CN109087293A - A kind of method and device adjusting Electron Microscope images parameter - Google Patents
A kind of method and device adjusting Electron Microscope images parameter Download PDFInfo
- Publication number
- CN109087293A CN109087293A CN201810843900.0A CN201810843900A CN109087293A CN 109087293 A CN109087293 A CN 109087293A CN 201810843900 A CN201810843900 A CN 201810843900A CN 109087293 A CN109087293 A CN 109087293A
- Authority
- CN
- China
- Prior art keywords
- parameter
- imaging
- image
- value
- key
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
Present disclose provides a kind of method and apparatus for adjusting Electron Microscope images parameter, applied to electron microscope EM, this method comprises: EM obtains the first parameter of the preparation stage before executing imaging, first parameter is inputted into corresponding first imaging model of the EM that training obtains in advance, obtains the second parameter；It is imaged according to the first parameter of the preparation stage with the second obtained parameter, obtains the first image；The third parameter is inputted corresponding second imaging model of the EM that training obtains in advance, obtains the 4th parameter by the third parameter in the second parameter obtained described in extraction；It is imaged according to the first parameter and third parameter and obtained the 4th parameter of the preparation stage, obtains the second image；Based on the first image and second image, the imaging parameters of the EM are determined, be imaged according to the determining imaging parameters.Imaging parameters can effectively be promoted and adjust efficiency.
Description
Technical field
This disclosure relates to big data applied technical field, in particular to a kind of adjusting electron microscope (EM,
Electron Microscope) imaging parameters method and device.
Background technique
EM is a kind of optical instrument being made of the combination of a lens or several lens, for amplify small items so as to
Obtain the microstructure information of the small items.Wherein, scanning electron microscope (SEM, Scanning Electron
Microscope) with its maximum resolution up to 1 nanometer (nm), amplification factor is continuously adjusted between 20-200000 times, can
Small items outside optical microscopy limit range are imaged, and the image based on imaging is analyzed, and is widely used in
In the fields such as biology, medicine, materialogy, electronics, semi-conductor industry.
When analyzing the image that SEM is imaged, picture quality, for example, image definition directly affects subsequent image
Analyze result.And picture quality is directly related with image quality, thus, image quality is promoted, image analysis can be effectively promoted
As a result precision.The principle of SEM or EM imaging is to collect sample surfaces reflection by signal collector by electron beam irradiating sample
Secondary electron (Secondary Electrons) out, is imaged on a display screen after handling using image technique.Wherein,
Voltage, electric current, electron beam spot size (Spotsize), operating distance, the astigmatism correction imagings such as parameter and amplification factor ginseng
Number synthesis influences SEM image quality.
Summary of the invention
In view of this, the disclosure is designed to provide a kind of method and apparatus for adjusting Electron Microscope images parameter,
It is longer the time required to adjusting clear image in the prior art for solving, cause imaging parameters to adjust the lower problem of efficiency.
In a first aspect, the embodiment of the present disclosure provides a kind of method for adjusting Electron Microscope images parameter, this method packet
It includes:
The EM obtains the first parameter of the preparation stage before executing imaging, first parameter input is trained in advance
Corresponding first imaging model of the EM arrived, obtains the second parameter, and the Electron Microscope images parameter includes described first
Parameter and the second parameter；
Control is imaged according to the first parameter of the preparation stage with the second obtained parameter, and the first image is obtained；
The third parameter is inputted the institute that training obtains in advance by the third parameter in the second parameter obtained described in extraction
Corresponding second imaging model of EM is stated, the 4th parameter is obtained；
It is imaged according to the first parameter of the preparation stage, the third parameter of extraction and the 4th obtained parameter,
Obtain the second image；
Based on the first image and second image, the Electron Microscope images parameter is determined, according to determination
The Electron Microscope images.
Optionally, described to be based on the first image and second image, determine the Electron Microscope images ginseng
Number, comprising:
Obtain the clarity of the first image and the clarity of the second imaging picture；
Calculate the difference of the clarity of the first image and the clarity of second image；
If the difference is less than or equal to default poor definition threshold value, the imaging ginseng of the highest image of the clarity is obtained
Number, the imaging parameters as the EM；
If the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, replaces the first image；
The third parameter is modified to adjust the imaging parameters of re-imaging, is executed described third parameter input is trained in advance
The step of EM arrived corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value.
Optionally, the method also includes:
Show the imaging parameters of the highest image of the clarity and the highest image of the clarity.
Optionally, the EM includes scanning electron microscope SEM, obtains the preparation stage before executing imaging in the EM
Before first parameter, the method also includes:
Clearly SEM sample graph image set is obtained, the imaging that the SEM sample image concentrates every SEM sample image is extracted
Parameter, the imaging parameters include the first parameter and the second parameter；
According to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtains with the first ginseng
Number is key, take corresponding second parameter of first parameter as the first key-value pair collection of value, and, it constructs using third parameter as key,
It take corresponding 4th parameter of the third parameter as the second key-value pair collection of value；
Using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to preset first
Imaging initial model is trained, and obtains the first imaging model；And using the key that second key-value pair is concentrated as input,
Using the corresponding value of the key as output, preset second imaging initial model is trained, the second imaging model is obtained.
