CN107644425A - Target image choosing method, device, computer equipment and storage medium - Google Patents
Target image choosing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN107644425A CN107644425A CN201710944304.7A CN201710944304A CN107644425A CN 107644425 A CN107644425 A CN 107644425A CN 201710944304 A CN201710944304 A CN 201710944304A CN 107644425 A CN107644425 A CN 107644425A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- collection
- pixel
- definition
- 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
Abstract
A kind of target image choosing method, device, computer equipment and storage medium, the method for one embodiment include:Obtain each image of collection;Each described image of collection is analyzed respectively, is analyzed from each image of collection and determines the most intermediate objective image of the target included;The image of the front and rear predetermined number adjacent with the intermediate objective image is chosen, and calculates the definition of each image of selection;The final goal image that image corresponding to the definition of maximum is defined as choosing.The embodiment of the present invention improves the efficiency and accuracy rate for choosing target image.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of target image choosing method, a kind of target image
Selecting device, a kind of computer equipment and storage medium.
Background technology
With the development of computer technology, increasingly hot topic is detected to target using computer image processing technology,
Target detection is also Objective extraction, be it is a kind of based on the image of target geometry and statistical nature split.And with digital in recent years
The development of image processing techniques, the Techniques of Automatic Focusing based on image procossing obtains long-range development, therefore is carrying out target inspection
During survey, image where target is generally selected by Techniques of Automatic Focusing, and the image for choosing carry out target detection or
Objective extraction.However, in modern medicine field of image detection, real image is various and complicated, and usual mode needs to expend
Image where target can just be found for a long time, and accuracy rate is low.
The content of the invention
Based on this, the embodiment of the present invention provides a kind of target image choosing method, a kind of target image selecting device, one kind
Computer equipment and storage medium, to improve the efficiency and accuracy rate of choosing target image.
A kind of target image choosing method, including step:
Obtain each image of collection;
Each described image of collection is analyzed respectively, is analyzed from each image of collection and determines the target included most
More intermediate objective images;
The image of the front and rear predetermined number adjacent with the intermediate objective image is chosen, and calculates the clear of each image of selection
Clear degree;
The final goal image that image corresponding to the definition of maximum is defined as choosing.
A kind of target image selecting device, including:
Image analysis module, for obtaining each image of collection;And each described image is analyzed respectively, from each described
The most intermediate objective image of the target included is determined in analysis in image;
Sharpness computation module, for choosing the image of the front and rear predetermined number adjacent with the intermediate objective image, and
Calculate the definition for each image chosen;
Module is chosen, for image corresponding to the definition of maximum to be chosen for into final goal image.
A kind of computer equipment, including memory, processor and be stored on the memory and can be in the processing
The computer program run on device, method as described above is realized described in the computing device during computer program.
A kind of computer-readable storage medium, is stored thereon with computer program, is realized as above when the program is executed by processor
Described method.
Based on the scheme in embodiment as described above, it is first analyzed each image of collection, and therefrom analysis determines
Go out the most intermediate objective image of the target included, then choose the figure of the front and rear predetermined number adjacent with the intermediate objective image
Picture, so as to fast and efficiently find the section where target image, then choose image corresponding to the definition of maximum
As final goal image, so that the target image definition highest finally determined, while improve selection target image
Efficiency and accuracy rate.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the target image choosing method in one embodiment;
Fig. 2 is the schematic diagram behind label target region in one image in a concrete application example;
Fig. 3 is the structural representation of the target image selecting device in one embodiment.
Embodiment
For the objects, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with drawings and Examples, to this
Invention is described in further detail.It should be appreciated that the present invention can realize in many different forms, however it is not limited to this
Embodiment described by text.On the contrary, the purpose for providing these embodiments is to make understanding to the disclosure more
Thorough and comprehensive.
Unless otherwise defined, all of technologies and scientific terms used here by the article is with belonging to technical field of the invention
The implication that technical staff is generally understood that is identical.Term used in the description of the invention herein is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term as used herein " and/or " include one or more phases
The arbitrary and all combination of the Listed Items of pass.
The target image choosing method of the embodiment of the present invention can apply to various needs and one chosen from multiple images
The technology application scenarios of target image, such as the various microscopy automations such as urine sediments analyzer, copra analysis instrument, gynaecology's analyzer
Instrument chooses the one of image gathered as target image to carry out various automated analysis etc..
The schematic flow sheet of the target image choosing method of one embodiment is shown in Fig. 1, as shown in figure 1, the implementation
The method of example includes step S101 to step S104.
Step S101:Obtain each image of collection.
It is appreciated that each image here is to treat therefrom to select each image in the image set of target image.The image
Each image concentrated can refer to determine each image under sample catalogue, and it is typically to give tacit consent to when gathering each image that this, which specifies sample catalogue,
The paths different from the store path of the acquiescence for storing the store path of the image of collection or separately specifying, as long as
It can determine targeted each image.
In one example, it can be collection is obtained from sample catalogue each image, each image here can be phase
Image capture device (such as urine sediments analyzer, copra analysis instrument, the CCD of gynaecology's analyzer microscopy self-reacting device of pass
(Charge Coupled Device, charge coupled cell) camera etc.) each image for collecting, typically image capture device
The image of acquisition is gathered in units of frame, these images constitute image sequence, and each image in image sequence there can be base
In the picture numbers that acquisition order determines, the picture numbers can as the image identification of the image, in certain embodiments,
Can be the picture numbers using the acquisition time of image as the image, as long as the priority that can distinguish the collection of each image is suitable
Sequence, it can make up image sequence.
Step S102:Each described image of collection is analyzed respectively, is analyzed from each image of collection and determines to wrap
The most intermediate objective image of the target that contains.
In one embodiment, each described image of collection is analyzed respectively, analyzed from each image of collection true
When making the most intermediate objective image of the target included, following manner can be used to carry out:
The foreground area of each image of collection is extracted respectively;
The area of the foreground area of each image of collection is calculated respectively, and will be schemed corresponding to the area of the foreground area of maximum
Picture, it is defined as the most intermediate objective image of the target that includes.
When extracting the foreground area of each image of collection respectively, specific step can include:For the figure of each collection
Picture, by the gray value of each pixel of the image compared with presetted pixel threshold value;And according to the gray value of each pixel with
The comparative result of presetted pixel threshold value is split to the image, obtains the foreground area of the image of extraction.
Wherein, the presetted pixel threshold value is determined by following manner:
By the gray value of each pixel of image compared with pixel threshold undetermined, determine that the image treats fixation based on this
The foreground pixel point and background pixel point of plain threshold value;
According to each foreground pixel point and each background pixel point, side between prospect class pixel and the class of background classes pixel is calculated
Difference;
Pixel threshold undetermined corresponding to the inter-class variance of maximum is defined as the presetted pixel threshold value.
In yet another embodiment, before the foreground area of each image of collection is extracted respectively, step can also be included:
Each image of collection is smoothed respectively.The mode being specifically smoothed, any possible side can be used
Formula is carried out.
After the most intermediate objective image of the target included is determined in analysis in above-mentioned each image from collection, may be used also
To further determine that the target area of the intermediate objective image, and pair target area determined carries out rectangle sign, acquisition pair
Intermediate objective image after the rectangle mark of target area.So as to intuitively be verified accordingly to accuracy.
Step S103:The image of the front and rear predetermined number adjacent with the intermediate objective image is chosen, and calculates selection
The definition of each image.
It is appreciated that here adjacent generally relevant with putting in order for each image, and putting in order for image can be
Corresponding with acquisition order, such put in order can be based on the determination such as picture numbers as described above.The predetermined number
It can combine to be actually needed and be set, in a specific example, the predetermined number can be set as 20, so as to choose
Each 20 width of the intermediate objective image or so, 41 width images are as the image chosen altogether.
When calculating the definition for each image chosen, can be calculated using any possible mode.In a tool
In body example, calculate choose each image definition when, can be calculate choose each image target area it is clear
Degree, and the definition using the definition of the target area of each image as the image.
Step S104:The final goal image that image corresponding to the definition of maximum is defined as choosing.
Based on the scheme in embodiment as described above, it is first analyzed each image of collection, and therefrom analysis determines
Go out the most intermediate objective image of the target included, then choose the figure of the front and rear predetermined number adjacent with the intermediate objective image
Picture, so as to fast and efficiently find the section where target image, then choose image corresponding to the definition of maximum
As final goal image, so that the target image definition highest finally determined, while improve selection target image
Efficiency and accuracy rate.
Based on the target image choosing method in embodiment as described above, carried out below in conjunction with one of specific example
Describe in detail.
Collect and treat in the CCD by microscopy self-reacting devices such as urine sediments analyzer, copra analysis instrument, gynaecology's analyzers
After each image for detecting sample, by under each image collected storage to corresponding sample catalogue, during collection, can be using frame as
Unit, which is acquired, obtains each image.The sample catalogue can be only uniquely to should sample to be detected catalogue or
Corresponding multiple detection samples, in the case, image corresponding to variant detection sample can be named by different images
Either each subdirectory is set to make a distinction.
A target image can be then chosen from all images corresponding to the sample to be detected, with to the target image
Analyzed so as to obtain the testing result for the sample to be detected.The present embodiments relate to be from the sample to be detected
The process of a target image is chosen in corresponding all images.
When choosing target image, first obtain corresponding under sample catalogue, all images corresponding to the sample to be detected, can
To understand, all images corresponding to the sample to be monitored have the graphical arrangement order determined based on acquisition order, so as to form
Image sequence, each image can have the picture numbers in the image sequence, and the picture numbers can be with acquisition time, adopt
Any possible modes such as collection number, acquisition order embody.
Then each image can be analyzed, the most intermediate objective image of the target included is determined in therefrom analysis.
In the specific example, by the image that foreground image areas area is maximum, as being the most image of target.Therefore, specific
When the target included most intermediate objective image is determined in analysis, following manner can be used to carry out.
Each image is smoothed first, specific smoothing processing mode can be entered using any possible mode
OK, the feature to reduce the noise of image and extract object out.Then image segmentation is carried out to the image after smoothing processing, by right
Image after smoothing processing carries out image segmentation, divides the image into as foreground area and background area two parts.
During segmentation, a pixel threshold k undetermined can be first set, and the gray value of each pixel of image is treated into fixation with this
Plain threshold value is compared, and pixel is given into foreground pixel C0 and the classes of background pixel C1 two according to comparative result.Wherein, prospect picture
Pixel-level residing for this kind of pixel of plain C0 is 0~k-1, and the Pixel-level residing for this kind of pixel of background pixel C1 is k~L-
1。
Each foreground pixel and background pixel of image based on determination, can calculate the overall average gray scale for determining the image
LevelAnd calculate the total area ratio shared by all foreground pixel C0Shared by all background pixel C1
Total area ratio ω1=1- ω0;And then all foreground pixel C0 average gray level u can be calculated0=u0(k)/ω0, own
Background pixel C1 average gray level u1=u1(k)/ω1.Wherein,
Then, you can calculate the inter-class variance between all foreground pixels and all background pixels:
δ2(k)=ω0(u-u0)2+ω1(u-u1)2。
Now, the pixel threshold k undetermined separately set changes from 0~L-1, calculates the inter-class variance δ under different k values2
(k), and by maximum δ2(k) k values corresponding to set it to presetted pixel threshold value as most having as optimal value.
Then, with the presetted pixel threshold value compared with the gray value of each pixel of image, obtain it is final it is each before
Scene element and background pixel, and each foreground pixel finally given is extracted, obtain the foreground area of image.And calculate each image
The area of foreground area, the area of maximum is corresponded into image as intermediate objective image.
Then, the pretreatment of correlation is done to the foreground area of the intermediate objective image, pretreatment here includes:Smooth place
Reason, Threshold segmentation, morphological change etc., the target area of pretreated intermediate objective image is then further determined that, and it is right
The target area of determination is labeled, such as is indicated with rectangle, obtains the intermediate objective image after being marked to target area rectangle,
The schematic diagram after being labelled with target area with rectangle in one image in a specific example is shown in Fig. 2.By to mesh
Mark is labeled, and intuitively accuracy can be verified accordingly.
Then the image of the front and rear predetermined number adjacent with intermediate objective image is chosen, can in a concrete application example
Be choose image sequence in, the intermediate objective image it is adjacent before and after each 20 width image.
Then, the definition of each image of selection is calculated.Can pass through calculating it is appreciated that when calculating definition
The definition of each target area in image, and using the definition sum of each target area of the image as the clear of the image
Degree.Lead to when calculating definition, following formula can be used to calculate:
In above formula, Gx(x, y), Gy(x, y) is gradient magnitude, and F (I) is exactly the definition values for the image I being calculated.Its
In, the G of gradient magnitudex(x, y), GyThe calculating of (x, y) is eight neighborhood subgraph and the Sobel centered on (x, y) in image I
Gradient operator template carries out convolution acquisition, and Convolution Formula is:
Wherein, I8(x, y) represents the eight neighborhood subgraph centered on (x, y) in image I, SxAnd SyCalculated for Sobel gradients
Son, its operator template are respectively:
It is defined as what is chosen after the definition of each image of selection is calculated, and by image corresponding to the definition of maximum
Final goal image.In one application example, the corresponding of the picture numbers of image and the definition of the image can also be drawn out
The curve of relation, and image corresponding to the peak of curve place is defined as final goal image.
After selected final goal image, you can the target area in the final goal image is analyzed, so as to most
The testing result to sample to be detected is obtained eventually.
It will appreciated by the skilled person that realizing all or part of flow in above-described embodiment method, being can
To instruct the hardware of correlation to complete by computer program, described program can be stored in a non-volatile computer can
Read in storage medium, in the embodiment of the present invention, the program can be stored in the storage medium of computer system, and is counted by this
At least one computing device in calculation machine system, to realize the flow for including the embodiment such as above-mentioned each method.Wherein, it is described
Storage medium can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) or random access memory
(Random Access Memory, RAM) etc..
Accordingly, a kind of storage medium is also provided in one embodiment, is stored thereon with computer program, wherein, the journey
Any one target image choosing method in each embodiment as described above is realized when sequence is executed by processor.
A kind of target image selecting device is also provided based on thought same as mentioned above, in one embodiment, Fig. 3 shows
The structural representation of the target image selecting device of one embodiment is gone out.As shown in figure 3, the device in the embodiment includes:
Image analysis module 301, sharpness computation module 302 and selection module 303.
Image analysis module 301, for obtaining each image of collection;And each described image is analyzed respectively, from each
The most intermediate objective image of the target included is determined in described image analysis.
It is appreciated that each image here is to treat therefrom to select each image in the image set of target image.The image
Each image concentrated can refer to determine each image under sample catalogue, and it is typically to give tacit consent to when gathering each image that this, which specifies sample catalogue,
The paths different from the store path of the acquiescence for storing the store path of the image of collection or separately specifying, as long as
It can determine targeted each image.
In one example, it can be collection is obtained from sample catalogue each image, each image here can be phase
Image capture device (such as urine sediments analyzer, copra analysis instrument, the CCD phases of gynaecology's analyzer microscopy self-reacting device of pass
Machine etc.) each image for collecting, typically image capture device gathers the image of acquisition in units of frame, and these images constitute
Image sequence, each image in image sequence can have a picture numbers determined based on acquisition order, and the picture numbers can be with
As the image identification of the image, in some embodiments, it is also possible to be the image using the acquisition time of image as the image
Sequence number, as long as the sequencing of the collection of each image can be distinguished, can make up image sequence.
In one embodiment, image analysis module 301 is analyzed each described image of collection respectively, from collection
When the target included most intermediate objective image is determined in analysis in each image, following manner can be used to carry out:Carry respectively
Take the foreground area of each image of collection;Calculate the area of the foreground area of each image of collection respectively, and by the prospect of maximum
Image corresponding to the area in region, it is defined as the most intermediate objective image of the target that includes.
When extracting the foreground area of each image of collection respectively, can specifically following manner be used to carry out:For respectively adopting
The image of collection, by the gray value of each pixel of the image compared with presetted pixel threshold value;And according to the ash of each pixel
The comparative result of angle value and presetted pixel threshold value is split to the image, obtains the foreground area of the image of extraction.
Wherein, the presetted pixel threshold value is determined by following manner:By the gray value of each pixel of image and treat fixation
Plain threshold value is compared, and determines foreground pixel point and background pixel point of the image based on the pixel threshold undetermined;Before each
Scene vegetarian refreshments and each background pixel point, calculate the inter-class variance of prospect class pixel and background classes pixel;By side between the class of maximum
Pixel threshold undetermined corresponding to difference is defined as the presetted pixel threshold value.
On the other hand, image analysis module 301 can also further determine that the target area of the intermediate objective image, and
Pair determine target area carry out rectangle sign, obtain to target area rectangle mark after intermediate objective image.So as to
Intuitively accuracy is verified accordingly.
Sharpness computation module 302, for choosing the image of the front and rear predetermined number adjacent with the intermediate objective image,
And calculate the definition of each image of selection.
It is appreciated that here adjacent generally relevant with putting in order for each image, and putting in order for image can be
Corresponding with acquisition order, such put in order can be based on the determination such as picture numbers as described above.The predetermined number
It can combine to be actually needed and be set, in a specific example, the predetermined number can be set as 20, so as to choose
Each 20 width of the intermediate objective image or so, 41 width images are as the image chosen altogether.
When calculating the definition for each image chosen, can be calculated using any possible mode.In a tool
In body example, calculate choose each image definition when, can be calculate choose each image target area it is clear
Degree, and the definition using the definition of the target area of each image as the image.Choose module 303, for by maximum it is clear
Image corresponding to clear degree is chosen for final goal image.
It will be appreciated by those skilled in the art that device as described above can be set on a computing device, by computer equipment
Perform.Accordingly, a kind of computer equipment is also provided in one embodiment, the computer equipment include memory, processor and
Storage on a memory and the computer program that can run on a processor, wherein, realization is such as during computing device described program
Any one target image choosing method in the various embodiments described above.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of target image choosing method, it is characterised in that including step:
Obtain each image of collection;
Each described image of collection is analyzed respectively, from each image of collection analysis determine that the target that includes is most
Intermediate objective image;
The image of the front and rear predetermined number adjacent with the intermediate objective image is chosen, and calculates the clear of each image of selection
Degree;
The final goal image that image corresponding to the definition of maximum is defined as choosing.
2. target image choosing method according to claim 1, it is characterised in that enter respectively to each described image of collection
The step of row is analyzed, and the target included most intermediate objective image is determined in analysis from each image of collection includes:
The foreground area of each image of collection is extracted respectively;
Calculate the area of the foreground area of each image of collection respectively, and by image corresponding to the area of the foreground area of maximum,
It is defined as the most intermediate objective image of the target that includes.
3. target image choosing method according to claim 2, it is characterised in that extracting each image of collection respectively
Before foreground area, in addition to step:
Each image of collection is smoothed respectively.
4. target image choosing method according to claim 2, it is characterised in that before each image for extracting collection respectively
The step of scene area, includes:
For the image of each collection, by the gray value of each pixel of the image compared with presetted pixel threshold value;
The image is split according to the gray value of each pixel and the comparative result of presetted pixel threshold value, obtains being somebody's turn to do for extraction
The foreground area of image.
5. target image choosing method according to claim 4, it is characterised in that the presetted pixel threshold value passes through following
Mode determines:
By the gray value of each pixel of image compared with pixel threshold undetermined, determine that the image is based on the pixel threshold undetermined
The foreground pixel point and background pixel point of value;
According to each foreground pixel point and each background pixel point, the inter-class variance of calculating prospect class pixel and background classes pixel;
Pixel threshold undetermined corresponding to the inter-class variance of maximum is defined as the presetted pixel threshold value.
6. target image choosing method according to claim 1, it is characterised in that analyzed in each image from collection true
After making the most intermediate objective image of the target included, the front and rear predetermined number adjacent with the intermediate objective image is chosen
Image before, in addition to step:
The target area of the intermediate objective image is determined, and pair target area determined carries out rectangle sign, obtains to target
Intermediate objective image after region rectangle mark.
7. target image choosing method according to claim 6, it is characterised in that calculate the definition of each image of selection
Mode include:
The definition of the target area for each image chosen is calculated, and using the definition of the target area of each image as the image
Definition.
A kind of 8. target image selecting device, it is characterised in that including:
Image analysis module, for obtaining each image of collection;And each described image is analyzed respectively, from each described image
The most intermediate objective image of the target included is determined in middle analysis;
Sharpness computation module, for choosing the image of the front and rear predetermined number adjacent with the intermediate objective image, and calculate
The definition for each image chosen;
Module is chosen, for image corresponding to the definition of maximum to be chosen for into final goal image.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be in the processor
The computer program of upper operation, it is characterised in that described in the computing device during computer program realize as claim 1 to
Method described in 7 any one.
10. a kind of computer-readable storage medium, is stored thereon with computer program, it is characterised in that the program is executed by processor
Methods of the Shi Shixian as described in claim 1 to 7 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710944304.7A CN107644425B (en) | 2017-09-30 | 2017-09-30 | Target image choosing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710944304.7A CN107644425B (en) | 2017-09-30 | 2017-09-30 | Target image choosing method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107644425A true CN107644425A (en) | 2018-01-30 |
CN107644425B CN107644425B (en) | 2018-08-24 |
Family
ID=61123063
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710944304.7A Active CN107644425B (en) | 2017-09-30 | 2017-09-30 | Target image choosing method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107644425B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109151320A (en) * | 2018-09-29 | 2019-01-04 | 联想(北京)有限公司 | A kind of target object choosing method and device |
CN110175980A (en) * | 2019-04-11 | 2019-08-27 | 平安科技(深圳)有限公司 | Image definition recognition methods, image definition identification device and terminal device |
CN110763679A (en) * | 2019-10-31 | 2020-02-07 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
CN110781713A (en) * | 2019-06-21 | 2020-02-11 | 中云智慧(北京)科技有限公司 | Method and device for obtaining target image |
CN112734767A (en) * | 2020-12-28 | 2021-04-30 | 平安科技(深圳)有限公司 | Pathological image tissue region based extraction method, device, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101702053A (en) * | 2009-11-13 | 2010-05-05 | 长春迪瑞实业有限公司 | Method for automatically focusing microscope system in urinary sediment examination equipment |
CN103345756A (en) * | 2013-07-19 | 2013-10-09 | 浙江农林大学 | Automatic focusing method, device and electronic equipment of microscope in urinary sediment analyzer |
CN103761521A (en) * | 2014-01-09 | 2014-04-30 | 浙江大学宁波理工学院 | LBP-based microscopic image definition measuring method |
CN105760878A (en) * | 2014-12-19 | 2016-07-13 | 西门子医疗保健诊断公司 | Method and device for selecting urinary sediment microscope image with optimal focusing performance |
CN107205113A (en) * | 2016-03-18 | 2017-09-26 | 松下知识产权经营株式会社 | Video generation device, image generating method and program |
-
2017
- 2017-09-30 CN CN201710944304.7A patent/CN107644425B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101702053A (en) * | 2009-11-13 | 2010-05-05 | 长春迪瑞实业有限公司 | Method for automatically focusing microscope system in urinary sediment examination equipment |
CN103345756A (en) * | 2013-07-19 | 2013-10-09 | 浙江农林大学 | Automatic focusing method, device and electronic equipment of microscope in urinary sediment analyzer |
CN103761521A (en) * | 2014-01-09 | 2014-04-30 | 浙江大学宁波理工学院 | LBP-based microscopic image definition measuring method |
CN105760878A (en) * | 2014-12-19 | 2016-07-13 | 西门子医疗保健诊断公司 | Method and device for selecting urinary sediment microscope image with optimal focusing performance |
CN107205113A (en) * | 2016-03-18 | 2017-09-26 | 松下知识产权经营株式会社 | Video generation device, image generating method and program |
Non-Patent Citations (1)
Title |
---|
冯雁 等: "融合灰度直方图分布的自动聚焦改进算法", 《现代电子技术》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109151320A (en) * | 2018-09-29 | 2019-01-04 | 联想(北京)有限公司 | A kind of target object choosing method and device |
CN110175980A (en) * | 2019-04-11 | 2019-08-27 | 平安科技(深圳)有限公司 | Image definition recognition methods, image definition identification device and terminal device |
WO2020206912A1 (en) * | 2019-04-11 | 2020-10-15 | 平安科技(深圳)有限公司 | Image definition recognition method, image definition recognition apparatus, and terminal device |
CN110781713A (en) * | 2019-06-21 | 2020-02-11 | 中云智慧(北京)科技有限公司 | Method and device for obtaining target image |
CN110763679A (en) * | 2019-10-31 | 2020-02-07 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
CN112734767A (en) * | 2020-12-28 | 2021-04-30 | 平安科技(深圳)有限公司 | Pathological image tissue region based extraction method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107644425B (en) | 2018-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107644425B (en) | Target image choosing method, device, computer equipment and storage medium | |
CN109284670B (en) | Pedestrian detection method and device based on multi-scale attention mechanism | |
JP5464244B2 (en) | Image processing apparatus, program, and image processing system | |
CN106529602B (en) | A kind of millimeter-wave image automatic target recognition method and device | |
CN110119728A (en) | Remote sensing images cloud detection method of optic based on Multiscale Fusion semantic segmentation network | |
RU2010117215A (en) | DEVICE AND METHOD OF PROCESSING IMAGES, DEVICE FOR IMPOSING IMAGES AND PROGRAM | |
US8811750B2 (en) | Apparatus and method for extracting edge in image | |
CN111462075B (en) | Rapid refocusing method and system for full-slice digital pathological image fuzzy region | |
WO1996009598A1 (en) | Cytological slide scoring apparatus | |
CN110443212B (en) | Positive sample acquisition method, device, equipment and storage medium for target detection | |
CN109492543A (en) | The small target detecting method and system of infrared image | |
CN111062967B (en) | Electric power business hall passenger flow statistical method and system based on target dynamic tracking | |
WO2014192184A1 (en) | Image processing device, image processing method, program, and storage medium | |
CN111027343B (en) | Bar code region positioning method and device | |
CN110334760B (en) | Optical component damage detection method and system based on RESUnet | |
CN109492576A (en) | Image-recognizing method, device and electronic equipment | |
KR101932595B1 (en) | Image processing apparatus and method for detecting translucent objects in image | |
CN108664970A (en) | A kind of fast target detection method, electronic equipment, storage medium and system | |
CN105869148A (en) | Target detection method and device | |
CN105139391A (en) | Edge detecting method for traffic image in fog-and-haze weather | |
CN114781514A (en) | Floater target detection method and system integrating attention mechanism | |
CN107341793A (en) | A kind of target surface image processing method and device | |
Ashourian et al. | Real time implementation of a license plate location recognition system based on adaptive morphology | |
JP6326622B2 (en) | Human detection device | |
KR102416714B1 (en) | System and method for city-scale tree mapping using 3-channel images and multiple deep 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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Liang Ke Inventor after: Liang Guangming Inventor after: Yu Yuena Inventor before: Liang Guangming Inventor before: Liang Ke Inventor before: Yu Yuena |