CN103345756B - Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer - Google Patents
Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer Download PDFInfo
- Publication number
- CN103345756B CN103345756B CN201310302672.3A CN201310302672A CN103345756B CN 103345756 B CN103345756 B CN 103345756B CN 201310302672 A CN201310302672 A CN 201310302672A CN 103345756 B CN103345756 B CN 103345756B
- Authority
- CN
- China
- Prior art keywords
- image
- frequency sub
- focusing
- energy
- band coefficient
- 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.)
- Expired - Fee Related
Links
Abstract
The invention discloses microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer, described method is: obtains in different focusings respectively and takes the photograph image in advance accordingly;It is loaded into these source images;Respectively these images are carried out NSCT decomposition, and produces sub-band coefficients (image);Calculate this image low frequency, the energy of high frequency coefficient and ratio;Ratio is utilized to obtain focus estimated value as reference data;Focus estimated value is utilized constantly to adjust focusing position;Repeat said process, determine the optimal focusing position of present image.The present invention proposes a kind of microscopical Atomatic focusing method decomposed based on NSCT, can be efficiently applied to microscopical auto-focusing in urine sediments analyzer.Present invention can ensure that the microscope of urine sediments analyzer carries out auto-focusing and makes display image the most clearly, substantially increase the reliability and sensitivity of focusing system.
Description
Technical field
The present invention relates to a kind of microscopical Atomatic focusing method, particularly to a kind of based on urine sediments analyzer high-precision
Spend microscopical Atomatic focusing method, device and electronic equipment.
Background technology
Along with deepening continuously that urine sediments analyzer and computer technology combine, the microscope as its core technology is automatic
Focus algorithm has become as an important research direction in computer vision.The urine sediment image pair of clear profile can be obtained
In medical analysis afterwards, diagnosis etc. is particularly significant, also has influence on the degree of accuracy of instrument.
Check the visible component in urine all to use under microscope clinically and be manually analyzed differentiating.Auto-focusing one side
Face can alleviate the labor intensity of operator, operator is reduced or avoided because of the subjective error caused of repeatedly focusing.On the other hand,
It eliminates the focusing action of complexity, greatly facilitates operator.Comparing common imaging system, the depth of focus of microscope objective is
Extremely limited, and along with the increase of amplification, its depth of focus can constantly reduce.Especially under high x Microscope Objective,
Only those structures near focussing plane or its are only clearly, can relatively obscure away from the structure of focal plane and even may not be used
Seeing, the phenomenon that system imaging quality is limited by the depth of focus of high power objective and declines also can be extremely serious.Therefore, Urine sediments analyzer is shown
For the acquisition of micro-image, controlling microscopical auto-focusing just becomes urine Urine sediments analyzer divide to obtain micro-image the most clearly
The premise of analysis system normal assay.
The focusing mode being applied to microscope autofocus system at present mostly is passive mode.This mode is to use image
Treatment technology determines whether sample image focuses.This image processing techniques is to analyze the quality of image according to image, from
And obtain current image formation state, and the evaluation function value of the image of diverse location is calculated by focusing evaluation function, look for
Go out the image space that evaluation function value is maximum, complete focus operation.
The various image evaluation methods having pointed out, refer to shown in Fig. 1.One class is the evaluation methodology of time domain, directly with sharp
Change operator image is processed, then take the data after process as judgment basis, there is feature succinct, quick, but right
Noise is more sensitive, common are Gradient algorithm, laplacian evaluation algorithms etc., can obtain relation as shown in Figure 2 bent
Line;Another kind of is the evaluation methodology of frequency domain, mainly uses the method such as Fourier transformation, wavelet transformation, by analyzing the frequency of image
Rate composition carrys out the definition of evaluation image, can obtain relation curve as shown in Figure 3.
Preferably sharpness evaluation function should meet unimodality and unbiasedness, in actual image acquisition, owing to making an uproar
The impact of the factors such as the ambient interferences of sound, the dust of sample surface and sample, causes evaluation function multiple local maximums occur
Value, and maximum peak slip chart picture position the most clearly, have influence on pattern detection result accuracy.Have been presented for various side at present
Method eliminates the limitation extreme value of focusing curve, but major part is not of universal significance, and in some cases, no matter which kind of uses
Focusing evaluation function, all may cause the failure of auto-focusing.Thus eliminate multimodal and ambient interferences, build one reliably, soon
Fast and high-precision microscope autofocus system has great importance.
