CN106447633B - The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection - Google Patents
The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection Download PDFInfo
- Publication number
- CN106447633B CN106447633B CN201610852508.3A CN201610852508A CN106447633B CN 106447633 B CN106447633 B CN 106447633B CN 201610852508 A CN201610852508 A CN 201610852508A CN 106447633 B CN106447633 B CN 106447633B
- Authority
- CN
- China
- Prior art keywords
- indicate
- difference curvature
- objective function
- difference
- ray
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000004888 barrier function Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000009795 derivation Methods 0.000 abstract description 2
- 238000003384 imaging method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910052752 metalloid Inorganic materials 0.000 description 1
- 150000002738 metalloids Chemical class 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- G06T2207/10116—X-ray image
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The step of denoising method of Microfocus X-ray radioscopic image disclosed by the invention towards integrated antenna package detection includes following sequence: the Gauss of input picture is pre-processed；Microfocus X-ray x-ray observation image is divided into flat region and detail areas using difference curvature chart；Utilize division result and difference curvature estimation regularizing operator and regularization parameter；Objective function is constructed, iteratively faster solution is carried out to objective function using based on approximate Variable Step Algorithm.Denoising method of the invention is solved using based on approximate variable step iteratively faster derivation algorithm, and algorithm speed is fast, meets actual industrial requirement.
Description
Technical field
The present invention relates to image denoising fields, in particular to the Microfocus X-ray radioscopic image towards integrated antenna package detection
Denoising method.
Background technique
The focus of Microfocus X-ray X-ray machine only has 5-10 μm, is able to achieve the detection to small fine structure, is usually used in integrated circuit
Piece test and defects detection in encapsulation.Since the test object in integrated antenna package is usually from a variety of dissimilar metals
And combinations thereof body, different metal is different to the absorbing state of X-ray, so that Microfocus X-ray radioscopic image being capable of non-destructive testing circuit
Internal structure, but also because the absorbing state of each metalloid is closer to, so as to show contrast low for Microfocus X-ray radioscopic image
Feature, simultaneously because the influence of noise, fine faint structure is difficult to accurately detect.
The imaging process of Microfocus X-ray X-ray machine includes reaching receiver board and subsequent electromagnetism turn after X-ray is emitted by radiographic source
It changes, the processes such as signal transmission, wherein accounting for the noise type mainly influenced is Gaussian noise and poisson noise.Due to X-ray tube
Microfocus X-ray characteristic, the x-ray flux that x-ray source is generated in the unit time is less, causes the photon count levels of imaging low, often
It will form poisson noise；Meanwhile the thermoelectron of imaging device fluctuates and electromagnetic induction effect would generally introduce Gaussian noise；Two kinds
Noise is mixed in Microfocus X-ray radioscopic image, brings bigger difficulty for integrated antenna package detection；And existing doctor
The imaging characteristics and Microfocus X-ray radioscopic image difference of radioscopic image etc. are learned, the radiation in the former imaging device is logical
Often in hundred micron levels.And the radiation of Microfocus X-ray X-ray machine only has 5-10 μm.The Microfocus X-ray characteristic of Microfocus X-ray X-ray machine makes
The interaction situation of its noise is more complicated compared with existing common radioscopic image noise model；Meanwhile for towards collection
For Microfocus X-ray radioscopic image at circuit detection, need accurately to examine the part and defect of integrated circuit due to subsequent
It surveys, therefore to the more demanding of the details reservation of image while effective denoising, and its image has faint details more, comparison
Spend low, the low feature of signal-to-noise ratio increases the difficulty of denoising.
Existing research largely only focuses on single Gaussian noise or poisson noise, for what is detected towards integrated antenna package
It for Microfocus X-ray radioscopic image and is not suitable for, image shows the low feature of signal-to-noise ratio, and the actual conditions of noise are than single
Gaussian noise or single poisson noise are much more complex；On regularization method, existing most of research concern regularizing operator or
The single adaptation scheme of regularization parameter designs, and cannot combine well the two, both need to take a significant amount of time specific
It on parameter determines, and cannot be guaranteed noise remove and the balance that details retains, actual industrial integrated circuit can not be met well
To the requirement of denoising in package detection.