Optionally, first parameter includes times magnification numerical value and acceleration voltage value, and second parameter includes: electric current
Value, beam spot diameter, value, operating distance value, focus function value, astigmatism functional value；The third parameter includes: that current value, beam spot are straight
Diameter value and operating distance value, the 4th parameter includes focus function value and astigmatism functional value.
Second aspect, the embodiment of the present disclosure provide a kind of device for adjusting Electron Microscope images parameter, the device packet
It includes:
First imaging parameters obtain module, for obtaining the first parameter for executing the preparation stage before being imaged, by described the
One parameter input corresponding first imaging model of the electron microscope EM that training obtains in advance, obtains the second parameter；
First image-forming module is imaged for the first parameter according to the preparation stage and the second obtained parameter,
Obtain the first image；
Second imaging parameters obtain module, for extracting the third parameter in the second obtained parameter, by described the
Three parameters input corresponding second imaging model of the EM that training obtains in advance, obtains the 4th parameter；
Second image-forming module, for the first parameter and third parameter according to the preparation stage and the 4th obtained ginseng
Number is imaged, and the second image is obtained；
Imaging parameters determining module determines the electronic display for being based on the first image and second image
Micro mirror imaging parameters, according to the determining Electron Microscope images parametric imaging.
Optionally, the imaging parameters determining module, is specifically used for:
Obtain the clarity of the first image and the clarity of the second imaging picture；
Calculate the difference of the clarity of the first image and the clarity of second image；
If the difference is less than or equal to default poor definition threshold value, the imaging ginseng of the highest image of the clarity is obtained
Number, the imaging parameters as the EM；
If the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, replaces the first image；
The third parameter is modified to adjust the imaging parameters of re-imaging, is executed described third parameter input is trained in advance
The step of EM arrived corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value.
Optionally, described device further include:
Display module, for showing that the imaging of the highest image of the clarity and the highest image of the clarity is joined
Number.
Optionally, the EM includes scanning electron microscope SEM, described device further include:
Imaging model constructs module, for obtaining clearly SEM sample graph image set, extracts the SEM sample image and concentrates
The imaging parameters of every SEM sample image, the imaging parameters include the first parameter and the second parameter；
According to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtains with the first ginseng
Number is key, take corresponding second parameter of first parameter as the first key-value pair collection of value, and, it constructs using third parameter as key,
It take corresponding 4th parameter of the third parameter as the second key-value pair collection of value；
Using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to preset first
Imaging initial model is trained, and obtains the first imaging model；And using the key that second key-value pair is concentrated as input,
Using the corresponding value of the key as output, preset second imaging initial model is trained, the second imaging model is obtained.
Optionally, first parameter includes times magnification numerical value and acceleration voltage value, and second parameter includes: electric current
Value, beam spot diameter, value, operating distance value, focus function value, astigmatism functional value；The third parameter includes: that current value, beam spot are straight
Diameter value and operating distance value, the 4th parameter includes focus function value and astigmatism functional value.
The third aspect, the embodiment of the present disclosure provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
The step of existing above method.
Fourth aspect, the embodiment of the present disclosure provide a kind of computer readable storage medium, the computer-readable storage
Computer program is stored on medium, the computer program executes above-mentioned method when being run by processor the step of.
A kind of method for adjusting Electron Microscope images parameter that the embodiment of the present disclosure provides, trained in advance by utilization
To corresponding first imaging model of the EM and the second imaging model obtain the imaging parameters of EM respectively, based on obtaining respectively
Imaging parameters be imaged, by comparing the clarity of the image of imaging, the final imaging parameters for determining EM.In this way, passing through
The mode that big data is excavated automatically determines the imaging parameters of the corresponding EM of clear image, can effectively reduce manual adjustment imaging ginseng
Time needed for number obtains clear image shortens the time needed for adjusting obtains clear image, improves imaging parameters and adjusts effect
Rate, and can effectively reduce the cost of EM operation and maintenance cost and training technique personnel.
To enable the above objects, features, and advantages of the disclosure to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to needed in the embodiment attached in order to illustrate more clearly of the technical solution of the embodiment of the present disclosure
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the disclosure, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the method flow schematic diagram for the adjusting Electron Microscope images parameter that the embodiment of the present disclosure provides；
Fig. 2 is the flow diagram for the step 105 based on Fig. 1 that the embodiment of the present disclosure provides；
Fig. 3 is the flow diagram of building the first imaging model and the second imaging model that the embodiment of the present disclosure provides；
Fig. 4 is the apparatus structure schematic diagram for the adjusting Electron Microscope images parameter that the embodiment of the present disclosure provides；
Fig. 5 is a kind of structural schematic diagram for computer equipment 5400 that the embodiment of the present disclosure provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present disclosure clearer, below in conjunction with the embodiment of the present disclosure
The technical solution in the embodiment of the present disclosure is clearly and completely described in middle attached drawing, it is clear that described embodiment is only
It is disclosure a part of the embodiment, instead of all the embodiments.The disclosure being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the disclosure provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed the scope of the present disclosure, but is merely representative of the selected reality of the disclosure
Apply example.Based on embodiment of the disclosure, those skilled in the art institute obtained without making creative work
There are other embodiments, belongs to the range of disclosure protection.