Summary of the invention
Present invention aims to urine sediments analyzer and a kind of image definition evaluation under microscopic field is provided
Algorithm, be can ensure that microscope focus operation completes after, the image on display screen be correct the most clearly.
Microscope Atomatic focusing method based on NSCT in a kind of urine sediments analyzer, this focusing process includes following step
Rapid:
A1 takes the photograph image X in advance X different object distances acquisition the most continuously and opens, and taking the photograph image Px in advance for each all has accordingly
X object distance position;
A2 is loaded into described source images;
A3 continuous print X is opened take the photograph in advance image carry out N level NSCT decompose, every image obtainsIndividual high-frequency sub-band coefficient
With 1 low frequency sub-band coefficient;
A4 utilizes sub-band coefficients structure based on the Laplce's energy improved and function, low frequency sub-band coefficient Laplce's energy
The ratio of amount and functional value and high-frequency sub-band coefficient Laplce's energy and functional value is sharpness evaluation function value;
Ratio described in A5 utilization obtains focus estimated value as reference data;
A6 utilizes focus estimated value constantly to adjust focusing position;
A7 repeats said process, determines the optimal focusing position of present image.
Described method, described step A3, method particularly includes: initially with the tower bank of filters of non-lower sampling to input
Image F carries out multi-resolution decomposition, obtains low frequency sub-band coefficient and high-frequency sub-band coefficient;Then the pyramidal structure obtained is entered
The multi-direction decomposition of row non-lower sampling directional filter banks, obtains the sub-band coefficients of different scale, different directions:
Wherein, N is Decomposition order,Represent low frequency (L) sub-band coefficients,Represent on n yardstick k direction
Position is at (i, each high frequency (H) directional subband coefficient j), knFor the Directional Decomposition progression under yardstick n,Number for directional subband
Mesh.
Described method, described step A4-A6, method particularly includes: at NSCT transform domain, the La Pula of described improvement
This (ML) and SML function definition are as follows:
MLN, k(i, j)=| 2CN, k(i, j)-CN, k(i-1, j)+
CN, k(i+1, j) |+| 2CN, k(i, j)-
CN, k(i, j-1)+CN, k(i, j+1) |
Wherein, CN, k(i j) is image sub-band coefficients after NSCT decomposes;
Low frequency sub-band coefficient and Laplce's energy of high-frequency sub-band coefficient and function (SML) is obtained at NSCT transform domain:
High-frequency sub-band coefficient energy according to different directions, obtains every grade of high-frequency sub-band coefficient energy:
The gross energy of high-frequency sub-band coefficient is obtained by following formula:
In conjunction with the Variation Features of both high and low frequency sub-band coefficients (image) energy, calculate sharpness evaluation function value:
It is principle to the maximum with the sharpness evaluation function value of image, contrasts the clear of previous width or a few width image focusing position
Degree evaluation function value, estimating the optimal focusing position of present image, then doing small adjustment near estimation position, until obtaining
Take focus image the most clearly.
The present invention also provides for a kind of microscope automatic focusing mechanism, and this automatic focusing mechanism includes:
Image capture device based on CMOS, takes the photograph image in order to shoot the pre-of microscope different focus point;
USB interface, is used for connecting image capture device and computer, is the passage of image transmitting;
Computer, is used for analyzing, storing source images, produces focus estimated value to determine camera lens according to object selection value
Focusing position for sample;
Single-chip microcomputer, receives the instruction from computer, and drive stepping motor adjusts;
Stepper motor driver, by Single-chip Controlling, is used for driving microscope camera lens, so that focus lens to move to prediction
Focus lens position;
Wherein, this computer utilizes the sharpness evaluation function value of image to estimate the optimal of present image with corresponding object distance
Focusing object distance.
Described microscope automatic focusing mechanism, also includes that auto exposure parameter determines and control unit, and it is arranged at institute
State in computer, in order to according to the environment captured by this image capture device, to determine time of exposure when subject shoots, light
Circle size and at least one person of ISO value.
