CN114581605A - Method, device and equipment for generating scanning image of workpiece and computer storage medium - Google Patents
Method, device and equipment for generating scanning image of workpiece and computer storage medium Download PDFInfo
- Publication number
- CN114581605A CN114581605A CN202210164352.5A CN202210164352A CN114581605A CN 114581605 A CN114581605 A CN 114581605A CN 202210164352 A CN202210164352 A CN 202210164352A CN 114581605 A CN114581605 A CN 114581605A
- Authority
- CN
- China
- Prior art keywords
- target object
- image
- simulation
- dimensional
- simulated
- 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
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000004088 simulation Methods 0.000 claims abstract description 160
- 238000002591 computed tomography Methods 0.000 claims abstract description 94
- 238000011960 computer-aided design Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 239000000463 material Substances 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 16
- 238000005094 computer simulation Methods 0.000 abstract description 10
- 230000008569 process Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 16
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000005070 sampling Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013170 computed tomography imaging Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000009659 non-destructive testing Methods 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003042 antagnostic effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application discloses a method, a device and equipment for generating a scanning image of a workpiece and a computer storage medium, wherein the method comprises the following steps: acquiring a computer aided design file of a target object; carrying out three-dimensional simulation reconstruction on a computer aided design file of a target object to obtain a three-dimensional simulation image of the target object; inputting the three-dimensional simulation image into a target prediction model, and taking an image output by the target prediction model as a Computed Tomography (CT) image of the target object, wherein the target prediction model is a neural network model obtained by training a historical training sample, and the historical training sample comprises a three-dimensional simulation image and a CT image of a historical workpiece. According to the embodiment of the application, the simulated CT image of the detected object can be obtained through computer simulation under the condition of not carrying out CT detection.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a computer storage medium for generating a scanned image of a workpiece.
Background
The CT imaging technology obtains projection data of an object within a certain angle range through relative movement between the object to be detected and a detector, reconstructs the projection data into three-dimensional data of the object to be detected through an FDK algorithm, and can obtain a three-dimensional structure of the object on the premise of not damaging the object, so that the CT imaging technology is widely applied to the industrial fields of nondestructive testing, safety inspection and the like.
At present, the actual CT detection and the image labeling mode are used for obtaining the CT image of a workpiece or a sample, which is time-consuming, labor-consuming, poor in economy and difficult to manufacture an accurate sample die body. Therefore, there is a need for a new industrial CT data set generation method for acquiring CT images of various samples without actual CT detection.
Disclosure of Invention
The embodiment of the application provides a method, a device and equipment for generating a scanning image of a workpiece and a computer storage medium, which can acquire a simulated CT image of a detected object through computer simulation under the condition of not carrying out CT detection.
In a first aspect, an embodiment of the present application provides a method for generating a scan image of a workpiece, where the method includes:
acquiring a computer aided design file of a target object;
carrying out three-dimensional simulation reconstruction on a computer aided design file of a target object to obtain a three-dimensional simulation image of the target object;
inputting the three-dimensional simulation image into a target prediction model, and taking an image output by the target prediction model as a Computed Tomography (CT) image of the target object, wherein the target prediction model is a neural network model obtained by training a historical training sample, and the historical training sample comprises a three-dimensional simulation image and a CT image of a historical workpiece.
In a second aspect, an embodiment of the present application provides an apparatus for generating a scanned image of a workpiece, the apparatus including:
the acquisition module is used for acquiring a computer aided design file of a target object;
the reconstruction module is used for carrying out three-dimensional simulation reconstruction on the computer aided design file of the target object to obtain a three-dimensional simulation image of the target object;
and the prediction module is used for inputting the three-dimensional simulation image into a target prediction model and taking an image output by the target prediction model as a Computed Tomography (CT) image of the target object, wherein the target prediction model is a neural network model obtained by training a historical training sample, and the historical training sample comprises the three-dimensional simulation image and the CT image of a historical workpiece.
In a third aspect, an embodiment of the present application provides an electronic device, where the device includes: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of generating a scan image of a workpiece according to the first aspect of the present application.
In a fourth aspect, the present application provides a computer storage medium having computer program instructions stored thereon, which when executed by a processor implement the method for generating a scanned image of a workpiece according to the first aspect of the present application.