Fig. 1 is the method flow schematic diagram for the adjusting Electron Microscope images parameter that the embodiment of the present disclosure provides.Such as Fig. 1 institute
Show, this method comprises:
Step 101, the EM obtains the first parameter of the preparation stage before executing imaging, first parameter is inputted pre-
First corresponding first imaging model of the EM that training obtains, obtains the second parameter, the Electron Microscope images parameter includes
First parameter and the second parameter；
In the embodiment of the present disclosure, when being imaged using EM, by starting EM, the acceleration voltage value of EM is set, low
After finding the sample area for imaging under times magnification numerical value situation, times magnification numerical value is adjusted to the amplification factor needed, as
EM executes the preparation stage before imaging.Then, then other parameters are adjusted so that EM carries out blur-free imaging.Currently, carry out EM its
When his imaging parameters (imaging parameters in addition to acceleration voltage value and amplification factor) are adjusted, the main personal warp according to operator
It tests, in the imaging parameters adjusting panel of EM, other imaging parameters is manually adjusted by operator, in conjunction on observation display screen
Imaging, until adjusting obtains clear image.But due to influencing each other between EM imaging parameters, thus, even experience is rich
Rich operator, the time needed for adjusting obtains clear image is also long, so that imaging parameters adjusting is inefficient.
In the embodiment of the present disclosure, it is contemplated that adjust common two operations, i.e. setting acceleration voltage value when EM imaging parameters
And times magnification numerical value, thus, as an alternative embodiment, by two parameters, i.e. acceleration voltage and amplification factor is corresponding
Value as EM execute imaging before the first parameter.Certainly, in practical application, the first parameter is also possible to other parameters value, example
Such as, acceleration voltage value and operating distance value, alternatively, times magnification numerical value and operating distance value etc..
In the embodiment of the present disclosure, advances with clearly EM sample image and concentrate the corresponding imaging ginseng of every EM sample image
Number, wherein imaging parameters include the first parameter and the second parameter, are trained to preset imaging model, and it is corresponding to obtain the EM
The first imaging model.The first parameter before imaging is executed so as to the EM based on acquisition, is obtained from first imaging model
Second parameter can obtain relatively clear image so that EM is imaged according to first parameter and the second parameter.Can have
Time needed for effect reduces manual adjustment imaging parameters shortens the time needed for adjusting obtains clear image, improves imaging ginseng
Number adjusts efficiency.
In the embodiment of the present disclosure, for different types of EM, the first different imaging models is respectively corresponded.As another
Alternative embodiment can also be directed to the EM of same type of different model, there is the first different imaging models respectively.
Step 102, it is imaged according to the first parameter of the preparation stage and the second obtained parameter, obtains the first figure
Picture；
In the embodiment of the present disclosure, imaging parameters include: the first parameter and the second parameter.As an alternative embodiment, first
Parameter includes times magnification numerical value and acceleration voltage value, and the second parameter includes: current value, beam spot diameter, value, operating distance value, focuses
Functional value, astigmatism functional value.
In the embodiment of the present disclosure, as an alternative embodiment, it can be automatically write in the imaging parameters adjusting panel of EM
The second parameter obtained according to the first imaging model.
Step 103, the third parameter is inputted training in advance by the third parameter in the second parameter obtained described in extraction
Corresponding second imaging model of the obtained EM, obtains the 4th parameter；
In the embodiment of the present disclosure, as an alternative embodiment, third parameter includes: current value, beam spot diameter, value and work
Distance value, the 4th parameter include focus function value and astigmatism functional value.
In the embodiment of the present disclosure, using corresponding second parameter of clearly EM sample image, to preset imaging model into
Row training, obtains the second imaging model, so as to carry out finer clarity adjusting to imaging.
It should be noted that there is no points of sequencing for step 102 and step 103.In practical application, step 102 can
To be executed after step 103, can also be performed simultaneously with step 103, the present embodiment is not construed as limiting this.
Step 104, according to the first parameter of the preparation stage and third parameter and the 4th obtained parameter carry out at
Picture obtains the second image；
In the embodiment of the present disclosure, in the case of the first parameter constant, according to third parameter and from the second imaging model
The 4th obtained parameter carries out re-imaging to the same position of sample.
Step 105, it is based on the first image and second image, determines the Electron Microscope images parameter,
And according to the determining Electron Microscope images parametric imaging.
It,, can by translation sample or horizontal plane inward turning sample transfer product after determining the imaging parameters of EM in the embodiment of the present disclosure
To carry out continuous blur-free imaging to sample under same acceleration voltage and amplification factor.
In the embodiment of the present disclosure, EM is after completing Irnaging procedures according to determining imaging parameters, if operator needs to become
More the first parameter, then the first parameter that can be changed according to operator, re-execute the steps 101, to obtain the first of corresponding change
The corresponding imaging parameters of parameter carry out new round imaging.