The present invention also provides for a kind of electronic imaging device using any of the above-described described method.
The invention have the characteristics that:
1. the present invention proposes a kind of microscopical Atomatic focusing method decomposed based on NSCT, can be efficiently applied to urine heavy
Microscopical auto-focusing in slag analyser.
2. present invention can ensure that the microscope of urine sediments analyzer carries out auto-focusing and makes display image the most clearly, greatly
Improve greatly the reliability and sensitivity of focusing system.
3. the algorithm in the present invention realizes simple, and kernel software algorithm part only needs a PC just can be automatically performed.
Accompanying drawing explanation
Fig. 1 prior art utilizes 2 images to be evaluated the schematic diagram of focusing;
The relation schematic diagram of the evaluation result that Fig. 2 prior art is calculated in time domain and object distance;
The relation schematic diagram of the evaluation result that Fig. 3 prior art is calculated at frequency domain and object distance;
The principle schematic of Fig. 4 present invention;
The evaluation result of Fig. 5 present invention and the relation schematic diagram of object distance;
The auto-focusing of Fig. 6 embodiment of the present invention controls the block diagram representation of circuitry configuration;
Wherein, reference:
300 microscope automatic focusing control apparatus, 310 auto-focusing microscopes, 320 image capture devices, 330USB connects
Mouthful, 340 computers, 350 single-chip microcomputers, 360 stepper motor drivers;
Detailed description of the invention
Embodiment 1
For the basic operation workflow of the present invention can be clearly described, refer to shown in Fig. 4, different at X continuously first respectively
Object distance acquisition is taken the photograph image X in advance and is opened, and taking the photograph image Px in advance for each all has corresponding X object distance position;X=3 in the diagram.It is loaded into pre-
Take the photograph image;Continuous print X is opened take the photograph in advance image carry out N level NSCT decompose, every image obtainsIndividual high-frequency sub-band coefficient (figure
Picture) and 1 low frequency sub-band coefficient (image);N=3 in the diagram.After this decomposing program, sub-band coefficients (image) contains source
The marginal information that image is abundant, utilizes sub-band coefficients (image) structure based on the Laplce's energy improved and function, low frequency
Band coefficient Laplce's energy and functional value are with the ratio of high-frequency sub-band coefficient (image) Laplce's energy and functional value
Sharpness evaluation function value, the success rate of auto-focusing will be substantially improved.
In the diagram, as a example by X=3, obtain respectively and first take the photograph image P1 in advance, second image P2 in advance, the 3rd image P3 in advance.
Subsequently, these images (P is calculated1~P3) low frequency, Laplce's energy of high-frequency signal and the ratio of functional value;So just can obtain
To the object distance relation corresponding thereto of source images as shown in Figure 5.Compared to the relation curve obtained by prior art, Fig. 5 has
There is more specific focusing position, and show more preferable noise immunity and unimodality.The success rate of auto-focusing will be substantially improved.
Last further according to these images (P1~P3) sharpness evaluation function value object distance relation corresponding thereto, with result maximum
For principle, determine the focusing object distance that the maximum of sharpness evaluation function value is corresponding.
In actual applications, refer to shown in Fig. 6, its be the embodiment of the present invention auto-focusing control equipment circuit join
The block diagram put.The microscope automatic focusing control apparatus 300 of the present invention includes: auto-focusing microscope 310, image acquisition set
Standby (based on CMOS) 320, USB interface 330, computer 340, single-chip microcomputer 350 and stepper motor driver 360.,
The image capture device 320 of this device is connected with computer 340, in order to shooting environmental and sample by USB interface 330
This imaging obtains pre-image of taking the photograph, and will take the photograph image transmitting in advance to computer 340.When reality performs, auto exposure parameter meeting
Automatically suitably adjustment is made according to shooting environmental.Computer 340 receives the pre-of image capture device 320 transmission and takes the photograph image, should
Take the photograph image in advance preserve and be converted into digital signal;Utilize this digital signal that this pre-image of taking the photograph is carried out NSCT conversion, obtain source figure
1 low frequency sub-band coefficient of picture and multiple high-frequency sub-band coefficient, calculate every image low frequency sub-band coefficient, high-frequency sub-band coefficient
Laplce's energy of (image) and the ratio of functional value are worth to sharpness evaluation function value, clear with a width or a few width image
Degree evaluation function value compares, and obtains homologue away from relation curve, for search by hill climbing;Simultaneously according to each image definition
Evaluation function value output control command with instrumentality away from, this control command is exported to single-chip microcomputer 350 by serial ports.Single-chip microcomputer 350
It is connected with computer 340 serial ports, rotates to control stepper motor driver in order to receive the above-mentioned control command of computer 340.