The device for generating the scanned image of the workpiece according to the embodiment of the application can acquire the simulated CT image of the target object according to the CAD file of the target object, and endow the simulated image with the characteristics of the actual CT scanned image by using the pre-trained neural network, thereby generating the CT scanned image of the target object. According to the embodiment of the application, actual CT detection is not needed, the physical process of CT scanning is simulated in a computer simulation mode, the neural network is used for endowing the simulated images with actual image characteristics, so that CT images of various workpieces are generated, the efficiency of obtaining the CT scanning images is improved, and the economy of image obtaining is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a scanned image generation method of a workpiece according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a simulation model for simulating an object according to an embodiment of the present application;
FIG. 3 is a schematic diagram of boundary contour pixel points of a simulation object according to an embodiment of the present application;
FIG. 4 is a schematic diagram of three-dimensional volume data of a simulated object to which embodiments of the present application relate;
FIG. 5 is a schematic diagram of reconstructed volume data of a simulated object according to an embodiment of the application;
FIG. 6 is a schematic diagram of an actual CT system scan image of a simulated object according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a simulated image of a simulated object according to an embodiment of the application;
fig. 8 is a schematic structural diagram of a scanned image generating apparatus for a workpiece according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In order to solve the prior art problems, embodiments of the present application provide a method, an apparatus, a device, and a computer storage medium for generating a scan image of a workpiece. First, a method for generating a scan image of a workpiece according to an embodiment of the present application will be described.
Fig. 1 is a flowchart illustrating a method for generating a scan image of a workpiece according to an embodiment of the present application. As shown in fig. 1, a method for generating a scan image of a workpiece according to an embodiment of the present application includes:
102, carrying out three-dimensional simulation reconstruction on a computer aided design file of a target object to obtain a three-dimensional simulation image of the target object;
The device for generating the scanned image of the workpiece according to the embodiment of the application can acquire the simulated CT image of the target object according to the CAD file of the target object, and endow the simulated image with the characteristics of the actual CT scanned image by using the pre-trained neural network, thereby generating the CT scanned image of the target object. According to the embodiment of the application, actual CT detection is not needed, the physical process of CT scanning is simulated in a computer simulation mode, the neural network is used for endowing the simulated images with actual image characteristics, so that CT images of various workpieces are generated, the efficiency of obtaining the CT scanning images is improved, and the economy of image obtaining is improved.
The method for generating a scanned image of a workpiece according to the embodiments of the present application can be applied to an industrial design process to obtain a scanned image of the workpiece, and can be executed by a computer when the method is applied to the industrial design process. In the present application, the generation of the scanned image of the workpiece is for convenience of description, and the method for generating the scanned image of the workpiece is not to be construed as limiting the scope of application of the method for generating the scanned image of the workpiece in the present application.
Referring to step 101, a computer may obtain a computer-aided design file of a target object.
The target object may be an object or a workpiece in an industrial CT, such as a product or a part of a product in an industrial manufacturing process. For detection tasks such as security inspection focusing on object identification and segmentation, the object to be simulated can be designed into various different kinds of workpiece combinations.
The target object may be composed of one or more materials, and the kind, density, and properties of the material itself of each part of the target object may be obtained according to the design properties of the target object.
The computer aided design file is a file formed in a computer aided design process, which contains structural data of a target object, and the computer aided design file of the embodiment of the present application may be a product (engineering) design file formed in a digital manner by using a computer aided design system, for example: STL format and OBJ format files, etc.
The computer-aided design software may include: AutoCAD, CAXA, CATIA, Solid works, and the like.
The computer aided design file of the target object can be obtained by a computer from a storage device or a cloud server, and can also be input by a user.
For example, assuming that the scan image acquisition method of a workpiece of the present application is applied to industrial manufacturing, a computer may acquire a computer-aided design file of a workpiece for which a scan image is to be generated when acquiring a scan image of the workpiece.
The three-dimensional simulation reconstruction refers to a process of acquiring a three-dimensional simulation image of a target object by a computer in a simulation mode.
The three-dimensional simulation image may be a simulated CT image of the target object, i.e. a simulated scan image of a simulated model of the target object.
For example, assuming that the scanning image acquiring method of the workpiece of the present application is applied to industrial manufacturing, the computer may acquire three-dimensional data of a target object according to a computer-aided design file of the target object, build a simulation model according to the three-dimensional data of the target object, and perform CT imaging simulation according to the simulation model, thereby acquiring a three-dimensional simulation image of the target object.
In an embodiment of the present application, performing three-dimensional simulation reconstruction on a computer-aided design file of a target object to obtain a three-dimensional simulation image of the target object includes:
acquiring boundary contour pixel point information of a simulation model of a target object through a computer aided design file;
filling the simulation model according to the boundary contour pixel point information of the simulation model of the target object to obtain three-dimensional volume data of the target object;
acquiring first simulation attenuation projection data of a target object according to the three-dimensional volume data of the target object;
and reconstructing the first simulation attenuation projection data to obtain a three-dimensional simulation image of the target object.
The simulation model of the target object may be a computer simulation model of the target object generated from a computer aided design file of the target object, and specifically, the simulation model may be a three-dimensional solid model of the target object generated by modeling according to parameter characteristics of the target object. The simulation model of the target object includes structural information such as point-plane data of the target object.