In the embodiment of the present disclosure, when being imaged using EM, inputted in advance by the way that EM to be executed to the first parameter before imaging
First corresponding first imaging model of the EM that training obtains, obtains the second parameter；The third parameter in the second parameter is extracted again,
Third parameter is inputted into corresponding second imaging model of the EM that training obtains in advance, obtains the 4th parameter；According to preparation rank
First parameter of section and the second obtained parameter are imaged, and the first image is obtained, and, according to the first ginseng of preparation stage
Number, the third parameter extracted and the 4th parameter are imaged, and the second image is obtained；Based on the first image and the second image,
It can determine the imaging parameters of EM.In this way, the imaging parameters of EM are automatically determined in such a way that big data is excavated, so that according to this
The image of imaging parameters shooting is relatively clear, when can effectively reduce manual adjustment imaging parameters and obtaining needed for clear image
Between, shorten the time needed for adjusting obtains clear image, improves imaging parameters and adjust efficiency；Further, in the sample room EM
In the case of inside there is a small amount of air, the bombardment of the higher electron beam of energy is easy to make the carbonaceous material in air in sample surfaces
Accumulation forms black region, and since carbonaceous material is non-conductive, it can not be discharged by galvanic circle, be easy to cause image fuzzy,
Since embodiment of the present disclosure method can effectively shorten imaging parameters regulating time, so that carbonaceous material was accumulated in sample surfaces
Time is short, it is possible to prevente effectively from the generation of image blur phenomena, to promote the quality of image；Moreover, being excavated using big data
Mode automatically determine the imaging parameters of EM, to EM operator without technical requirements, without carrying out complicated EM to operator
Training on operation so as to reduce the cost of EM operation and maintenance cost and training technique personnel (operator), and can avoid
Human operational error damages caused by EM, reduces the probability that EM is abnormal.
Fig. 2 is the flow diagram for the step 105 based on Fig. 1 that the embodiment of the present disclosure provides.As shown in Fig. 2, the process
Include:
Step 201, the clarity of the first image and the clarity of the second imaging picture are obtained；
In the embodiment of the present disclosure, as an alternative embodiment, the quality of image is characterized using clarity.
In the embodiment of the present disclosure, as an alternative embodiment, using Brenner gradient method, Tenegrad gradient method,
Laplace gradient method, variance method, energy gradient method etc. calculate the clarity of image, to obtain the clarity of image.
Step 202, the difference of the clarity of the first image and the clarity of second image is calculated；
In the embodiment of the present disclosure, the difference of the clarity of the first image and the second image is calculated.
Step 203, if the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, described in replacement
First image；
In the embodiment of the present disclosure, when the clarity difference of two images is greater than poor definition threshold value, show also to need at
As parameter is made further to adjust to obtain clearer image.
In the embodiment of the present disclosure, if the clarity of the first image is greater than the clarity of the second image, the first image is clear
Spend highest image.If the clarity of two images is identical, an image is randomly selected as the highest image of clarity.Benefit
The first image is replaced with the highest image of clarity, the clarity of replaced first image is that the highest image of clarity is corresponding
Clarity.
In the embodiment of the present disclosure, as an alternative embodiment, after extracting the highest image of clarity, for the ease of behaviour
Author has intuitive impression, this method to the highest image of the clarity further include:
Show the imaging parameters of the highest image of the clarity and the highest image of the clarity.
It, can be in order to which operator be manually in imaging parameters tune by being shown imaging parameters in the embodiment of the present disclosure
Corresponding parametric values are inputted in solution panel.
In the embodiment of the present disclosure, this method further include:
If the difference is less than or equal to default poor definition threshold value, the imaging ginseng of the highest image of the clarity is obtained
Number, the imaging parameters as the EM.
In the embodiment of the present disclosure, preset if the difference of the clarity of the first image and the clarity of the second image is less than or equal to
Poor definition threshold value obtains the imaging parameters of the highest image of clarity, as the imaging parameters of the EM, controls EM according to clear
The imaging parameters imaging of the clear highest image of degree.
Step 204, the third parameter is modified, execution is described to input the third parameter described in trained in advance obtain
The step of EM corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value.
In the embodiment of the present disclosure, the third parameter of modification is inputted into the second imaging model, obtains one the 4th parameter.According to this
4th parameter and the third parameter of modification are imaged, and an image is obtained, and replace the second image with the image.Then, it returns
Step 201 is executed, if until the difference being calculated is less than or equal to default poor definition threshold value, the acquisition highest figure of clarity
The imaging parameters of picture, until the imaging parameters as the EM.
In the embodiment of the present disclosure, as an alternative embodiment, ginseng algorithm can be passed according to preset intelligence to third parameter
Assignment is carried out, i.e., is modified to third parameter.As another alternative embodiment, it is also possible to present and third parameter to user
Relevant other parameters value, for example, the third parameter of other clear images under same acceleration voltage and amplification factor, operator
It can therefrom choose.
Fig. 3 is the flow diagram of building the first imaging model and the second imaging model that the embodiment of the present disclosure provides.Such as
Shown in Fig. 3, by taking EM is SEM as an example, which includes:
Step 301, clearly SEM sample graph image set is obtained, the SEM sample image is extracted and concentrates every SEM sample graph
The imaging parameters of picture, the imaging parameters include the first parameter and the second parameter；
In the embodiment of the present disclosure, the first parameter includes times magnification numerical value and acceleration voltage value, and the second parameter includes third ginseng
Several and the 4th parameter, third parameter include: electric current, beam spot diameter, and operating distance, the 4th parameter include focus function value and
Astigmatism functional value.