Summary of the invention
The purpose of the present invention is to overcome the shortcomings of the existing technology and deficiency, provides towards the micro- of integrated antenna package detection
The denoising method of focal spot x-ray image.
The purpose of the present invention is realized by the following technical solution:
The step of denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection includes following sequence:
(1) Gauss of input picture is pre-processed；
(2) the difference curvature chart Img_dc for calculating image Img_ft after pre-processing, is penetrated Microfocus X-ray X using difference curvature chart
Line observed image Img_ob points are flat region and detail areas；
(3) division result and difference curvature estimation regularizing operator and regularization parameter are utilized:
A, using difference curvature value, with the form calculus regularizing operator of class inverse proportion function；
Wherein, (x, y) is image rectangular co-ordinate, and x, y are positive integer, and p (x, y) indicates regularization LpP in operator
Norm parameter, Img_dc indicate difference curvature chart (i.e. Img_dc (x, y) indicates the difference curvature value on image coordinate (x, y)),
The full figure intermediate value of med_dc expression difference curvature chart Img_dc；
B, using difference curvature value, with the form calculus regularization parameter of barrier function, be conducive to keep faint edge；
Wherein, Lamda indicates that regularization parameter, Lamda_d indicate that the regularization parameter of detail areas, Lamda_s indicate flat
The regularization parameter in smooth area, mean_bdc indicate difference curvature mean value, and max () expression is maximized；
(4) objective function is constructed, iteratively faster solution is carried out to objective function using based on approximate Variable Step Algorithm.
The step (2) specifically: after the difference curvature chart for calculating pretreatment image, solve difference song using Da-Jin algorithm
The binarization threshold of rate figure divides the image into foreground zone and background area using the binarization threshold；The difference for counting background area is bent
The summation of difference curvature value of background area and the sum of corresponding pixel points are divided by by the summation of rate value and the sum of corresponding pixel points
Obtain the mean value of background area difference curvature；Subregion is carried out to image with the mean value combination difference curvature chart of background area difference curvature:
For a pixel, if its corresponding difference curvature is greater than the mean value of background area difference curvature, which is edge
The point in area；If it is less than the mean value of background area difference curvature, then the pixel is the point of flat region.
The step (4) specifically:
Firstly, noise model is converted based on second order Taylors approximation, obtain the conversion of objective function:
Wherein, I*Indicate the optimal solution of objective function, I is the solution of objective function to be asked, and α is two in second order Taylors approximation
Secondary item parameter,For gradient operator, | | | |pIndicate p norm, I_s is intermediate projection result；
Solve intermediate projection result
Wherein, Y is hypothesis known variables when carrying out second order Taylors approximation, and second order Taylors approximation is unfolded at Y；Fid()
Indicate the data fidelity term based on Gauss-Poisson mixed noise in objective function；()kIndicate k-th of component；Herein, second order is safe
The quadratic term parameter alpha in approximation is strangled to be considered to decline step parameter；Wherein, step-lengthIt can be adaptive with iterations going on
It calculates, i.e. variable step, accelerates iteration speed；
Then intermediate variable is updated
Wherein, IiIndicate the solution of objective function in i-th iteration, Ii-1Indicate the solution of objective function in (i-1)-th iteration, ti
Indicate the step-size factor in i-th iteration, ti+1Indicate the step-size factor updated in i-th iteration；
Between in the updating when variable, step-lengthMiddle tiAnd ti+1Can adaptive calculating with iterations going on, that is, become
Step-length accelerates iteration speed；
By the approximation and two variable steps updates to objective function, realize that the iteratively faster of algorithm solves.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1, the present invention is solved using based on approximate variable step iteratively faster derivation algorithm, and algorithm speed is fast, is met practical
Industrial requirements.
2, The present invention gives the calculation methods of more preferably adaptive operator and parameter, and for faint edge holding into
It has gone design, denoising result is enabled to be effectively retained faint marginal information.
3, novelty of the invention essentially consists in image border operator different from the prior art, specific regularizing operator and
The calculation method of parameter is different；And in regularization method, the calculation method of regularizing operator and parameter is exactly to influence algorithm speed
And the key of effect, the setting of image border operator, regularizing operator and parameter calculation through the invention and iteration are calculated
Method (explanation: because subsequent application of explicit difference method is a kind of iterative algorithm), can effectively improve algorithm speed.Different from explicit difference
Method, application of explicit difference method solve, and algorithm speed is slow.
Detailed description of the invention
Fig. 1 is the process of the denoising method of the Microfocus X-ray radioscopic image of the present invention towards integrated antenna package detection
Figure.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Such as Fig. 1, the denoising method of the Microfocus X-ray radioscopic image towards integrated antenna package detection includes following sequence
Step:
(1) Gauss of input picture is pre-processed；
(2) the difference curvature chart Img_dc for calculating image Img_ft after pre-processing, is penetrated Microfocus X-ray X using difference curvature chart
Line observed image Img_ob points are flat region and detail areas；
Specifically: after the difference curvature chart for calculating pretreatment image, the two-value of the difference curvature chart is solved using Da-Jin algorithm
Change threshold value, divides the image into foreground zone and background area using the binarization threshold；Count the summation of the difference curvature value of background area
And the sum of corresponding pixel points, it is divided by the summation of difference curvature value of background area and the sum of corresponding pixel points to obtain background area
The mean value of difference curvature；Subregion is carried out to image with the mean value combination difference curvature chart of background area difference curvature: for a picture
Vegetarian refreshments, if its corresponding difference curvature is greater than the mean value of background area difference curvature, which is the point of marginal zone；If
Less than the mean value of background area difference curvature, then the pixel is the point of flat region.
(3) division result and difference curvature estimation regularizing operator and regularization parameter are utilized:
A, using difference curvature value, with the form calculus regularizing operator of class inverse proportion function；
Wherein, (x, y) is image rectangular co-ordinate, and x, y are positive integer, and p (x, y) indicates regularization LpP in operator
Norm parameter, Img_dc indicate difference curvature chart (i.e. Img_dc (x, y) indicates the difference curvature value on image coordinate (x, y)),
The full figure intermediate value of med_dc expression difference curvature chart Img_dc；
B, using difference curvature value, with the form calculus regularization parameter of barrier function, be conducive to keep faint edge；
Wherein, Lamda indicates that regularization parameter, Lamda_d indicate that the regularization parameter of detail areas, Lamda_s indicate flat
The regularization parameter in smooth area, mean_bdc indicate difference curvature mean value, and max () expression is maximized；
(4) objective function is constructed, iteratively faster solution is carried out to objective function using based on approximate Variable Step Algorithm；
Specifically:
Firstly, noise model is converted based on second order Taylors approximation, obtain the conversion of objective function:
Wherein, I*Indicate the optimal solution of objective function, I is the solution of objective function to be asked, and α is two in second order Taylors approximation
Secondary item parameter,For gradient operator, | | | |pIndicate p norm, I_s is intermediate projection result；
Solve intermediate projection result
Wherein, Y is hypothesis known variables when carrying out second order Taylors approximation, and second order Taylors approximation is unfolded at Y；Fid()
Indicate the data fidelity term based on Gauss-Poisson mixed noise in objective function；()kIndicate k-th of component；Herein, second order is safe
The quadratic term parameter alpha in approximation is strangled to be considered to decline step parameter；Wherein, step-lengthIt can be adaptive with iterations going on
It calculates, i.e. variable step, accelerates iteration speed；
Then intermediate variable is updated
Wherein, IiIndicate the solution of objective function in i-th iteration, Ii-1Indicate the solution of objective function in (i-1)-th iteration, ti
Indicate the step-size factor in i-th iteration, ti+1Indicate the step-size factor updated in i-th iteration；
Between in the updating when variable, step-lengthMiddle tiAnd ti+1Can adaptive calculating with iterations going on, that is, become
Step-length accelerates iteration speed；
By the approximation and two variable steps updates to objective function, realize that the iteratively faster of algorithm solves.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (2)
1. the denoising method of the Microfocus X-ray radioscopic image towards integrated antenna package detection, which is characterized in that include following sequence
The step of:
(1) Gauss of input picture is pre-processed；
(2) the difference curvature chart Img_dc for calculating image Img_ft after pre-processing, is seen Microfocus X-ray X-ray using difference curvature chart
Altimetric image Img_ob points are flat region and detail areas；
(3) division result and difference curvature estimation regularizing operator and regularization parameter are utilized:
A, using difference curvature value, with the form calculus regularizing operator of class inverse proportion function；
Wherein, (x, y) is image rectangular co-ordinate, and x, y are positive integer, and p (x, y) indicates regularization LpP norm ginseng in operator
Number, Img_dc indicate that difference curvature chart, med_dc indicate the full figure intermediate value of difference curvature chart Img_dc；
B, using difference curvature value, with the form calculus regularization parameter of barrier function；
Wherein, Lamda indicates that regularization parameter, Lamda_d indicate that the regularization parameter of detail areas, Lamda_s indicate flat region
Regularization parameter, mean_bdc indicate difference curvature mean value, max () expression be maximized；
(4) objective function is constructed, iteratively faster solution is carried out to objective function using based on approximate Variable Step Algorithm:
Firstly, noise model is converted based on second order Taylors approximation, obtain the conversion of objective function:
Wherein, I*Indicate the optimal solution of objective function, I is the solution of objective function to be asked, and α is the quadratic term in second order Taylors approximation
Parameter,For gradient operator, | | | |pIndicate p norm, I_s is intermediate projection result；
Solve intermediate projection result
Wherein, Y is hypothesis known variables when carrying out second order Taylors approximation, and second order Taylors approximation is unfolded at Y；Fid () is indicated
Based on the data fidelity term of Gauss-Poisson mixed noise in objective function；()kIndicate k-th of component；Herein, second order Taylor is close
Quadratic term parameter alpha like in is considered to decline step parameter；Wherein, step-lengthIt being capable of adaptive meter with iterations going on
It calculates, i.e. variable step；
Then intermediate variable is updated
Wherein, IiIndicate the solution of objective function in i-th iteration, Ii-1Indicate the solution of objective function in (i-1)-th iteration, tiIt indicates
Step-size factor in i-th iteration, ti+1Indicate the step-size factor updated in i-th iteration；
Between in the updating when variable, step-lengthMiddle tiAnd ti+1It being capable of adaptive calculating with iterations going on, i.e. variable step；
By the approximation and two variable steps updates to objective function, realize that the iteratively faster of algorithm solves.
2. the denoising method of the Microfocus X-ray radioscopic image according to claim 1 towards integrated antenna package detection, feature
It is, the step (2) specifically: after the difference curvature chart for calculating pretreatment image, solve the difference curvature using Da-Jin algorithm
Pretreatment image is divided into foreground zone and background area using the binarization threshold by the binarization threshold of figure；Count the difference of background area
Divide the summation of curvature value and the sum of corresponding pixel points, by the sum of the summation of the difference curvature value of background area and corresponding pixel points
It is divided by obtain the mean value of background area difference curvature；Image is divided with the mean value combination difference curvature chart of background area difference curvature
Area: for a pixel, if its corresponding difference curvature is greater than the mean value of background area difference curvature, which is side
The point in edge area；If it is less than the mean value of background area difference curvature, then the pixel is the point of flat region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610852508.3A CN106447633B (en) | 2016-09-26 | 2016-09-26 | The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610852508.3A CN106447633B (en) | 2016-09-26 | 2016-09-26 | The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106447633A CN106447633A (en) | 2017-02-22 |
| CN106447633B true CN106447633B (en) | 2019-05-14 |
Family