The boundary contour pixel points of the simulation model of the target object are pixel points located on the boundary contour of the simulation model of the target object, and the boundary contour pixel points can be obtained through computer discretization sampling.
The computer can carry out discretization sampling in Matlab software according to the point-surface data of the object to be simulated so as to obtain boundary contour pixel points of a simulation model of the target object, the number of sampling points is determined by the requirement of simulation precision, and the more the number of the sampling points is, the finer the model of the simulation object is.
The physical size of the pixel can be determined according to the ratio of the actual physical size of the simulation model in the x, y and z directions to the number of sampling points of the simulation model in the x, y and z directions, and the specific formula is as follows:
wherein d isx,y,zIs the physical size of the pixel in the x, y, z direction of the volume data pixel, Sx,y,zIs the actual physical dimension of the object in the x, y, z directions, Nx,y,zIs the number of sampling points in the x, y, z direction.
The filling of the target object simulation model may be filling of the simulation model according to the boundary contour pixel point information of the target object simulation model to generate three-dimensional volume data of the target object, and specifically, the computer may fill a closed structure formed by the boundary contour pixel points of the target object.
The three-dimensional volume data of the target object is three-dimensional structure data of the target object after the filling of the simulation model.
The first simulated attenuation projection data is CT projection data of the target object predicted from target object material and structure information and simulated ray parameters, and may also be referred to as theoretical attenuation projection data.
The computer may acquire first simulated attenuation projection data based on the material of the target object and the simulated CT image actual acquisition process.
The three-dimensional simulation image of the target object is a reconstructed image of the target object obtained by three-dimensionally reconstructing the target object by a computer.
Specifically, the computer may reconstruct from the first simulated attenuation projection data of the target object using a CT image reconstruction algorithm to obtain a simulated CT image of the target object.
The CT image reconstruction algorithm may include: back projection method, iterative reconstruction algorithm, analytic method, etc.
As an implementation manner of the present application, the computer may reconstruct the first simulated attenuation projection data of the target object by using an FDK (Filtered back projection) algorithm.
FDK algorithm principle: by measuring and operating the X-ray passing through the cross section of the object, the absorption coefficients corresponding to the space positions of the body layers of the object one by one are obtained, so that the structural information of the cross section of the object is recovered.
For example, assuming that the scanning image obtaining method of the workpiece of the present application is applied to industrial manufacturing, a computer may obtain a simulation model of a target object according to a computer-aided design file of the target object, and obtain boundary contour pixel point information of the simulation model through discretization sampling. The computer can fill the closed structure formed by the boundary contour pixel points of the target object simulation model to obtain the three-dimensional volume data of the target object. The computer generates first simulation attenuation projection data of the target object according to the three-dimensional volume data of the target object and the actual generation process of the CT image, and reconstructs the three-dimensional simulation image of the target object according to the first simulation attenuation projection data.
In the embodiment, the physical process of CT scanning is simulated by the computer, and CT images of various workpieces can be generated according to the three-dimensional volume data of the target object and relevant parameters of CT image scanning without actual CT detection, so that the efficiency of acquiring the CT scanning images is improved, and the economy of image acquisition is improved.
In an embodiment of the present application, before filling the simulation model according to the boundary contour pixel point information of the simulation model of the target object to obtain the three-dimensional volume data of the target object, the method includes:
acquiring target input of the simulation model;
responding to target input, updating boundary contour pixel point information of the simulation model to obtain updated boundary contour pixel point information;
filling the target object according to the boundary contour pixel point information of the simulation model of the target object to obtain the three-dimensional volume data of the target object, comprising the following steps:
and filling the simulation model of the target object based on the updated boundary contour pixel point information to obtain the three-dimensional volume data of the simulation model of the target object after the boundary contour pixel point information is updated.
The target input may be modification input to the boundary contour pixel points of the simulation model, for example, changing the sparsity of the boundary contour pixel points or deleting part of the boundary contour pixel points.
The computer can modify the boundary contour pixel points of the target object simulation model according to the corresponding target input so as to obtain the corresponding modified boundary contour pixel points of the target object simulation model.
The filling of the simulation model of the target object may be filling the simulation model according to the modified boundary contour pixel point information of the simulation model of the target object, so as to generate three-dimensional volume data of the target object. Specifically, the computer may fill the closed structure formed by the modified boundary contour pixel points of the target object.
Exemplarily, assuming that the method for acquiring a scanned image of a workpiece is applied to industrial manufacturing, a computer may acquire an input instruction to a simulation model of a target object, modify boundary contour pixel points of the target object according to the input instruction, and fill a closed structure formed by the modified boundary contour pixel points of the target object to acquire three-dimensional volume data of the target object.