Step 302, according to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtain
It take corresponding second parameter of first parameter as the first key-value pair collection of value using the first parameter as key, and, building is joined with third
Number is key, take corresponding 4th parameter of the third parameter as the second key-value pair collection of value；
In the embodiment of the present disclosure, the imaging parameters with identical times magnification numerical value and acceleration voltage value are classified as one kind.Make
For an alternative embodiment, the first key-value pair collection can be expressed as follows:
| Key | Value |
| U=6Kv, d=50x | A1=100mA, a2=12mm, a3=15mm, g1=0.3, g2=0.25mm |
| A1=120mA, a2=12mm, a3=15mm, g1=0.3, g2=0.25mm | |
| A1=120mA, a2=12mm, a3=20mm, g1=0.3, g2=0.25mm | |
| … | |
| U=6Kv, d=100x | A1=100mA, a2=10mm, a3=15mm, g1=0.33, g2=0.28mm |
| … | |
| U=8Kv, d=50x | A1=110mA, a2=12mm, a3=15mm, g1=0.22, g2=0.27mm |
| … | |
| … | … |
In table, U is voltage, and d is amplification factor, and a1 is electric current, and a2 is beam spot diameter, and a3 is operating distance, and g1 is to focus
Function, g2 are astigmatism function.Wherein,
Key=(U, d), value=(a1, a2, a3, g1, g2).
Key is key, and value is value, and the first key-value pair collection is (key, value).
In the embodiment of the present disclosure, the format of the second key-value pair collection is similar with the format of the first key-value pair collection.
Step 303, using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to pre-
If first imaging initial model be trained, obtain the first imaging model；And made with the key that second key-value pair is concentrated
Preset second imaging initial model is trained, the second imaging mould is obtained using the corresponding value of the key as output for input
Type.
In the embodiment of the present disclosure, it is initial to be utilized respectively the first imaging for different types of EM as an alternative embodiment
Model is trained the first imaging model of building, is trained the second imaging model of building using the second imaging initial model.Make
For another alternative embodiment, the first imaging initial model and the second imaging initial model can be identical model.
In the embodiment of the present disclosure, with ((U, d), (a1, a2, a3, g1, g2)) as data source training the first imaging introductory die
Type.It is data source training the second imaging initial model with ((a1, a2, a3), (g1, g2)).
In the embodiment of the present disclosure, as an alternative embodiment, the EM obtained after being trained is the first one-tenth corresponding
As model and the second imaging model are saved into SEM data library.
Fig. 4 is the apparatus structure schematic diagram for the adjusting Electron Microscope images parameter that the embodiment of the present disclosure provides.Such as Fig. 4 institute
Show, which includes:
First imaging parameters obtain module 401, will be described for obtaining the first parameter of the preparation stage before executing imaging
First parameter input corresponding first imaging model of the EM that training obtains in advance, obtains the second parameter, the electron microscopic
Mirror imaging parameters include first parameter and the second parameter；
First image-forming module 402, for according to the preparation stage the first parameter and obtained the second parameter carry out at
Picture obtains the first image；
In the embodiment of the present disclosure, as an alternative embodiment, it can be automatically write in the imaging parameters adjusting panel of EM
The second parameter obtained according to the first imaging model.
Second imaging parameters obtain module 403, will be described for extracting the third parameter in the second obtained parameter
Third parameter input corresponding second imaging model of the EM that training obtains in advance, obtains the 4th parameter；
Second image-forming module 404, for the first parameter and third parameter according to the preparation stage and obtain
Four parameters are imaged, and the second image is obtained；
In the embodiment of the present disclosure, in the case of the first parameter constant, according to third parameter and from the second imaging model
The 4th obtained parameter carries out re-imaging to the same position of sample.
Imaging parameters determining module 405 determines the EM's for being based on the first image and second image
Imaging parameters, according to the determining Electron Microscope images parametric imaging.
In the embodiment of the present disclosure, after determining the imaging parameters of EM, by translation sample or sample, Ke Yi are rotated horizontally
Under same acceleration voltage and amplification factor, continuous blur-free imaging is carried out to sample.
In the embodiment of the present disclosure, EM is after completing Irnaging procedures according to determining imaging parameters, if operator needs to become
More the first parameter, then the first parameter that can be changed according to operator are again trained in advance by the input of the first parameter of the change
Corresponding first imaging model of the EM arrived, with obtain the imaging parameters of the first parameter of corresponding change carry out a new round at
Picture.
In the embodiment of the present disclosure, as an alternative embodiment, imaging parameters determining module 405 is specifically used for:
Obtain the clarity of the first image and the clarity of the second imaging picture；
Calculate the difference of the clarity of the first image and the clarity of second image；
If the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, replaces the first image；
The third parameter is modified to adjust the imaging parameters of re-imaging, is executed described third parameter input is trained in advance
The step of EM arrived corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value；
If the difference is less than or equal to default poor definition threshold value, the imaging ginseng of the highest image of the clarity is obtained
Number, the imaging parameters as the EM.
In the embodiment of the present disclosure, as an alternative embodiment, using Brenner gradient method, Tenegrad gradient method,
Laplace gradient method, variance method, energy gradient method etc. calculate the clarity of image, to obtain the clarity of image.
In the embodiment of the present disclosure, as an alternative embodiment, the device further include:
Display module (not shown), for showing the highest image of the clarity and the highest figure of the clarity
The imaging parameters of picture.
It, can be in order to which operator be manually in imaging parameters tune by being shown imaging parameters in the embodiment of the present disclosure
Corresponding parametric values are inputted in solution panel.
In the embodiment of the present disclosure, as an alternative embodiment, the EM includes scanning electron microscope SEM, and the device is also
Include:
Imaging model constructs module (not shown), for obtaining clearly SEM sample graph image set, extracts the SEM
Sample image concentrates the imaging parameters of every SEM sample image, and the imaging parameters include the first parameter and the second parameter；
According to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtains with the first ginseng
Number is key, take corresponding second parameter of first parameter as the first key-value pair collection of value, and, it constructs using third parameter as key,
It take corresponding 4th parameter of the third parameter as the second key-value pair collection of value；
Using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to preset first
Imaging initial model is trained, and obtains the first imaging model；And using the key that second key-value pair is concentrated as input,
Using the corresponding value of the key as output, preset second imaging initial model is trained, the second imaging model is obtained.
In the embodiment of the present disclosure, as an alternative embodiment, the EM obtained after being trained is the first one-tenth corresponding
As model and the second imaging model are saved into SEM data library.
In the embodiment of the present disclosure, as an alternative embodiment, the first parameter includes times magnification numerical value and acceleration voltage value, institute
Stating the second parameter includes: current value, beam spot diameter, value, operating distance value, focus function value, astigmatism functional value；The third ginseng
Number includes: current value, beam spot diameter, value and operating distance value, and the 4th parameter includes focus function value and astigmatism functional value.
As shown in figure 5, one embodiment of the disclosure provides a kind of computer equipment 500, for executing Fig. 1 into Fig. 3
The method for adjusting Electron Microscope images parameter, the equipment include memory 501, processor 502 and are stored in the memory 501
Computer program that is upper and being run on the processor 502, wherein when above-mentioned processor 502 executes above-mentioned computer program
The step of realizing the method for above-mentioned adjusting Electron Microscope images parameter.
Specifically, above-mentioned memory 501 and processor 502 can be general memory and processor, do not do have here
Body limits, and when the computer program of 502 run memory 501 of processor storage, is able to carry out above-mentioned adjusting electron microscope
The method of imaging parameters, it is longer the time required to adjusting clear image in the prior art for solving, cause imaging parameters to adjust effect
The lower problem of rate, the disclosure, which passes through, utilizes corresponding first imaging model of the EM that training obtains in advance and the second imaging
Model obtains the imaging parameters of EM respectively, is imaged based on the imaging parameters obtained respectively, by comparing the image being imaged
Clarity, the final imaging parameters for determining EM.In this way, automatically determining the corresponding EM of clear image in such a way that big data is excavated
Imaging parameters, can effectively reduce the time needed for manual adjustment imaging parameters obtain clear image, shorten adjust obtaining it is clear
Time needed for clear image improves imaging parameters and adjusts efficiency.
Corresponding to the method for adjusting Electron Microscope images parameter of the Fig. 1 into Fig. 3, the embodiment of the present disclosure additionally provides one
Computer readable storage medium is planted, is stored with computer program on the computer readable storage medium, which is located
The step of executing the method for above-mentioned adjusting Electron Microscope images parameter when reason device operation.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, the method for being able to carry out above-mentioned adjusting Electron Microscope images parameter, for solving existing skill
It is longer the time required to adjusting clear image in art, cause imaging parameters to adjust the lower problem of efficiency, the disclosure passes through using pre-
Corresponding first imaging model of the EM and the second imaging model that first training obtains obtain the imaging parameters of EM respectively, are based on
The imaging parameters obtained respectively are imaged, by comparing the clarity of the image of imaging, the final imaging parameters for determining EM.This
Sample automatically determines the imaging parameters of the corresponding EM of clear image in such a way that big data is excavated, can effectively reduce artificial tune
Time needed for section imaging parameters obtain clear image shortens the time needed for adjusting obtains clear image, improves imaging ginseng
Number adjusts efficiency.
In the embodiment provided by the disclosure, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in the embodiment that the disclosure provides can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the disclosure is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the disclosure all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, the only specific embodiment of the disclosure, to illustrate the disclosure
Technical solution, rather than its limitations, the protection scope of the disclosure is not limited thereto, although with reference to the foregoing embodiments to this public affairs
It opens and is described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope that the disclosure discloses, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of embodiment of the present disclosure technical solution.The protection in the disclosure should all be covered
Within the scope of.Therefore, the protection scope of the disclosure shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of method for adjusting Electron Microscope images parameter, which is characterized in that be applied to electron microscope EM, this method packet
It includes:
The EM obtains the first parameter of the preparation stage before executing imaging, and first parameter is inputted what training in advance obtained
Corresponding first imaging model of the EM, obtains the second parameter, the Electron Microscope images parameter includes first parameter
With the second parameter；
It is imaged according to the first parameter of the preparation stage with the second obtained parameter, obtains the first image；
The third parameter is inputted the EM that training obtains in advance by the third parameter in the second parameter obtained described in extraction
Corresponding second imaging model, obtains the 4th parameter；
It is imaged, is obtained according to the first parameter of the preparation stage, the third parameter of extraction and the 4th obtained parameter
Second image；
Based on the first image and second image, the Electron Microscope images parameter is determined, and according to determining
The Electron Microscope images parametric imaging.
