CN110031960B

CN110031960B - Automatic adjustment method and device

Info

Publication number: CN110031960B
Application number: CN201910462387.5A
Authority: CN
Inventors: 牛临潇; 李�诚
Original assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Priority date: 2019-05-30
Filing date: 2019-05-30
Publication date: 2021-06-22
Anticipated expiration: 2039-05-30
Also published as: CN110031960A

Abstract

The embodiment of the application provides an automatic adjustment method and device, and the method comprises the following steps: adjusting a microscope from an initial state to a reference state according to an initial focusing point of a first image, wherein the first image is an image obtained from a measured object in the initial state of the microscope, and the measured object comprises at least one cell; obtaining a second image of the test object at the reference state and obtaining a confidence score for each of the at least one cell from the second image; adjusting the microscope to a target state based on the confidence score for each cell. Therefore, the efficiency of microscope adjustment can be improved to a certain extent.

Description

Automatic adjustment method and device

Technical Field

The application relates to the technical field of data processing, in particular to an automatic adjustment method and device.

Background

With the continuous development of science and technology, the observation of miniature objects by using a microscope is more and more popular. When an object is observed through a microscope traditionally, human eyes usually observe through an eyepiece, the distance between a lens and a glass slide is manually adjusted, when the distance is roughly adjusted to be roughly clear, fine adjustment is carried out through a fine adjustment knob, so that the image of the observed object can be clearly imaged, long time is needed when the microscope is adjusted, although some automatic focusing electron microscopes are also provided, automatic focusing can be realized, and the lens and the glass slide are adjusted, but in the existing scheme, a very complex focusing algorithm is mainly adopted, so that the efficiency of the system is low when the automatic focusing is carried out.

Disclosure of Invention

The embodiment of the application provides an automatic adjusting method and device, which can improve the efficiency of microscope adjustment.

A first aspect of an embodiment of the present application provides an automatic adjustment method applied to a microscope, where the method includes:

adjusting a microscope from an initial state to a reference state according to an initial focusing point of a first image, wherein the first image is an image obtained from a measured object in the initial state of the microscope, and the measured object comprises at least one cell;

obtaining a second image of the test object at the reference state and obtaining a confidence score for each of the at least one cell from the second image;

adjusting the microscope to a target state based on the confidence score for each cell.

Optionally, the microscope includes an object stage and a lens, the initial state includes that the object stage is located at an initial object stage position and the lens is located at an initial lens position, the reference state includes that the object stage is located at a reference object stage position and the lens is located at a reference lens position, and the adjusting the microscope from the initial state to the reference state according to the initial focusing component of the first image includes:

adjusting the lens from the initial lens position to a first lens position according to the initial focusing point, wherein the first lens position is a position where the focusing point of the image of the object to be measured is a first preset focusing point, and the initial focusing point is smaller than the first preset focusing point;

adjusting the objective table from the initial objective table position to a first objective table position at the first lens position according to a preset adjusting method;

acquiring a first focusing component of the image of the measured object at the first objective table position, and adjusting the lens from the first lens position to a second lens position according to the first focusing component, wherein the second lens position is a position where the focusing component of the image of the measured object is a second preset focusing component, and the second preset focusing component is larger than the first preset focusing component;

in the second lens position, adjusting the object stage from the first object stage position to a second object stage position according to the preset adjusting method, wherein the second object stage position is the reference object stage position;

and acquiring a second focusing component of the image of the measured object at the position of the reference object stage, and adjusting the lens from the second lens position to the reference lens position according to the second focusing component.

Optionally, the adjusting, at the first lens position, the stage from the initial stage position to the first stage position according to a preset adjustment method includes:

acquiring a reference image of the measured object at the first lens position;

dividing the central point of the reference image according to a preset dividing method to obtain four image blocks, wherein the four image blocks have the same area;

acquiring a focusing score of each image block in the four image blocks;

determining a target image block from the four image blocks, wherein the target image block is the image block with the highest focusing score;

moving the object stage along the extending direction of the target ray by a target distance to obtain the position of the first object stage, wherein the end point of the target ray is the central point of the reference image, the target ray is overlapped with the symmetry axis of the target image block and is far away from the target image block, the symmetry axis passes through the central point of the reference image, the target distance is one half of the length of a target line segment, and the target line segment is a line segment between the end point of the ray and the intersection point of the target ray and the target image block.

Optionally, the obtaining a confidence score of each cell of the at least one cell from the second image includes:

determining a positioning frame of each cell through a preset network model;

and taking the confidence score of the localization frame of each cell as the confidence score of the corresponding cell.

Optionally, the adjusting the lens from the initial lens position to the first lens position according to the initial focusing fraction includes:

according to the initial focusing point, a preset lens moving method is adopted to move the lens to a first middle lens position, wherein the first middle lens position is a position which is behind and adjacent to the initial lens position in the plurality of middle lens positions;

acquiring a middle position focusing point of the image of the object to be measured at the first middle lens position, and moving the lens to a second middle lens position by adopting the preset lens moving method according to the middle position focusing point, wherein the second middle lens position is a position which is behind and adjacent to the first middle lens position in the plurality of middle lens positions;

by adopting the method for moving the lens, the lens is moved among the plurality of intermediate lens positions until the lens is moved to the first lens position.

Optionally, the moving the lens to a first intermediate lens position by using a preset lens moving method according to the initial focusing score includes:

determining a formula according to the initial focusing score and a preset step length, and determining a target adjusting step length;

moving the lens to the first intermediate lens position with the target adjustment step length;

the preset step length determination formula is as follows:

y＝k(1-0.9x)，

wherein y is the adjustment step length, x is the focusing point, and k is the adjustment coefficient.