Motor often rotates once, and microscope 310 adjusts object distance towards the direction that sharpness evaluation function value is big;Again by image acquisition
Equipment 320 shoots new image, and is transferred to computer 340 and repeats above-mentioned analysis.
Repeating the step described in epimere, according to previous width or a few width Image Definition value, using climbs the mountain searches
Rope algorithm, calculates the sharpness evaluation function value of current position image, until the sharpness evaluation function value of new image is more than
The functional value of the most all images, makes this microscope camera lens 310 stop in this place, the focusing position of this i.e. this microscope 310, by
This just completes auto-focusing.Because the autofocus system of the present embodiment is according to the image gained of display on computer 340
Result carry out focus operation, it is thus ensured that after focus operation completes, the image being projeced on computer 340 screen is correct
Clearly.
Embodiment 2
The present embodiment describes Laplce's energy and the function of above-mentioned improvement in detail.
Image capture device by the image transmitting that photographed to computer, being given subsequent algorithm by computer and carry out frame by frame
Process.Need exist for explanation is original each two field picture to have carried out 1/4th samplings (such as: original graph in the present invention
As size is 800 × 600, it is 200 × 150 after sampling), so can improve follow-up calculation on the premise of not affecting Detection results
The arithmetic speed of method.
Initially with the tower bank of filters of non-lower sampling (NSP), input picture F is carried out multi-resolution decomposition, obtain low frequency
Band coefficient (image) and high-frequency sub-band coefficient (image);Then the pyramidal structure obtained is carried out non-lower sampling trend pass filtering
Device group (NSDFB) multi-direction decomposition, obtains the sub-band coefficients of different scale, different directions:
Wherein, N is Decomposition order,Represent low frequency (L) sub-band coefficients,Represent on n yardstick k direction
Position is at (i, each high frequency (H) directional subband coefficient j), knFor the Directional Decomposition progression under yardstick n,Number for directional subband
Mesh.Coefficient magnitude keeps consistent with original image, therefore can regard the sub-band coefficients of NSCT transform domain as image.
Then the Laplce's energy and the function (Sum-modified laplacian, SML) that define improvement carry out phenogram
The energy value of picture.At NSCT transform domain, the Laplce (ML) of improvement and SML function definition are as follows:
MLN, k(i, j)=| 2CN, k(i, j)-CN, k(i-1, j)+
CN, k(i+1, j) |+| 2CN, k(i, j)-
CN, k(i, j-1)+CN, k(i, j+1) |
Wherein, CN, k(i j) is image sub-band coefficients (image) after NSCT decomposes.
Low frequency sub-band coefficient and Laplce's energy of high-frequency sub-band coefficient (image) and function is obtained at NSCT transform domain
(SML):
High-frequency sub-band coefficient (image) energy according to different directions, obtains every grade of high-frequency sub-band coefficient (image) energy:
The gross energy of high-frequency sub-band coefficient (image) is obtained by following formula:
In conjunction with the Variation Features of both high and low frequency sub-band coefficients (image) energy, calculate sharpness evaluation function
Value:
It is principle to the maximum with the sharpness evaluation function value of image, contrasts the clear of previous width or a few width image focusing position
Degree evaluation function value, estimating the optimal focusing position of present image, then doing small adjustment near estimation position, until obtaining
Take focus image the most clearly.
The tower wave filter of the non-lower sampling (NSP) that described NSCT uses is one group of two passage non-lower sampling wave filter.Often
The bank of filters that one-level is used is that the wave filter being used upper level is by sampling matrix Carry out sampling
Arrive.Image, after N level non-lower sampling QMF compression, can obtain N+1 the subband system with source images with same size size
Number (image).