2. the method as described in claim 1, which is characterized in that it is described to be based on the first image and second image,
Determine the Electron Microscope images parameter, comprising:
Obtain the clarity of the first image and the clarity of the second imaging picture；
Calculate the difference of the clarity of the first image and the clarity of second image；
If the difference is less than or equal to default poor definition threshold value, the imaging parameters of the highest image of the clarity are obtained,
Imaging parameters as the EM；
If the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, replaces the first image；Modification
The third parameter executes to adjust the imaging parameters of re-imaging and described the third parameter is inputted what training in advance obtained
The step of EM corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value.
3. method according to claim 2, which is characterized in that the method also includes:
Show the imaging parameters of the highest image of the clarity and the highest image of the clarity.
4. the method as described in claim 1, which is characterized in that the EM includes scanning electron microscope SEM, is obtained in the EM
Before taking the first parameter for executing the preparation stage before being imaged, the method also includes:
Clearly SEM sample graph image set is obtained, the imaging parameters that the SEM sample image concentrates every SEM sample image are extracted,
The imaging parameters include the first parameter and the second parameter；
According to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtain be with the first parameter
Key take corresponding second parameter of first parameter as the first key-value pair collection of value, and, it constructs using third parameter as key, with this
Corresponding 4th parameter of third parameter is the second key-value pair collection of value；
Using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to preset first imaging
Initial model is trained, and obtains corresponding first imaging model of the SEM；And the key concentrated with second key-value pair
As input, using the corresponding value of the key as output, preset second imaging initial model is trained, the SEM is obtained
Corresponding second imaging model.
5. such as the described in any item methods of Claims 1-4, which is characterized in that first parameter include times magnification numerical value and
Acceleration voltage value, second parameter include: current value, beam spot diameter, value, operating distance value, focus function value, astigmatism function
Value；The third parameter includes: current value, beam spot diameter, value and operating distance value, and the 4th parameter includes focus function value
With astigmatism functional value.
6. a kind of device for adjusting Electron Microscope images parameter, which is characterized in that the device includes:
First imaging parameters obtain module, the first parameter of the preparation stage for obtaining the preparation stage before executing imaging, will
First parameter input corresponding first imaging model of the EM that training obtains in advance, obtains the second parameter, the electronics
Microscope imaging parameter includes first parameter and the second parameter；
First image-forming module is imaged for the first parameter according to the preparation stage and the second obtained parameter, is obtained
First image；
Second imaging parameters obtain module, and for extracting the third parameter in the second obtained parameter, the third is joined
Number input corresponding second imaging model of the EM that training obtains in advance, obtains the 4th parameter；
Second image-forming module, for according to the first parameter of the preparation stage, the third parameter of extraction and obtain the 4th
Parameter is imaged, and the second image is obtained；
Imaging parameters determining module determines the electron microscope for being based on the first image and second image
Imaging parameters, according to the determining Electron Microscope images parametric imaging.
7. device as claimed in claim 6, which is characterized in that the imaging parameters determining module is specifically used for:
Obtain the clarity of the first image and the clarity of the second imaging picture；
Calculate the difference of the clarity of the first image and the clarity of second image；
If the difference is less than or equal to default poor definition threshold value, the imaging parameters of the highest image of the clarity are obtained,
Imaging parameters as the EM；
If the difference is greater than default poor definition threshold value, the highest image of clarity is extracted, replaces the first image；Modification
The third parameter executes to adjust the imaging parameters of re-imaging and described the third parameter is inputted what training in advance obtained
The step of EM corresponding second imaging model, until the difference is less than or equal to default poor definition threshold value.
8. device as claimed in claim 7, which is characterized in that described device further include:
Display module, for showing the imaging parameters of the highest image of the clarity and the highest image of the clarity.
9. device as claimed in claim 6, which is characterized in that the EM includes scanning electron microscope SEM, and described device is also
Include:
Imaging model constructs module, and for obtaining clearly SEM sample graph image set, it is each to extract the SEM sample image concentration
The imaging parameters of SEM sample image, the imaging parameters include the first parameter and the second parameter；
According to first parameter, classify to the imaging parameters of each SEM sample image of extraction, obtain be with the first parameter
Key take corresponding second parameter of first parameter as the first key-value pair collection of value, and, it constructs using third parameter as key, with this
Corresponding 4th parameter of third parameter is the second key-value pair collection of value；
Using the key that first key-value pair is concentrated as input, using the corresponding value of the key as output, to preset first imaging
Initial model is trained, and obtains the first imaging model；And using the key that second key-value pair is concentrated as input, with this
The corresponding value of key is trained preset second imaging initial model, obtains the second imaging model as output.
10. such as the described in any item devices of claim 6 to 9, which is characterized in that first parameter include times magnification numerical value and
Acceleration voltage value, second parameter include: current value, beam spot diameter, value, operating distance value, focus function value, astigmatism function
Value；The third parameter includes: current value, beam spot diameter, value and operating distance value, and the 4th parameter includes focus function value
With astigmatism functional value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810843900.0A CN109087293B (en) | 2018-07-27 | 2018-07-27 | Method and device for adjusting imaging parameters of electron microscope |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810843900.0A CN109087293B (en) | 2018-07-27 | 2018-07-27 | Method and device for adjusting imaging parameters of electron microscope |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109087293A true CN109087293A (en) | 2018-12-25 |
| CN109087293B CN109087293B (en) | 2020-10-16 |
Family
ID=64831166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810843900.0A Active CN109087293B (en) | 2018-07-27 | 2018-07-27 | Method and device for adjusting imaging parameters of electron microscope |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087293B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509119A (en) * | 2019-12-23 | 2021-03-16 | 首都医科大学附属北京友谊医院 | Spatial data processing and positioning method and device for temporal bone and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0222328D0 (en) * | 2002-09-26 | 2002-10-30 | Leo Electron Microscopy Ltd | Improvements in and relating to the control of instruments |
| CN102543793A (en) * | 2012-02-29 | 2012-07-04 | 无锡睿当科技有限公司 | Wafer focusing image quality feedback system and method therefor |
| CN103733298A (en) * | 2011-09-05 | 2014-04-16 | 株式会社日立高新技术 | Charged particle beam apparatus |
| CN106415774A (en) * | 2014-07-02 | 2017-02-15 | 株式会社日立高新技术 | Electron microscope device and imaging method using same |
| CN106815871A (en) * | 2016-12-26 | 2017-06-09 | 华中科技大学 | A kind of modeling method of SEM imaging system |
-
2018
- 2018-07-27 CN CN201810843900.0A patent/CN109087293B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0222328D0 (en) * | 2002-09-26 | 2002-10-30 | Leo Electron Microscopy Ltd | Improvements in and relating to the control of instruments |
| CN103733298A (en) * | 2011-09-05 | 2014-04-16 | 株式会社日立高新技术 | Charged particle beam apparatus |
| CN102543793A (en) * | 2012-02-29 | 2012-07-04 | 无锡睿当科技有限公司 | Wafer focusing image quality feedback system and method therefor |
| CN106415774A (en) * | 2014-07-02 | 2017-02-15 | 株式会社日立高新技术 | Electron microscope device and imaging method using same |
| CN106815871A (en) * | 2016-12-26 | 2017-06-09 | 华中科技大学 | A kind of modeling method of SEM imaging system |
Non-Patent Citations (2)
| Title |
|---|
| LE CUI ET AL: "Calibration of scanning electron microscope using a multi-image non-linear minimization process", 《2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)》 * |
| YEO HUN YOON ET AL: "Analysis of improvement in performance and design parameters for enhancing resolution in an atmospheric scanning electron microscope", 《MICROSCOPY》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509119A (en) * | 2019-12-23 | 2021-03-16 | 首都医科大学附属北京友谊医院 | Spatial data processing and positioning method and device for temporal bone and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109087293B (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7030423B2 (en) | How to manufacture image analysis methods, equipment, programs and deep learning algorithms | |
| Sulaiman et al. | Adaptive fuzzy-K-means clustering algorithm for image segmentation | |
| CN111007661B (en) | Microscopic image automatic focusing method and device based on deep learning | |
| CN110070601A (en) | Micro-image is rebuild and the methods, devices and systems of the long-range deep learning of segmentation | |
| US7949181B2 (en) | Segmentation of tissue images using color and texture | |
| JP7419007B2 (en) | Object tracking using image segmentation | |
| JPWO2020031243A1 (en) | Teacher label image correction method, trained model creation method and image analysis device | |
| CN112102237A (en) | Brain tumor recognition model training method and device based on semi-supervised learning | |
| WO2015117904A1 (en) | Hough processor | |
| US20210286972A1 (en) | Determination method, elimination method and apparatus for electron microscope aberration | |
| Setiawan et al. | Classification of cell types in Acute Myeloid Leukemia (AML) of M4, M5 and M7 subtypes with support vector machine classifier | |
| CN108875931A (en) | Neural metwork training and image processing method, device, system | |
| JP2020139945A (en) | Use of convolution neural network for reconstituting on-the-fly single particle | |
| JP2021508127A (en) | Control methods for autonomous microscope systems, microscope systems, and computer-readable storage media | |
| CN109087293A (en) | A kind of method and device adjusting Electron Microscope images parameter | |
| CN111462005B (en) | Method, apparatus, computer device and storage medium for processing microscopic image | |
| CN111985488B (en) | Target detection segmentation method and system based on offline Gaussian model | |
| EP3951832A1 (en) | Method of aligning a charged particle beam apparatus | |
| CN112765354A (en) | Model training method, model training device, computer apparatus, and storage medium | |
| Gabriel et al. | Analysis of the discriminative generalized Hough transform as a proposal generator for a deep network in automatic pedestrian and car detection | |
| CN102851208B (en) | High-precision cell statistic counting and analyzing device | |
| WO2013025173A1 (en) | A method and system for tracking motion of microscopic objects within a three-dimensional volume | |
| CN116524495A (en) | Traditional Chinese medicine microscopic identification method and system based on multidimensional channel attention mechanism | |
| Bardosi et al. | Metacarpal bones localization in x-ray imagery using particle filter segmentation | |
| Unal et al. | Customized design of hearing aids using statistical shape learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |