CN112304950A - Micro-droplet observation device and micro-droplet image recognition method based on shape matching - Google Patents
Micro-droplet observation device and micro-droplet image recognition method based on shape matching Download PDFInfo
- Publication number
- CN112304950A CN112304950A CN202011067389.3A CN202011067389A CN112304950A CN 112304950 A CN112304950 A CN 112304950A CN 202011067389 A CN202011067389 A CN 202011067389A CN 112304950 A CN112304950 A CN 112304950A
- Authority
- CN
- China
- Prior art keywords
- micro
- droplet
- observation
- image
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
- B01L3/00—Containers or dishes for laboratory use, e.g. laboratory glassware; Droppers
- B01L3/50—Containers for the purpose of retaining a material to be analysed, e.g. test tubes
- B01L3/502—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures
- B01L3/5027—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Dispersion Chemistry (AREA)
- Hematology (AREA)
- Clinical Laboratory Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
本发明提供一种微液滴观测装置及基于形状匹配的微液滴图像识别方法，其中微液滴观测装置，包括：微液滴生成装置，用于生成微液滴；微液滴芯片，所述微液滴芯片上构造有观察腔，所述微液滴生成装置生成的微液滴能够通过相应的微管道进入所述观察腔内，垂直于所述微液滴的流动方向，所述微管道具有的宽度小于所述观察腔具有的宽度；光学成像部件，用于对处于所述观察腔中微液滴进行成像为第一图像。本发明微液滴观测装置及基于形状匹配的微液滴图像识别方法，微液滴在观察腔内流速降低，进而能够便于相机对观察腔内微液滴的清晰图像的获取，降低了对相机性能的要求，从而降低微液滴观测装置的成本。
The invention provides a micro-droplet observation device and a micro-droplet image recognition method based on shape matching, wherein the micro-droplet observation device includes: a micro-droplet generating device, which is used to generate micro-droplets; An observation cavity is constructed on the micro-droplet chip, and the micro-droplets generated by the micro-droplet generating device can enter the observation cavity through the corresponding micro-pipes, and are perpendicular to the flow direction of the micro-droplets. The width of the pipe is smaller than the width of the observation chamber; the optical imaging component is used for imaging the microdroplets in the observation chamber as a first image. The micro-droplet observation device and the micro-droplet image recognition method based on shape matching of the present invention reduce the flow rate of the micro-droplets in the observation chamber, thereby facilitating the camera to obtain a clear image of the micro-droplets in the observation chamber, reducing the need for the camera performance requirements, thereby reducing the cost of droplet observation devices.
Description
Technical Field
The invention belongs to the technical field of micro-droplet detection, and particularly relates to a micro-droplet observation device and a micro-droplet image recognition method based on shape matching.
Background
Micro-droplet microfluidics (droplet-based microfluidics) is a technical platform for controlling micro-volume liquid developed on a microfluidic chip in recent years, and the principle of the micro-droplet microfluidics is as follows: two mutually insoluble liquids are taken as an example, one of the liquids is an oil phase, and the other one is a water phase, after the oil phase and the water phase simultaneously enter the micro-channel, the water phase is distributed in the oil phase in the form of micro volume units under the action of the micro-channel to form a series of discrete micro droplets. Each droplet acts as a microreactor to accomplish a set of chemical or biological reactions.
For most biochemical applications developed based on microdroplet technology, monodispersity of the microdroplet size is important for the consistency of the reaction. The monodispersity of the micro-droplets is determined by the generation process of the micro-droplets, so that the establishment of a corresponding quality control link for the generation process is particularly important.
The bright field imaging of the generation process of the micro-droplets is a commonly used micro-droplet quality control method, and the size information of the generation process of the micro-droplets is obtained according to the obtained graph. However, since the micro-droplets move at a high speed, the conventional camera cannot capture a clear image, and therefore a high-frequency camera with a global shutter is required to obtain the clear image, and the high-performance camera is often expensive.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to provide a micro-droplet observation device and a micro-droplet image recognition method based on shape matching, in which the flow velocity of micro-droplets in an observation cavity is reduced, thereby facilitating the acquisition of clear images of micro-droplets in the observation cavity by a camera, reducing the requirements on the performance of the camera, and reducing the cost of the micro-droplet observation device.
In order to solve the above problems, the present invention provides a micro-droplet observation device including:
micro-droplet generating means for generating micro-droplets;
the micro-droplet generating device comprises a micro-droplet chip, wherein an observation cavity is formed on the micro-droplet chip, micro-droplets generated by the micro-droplet generating device can enter the observation cavity through corresponding micro-pipelines and are perpendicular to the flow direction of the micro-droplets, and the width of the micro-pipeline is smaller than that of the observation cavity;
and the optical imaging component is used for imaging the micro-liquid drop in the observation cavity into a first image.
Preferably, the height of the observation cavity is H, the diameter of the micro-droplet is D, and H is more than or equal to 1.2D and less than or equal to D, wherein the height of the observation cavity is H, and the diameter of the micro-droplet is D; and/or a plurality of observation cavities are adjacently arranged in parallel to the flowing direction of the micro-droplets.
Preferably, the micro-droplet observation device further comprises a micro-droplet collection device, and the micro-droplet collection device is positioned in the observation cavity and is positioned at the downstream of the micro-droplet flowing direction.
Preferably, the optical imaging component comprises a camera and a white light source, wherein the camera and the white light source are respectively arranged on two opposite sides of the micro-droplet chip and correspond to the region of the observation cavity.
Preferably, the micro-droplet observation device further comprises an image processing and analyzing device which is in communication connection with the camera.
The invention also provides a micro-droplet image recognition method based on shape matching, which is used for processing the obtained first image and comprises the following steps:
a template specifying step for obtaining a matching template of the target shape;
and positioning and counting target micro-droplets, namely searching and identifying micro-droplets matched with the shape of the matching template in the first image by adopting the matching template.
Preferably, before the step of specifying the template, the method further comprises:
and a matching template generation step, namely selecting a single micro-droplet image meeting a preset target, and performing image processing on the single micro-droplet image to serve as a matching template of the target shape.
Preferably, after the template generating and specifying step before the target micro-droplet positioning and counting step, the method further comprises: and a matching parameter adjusting step, which is used for adjusting the matching parameters in the searching and identifying process so as to improve the identifying efficiency and/or the accuracy of the identifying result.
Preferably, the matching parameters include: at least one of a contrast threshold parameter, a visibility parameter, an image pyramid layer number, a rotation angle parameter, a zoom parameter, a search completeness parameter, an inter-object maximum overlapping area ratio parameter, and a rotation angle parameter.
Preferably, before the target micro-droplet positioning and counting step, the method further comprises: and an identification area framing step, which is used for framing a partial area of the first image to serve as an identification area so as to perform matching identification on the micro-droplets in the identification area.
According to the micro-droplet observation device and the micro-droplet image recognition method based on shape matching, the width of the observation cavity is larger than that of the micro-pipeline, so that the flow velocity of micro-droplets is reduced after the micro-droplets flow into the observation cavity from the micro-pipeline, a camera can conveniently acquire clear images of the micro-droplets in the observation cavity, the requirements on the performance of the camera are reduced, and the cost of the micro-droplet observation device is reduced.
Drawings
FIG. 1 is a schematic structural diagram of a micro-droplet observation device according to an embodiment of the present invention;
FIG. 2 is a first image obtained using a microdroplet observation device according to an embodiment of the present invention;
FIG. 3 is a schematic representation of one way of specifying generation of a matching template;
FIG. 4 is the matching template specified for generation in FIG. 3;
fig. 5 shows the shape matching results when the contrast threshold parameter (MinContrast) is 50 (left side) and 30 (right side), respectively, and it can be seen that the smaller the contrast threshold parameter is, the more the number of shape matches is;
fig. 6 shows the result of shape matching when the maximum overlap area ratio parameter (maxooverlap) is 0.1 (left side) and 0.3 (right side), respectively, and it can be seen that the larger the maximum overlap area ratio parameter is, the larger the number of shape matches is;
fig. 7 shows the result of the shape matching when the visibility parameters (MinScore) are 0.9 (left side) and 0.7 (right side), respectively, and it can be seen that the smaller the maximum overlapping area ratio parameter is, the larger the number of shape matches.
The reference numerals are represented as:
10. a micro-droplet generating device; 20. a micro droplet chip; 21. an observation cavity; 30. a micro-droplet collection device; 41. a camera; 42. a white light source; 50. image processing and analysis equipment.
Detailed Description
Referring to fig. 1 to 7 in combination, according to an embodiment of the present invention, there is provided a micro-droplet observation device including: a micro-droplet generating device 10 for generating micro-droplets; a micro droplet chip 20, wherein an observation cavity 21 is configured on the micro droplet chip 20, the micro droplet generated by the micro droplet generating device 10 can enter the observation cavity 21 through a corresponding micro pipeline, and is perpendicular to the flow direction of the micro droplet, the micro pipeline has a width smaller than that of the observation cavity 21, that is, the micro droplet enters the observation cavity 21 through the micro pipeline, and the micro droplet has an increasing trend in volume, so that the micro droplet entering the observation cavity 21 is prevented from being tightly attached to each other and deformed; and the optical imaging component is used for imaging the micro-droplets in the observation cavity 21 into a first image. In the technical scheme, the width of the observation cavity 21 is larger than that of the micro-pipeline, so that the flow velocity of micro-droplets is reduced after the micro-droplets flow into the observation cavity 21 through the micro-pipeline, the camera can conveniently acquire clear images of the micro-droplets in the observation cavity, the requirement on the performance of the camera is reduced, and the cost of the micro-droplet observation device is reduced. The first image may be a plurality of images, for example, the optical imaging component is controlled to acquire and acquire the images at preset intervals, for example, one image is acquired every 0.5 s.
Preferably, perpendicular to the flowing direction of the micro-droplets, the height of the observation cavity 21 is H, the diameter of the micro-droplets is D, 1.2D ≦ H ≦ D, and more preferably D ═ H, so that it can be ensured that a plurality of micro-droplets in the observation cavity 21 can be tiled without overlapping in the height direction, thereby making the final observation result more accurate; the observation cavities 21 are adjacently arranged in a plurality parallel to the flowing direction of the micro-droplets, that is, a plurality of observation cavities 21 with micro-droplets can be simultaneously presented in the first image, so that one image with more micro-droplets can be provided, and the number of identification samples can be increased. As a specific embodiment, as shown in fig. 2, the observation chamber 21 is provided with 4.
Further, the micro-droplet observing device further comprises a micro-droplet collecting device 30, wherein the micro-droplet collecting device 30 is located downstream in the flow direction of the micro-droplets in the observing cavity 21 to collect the micro-droplets flowing out of the observing cavity 21.
The optical imaging component comprises a camera 41 and a white light source 42, the camera 41 and the white light source 42 are respectively located at two opposite sides of the micro droplet chip 20 and correspond to the region of the observation cavity 21, and it can be understood that the imaging fields of view of the white light source 42 and the camera 41 are opposite to each other, so as to accurately acquire the image in the observation cavity 21, in a specific application, it is preferable that the camera 41 uses a telephoto lens to ensure the imaging quality, and the observation cavity 21 occupies most of the area in the field of view, so as to ensure the effective field of view utilization; further, the droplet observing apparatus further includes an image processing and analyzing device 50, which is in communication connection with the camera 41, for example, the camera 41 may be connected with the image processing and analyzing device 50 through a wired USB interface, and of course, the image processing and analyzing device may also be connected in a wireless communication manner such as bluetooth and wifi, which is not particularly limited in the present invention, but it is understood that the image processing and analyzing device 50 may be, for example, a computer, which is configured to receive the first image (which may be multiple images) acquired by the camera 41 and identify, analyze and count the first image.
According to an embodiment of the present invention, there is also provided a method for identifying microdroplet images based on shape matching, which is used for processing the first image obtained above, and it can be understood that the method can be specifically performed by using the image processing and analyzing apparatus 50 described above, and includes the following steps:
a template specifying step for obtaining a matching template of the target shape; and positioning and counting target micro-droplets, namely searching and identifying micro-droplets matched with the shape of the matching template in the first image by adopting the matching template.
In the technical scheme, the object can be searched and positioned based on a single template or a template image based on shape matching, and the method has stronger robustness on noise, clutter, shading and any nonlinear illumination change; the precision of positioning the two-dimensional object can reach a sub-pixel level, and the two-dimensional object can be matched even if the two-dimensional object is rotated or zoomed; the method can be applied to standard 8-bit gray value images, images with the depth larger than 8-bit gray value and color (generally, multi-channel) images, has strong adaptability, is suitable for searching objects with fixed characteristics based on a shape matching algorithm, is very suitable for identifying scenes of micro-droplets, and the outlines of the micro-droplets in the observation cavity 21 shot by the camera 41 are similar circles. In addition, the micro-droplet image recognition method based on shape matching is high in recognition accuracy and relatively low in calculation complexity.
Preferably, before the step of specifying the template, the method further comprises: and a matching template generation step, namely selecting a single micro-droplet image meeting a preset target, and performing image processing on the single micro-droplet image to serve as a matching template of the target shape. Specifically, a certain number of representative microdroplet images are collected, a part of the microdroplets in the microdroplets is artificially selected and labeled, the selected microdroplets are used as templates, and for example, in fig. 2, a microdroplet image meeting the preset requirement is selected from an acquired first image, so that the matching template shown in fig. 3 is formed. It is important to construct a suitable template, which also gives good accuracy to the final match, and which can be saved in a file for reuse in different applications. More specifically, for example, the resolution of the acquired image is 2448 × 2048. In the middle stage of droplet generation, the size of the micro droplets is relatively uniform and the shape is most regular, so that a certain conventional droplet at this stage is selected, as shown in fig. 3, the outline of the droplet can be abstracted into a ring, the inner diameter of the ring is 30 pixels, the outer diameter of the ring is 36 pixels, at this time, a template picture with the specification of 40 × 40 pixels can be created, two circles with the radii of 15 and 18 respectively are drawn on the picture, in order to reflect the gray level difference of the outline of the micro droplet, the outer circle is filled with the gray level of 80, the inner circle is filled with the gray level of 210, a template in the shape of a ring is obtained, as shown in fig. 4, and the next matching process uses the template or the affine transformation form thereof.
Preferably, before the target micro-droplet positioning and counting step, the method further comprises: and an identification Region framing step, configured to frame a partial Region of the first image as an identification Region to perform matching identification on the microdroplets in the identification Region, where the identification Region may also be regarded as a Region of interest (ROI), and specifically, a center point of the ROI is used as a reference point of the template for estimating a position, rotation, and scaling, and selecting the ROI may avoid finding microdroplets on the entire image, so as to save matching time.
Further, after the template generating and specifying step before the target micro-droplet positioning and counting step, the method further comprises: and a matching parameter adjusting step, which is used for adjusting the matching parameters in the searching and identifying process so as to improve the identifying efficiency and/or the accuracy of the identifying result. For example, the matching parameters may include: at least one of a contrast threshold parameter, a visibility parameter, an image pyramid layer number, a rotation angle parameter, a zoom parameter, a search completeness parameter, and an inter-object maximum overlap area ratio parameter.
Specifically, since the droplet may be squeezed instead of a perfect circle, but rather an ellipse, an anisotropic matching mode is adopted, since the ellipse is an axisymmetric image, the rotation angle parameter allowed by matching is set to 0-90 ° (angle extend), the zoom range of the vertical axis and the zoom range of the horizontal axis (zoom parameter) are both set to 0.5-1.3(scaleR, scaleC), and an excessively large or excessively small recognition object is generally considered as a bubble, so that a meaningful zoom range is required to find the micro-droplet object in the range near the size of the template. To speed up the matching process, an image pyramid is used, which consists of an initial full-size image and a series of down-sampled images. The template will be generated and searched at different pyramid levels. The image pyramid is configured using an image pyramid layer number (NumLevels) parameter. Specifically, when the size of the template is only 40 × 40, the number of pyramid layers (NumLevels) of the image may be 1.