The non-lower sampling anisotropic filter (NSDFB) that described NSCT is used is a class frequency response characteristic for fan-shaped shape
The two non-lower employing bank of filters of passage of shape.In order to obtain more Directional Decomposition, NSCT is also by employing two-way repeatedly
Road directional filter banks travel direction filtering realizes.The wave filter that every one-level uses is the wave filter by using upper level
By sampling matrix Sampling obtains.Can get 2 after sub-band coefficients (image) carries out k level decomposition under certain yardstickkIndividual
The sub-band coefficients (image) identical with original input picture size.Image obtains 1 low frequency sub-band after N level NSCT is decomposed
Coefficient (image) andIndividual high-frequency sub-band coefficient (image).
Except above-described embodiment, it is to utilize this microscope mobile equally that the Atomatic focusing method of the present invention can also be used for other
310, and obtain image in each lens location and calculate the sharpness evaluation function value of this image, then compare to take
Obtain maximum image sharpness evaluation function value, and make this microscope 310 camera lens be positioned at the mode of opposite position.The most existing
Universe searches (Global Search) method, Fei Shi searches the focusing modes such as (Fibonacci Search) method.
It should be appreciated that for those of ordinary skills, can be improved according to the above description or be converted,
And all these modifications and variations all should belong to the protection domain of claims of the present invention.
Claims (6)
1. microscope Atomatic focusing method based on NSCT in a urine sediments analyzer, it is characterised in that this focusing process bag
Include the following step:
A1 takes the photograph image X in advance X different object distances acquisition the most continuously and opens, and takes the photograph image P in advance for eachXAll there is corresponding X thing
Away from position;
Continuous print X described in A2 loading A1 opens and takes the photograph image in advance;
A3 continuous print X is opened take the photograph in advance image carry out N level NSCT decompose, every image obtainsIndividual high-frequency sub-band coefficient and 1
Low frequency sub-band coefficient;
A4 utilizes Laplce's energy and the function SML of sub-band coefficients structure improvementN, k, wherein subscript k represents the side that NSCT decomposes
To number, the low frequency sub-band coefficient obtained at NSCT transform domain and Laplce's energy of the improvement of high-frequency sub-band coefficient and function
SML is respectively ELWithWherein subscript k represents the direction number that NSCT decomposes, according to the high-frequency sub-band coefficient energy of different directions
Amount, obtains every grade of high-frequency sub-band coefficient ENERGY En, by first order high-frequency sub-band coefficient ENERGY E1 HWeights be α, other is at different levels high
Frequently the weights of the average of sub-band coefficients energy are that the mode of 1-α is weighted gross energy EH, the improvement of low frequency sub-band coefficient
Laplce's energy and functional value ELLaplce's energy of the improvement with high-frequency sub-band coefficient and functional value EHRatio be
Sharpness evaluation function value;
Ratio described in A5 utilization obtains focus estimated value as reference data;
A6 utilizes focus estimated value constantly to adjust focusing position;
A7 repeats said process, determines the optimal focusing position of present image.
Method the most according to claim 1, it is characterised in that described step A3, method particularly includes: under non-
Tower bank of filters of sampling carries out multi-resolution decomposition to input picture F, obtains low frequency sub-band coefficient and high-frequency sub-band coefficient;Then
The pyramidal structure obtained is carried out the multi-direction decomposition of non-lower sampling directional filter banks, obtains different scale, different directions
Sub-band coefficients:
Wherein, N is Decomposition order,Represent low frequency sub-band coefficient,Represent on n yardstick k direction position (i,
J) each high frequency direction sub-band coefficients, knFor the Directional Decomposition progression under yardstick n,Number for directional subband.
Method the most according to claim 1, it is characterised in that described step A4-A6, method particularly includes: become at NSCT
Changing territory, the Laplce ML of improvement and Laplce's energy of improvement and function SML definition are as follows:
MLN, k(i, j)=| 2CN, k(i, j)-CN, k(i-1, j)+
CN, k(i+1, j) |+| 2CN, k(i, j)-
CN, k(i, j-1)+CN, k(i, j+1) |
Wherein, CN, k(i j) is image sub-band coefficients after NSCT decomposes;
Laplce's energy and the function SML of the improvement of low frequency sub-band coefficient and high-frequency sub-band coefficient is obtained at NSCT transform domain:
High-frequency sub-band coefficient energy according to different directions, obtains every grade of high-frequency sub-band coefficient energy:
The gross energy of high-frequency sub-band coefficient is obtained by following formula:
α in above formula is the weight coefficient of first order high-frequency sub-band coefficient and other high-frequency sub-band Coefficient Means at different levels, in conjunction with two
The Variation Features of person's high and low frequency sub-band coefficients energy, calculates sharpness evaluation function value:
Being principle to the maximum with the sharpness evaluation function value of image, the definition contrasting previous width or a few width image focusing position is commented
Valency functional value, estimates the optimal focusing position of present image, then does small adjustment near estimation position, until obtaining
Focus image clearly.
4. according to the microscope automatic focusing mechanism of the arbitrary described method of claim 1-3, it is characterised in that this auto-focusing
Device includes:
Image capture device based on CMOS, takes the photograph image in order to shoot the pre-of microscope different focus point;
USB interface, is used for connecting image capture device and computer, is the passage of image transmitting;
Computer, is used for analyzing, storing source images, according to object selection value produce focus estimated value with determine camera lens for
The focusing position of sample;
Single-chip microcomputer, receives the instruction from computer, and drive stepping motor adjusts;
Stepper motor driver, by Single-chip Controlling, is used for driving microscope camera lens, so that focus lens to move to prediction focusing
Lens location;
Wherein, this computer utilizes the sharpness evaluation function value of image to estimate the optimal focusing of present image with corresponding object distance
Object distance.
Microscope automatic focusing mechanism the most according to claim 4, it is characterised in that also include that auto exposure parameter determines
With control unit, it is arranged in described computer, in order to according to the environment captured by this image capture device, to determine to be taken
At least one person of time of exposure, aperture size and ISO value during thing shooting.
6. the electronic imaging device using the arbitrary described method of claim 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310302672.3A CN103345756B (en) | 2013-07-19 | 2013-07-19 | Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310302672.3A CN103345756B (en) | 2013-07-19 | 2013-07-19 | Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103345756A CN103345756A (en) | 2013-10-09 |
CN103345756B true CN103345756B (en) | 2016-08-10 |
Family
ID=49280549
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310302672.3A Expired - Fee Related CN103345756B (en) | 2013-07-19 | 2013-07-19 | Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103345756B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015100738A1 (en) * | 2014-01-04 | 2015-07-09 | 陈加志 | Automatic astronomical observation system and observation method |
EP3081977A1 (en) * | 2015-04-16 | 2016-10-19 | Leica Instruments (Singapore) Pte. Ltd. | Microscopic image controller device for a microscope, microscope, and microscoping method |
CN105093509B (en) * | 2015-09-29 | 2017-09-01 | 爱威科技股份有限公司 | Microscopical auto focusing method, system and stool microscopy microscope |
CN107644425B (en) * | 2017-09-30 | 2018-08-24 | 湖南友哲科技有限公司 | Target image choosing method, device, computer equipment and storage medium |
CN108053369A (en) * | 2017-11-27 | 2018-05-18 | 努比亚技术有限公司 | A kind of method of image procossing, equipment and storage medium |
CN109047228B (en) * | 2018-07-16 | 2023-07-18 | 朱鑫国 | Online cleaning and airtight sampling integrated device for glass bottle |
CN109035176B (en) * | 2018-08-24 | 2022-03-04 | 宁波永新光学股份有限公司 | Microscopic image definition evaluation method |