In this embodiment, in response to the input command, the computer may modify the boundary contour pixel points of the simulation model of the target object, simulate the situation that holes or cracks exist in the target object or the workpiece, and simulate the generation of the CT scan image of the defective workpiece. Defects such as holes and cracks can be artificially manufactured in a mode of manually modifying boundary contour pixel points of a simulation model of a target object, so that a nondestructive testing task of defect detection is realized, and resources consumed by actual detection are saved through computer simulation.
In an embodiment of the present application, before obtaining the first simulated attenuation projection data of the target object according to the three-dimensional volume data of the target object, the method further includes:
acquiring material information of each part of a simulation model of a target object and physical parameters of simulation rays;
obtaining first simulated attenuation projection data of a target object according to three-dimensional volume data of the target object, comprising:
and acquiring first simulation attenuation projection data of the target object according to the material information of each part of the target object simulation model and the physical parameters of the simulation rays.
The simulated ray is a ray emitted by a ray source in the actual generation process of the computer simulation CT image, such as an X-ray. The physical parameters of the simulated ray may refer to relevant parameters of the actual ray, and in particular, the physical parameters of the simulated ray may include energy spectrum information of the simulated ray.
The computer may obtain materials and material properties corresponding to portions of the simulation model of the target object, and the material properties may include absorption coefficients of the materials for different rays.
The materials corresponding to each part of the simulation model of the target object can be determined according to the design requirements of the target object or according to the information in the design file of the target object, or can be specified by user input.
The computer can acquire material information of each part of the target object from a design file of the target object, and can also acquire the material information of the target object according to information input by a user. In particular, the computer may acquire first simulated attenuation projection data based on the material of the target object and the simulated CT image actual acquisition process.
For example, assuming that the scanned image acquisition method of a workpiece of the present application is applied to industrial manufacturing, a computer may acquire material information of a simulation model of a target object and parameter information of a simulation ray, and acquire first simulated attenuation projection data of the target object by using a computer simulation manner according to the material information of the target object and the parameter information of the simulation ray.
In this embodiment, the computer may simulate the CT image generation process to obtain first simulated attenuation projection data of the target object by obtaining material parameters of portions of the simulated model of the target object and physical parameters of the simulated rays. The first simulation attenuation projection data of the target object is obtained in a computer simulation mode, so that the actual scanning process required for obtaining the CT image is avoided, and time and computer resources can be saved.
In an embodiment of the present application, acquiring first simulated attenuation projection data of a target object according to material information of each part of a target object simulation model and physical parameters of simulated rays includes:
assigning the three-dimensional volume data of the target object based on the material information and the physical parameters of the simulation rays to obtain the three-dimensional volume data of the target object after assignment;
acquiring preset path information from a ray source to a detector unit;
and performing orthographic projection processing on the three-dimensional data of the assigned target object according to the path information to obtain first simulation attenuation projection data of the target object.
Assigning the three-dimensional volume data of the target object may be assigning materials and material-corresponding ray attenuation coefficients of respective portions of the three-dimensional volume data of the target object to respective portions of the three-dimensional volume data of the target object.
Linear attenuation coefficient: the linear attenuation coefficient μ represents the probability of a photon to interact with a substance through a unit path.
The computer can calculate the ray attenuation coefficient mu of different materials according to the ray energy spectrum f (E) and the material informationi。
The ray attenuation coefficient corresponding to the material of the target object is the sum of the products of the size of a unit pixel of the target object and the line attenuation coefficient of the ray corresponding to the unit pixel.
The specific formula is as follows:
wherein, K is the number of segments of the energy spectrum f (E), j is the index of the energy segment, EjIs the energy of the radiation in the j energy segment,
for the ith material to an energy of EjD is the size of a unit pixel in the three-dimensional volume data.
Ray attenuation coefficients corresponding to the material of the target object may be assigned to the corresponding material of each portion of the three-dimensional volume data of the target object.
The preset ray source and detector unit can be a ray source and detector unit in the process of simulating the actual CT image acquisition by a computer.
The computer can simulate the position relation between the detection unit and the ray source in the actual CT image acquisition process, and obtain the preset path from the ray source to the detection unit according to the geometric parameters actually acquired by the system.
The orthographic projection process is a process of acquiring projection data by utilizing integral transformation in the CT scanning process.
The computer can calculate the path l from the ray source to the detector unitnThe first simulation attenuation projection data of the target object is obtained by the line integral of the attenuation coefficient of the passed detected object.
Exemplarily, assuming that the scanning image obtaining method of the workpiece of the present application is applied to industrial manufacturing, the computer may obtain line attenuation coefficients of materials of each portion of the target object to the ray according to the obtained material information of each portion of the target object and physical parameters of the simulated ray, and assign the line attenuation coefficients of the corresponding materials to corresponding portions of the three-dimensional volume data of the target object; and the computer carries out forward projection on the three-dimensional data of the target object according to the corresponding parameters of each part and the path from the simulated ray source to the detector unit so as to obtain first simulated attenuation projection data of the target object.
In this embodiment, the computer may simulate a CT scanning process to forward project the three-dimensional volume data of the target object according to the parameter information of each portion of the three-dimensional volume data of the target object and the parameter information of the simulated rays and the path of the simulated CT scan to obtain first simulated attenuation projection data of the target object.
In an embodiment of the present application, reconstructing the first simulated attenuation projection data to obtain a three-dimensional simulated image of the target object includes:
adding Poisson noise to the first simulated attenuation projection data to obtain second simulated attenuation projection data;
and reconstructing the second simulation attenuation projection data according to a CT image reconstruction algorithm to obtain a three-dimensional simulation image of the target object.
In the embodiment of the present application, poisson noise is a noise model conforming to a poisson distribution model. The second simulated attenuation projection data is the first simulated attenuation projection data added with the Poisson noise.
Illustratively, the computer may pre-process the first simulated attenuation projection data, e.g. add poisson noise to the first simulated attenuation projection data to obtain the second simulated attenuation projection data. And the computer reconstructs the data according to the second simulation attenuation projection data to generate a three-dimensional simulation image of the target object.
In this embodiment, the real projection data may be simulated by adding poisson noise to the first simulated attenuation projection data of the target object, improving the accuracy of the simulated image.
The target prediction model may be a neural network model, which may impart features of the actual CT scan image to the simulated image to approximate the simulated data to the actual CT scan data. The image output by the target prediction model is a CT predicted image of the target object.
The neural network model may be a generation of an antagonistic neural network, and may specifically be a Cycle GAN.
The historical training samples of the target prediction model may be actual CT images of historical workpieces as well as simulated CT images.
The computer can use a Pythrch deep learning tool to train a Cycle-GAN network for style migration, wherein two types of A, B data sets are needed for training, and the trained model can perform migration transformation on image styles in A, B data sets. The data set a required for training is an image set obtained by scanning of an actual CT system, and the required training set B is a set of simulation images generated by the method for generating a scanned image of a workpiece according to the embodiment of the present application.
For example, assuming that the scanned image acquisition method of a workpiece of the present application is applied to industrial manufacturing, a computer may input a generated three-dimensional simulation image of a target object into a target prediction model, and assign features of an actual CT image to the three-dimensional simulation image using the target prediction model to obtain a computed tomography CT image of the target object.
The embodiment of the present application further provides a specific implementation manner:
step one, according to the detection task and the characteristics of the detection object, a computer aided design drawing of the object to be simulated is designed by using computer aided design software. A simulation model of a simulated object is shown in FIG. 2
And step two, reading the computer aided design file of the object to be simulated in Matlab software to obtain point-surface data of the simulated object.
As shown in fig. 3, according to the point-surface data of the object to be simulated, discretization sampling is performed in Matlab software to obtain pixel points of the boundary profile of the volume data of the simulated object.
Step three, as shown in fig. 4, three-dimensional filling is carried out on the boundary contour pixel points of the simulation object obtained by the method, and three-dimensional volume data V of the object to be simulated is obtained1. For nondestructive testing tasks that focus on defect detection, the simulation can be changedDefects such as holes and cracks are artificially produced by means of pixel values in the three-dimensional volume data of the real object.
And step four, assigning the three-dimensional volume data of the simulation object, wherein the value of each pixel is determined by the material type of the position and the energy spectrum of the radioactive source adopted by CT scanning. The value can be calculated by the following formula:
wherein, K is the number of segments of the energy spectrum f (E), j is the energy segment index, EjIs the energy of the radiation in the j energy segment,
for the i-th material to an energy of EjD is the size of a unit pixel in the volume data V.
For three-dimensional volume data V1Carrying out orthographic projection according to the geometric parameters actually acquired by the system to obtain theoretical attenuation projection data
The orthographic projection process is to calculate the path l from a ray source to a detector unitnThe line integral of the attenuation coefficient of the passing detected object is as follows:
as shown in fig. 5, after poisson noise is added to the theoretical attenuation projection data, FDK or iterative algorithm is used to perform three-dimensional reconstruction, and reconstructed volume data V is obtained2。
And fifthly, training a Cycle-GAN network for style migration by using a Pythrch deep learning tool, wherein two types of A, B data sets are required for training, and the trained model can perform migration conversion on the image style in the A, B data set. Wherein, the data set A required by training is the image set obtained by scanning the actual CT system, and the required training set B is the above-mentioned data setThe simulation image V obtained in the step2A collection of (a). The image acquired by the actual CT system scan in data set a may be an image as shown in fig. 6.
Sixthly, reconstructing the data V obtained in the step2Inputting the tomogram into the Cycle-GAN network model obtained in the fifth step to obtain a simulated image I of the tomogram, and combining the simulated images of all the tomograms to form simulated volume data V3. A simulation image of a tomographic image output by the Cycle-GAN is shown in FIG. 7.
Sixthly, repeating the steps to obtain a large amount of simulation volume data V3And summarizing the data to obtain a final data set S. The number of reconstructions is determined by the number of workpiece types required.
As shown in fig. 8, the present application further provides a scanned image generating apparatus 800 of a workpiece, comprising:
an obtaining module 801, configured to obtain a computer-aided design file of a target object;
a reconstruction module 802, configured to perform three-dimensional simulation reconstruction on the computer-aided design file of the target object to obtain a three-dimensional simulation image of the target object;
a prediction module 803, configured to input the three-dimensional simulation image into a target prediction model, and take an image output by the target prediction model as a Computed Tomography (CT) image of a target object, where the target prediction model is a neural network model obtained through training of a historical training sample, and the historical training sample includes the three-dimensional simulation image of a historical workpiece and the CT image
The device for generating the scanned image of the workpiece according to the embodiment of the application can acquire the simulated CT image of the target object according to the CAD file of the target object, and endow the simulated image with the characteristics of the actual CT scanned image by using the pre-trained neural network, thereby generating the CT scanned image of the target object. According to the embodiment of the application, actual CT detection is not needed, the physical process of CT scanning is simulated in a computer simulation mode, the neural network is used for endowing the simulated images with actual image characteristics, so that CT images of various workpieces are generated, the efficiency of obtaining the CT scanning images is improved, and the economy of image obtaining is improved.
In some embodiments of the present application, the reconstruction module 802 includes:
the first acquisition unit is used for acquiring boundary contour pixel point information of a simulation model of a target object through a computer aided design file;
the filling unit is used for filling the simulation model according to the boundary contour pixel point information of the simulation model of the target object to obtain three-dimensional volume data of the target object;
the second acquisition unit is used for acquiring first simulation attenuation projection data of the target object according to the three-dimensional volume data of the target object;
and the reconstruction unit is used for reconstructing the first simulation attenuation projection data to obtain a three-dimensional simulation image of the target object.
In some embodiments of the present application, the reconstruction module 802 further comprises:
a third obtaining unit, configured to obtain a target input to the simulation model;
the updating unit is used for responding to target input and updating the boundary contour pixel point information of the simulation model to obtain updated boundary contour pixel point information;
the filling unit is specifically configured to:
and filling the simulation model of the target object based on the updated boundary contour pixel point information to obtain the three-dimensional volume data of the simulation model of the target object after the boundary contour pixel point information is updated.
In some embodiments of the present application, the reconstruction module 802 further comprises:
the fourth acquisition unit is used for acquiring material information of each part of the simulation model of the target object and physical parameters of the simulation rays;
the second obtaining unit is specifically configured to:
and acquiring first simulation attenuation projection data of the target object according to the material information of each part of the target object simulation model and the physical parameters of the simulation rays.
In some embodiments of the present application, the second obtaining unit is further specifically configured to:
assigning the three-dimensional volume data of the target object based on the material information and the physical parameters of the simulation rays to obtain the three-dimensional volume data of the target object after assignment;
acquiring preset path information from a ray source to a detector unit;
and performing orthographic projection processing on the three-dimensional data of the assigned target object according to the path information to obtain first simulation attenuation projection data of the target object.
In some embodiments of the present application, the reconstruction unit is further specifically configured to:
adding Poisson noise to the first simulated attenuation projection data to obtain second simulated attenuation projection data;
and reconstructing the second simulation attenuation projection data according to a CT image reconstruction algorithm to obtain a three-dimensional simulation image of the target object.
Each module/unit in the apparatus shown in fig. 8 has a function of implementing each step in the method embodiment, and can achieve the corresponding technical effect, and for brevity, no further description is given here.
Fig. 9 shows a hardware structure diagram of an electronic device 900 provided in an embodiment of the present application.
The electronic device 900 may include a processor 901 and a memory 902 that stores computer program instructions.
Specifically, the processor 901 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory may include Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the application.
The processor 901 realizes the scan image generation method of any one of the workpieces in the above embodiments by reading and executing the computer program instructions stored in the memory 902.
In one example, electronic device 900 may also include a communication interface 909 and a bus 910. As shown in fig. 9, the processor 901, the memory 902, and the communication interface 909 are connected by a bus 910 to complete communication therebetween.
The communication interface 909 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present application.
The electronic device 900 may execute the scanned image generation method of the workpiece in the embodiment of the present application, so as to implement the scanned image generation method and apparatus of the workpiece described in conjunction with fig. 1 and 8.
In addition, in combination with the method for generating a scanned image of a workpiece in the above embodiments, the embodiments of the present application may be implemented by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement a method of generating a scanned image of a workpiece as in any of the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations 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, 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, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (10)
1. A method of generating a scan image of a workpiece, comprising:
acquiring a computer aided design file of a target object;
carrying out three-dimensional simulation reconstruction on a computer aided design file of a target object to obtain a three-dimensional simulation image of the target object;
inputting the three-dimensional simulation image into a target prediction model, and taking an image output by the target prediction model as a Computed Tomography (CT) image of the target object, wherein the target prediction model is a neural network model obtained by training a historical training sample, and the historical training sample comprises a three-dimensional simulation image and a CT image of a historical workpiece.
2. The method of claim 1, wherein the performing three-dimensional simulation reconstruction on the computer-aided design file of the target object to obtain a three-dimensional simulation image of the target object comprises:
acquiring boundary contour pixel point information of a simulation model of the target object through the computer aided design file;
filling the simulation model according to the boundary contour pixel point information of the simulation model of the target object to obtain three-dimensional volume data of the target object;
acquiring first simulation attenuation projection data of the target object according to the three-dimensional volume data of the target object;
and reconstructing the first simulation attenuation projection data to obtain a three-dimensional simulation image of the target object.
3. The method according to claim 2, wherein before the filling the simulation model of the target object according to the boundary contour pixel point information of the simulation model to obtain the three-dimensional volume data of the target object, the method comprises:
acquiring target input to the simulation model;
responding to the target input, updating the boundary contour pixel point information of the simulation model to obtain updated boundary contour pixel point information;
the filling the target object according to the boundary contour pixel point information of the simulation model of the target object to obtain the three-dimensional volume data of the target object includes:
and filling the simulation model of the target object based on the updated boundary contour pixel point information to obtain the three-dimensional volume data of the simulation model of the target object after the boundary contour pixel point information is updated.
4. The method of claim 2, further comprising, prior to the obtaining first simulated attenuation projection data of the target object from three-dimensional volume data of the target object:
acquiring material information of each part of a simulation model of the target object and physical parameters of simulation rays;
the acquiring first simulated attenuation projection data of the target object according to the three-dimensional volume data of the target object comprises:
and acquiring first simulation attenuation projection data of the target object according to the material information of each part of the target object simulation model and the physical parameters of the simulation rays.
5. The method of claim 4, wherein the obtaining the first simulated attenuation projection data of the target object according to the material information of each part of the target object simulation model and the physical parameters of the simulated ray comprises:
assigning the three-dimensional volume data of the target object based on the material information and the physical parameters of the simulation rays to obtain the three-dimensional volume data of the target object after assignment;
acquiring preset path information from a ray source to a detector unit;
and performing orthographic projection processing on the three-dimensional data of the assigned target object according to the path information to obtain first simulation attenuation projection data of the target object.
6. The method of claim 2, wherein said reconstructing the first simulated attenuation projection data to obtain a three-dimensional simulated image of the target object comprises:
adding Poisson noise to the first simulated attenuation projection data to obtain second simulated attenuation projection data;
and reconstructing the second simulation attenuation projection data according to a CT image reconstruction algorithm to obtain a three-dimensional simulation image of the target object.
7. An apparatus for generating a scan image of a workpiece, the apparatus comprising:
the acquisition module is used for acquiring a computer aided design file of a target object;
the reconstruction module is used for carrying out three-dimensional simulation reconstruction on the computer aided design file of the target object to obtain a three-dimensional simulation image of the target object;
and the prediction module is used for inputting the three-dimensional simulation image into a target prediction model and taking an image output by the target prediction model as a Computed Tomography (CT) image of the target object, wherein the target prediction model is a neural network model obtained by training a historical training sample, and the historical training sample comprises the three-dimensional simulation image and the CT image of a historical workpiece.
8. An electronic device, characterized in that the device comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of generating a scan image of a workpiece according to any of claims 1 to 6.
9. A computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, implement a method of generating a scan image of a workpiece as claimed in any one of claims 1 to 6.
10. A computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform a method of generating a scan image of a workpiece according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210164352.5A CN114581605A (en) | 2022-02-22 | 2022-02-22 | Method, device and equipment for generating scanning image of workpiece and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210164352.5A CN114581605A (en) | 2022-02-22 | 2022-02-22 | Method, device and equipment for generating scanning image of workpiece and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114581605A true CN114581605A (en) | 2022-06-03 |
Family
ID=81773123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210164352.5A Pending CN114581605A (en) | 2022-02-22 | 2022-02-22 | Method, device and equipment for generating scanning image of workpiece and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581605A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611750A (en) * | 2023-12-05 | 2024-02-27 | 北京思博慧医科技有限公司 | Method and device for constructing three-dimensional imaging model, electronic equipment and storage medium |
| CN117710199A (en) * | 2023-12-26 | 2024-03-15 | 中国矿业大学 | Three-dimensional imaging method and related equipment thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978965A (en) * | 2019-03-21 | 2019-07-05 | 江南大学 | A kind of simulation CT image generating method, device, computer equipment and storage medium |
| CN110337272A (en) * | 2017-02-24 | 2019-10-15 | 拜耳医药保健有限公司 | System and method for generating simulation computer tomoscan (CT) image |
| CN111047693A (en) * | 2019-12-27 | 2020-04-21 | 浪潮(北京)电子信息产业有限公司 | Image training data set generation method, device, equipment and medium |
| CN112233227A (en) * | 2020-10-20 | 2021-01-15 | 北京航星机器制造有限公司 | CT projection drawing generation method and device |
| US20210251590A1 (en) * | 2019-01-30 | 2021-08-19 | Tencent Technology (Shenzhen) Company Limited | Ct image generation method and apparatus, computer device, and computer-readable storage medium |
-
2022
- 2022-02-22 CN CN202210164352.5A patent/CN114581605A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110337272A (en) * | 2017-02-24 | 2019-10-15 | 拜耳医药保健有限公司 | System and method for generating simulation computer tomoscan (CT) image |
| US20210251590A1 (en) * | 2019-01-30 | 2021-08-19 | Tencent Technology (Shenzhen) Company Limited | Ct image generation method and apparatus, computer device, and computer-readable storage medium |
| CN109978965A (en) * | 2019-03-21 | 2019-07-05 | 江南大学 | A kind of simulation CT image generating method, device, computer equipment and storage medium |
| CN111047693A (en) * | 2019-12-27 | 2020-04-21 | 浪潮(北京)电子信息产业有限公司 | Image training data set generation method, device, equipment and medium |
| CN112233227A (en) * | 2020-10-20 | 2021-01-15 | 北京航星机器制造有限公司 | CT projection drawing generation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 陈雪睿 等: "基于仿真数据的辐射成像分类学习方法研究", 《核技术》, vol. 42, no. 3, 31 March 2019 (2019-03-31) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611750A (en) * | 2023-12-05 | 2024-02-27 | 北京思博慧医科技有限公司 | Method and device for constructing three-dimensional imaging model, electronic equipment and storage medium |
| CN117710199A (en) * | 2023-12-26 | 2024-03-15 | 中国矿业大学 | Three-dimensional imaging method and related equipment thereof |
| CN117710199B (en) * | 2023-12-26 | 2024-05-28 | 中国矿业大学 | Three-dimensional imaging method and related equipment thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114581605A (en) | Method, device and equipment for generating scanning image of workpiece and computer storage medium | |
| US20220035961A1 (en) | System and method for artifact reduction of computed tomography reconstruction leveraging artificial intelligence and a priori known model for the object of interest | |
| CN108921851B (en) | Medical CT image segmentation method based on 3D countermeasure network | |
| Bénière et al. | A comprehensive process of reverse engineering from 3D meshes to CAD models | |
| KR20210049086A (en) | Article inspection by dynamic selection of projection angle | |
| Kumar et al. | Reverse engineering in product manufacturing: an overview | |
| Bellon et al. | aRTist–analytical RT inspection simulation tool | |
| CN114693660B (en) | ICT-based solid rocket engine charge calculation grid generation method | |
| CN110268441B (en) | Method for obtaining 3D model data of multiple parts of an object | |
| CN109978985B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN111144449B (en) | Image processing method, device, storage medium and electronic equipment | |
| CN111681204A (en) | CT rib fracture focus relation modeling method and device based on graph neural network | |
| CN113762481B (en) | Tomographic imaging method and system based on deep learning | |
| Jung et al. | Crack modeling via minimum-weight surfaces in 3d Voronoi diagrams | |
| Caliskan et al. | Three-dimensional modeling in medical image processing by using fractal geometry | |
| Müller et al. | Data fusion of surface data sets of X-ray computed tomography measurements using locally determined surface quality values | |
| Elberfeld et al. | Parametric reconstruction of glass fiber-reinforced polymer composites from X-ray projection data—A simulation study | |
| Li et al. | Classify and explain: An interpretable convolutional neural network for lung cancer diagnosis | |
| CN116381650A (en) | Laser radar point cloud position and intensity simulation and test method | |
| Inanc et al. | A CAD interfaced simulation tool for X-ray NDE studies | |
| Jaenisch et al. | aRTist–Analytical RT inspection simulation tool for industrial application | |
| CN114663879A (en) | Target detection method and device, electronic equipment and storage medium | |
| US20120183121A1 (en) | Method of radio-synthetic examination of specimens | |
| Pirillo | Study on segmentation techniques for geometric measurements in industrial computed tomography | |
| CN115803825A (en) | Method relating to medical diagnosis and medical diagnosis system |
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 |