The above parameters are relatively fixed for identification matching of the liquid drop, and the parameters described below need to be adjusted to determine a relatively proper value through identification effect, so that the adjustment of the parameters is more universal. A Contrast threshold parameter (Contrast) specifies what Contrast points on the search image must be compared to the template. The main effect of this parameter is to exclude noise (e.g. grey value fluctuations during matching). The visibility parameter (MinScore) specifies how much of the template must be visible, the larger the visibility parameter (MinScore), the faster the search; the search thoroughness parameter (Greediness) determines the thoroughness of the search, and the parameters are adjusted to obtain the best micro-droplet matching effect, generally have a large influence on the search matching speed, and take different values for images with different overall gray levels. The following arrangement enables a successful match in all test images, i.e. all object instances are found. In some cases, if the search completeness parameter (Greediness) is too large, it may not be possible to find an object that is completely visible. Selecting the value 0 forces a thorough search. And (3) taking 1 for the micro-droplet identification search completeness parameter (greeness) does not influence the matching result at all. If the object is still to be recognized in a state where the Contrast of the recognition object is low, the Contrast threshold parameter (Contrast) is decreased. Fig. 5 shows the search results when the Contrast threshold parameter (Contrast) is equal to 50 and 30, respectively. The maximum overlap area ratio parameter (maxooverlap) determines the ratio of the overlapped part between the objects to the size of the template, and in this embodiment, the outline of the droplet is basically not overlapped, but the template image for matching is a rectangle with the size of 40 × 40, so that the template rectangles of the matched objects may be partially overlapped, and the parameter cannot be set too small. As shown in fig. 6, which is a search result when the maximum overlap area ratio parameter (maxooverlap) is equal to 0.1 and 0.3, respectively, it can be found that the close microdroplets stuck in the left graph are not recognized.
The parameters are adjusted in order to optimize the matching speed. As long as the matching is successful, the visibility parameter (MinScore) is increased as much as possible, and as shown in fig. 7, the search results when the visibility parameter (MinScore) is equal to 0.9 and 0.7, respectively, the completeness of the search (greeningess) is increased until the matching fails, and the visibility parameter (MinScore) is tried to be decreased if the previous value is not helped to be restored. The Min Contrast threshold parameter (Contrast) is increased as much as possible as long as the matching is successful. Under the condition of good matching effect (the complete microdroplet objects in the allowable size range can be identified), the speed of optimizing search matching can reach 800ms for one image. The method obtains a better identification effect, simultaneously controls the calculation time within a reasonable range, and better balances the relation between the micro-droplet image identification time and the efficiency.
It is readily understood by a person skilled in the art that the advantageous ways described above can be freely combined, superimposed without conflict.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention. The above is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the technical principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011067389.3A CN112304950A (en) | 2020-10-06 | 2020-10-06 | Micro-droplet observation device and micro-droplet image recognition method based on shape matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011067389.3A CN112304950A (en) | 2020-10-06 | 2020-10-06 | Micro-droplet observation device and micro-droplet image recognition method based on shape matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112304950A true CN112304950A (en) | 2021-02-02 |
Family
ID=74489876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011067389.3A Pending CN112304950A (en) | 2020-10-06 | 2020-10-06 | Micro-droplet observation device and micro-droplet image recognition method based on shape matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112304950A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009158024A2 (en) * | 2008-06-27 | 2009-12-30 | Massachusetts Institute Of Technology | Microfluidic droplets for metabolic engineering and other applications |
| CN103559704A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工程大学 | Method for visually positioning tank mouth of railway oil tank truck |
| CN106053467A (en) * | 2016-06-08 | 2016-10-26 | 中国科学院上海微系统与信息技术研究所 | Device and method for observing micro-droplets |
| CN108393103A (en) * | 2018-03-03 | 2018-08-14 | 北京工业大学 | A kind of achievable drop size does not depend on the micro-fluidic chip of flow |
| US20180229234A1 (en) * | 2017-02-15 | 2018-08-16 | International Business Machines Corporation | Hybrid microfluidics devices |
| CN109557149A (en) * | 2019-01-14 | 2019-04-02 | 大连大学 | Digital microcurrent-controlled chip and pathogen immunologic detection method based on pcb board |
| CN110702588A (en) * | 2019-09-25 | 2020-01-17 | 深圳先进技术研究院 | Digital PCR analysis device and PCR analysis method |
-
2020
- 2020-10-06 CN CN202011067389.3A patent/CN112304950A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009158024A2 (en) * | 2008-06-27 | 2009-12-30 | Massachusetts Institute Of Technology | Microfluidic droplets for metabolic engineering and other applications |
| CN103559704A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工程大学 | Method for visually positioning tank mouth of railway oil tank truck |
| CN106053467A (en) * | 2016-06-08 | 2016-10-26 | 中国科学院上海微系统与信息技术研究所 | Device and method for observing micro-droplets |
| US20180229234A1 (en) * | 2017-02-15 | 2018-08-16 | International Business Machines Corporation | Hybrid microfluidics devices |
| CN108393103A (en) * | 2018-03-03 | 2018-08-14 | 北京工业大学 | A kind of achievable drop size does not depend on the micro-fluidic chip of flow |
| CN109557149A (en) * | 2019-01-14 | 2019-04-02 | 大连大学 | Digital microcurrent-controlled chip and pathogen immunologic detection method based on pcb board |
| CN110702588A (en) * | 2019-09-25 | 2020-01-17 | 深圳先进技术研究院 | Digital PCR analysis device and PCR analysis method |
Non-Patent Citations (2)
| Title |
|---|
| MENG SU: "《Recognition and location of motile microorganisms by shape-matching photoluminescence micropatterns》", 《LAB ON A CHIP》 * |
| 张翔: "《基于工业机器人的多工件视觉识别与分拣》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111474701B (en) | Pathological microscopic image real-time acquisition and analysis system, method, device and medium | |
| CA2966555C (en) | Systems and methods for co-expression analysis in immunoscore computation | |
| Shah et al. | Ziehl–Neelsen sputum smear microscopy image database: a resource to facilitate automated bacilli detection for tuberculosis diagnosis | |
| CN101909510B (en) | Image processing device and image processing program | |
| CN109085113B (en) | A kind of automatic focusing method and device for cervical exfoliated cell detection device | |
| Fuhl et al. | Pistol: Pupil invisible supportive tool to extract pupil, iris, eye opening, eye movements, pupil and iris gaze vector, and 2d as well as 3d gaze | |
| CN113837079B (en) | Automatic focusing method, device, computer equipment and storage medium of microscope | |
| US20220012884A1 (en) | Image analysis system and analysis method | |
| CN106133750A (en) | For determining the 3D rendering analyzer of direction of visual lines | |
| JP2013050713A (en) | Method for determining in-focus position and vision inspection system | |
| CN115298692A (en) | Automatic candidate sperm identification | |
| JP6548227B2 (en) | Medical scan system and method for determining scan parameters based on scout images | |
| CN111369553A (en) | Sample slide scanning and image processing method and digital microscope system | |
| CN109171817A (en) | Three-dimensional breast ultrasound scan method and ultrasonic scanning system | |
| JP5513038B2 (en) | 3D cell image analyzer | |
| He et al. | Microscope images automatic focus algorithm based on eight-neighborhood operator and least square planar fitting | |
| WO2024088621A1 (en) | Method, processor unit and system for processing of images | |
| CN113538545A (en) | A monocular depth estimation method based on electro-hydraulic adjustable focus lens and corresponding camera and storage medium | |
| CN117576192A (en) | Multi-mode detection method and device for two-dimensional liquid drop array | |
| Tan et al. | 3D Lagrangian tracking of polydispersed bubbles at high image densities | |
| CN112304950A (en) | Micro-droplet observation device and micro-droplet image recognition method based on shape matching | |
| KR101782575B1 (en) | Image Processing Method and System For Extracting Distorted Circular Image Elements | |
| EP3202133B1 (en) | Focusing method | |
| CN111311631B (en) | Method, device and equipment for detecting fluid speed in microfluidic chip | |
| CN103279937B (en) | To the self-focusing method of area-of-interest under micro-vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210202 |
|
| RJ01 | Rejection of invention patent application after publication |