CN112241953B (en) * | 2020-10-22 | 2023-07-21 | 江苏美克医学技术有限公司 | Sample image fusion method and device based on multi-focus image fusion and HDR algorithm |
CN117576103B (en) * | 2024-01-17 | 2024-04-05 | 浙江大学滨江研究院 | Urinary sediment microscopic examination analysis system integrating electric control microscope and deep learning algorithm |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101660946A (en) * | 2009-09-28 | 2010-03-03 | 山东神戎电子股份有限公司 | Auto-focusing method and device of thermal imager |
CN101943839A (en) * | 2010-07-06 | 2011-01-12 | 浙江大学 | Integrated automatic focusing camera device and definition evaluation method |
CN102062929A (en) * | 2010-11-27 | 2011-05-18 | 长春迪瑞医疗科技股份有限公司 | Automatic focusing method and device for microscope system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9076204B2 (en) * | 2010-11-08 | 2015-07-07 | Panasonic Intellectual Property Management Co., Ltd. | Image capturing device, image capturing method, program, and integrated circuit |
-
2013
- 2013-07-19 CN CN201310302672.3A patent/CN103345756B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101660946A (en) * | 2009-09-28 | 2010-03-03 | 山东神戎电子股份有限公司 | Auto-focusing method and device of thermal imager |
CN101943839A (en) * | 2010-07-06 | 2011-01-12 | 浙江大学 | Integrated automatic focusing camera device and definition evaluation method |
CN102062929A (en) * | 2010-11-27 | 2011-05-18 | 长春迪瑞医疗科技股份有限公司 | Automatic focusing method and device for microscope system |
Non-Patent Citations (3)
Title |
---|
改进拉普拉斯能量和的尖锐频率局部化Contourlet域多聚焦图像融合方法;屈小波等;《光学精密工程》;20090531;第17卷(第5期);1203-1212 * |
时海亮等.一种基于像素清晰度的NSCT域多聚焦图像融合方法.《郑州轻工业学院学报(自然科学版)》.2012,第27卷(第3期),53-57. * |
王义文等.基于小波变换的显微图像清晰度评价函数及3-D自动调焦技术.《光学精密工程》.2006,第14卷(第6期),1063-1069. * |
Also Published As
Publication number | Publication date |
---|---|
CN103345756A (en) | 2013-10-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103345756B (en) | Microscopical Atomatic focusing method, device and electronic equipment in a kind of urine sediments analyzer | |
CN109829400B (en) | Rapid vehicle detection method | |
CN103714321B (en) | Driver's Face detection system based on range image and intensity image | |
CN109664820A (en) | Driving reminding method, device, equipment and storage medium based on automobile data recorder | |
CN102981347A (en) | Automatic SUSAN focusing method for video monitoring system | |
DE102020108640A1 (en) | Voice-controlled camera with AI scene detection for precise focusing | |
CN104079827A (en) | Light field imaging automatic refocusing method | |
DE102013221668A1 (en) | A system and method for providing a user interface in the vehicle, wherein recognizing a handheld shape track is used | |
CN112287896A (en) | Unmanned aerial vehicle aerial image target detection method and system based on deep learning | |
CN112581379A (en) | Image enhancement method and device | |
CN105894483A (en) | Multi-focusing image fusion method based on multi-dimensional image analysis and block consistency verification | |
CN107329233A (en) | A kind of droplet type PCR instrument Atomatic focusing method based on neutral net | |
CN104751186A (en) | Iris image quality classification method based on BP (back propagation) network and wavelet transformation | |
CN102542535B (en) | Method for deblurring iris image | |
CN110458128A (en) | A kind of posture feature acquisition methods, device, equipment and storage medium | |
CN109509274A (en) | Make the method and apparatus of the environmental information data reduction of driver assistance system | |
CN106682604B (en) | Blurred image detection method based on deep learning | |
CN103096117A (en) | Video noise detecting method and device | |
CN113705427A (en) | Fatigue driving monitoring and early warning method and system based on vehicle gauge chip SoC | |
CN116994164A (en) | Multi-mode aerial image fusion and target detection combined learning method | |
CN116453020A (en) | Binocular identification method, binocular identification system, binocular identification equipment and binocular identification medium | |
US20140192178A1 (en) | Method and system for tracking motion of microscopic objects within a three-dimensional volume | |
CN116342675A (en) | Real-time monocular depth estimation method, system, electronic equipment and storage medium | |
Mahmood et al. | 3D shape recovery from image focus using kernel regression in eigenspace | |
CN114419401B (en) | Method and device for detecting and identifying leucocytes, computer storage medium and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160810 Termination date: 20180719 |
|
CF01 | Termination of patent right due to non-payment of annual fee |