ID=58171096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610852508.3A Active CN106447633B (en) | 2016-09-26 | 2016-09-26 | The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447633B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108109123B (en) * | 2017-12-21 | 2020-05-15 | 成都微光集电科技有限公司 | Image denoising method |
| CN109815797B (en) * | 2018-12-17 | 2022-04-19 | 苏州飞搜科技有限公司 | Living body detection method and apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064046A (en) * | 2012-12-25 | 2013-04-24 | 深圳先进技术研究院 | Image processing method based on sparse sampling magnetic resonance imaging |
| CN103500441A (en) * | 2013-09-29 | 2014-01-08 | 华南理工大学 | Noise modeling and de-noising method for micro-focus X-ray image |
| CN105608679A (en) * | 2016-01-28 | 2016-05-25 | 重庆邮电大学 | Image denoising method integrated with structure tensor and non-local total variation |
| CN105678715A (en) * | 2016-02-15 | 2016-06-15 | 江苏大学 | Method for removing image noise based on kernel regression total variation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130336562A1 (en) * | 2012-06-15 | 2013-12-19 | Toshiba Medical Systems Corporation | Adaptively determined parameter values in iterative reconstruction method and system |
-
2016
- 2016-09-26 CN CN201610852508.3A patent/CN106447633B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064046A (en) * | 2012-12-25 | 2013-04-24 | 深圳先进技术研究院 | Image processing method based on sparse sampling magnetic resonance imaging |
| CN103500441A (en) * | 2013-09-29 | 2014-01-08 | 华南理工大学 | Noise modeling and de-noising method for micro-focus X-ray image |
| CN105608679A (en) * | 2016-01-28 | 2016-05-25 | 重庆邮电大学 | Image denoising method integrated with structure tensor and non-local total variation |
| CN105678715A (en) * | 2016-02-15 | 2016-06-15 | 江苏大学 | Method for removing image noise based on kernel regression total variation |
Non-Patent Citations (3)
| Title |
|---|
| Adaptive total variation regularization based scheme for Poisson noise removal;Weifeng Zhou, Qingguo Li;《Mathematical Methods in the Applied Sciences》;20131231;第36卷(第3期);第290-299页 |
| 基于正则化与保真项全变分自适应图像去噪模型;陈明举 等;《重庆邮电大学学报（自然科学版）》;20111031;第23卷(第5期);第621-625页 |
| 微聚焦X-ray图像自适应正则化去噪方法;万燕英;《中国优秀硕士学位论文全文数据库 信息科技辑》;20161215;正文全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106447633A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6051245B2 (en) | Method for inspecting a sample in a charged particle microscope | |
| US20200126190A1 (en) | Systems and methods for denoising medical images with deep learning network | |
| CN103345740B (en) | Based on the pulmonary nodule detection method of many projected images registration | |
| Dang et al. | Multi‐step radiographic image enhancement conforming to weld defect segmentation | |
| Hashemi et al. | Adaptively tuned iterative low dose CT image denoising | |
| US8744159B2 (en) | Methods, systems and computer program products for collapsing volume data to lower dimensional representations thereof using histogram projection | |
| CN106447633B (en) | The denoising method of Microfocus X-ray radioscopic image towards integrated antenna package detection | |
| JP2018519029A (en) | Motion detection with multi-element radio frequency antenna | |
| CN109993174B (en) | Aerial target detection method and system based on noise suppression | |
| Hussain et al. | A comparative analysis of edge detection techniques used in flame image processing | |
| CN110706208A (en) | Infrared dim target detection method based on tensor mean square minimum error | |
| CN111095075A (en) | Fully automatic, template-free particle pickup for electron microscopes | |
| Jang et al. | A new focus measure operator for enhancing image focus in 3D shape recovery | |
| Das et al. | Early started hybrid denoising technique for medical images | |
| CN108376393A (en) | A kind of blurred picture blind restoration method towards high-speed straight-line Moving Objects | |
| Subbuthai et al. | Reduction of types of noises in dental images | |
| Alekseychuk | Detection of crack-like indications in digital radiography by global optimisation of a probabilistic estimation function | |
| WO2015002247A1 (en) | Radiographic image generating device and image processing method | |
| Kala et al. | Removal of rician noise in MRI images using bilateral filter by fuzzy trapezoidal membership function | |
| Tarolli et al. | Multimodal image fusion with SIMS: Preprocessing with image registration | |
| Mortazavi et al. | Improving Canny edge detection algorithm using fractional-order derivatives | |
| CN109493290A (en) | The method, system and device of radioscopic image noise reduction | |
| Ouyang et al. | Research on DENOISINg of cryo-em images based on deep learning | |
| Shanmugavadivu et al. | Image edge and contrast enhancement using unsharp masking and constrained histogram equalization | |
| He et al. | Advanced processing methodologies improve neutron radiograph image quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |