts from top to bottom;
the segmented image is defined as a first image.
The embodiment of the invention also provides a device for determining the core type, which comprises:
the acquisition module is used for acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
the segmentation module is used for carrying out segmentation processing on the image to be identified to obtain a segmented first image;
the deconvolution module is used for carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface;
the determining module is used for extracting and identifying the features of the second image and determining the core categories of a plurality of cores in the image to be identified;
and the marking module is used for marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image for each core type.
An embodiment of the present invention further provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,
the processor is adapted to perform the steps of any of the methods described above when running the computer program.
The embodiment of the invention also provides a storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of any one of the methods are realized.
Embodiments of the present invention also provide a computer program product, where the computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of any of the methods described above.
The method, the device, the electronic equipment and the storage medium for determining the core category provided by the embodiment of the invention are used for acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule; carrying out segmentation processing on the image to be identified to obtain a segmented first image; carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface; performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified; and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image. By adopting the scheme provided by the invention, the automatic judgment of the core category can be realized, and the preparation rate and the judgment speed of the judgment are improved.
Drawings
FIG. 1 is a schematic flow chart of a method for determining a core category according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an overall framework for core discrimination according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a data tag according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a core category determination apparatus according to an embodiment of the present invention;
fig. 5 is an internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The embodiment of the invention provides a method for determining a core category, which comprises the following steps of:
step 101: acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
step 102: carrying out segmentation processing on the image to be identified to obtain a segmented first image;
step 103: carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface;
step 104: performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified;
step 105: and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image.
In practice, the cores drilled by the drilling machine are arranged according to the drilling depth. For example, referring to fig. 3, fig. 3 shows a core box used in practice, which comprises a plurality of spaces for accommodating cores, each space typically being one meter. The cores drilled up may be placed in the space of each cell of the core box in order from top to bottom according to the drilling depth. That is, typically, the first grid space places cores drilled to a depth of 0 to 1 meter; the second grid space is used for placing a core drilled with the depth of 1 to 2 meters; the third grid space is used for placing a core drilled with the depth of 2 to 3 meters; and by parity of reasoning, the placement of the core is completed.
After the rock core is placed according to the mode, the placed rock core box can be shot to obtain an image to be identified. Here, the image to be recognized may include a plurality of cores that need to be recognized, and the plurality of cores are arranged according to a certain rule.
After the image to be recognized is obtained, the image to be recognized can be input into a trained preset model for recognition. Here, the preset model may be set such that the preset model can perform the judgment and recognition operation of the core.
Specifically, after the image to be recognized is input into the preset model, the preset model performs segmentation processing on the image to be recognized to obtain a segmented first image. Because the image to be recognized contains a plurality of cores which need to be recognized, the image to be recognized contains more features, which is not beneficial to the judgment and recognition of the cores. And the image to be recognized is segmented, so that the characteristics in the image to be recognized can be dispersed, and the recognition precision of the rock core in the image to be recognized is improved. In addition, after the image to be recognized is segmented, the deconvolution network in the preset model is used for carrying out deconvolution processing on the segmented first image, so that the features in the segmented first image can be enlarged, the loss of the features is avoided, and the recognition accuracy is further improved.
After the segmentation and deconvolution processing are carried out, the feature extraction and identification can be carried out on the deconvolution processed second image, the core types of a plurality of cores needing to be identified in the image to be identified are judged, and therefore after the identification, the core types corresponding to the cores are marked on the cores, and the marked identification image is obtained. Specifically, the labeled recognition image can be as shown in fig. 3.
Specifically, the core category corresponding to the core may be marked at the marking position corresponding to the core. Specifically, the corresponding marked position of the core may be the upper left, the upper right, and the like of the core. Of course, during actual labeling, the labeling position can also be set according to other rules.
Furthermore, when the preset model is identified, unified identification can be carried out on each grid of rock core in the rock core box, and after identification is completed, the rock core category can be marked on each grid of rock core box. Of course, in practical application, each individual core may also be identified, and after the identification is completed, each individual core is labeled with the corresponding core category.
In addition, in an embodiment, the performing feature extraction and recognition on the second image, and determining core categories of a plurality of cores in the image to be recognized includes:
extracting the features of the second image by using a feature extraction network in a preset model to obtain a plurality of first vectors;
and classifying and identifying each first vector by using a classifier in the preset model, and determining the core category corresponding to each first vector.
Here, one first vector corresponds to one core recognition result, and a plurality of first vectors correspond to a plurality of core recognition results.
The feature extraction network here may be a trained SSD destination detection network. Feature extraction is performed on the second image through the network.
In practical application, the classifier stores a plurality of identification results, and the identification result corresponding to the numerical value can be found in the classifier according to the numerical value in the first vector, so that the identification result is output.
Further, in an embodiment, the performing classification and identification on each first vector by using a classifier in the preset model, and determining a core class corresponding to each first vector includes:
classifying and identifying each first vector by using a classifier in the preset model, and determining a first core class and a second core class corresponding to each first vector; wherein the first core category characterizes a degree of weathering of the core and the second core category characterizes a sample type of the core.
Here, the first core category may include strongly differentiated, fully weathered, moderately weathered, slightly weathered, according to the degree of weathering. The second core category may include granite, sandstone, by rock sample species.
Accordingly, after the first core type and the second core type are obtained, in an embodiment, the first core type and the second core type corresponding to each first vector may be labeled at a corresponding core position in the image to be identified, so as to obtain a labeled identification image.
Here, in the labeling, the first core type and the second core type corresponding to each first vector are labeled.
Further, in an embodiment, the extracting features of the second image by using a feature extraction network in a preset model, and obtaining a plurality of first vectors includes:
extracting the features of the second image by using a feature extraction network in the preset model to obtain feature information;
generating a feature map according to the feature information;
and carrying out weighting processing on the characteristic diagram to obtain a plurality of first vectors.
In actual application, the feature information after feature extraction can be used for generating a feature map, and the first vector can be obtained by using the feature map.
Further, in an embodiment, before acquiring the image to be recognized, the method includes:
acquiring a training image set;
labeling the training image set to obtain a first image set after labeling;
and training a model by using the first image set to obtain a preset model.
When the application is implemented, a training image set can be obtained, the recognition result is labeled in the training image set, and the labeled first image set is trained, so that a trained preset model is obtained.
The method for determining the core category, provided by the embodiment of the invention, comprises the steps of obtaining an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule; carrying out segmentation processing on the image to be identified to obtain a segmented first image; carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface; performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified; and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image. By adopting the scheme provided by the invention, the automatic judgment of the core category can be realized, and the preparation rate and the judgment speed of the judgment are improved.
The present invention will be described in further detail with reference to the following application examples.
The application embodiment provides a core distinguishing network, which is used for distinguishing the core in real time and improving the timeliness, limitation and accuracy of rock distinguishing.
Specifically, the core discriminating network is based on a convolutional neural network, and in the core discriminating network, methods of segmentation, deconvolution and feature extraction are provided for solving the problem of small feature plane of a rock sample. And a rock judging system based on the core judging network is constructed based on the core judging network.
Further, referring to fig. 2, the built rock judgment system can realize the judgment and identification of the rock core through the following processes:
(1) obtaining a rock sample to be judged;
(2) shooting by using an industrial camera to obtain an image to be identified;
(3) and extracting core characteristic information by using a core distinguishing network, and performing matching analysis on the core characteristic information and the database information through a classifier so as to output a rock distinguishing result at a PC (personal computer) end.
Here, referring to table 1, table 1 is a development and operation environment parameter of the rock judgment system.
TABLE 1
The core discrimination network is described in detail below:
the core distinguishing network in the embodiment can realize the classified identification and positioning of the cores. The core distinguishing network mainly comprises the following 4 parts: the method comprises an image segmentation algorithm, a two-layer deconvolution network, a feature map feature extraction network based on an SSD target detection network and a classifier.
In the network, after a target to be detected is obtained, filling processing is firstly carried out on the target to be detected, and a filling characteristic diagram with a proper size is generated; and then, carrying out image segmentation on the filling feature map to obtain an image after image segmentation. (here, since the core image to be detected has many features, the core image to be detected is subjected to segmentation processing in order to avoid loss of the features). And performing deconvolution operation on the segmented image through a deconvolution network to expand the feature plane and retain feature information (here, local feature expansion is performed through deconvolution operation, and features can be retained as much as possible during feature extraction). After the feature plane is expanded by the deconvolution network, feature information can be extracted by a feature extraction network based on the SSD target detection network to generate a new feature map, then the frame generated in the feature map is weighted, and the weighted frame feature information is extracted by the weighted feature map feature extraction network to generate a linear vector (which can be understood as the first vector in the above-described embodiment). And processing the linear vector through a classifier to realize the classification and positioning processing of the rock core.
Here, the core discrimination network in the above process is a trained network model. Therefore, before using the core discriminating network, model training is required.
Here, before the model training, data processing is performed to obtain a training image set.
The training process specifically comprises the following steps:
in order to realize the judgment, classification analysis operation and the like of the rock core under the static state, the data needs to be subjected to label processing. Namely, the data is processed by means of label marking. And (3) marking different types of rock cores, marking the corresponding types of the rock cores, such as strong differentiation, full weathering, medium weathering, micro weathering, granite, sandstone and the like, and marking the rock cores as shown in figure 3.
Here, in the core box shown in fig. 3, the rock sample is one meter and one grid, and in order to accurately judge the rock, the grid needs to be marked in units of grids.
Here, the data preprocessing process includes:
inputting: a core picture;
and (3) outputting: marking the processed core picture array to generate a label array;
step 1: defining a data graph path;
step 2: preprocessing a picture, carrying out histogram equalization and standardizing the size of the picture;
and step 3: labeling the picture;
and 4, step 4: defining data group, and writing into file.
The method mainly aims at the development analysis of the drilling core, and the core sample can be divided into strong differentiation, total weathering, medium weathering and slight weathering according to different weathering degrees; according to different rock samples, the rock samples can be divided into granite, sandstone and the like. This embodiment may be labeled according to core characteristics.
Here, in data processing, labeling is performed on an original data set, and the data set may be divided into a training set, a test set, and a verification set. Training is carried out through the data in the training set, testing is carried out through the data in the testing set, and verification is carried out through the data in the verification set.
In addition, during training, the training effect can be achieved through a loss function. Here, the loss function includes a classification loss and a localization loss.
After the labeled data after data processing is obtained, model training can be carried out by using the labeled data, and the specific training process is as follows:
inputting: training data set
And (3) outputting: core discriminating network
Step 1: preprocessing an image;
step 2: processing a data label;
and step 3: writing the processed data into an h5 file;
and 4, step 4: defining a core distinguishing network model;
and 5: selecting a training strategy-random gradient descent;
step 6: setting parameters such as data volume, learning rate and optimizer of each batch;
and 7: the core distinguishing network training, printing the loss value in the training process, storing a generation of training model, using a verification data set for verification, printing a verification result and storing the verification result in a training log;
and 8: importing test data for testing;
and step 9: model evaluation was performed on the test data set.
The embodiment is a core labeling method based on core characteristics, and a core determination model based on image segmentation, deconvolution and feature extraction is constructed. The core judgment model is utilized to analyze the data set, a system is built, the core judgment can be realized through experimental prediction, and the accuracy is high.
In order to implement the method according to the embodiment of the present invention, an embodiment of the present invention further provides a core category determining apparatus, and as shown in fig. 4, the core category determining apparatus 400 includes: an acquisition module 401, a segmentation module 402, a deconvolution module 403, a determination module 404 and a labeling module 405; wherein the content of the first and second substances,
an obtaining module 401, configured to obtain an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
a segmentation module 402, configured to perform segmentation processing on the image to be identified to obtain a segmented first image;
a deconvolution module 403, configured to perform deconvolution processing on the first image by using a deconvolution network in a preset model, to obtain a second image with an enlarged feature plane;
a determining module 404, configured to perform feature extraction and identification on the second image, and determine core categories of multiple cores in the image to be identified;
and the marking module 405 is configured to mark each of the core categories at corresponding core positions in the image to be identified to obtain the marked identification image.
In practical applications, the obtaining module 401, the segmenting module 402, the deconvolution module 403, the determining module 404 and the labeling module 405 may be implemented by a processor in the core category determination device.
It should be noted that: the above-mentioned apparatus provided in the above-mentioned embodiment is only exemplified by the division of the above-mentioned program modules when executing, and in practical application, the above-mentioned processing may be distributed to be completed by different program modules according to needs, that is, the internal structure of the terminal is divided into different program modules to complete all or part of the above-mentioned processing. In addition, the apparatus provided by the above embodiment and the method embodiment belong to the same concept, and the specific implementation process thereof is described in the method embodiment and is not described herein again.
To implement the method of the embodiments of the present invention, the embodiments of the present invention also provide a computer program object, which includes computer instructions, the computer instructions being stored in a computer readable storage medium. A processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of the above-described method.
Based on the hardware implementation of the program module, in order to implement the method according to the embodiment of the present invention, an electronic device (computer device) is also provided in the embodiment of the present invention. Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer apparatus includes a processor a01, a network interface a02, a display screen a04, an input device a05, and a memory (not shown in the figure) connected through a system bus. Wherein processor a01 of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises an internal memory a03 and a non-volatile storage medium a 06. The nonvolatile storage medium a06 stores an operating system B01 and a computer program B02. The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a 06. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program is executed by the processor a01 to implement the method of any of the above embodiments. The display screen a04 of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device a05 of the computer device may be a touch layer covered on the display screen, a button, a trackball or a touch pad arranged on a casing of the computer device, or an external keyboard, a touch pad or a mouse.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The device provided by the embodiment of the present invention includes a processor, a memory, and a program stored in the memory and capable of running on the processor, and when the processor executes the program, the method according to any one of the embodiments described above is implemented.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program object. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program object embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program objects according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (transmyedia) such as modulated data signals and carrier waves.
It will be appreciated that the memory of embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The described memory for embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of core class determination, the method comprising:
acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
carrying out segmentation processing on the image to be identified to obtain a segmented first image;
carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface;
performing feature extraction and identification on the second image, and determining the core categories of a plurality of cores in the image to be identified;
and for each core type, marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image.
2. The method of claim 1, wherein the feature extracting and identifying the second image and determining core categories of a plurality of cores in the image to be identified comprises:
extracting the features of the second image by using a feature extraction network in a preset model to obtain a plurality of first vectors;
and classifying and identifying each first vector by using a classifier in the preset model, and determining the core category corresponding to each first vector.
3. The method according to claim 2, wherein the classifying and identifying each first vector by using a classifier in the preset model, and the determining the core class corresponding to each first vector comprises:
classifying and identifying each first vector by using a classifier in the preset model, and determining a first core class and a second core class corresponding to each first vector; wherein the first core category characterizes a degree of weathering of the core and the second core category characterizes a sample type of the core.
4. The method according to claim 3, wherein for each core category, the core category is labeled at a corresponding core position in the image to be identified, and obtaining a labeled identification image comprises:
and marking the first core type and the second core type corresponding to each first vector at the corresponding core position in the image to be identified to obtain a marked identification image.
5. The method according to claim 2, wherein the extracting features of the second image by using a feature extraction network in a preset model, and obtaining a plurality of first vectors comprises:
extracting the features of the second image by using a feature extraction network in the preset model to obtain feature information;
generating a feature map according to the feature information;
and carrying out weighting processing on the characteristic diagram to obtain a plurality of first vectors.
6. The method of claim 1, wherein prior to acquiring the image to be identified, the method further comprises:
acquiring a training image set;
labeling the training image set to obtain a first image set after labeling;
and training a model by using the first image set to obtain the preset model.
7. The method according to claim 1, wherein the performing segmentation processing on the image to be recognized to obtain a segmented first image comprises:
equally dividing the image to be identified into three equal parts from top to bottom;
the segmented image is defined as a first image.
8. A core category determination apparatus, characterized in that the core category determination apparatus comprises:
the acquisition module is used for acquiring an image to be identified; the method comprises the steps that a plurality of rock cores in an image to be identified are arranged according to a preset rule;
the segmentation module is used for carrying out segmentation processing on the image to be identified to obtain a segmented first image;
the deconvolution module is used for carrying out deconvolution processing on the first image by using a deconvolution network in a preset model to obtain a second image with an enlarged characteristic surface;
the determining module is used for extracting and identifying the features of the second image and determining the core categories of a plurality of cores in the image to be identified;
and the marking module is used for marking the core type at the corresponding core position in the image to be identified to obtain the marked identification image for each core type.
9. An electronic device, comprising: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,
the processor is adapted to perform the steps of the method of any one of claims 1 to 7 when running the computer program.
10. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974902.5A CN113420768A (en) | 2021-08-24 | 2021-08-24 | Core category determination method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974902.5A CN113420768A (en) | 2021-08-24 | 2021-08-24 | Core category determination method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113420768A true CN113420768A (en) | 2021-09-21 |
Family
ID=77719213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110974902.5A Pending CN113420768A (en) | 2021-08-24 | 2021-08-24 | Core category determination method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420768A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082454A (en) * | 2022-07-27 | 2022-09-20 | 深圳市信润富联数字科技有限公司 | Core discriminating method, core discriminating device, electronic device and storage medium |
| CN115359348A (en) * | 2022-07-20 | 2022-11-18 | 中南大学 | Core characteristic identification statistical method, system, equipment and storage medium |
| CN116883852A (en) * | 2023-08-29 | 2023-10-13 | 北京建工环境修复股份有限公司 | Core data acquisition method and system based on hyperspectrum |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529402A (en) * | 2016-09-27 | 2017-03-22 | 中国科学院自动化研究所 | Multi-task learning convolutional neural network-based face attribute analysis method |
| CN109242833A (en) * | 2018-08-23 | 2019-01-18 | 江苏中机矿山设备有限公司 | A kind of coalcutter cutting control method |
| CN208858354U (en) * | 2018-08-23 | 2019-05-14 | 江苏中机矿山设备有限公司 | Coalcutter cutting control system |
| CN110472597A (en) * | 2019-07-31 | 2019-11-19 | 中铁二院工程集团有限责任公司 | Rock image rate of decay detection method and system based on deep learning |
| CN110490100A (en) * | 2019-07-31 | 2019-11-22 | 中铁二院工程集团有限责任公司 | Ground automatic identification based on deep learning names method and system |
| CN111144225A (en) * | 2019-12-03 | 2020-05-12 | 中铁第四勘察设计院集团有限公司 | Geological exploration rock core identification method and device and storage medium |
| CN111582383A (en) * | 2020-05-09 | 2020-08-25 | 浙江商汤科技开发有限公司 | Attribute identification method and device, electronic equipment and storage medium |
| CN112560722A (en) * | 2020-12-22 | 2021-03-26 | 中国人民解放军国防科技大学 | Airplane target identification method and device, computer equipment and storage medium |
| CN112733969A (en) * | 2021-03-31 | 2021-04-30 | 北京达佳互联信息技术有限公司 | Object class identification method and device and server |
-
2021
- 2021-08-24 CN CN202110974902.5A patent/CN113420768A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529402A (en) * | 2016-09-27 | 2017-03-22 | 中国科学院自动化研究所 | Multi-task learning convolutional neural network-based face attribute analysis method |
| CN109242833A (en) * | 2018-08-23 | 2019-01-18 | 江苏中机矿山设备有限公司 | A kind of coalcutter cutting control method |
| CN208858354U (en) * | 2018-08-23 | 2019-05-14 | 江苏中机矿山设备有限公司 | Coalcutter cutting control system |
| CN110472597A (en) * | 2019-07-31 | 2019-11-19 | 中铁二院工程集团有限责任公司 | Rock image rate of decay detection method and system based on deep learning |
| CN110490100A (en) * | 2019-07-31 | 2019-11-22 | 中铁二院工程集团有限责任公司 | Ground automatic identification based on deep learning names method and system |
| CN111144225A (en) * | 2019-12-03 | 2020-05-12 | 中铁第四勘察设计院集团有限公司 | Geological exploration rock core identification method and device and storage medium |
| CN111582383A (en) * | 2020-05-09 | 2020-08-25 | 浙江商汤科技开发有限公司 | Attribute identification method and device, electronic equipment and storage medium |
| CN112560722A (en) * | 2020-12-22 | 2021-03-26 | 中国人民解放军国防科技大学 | Airplane target identification method and device, computer equipment and storage medium |
| CN112733969A (en) * | 2021-03-31 | 2021-04-30 | 北京达佳互联信息技术有限公司 | Object class identification method and device and server |
Non-Patent Citations (2)
| Title |
|---|
| 张向荣，冯婕，刘芳: "《人工智能前言技术丛书 模式识别》", 30 September 2019, 西安：西安电子科技大学出版社 * |
| 赵文清 等: "基于反卷积和特征融合的SSD 小目标检测算法", 《智能系统学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115359348A (en) * | 2022-07-20 | 2022-11-18 | 中南大学 | Core characteristic identification statistical method, system, equipment and storage medium |
| CN115082454A (en) * | 2022-07-27 | 2022-09-20 | 深圳市信润富联数字科技有限公司 | Core discriminating method, core discriminating device, electronic device and storage medium |
| CN115082454B (en) * | 2022-07-27 | 2022-12-09 | 深圳市信润富联数字科技有限公司 | Core discriminating method, core discriminating device, electronic device and storage medium |
| CN116883852A (en) * | 2023-08-29 | 2023-10-13 | 北京建工环境修复股份有限公司 | Core data acquisition method and system based on hyperspectrum |
| CN116883852B (en) * | 2023-08-29 | 2024-03-08 | 北京建工环境修复股份有限公司 | Core data acquisition method and system based on hyperspectrum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113420768A (en) | Core category determination method and device, electronic equipment and storage medium | |
| CN109272031A (en) | A kind of training sample generation method and device, equipment, medium | |
| CN111062282A (en) | Transformer substation pointer type instrument identification method based on improved YOLOV3 model | |
| CN110472597A (en) | Rock image rate of decay detection method and system based on deep learning | |
| CN104112284B (en) | The similarity detection method and equipment of a kind of picture | |
| CN110490100A (en) | Ground automatic identification based on deep learning names method and system | |
| CN108681746A (en) | A kind of image-recognizing method, device, electronic equipment and computer-readable medium | |
| Weaver et al. | LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens | |
| Younis et al. | Detection and annotation of plant organs from digitised herbarium scans using deep learning | |
| CN108062377A (en) | The foundation of label picture collection, definite method, apparatus, equipment and the medium of label | |
| WO2020225592A1 (en) | Automated method and system for categorising and describing thin sections of rock samples obtained from carbonate rocks | |
| CN107273910A (en) | Filter learning method and method, learning device and the Object identifying support device that the object in test image is detected using filter | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| CN111242922A (en) | Protein image classification method, device, equipment and medium | |
| CN114565803A (en) | Method, device and mechanical equipment for extracting difficult sample | |
| CN114324336A (en) | Nondestructive measurement method for biomass of soybean in whole growth period | |
| Møller et al. | Mechanistic spatio-temporal point process models for marked point processes, with a view to forest stand data | |
| CN111863135B (en) | False positive structure variation filtering method, storage medium and computing device | |
| CN110309825A (en) | Uighur detection method, system and electronic equipment under a kind of complex background | |
| CN110457155B (en) | Sample class label correction method and device and electronic equipment | |
| CN111259903A (en) | Identification table counting method and device, readable storage medium and computer equipment | |
| CN114021716A (en) | Model training method and system and electronic equipment | |
| CN115082454B (en) | Core discriminating method, core discriminating device, electronic device and storage medium | |
| CN112990320A (en) | Lithology classification method and device, electronic equipment and storage medium | |
| CN113627522A (en) | Image classification method, device and equipment based on relational network and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210921 |
|
| RJ01 | Rejection of invention patent application after publication |