Optionally, the adjusting the microscope to a target state according to the confidence score of each cell comprises:

determining a target cell from the at least one cell, the target cell being the highest confidence cell of the at least one cell;

moving the stage from the reference stage position to a target stage position, the target stage position being a position where the target cell is located in a center of a field of view of the lens.

Optionally, the method further includes:

and analyzing the target cells to determine the name of the object to be detected.

A second aspect of embodiments of the present application provides an automatic adjustment device for use with a microscope, the device comprising a first adjustment unit, an acquisition unit, and a second adjustment unit, wherein,

the first adjusting unit adjusts the microscope from an initial state to a reference state according to an initial focusing point of a first image, wherein the first image is an image of a measured object obtained in the initial state of the microscope, and the measured object comprises at least one cell;

the acquiring unit is used for acquiring a second image of the measured object in the reference state and acquiring a confidence score of each cell in the at least one cell from the second image;

the second adjusting unit is used for adjusting the microscope to a target state according to the confidence score of each cell.

Optionally, the microscope includes an object stage and a lens, the initial state includes that the object stage is located at an initial object stage position and the lens is located at an initial lens position, the reference state includes that the object stage is located at a reference object stage position and the lens is located at a reference lens position, the microscope is adjusted from the initial state to the reference state according to the initial focusing component of the first image, and the first adjusting unit is specifically configured to:

Optionally, in the first lens position, in terms of adjusting the stage from the initial stage position to a first stage position according to a preset adjustment method, the first adjustment unit is specifically configured to:

acquiring a reference image of the measured object at the first lens position;

acquiring a focusing score of each image block in the four image blocks;

Optionally, in terms of the confidence score of each cell obtained from the second image, the obtaining unit is specifically configured to:

determining a positioning frame of each cell through a preset network model;

Optionally, a plurality of intermediate lens positions are included between the initial lens position and the first lens position, and in the aspect of adjusting the lens from the initial lens position to the first lens position according to the initial focusing fraction, the first adjusting unit is specifically configured to:

Optionally, in the aspect that the lens is moved to the first intermediate lens position by using a preset lens moving method according to the initial focusing point, the first adjusting unit is specifically configured to:

the preset step length determination formula is as follows:

y＝k(1-0.9x)，

Optionally, in the aspect that the microscope is adjusted to the target state according to the confidence score of each cell, the second adjusting unit is specifically configured to:

Optionally, the automatic adjusting device is further specifically configured to:

A third aspect of the embodiments of the present application provides a terminal, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiments of the present application.

A fourth aspect of embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program makes a computer perform part or all of the steps as described in the first aspect of embodiments of the present application.

A fifth aspect of embodiments of the present application provides a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps as described in the first aspect of embodiments of the present application. The computer program product may be a software installation package.

The embodiment of the application has at least the following beneficial effects:

acquiring an image of an object to be measured in an initial state of the microscope, the object to be measured including at least one cell, by adjusting the microscope from the initial state to a reference state based on an initial focus point of a first image, acquiring a second image of the object under test at the reference state, and acquiring a confidence score for each of the at least one cell from the second image, the microscope is adjusted to the target state based on the confidence score of each cell, and therefore, compared to the prior art, using a complicated focusing algorithm, by performing focus score extraction on an image of a measured object and a confidence score of each cell, and adjusting a microscope from an initial state to a target state according to the focus score and the confidence score, the time required for the score calculation is short, so that the time for adjusting the microscope can be reduced to a certain extent, and the efficiency for adjusting the microscope is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic diagram of an adjusting effect of an automatic adjusting method according to an embodiment of the present application;

fig. 2A is a schematic flow chart of an automatic adjustment method according to an embodiment of the present application;

FIG. 2B is a schematic diagram illustrating an adjusting effect of adjusting a lens from an initial position to a first lens position according to an embodiment of the present disclosure;

FIG. 2C is a schematic diagram illustrating the effect of moving the stage to the first stage position according to an embodiment of the present disclosure;

fig. 2D is a schematic diagram of processing an image block according to an embodiment of the present application;

FIG. 2E is a schematic illustration of an effect of moving the stage from the reference stage position to the target stage position;

FIG. 3 is a schematic flow chart diagram illustrating another automatic adjustment method according to an embodiment of the present application;

FIG. 4 is a schematic flow chart diagram illustrating another automatic adjustment method according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an automatic adjusting device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

In order to better understand an automatic adjustment method provided by the embodiment of the present application, a brief description of the automatic adjustment method is first provided below. Referring to fig. 1, fig. 1 is a schematic diagram illustrating an adjusting effect of an automatic adjusting method according to an embodiment of the present disclosure. As shown in fig. 1, the automatic adjustment method is described by showing an image of a measured object in three states when adjusting a microscope, in an initial state, the focus score of the measured object is low, the image is blurred, according to the focus score of the image, the focus score can be understood as a parameter for characterizing the definition of the image, the image is clearer when the focus score is larger, and conversely, the image is blurred when the focus score is smaller, the microscope is adjusted to a reference state, in the reference state, the measured object can be clearly observed, in the reference state, the confidence score of each cell is calculated to obtain the confidence score of each cell, the confidence score can be understood as a parameter for characterizing the definition of the cell, the cell with the highest confidence score can be determined as the most clear typical observation sample, such as the cell with the confidence scores of 0.8 and 0.9 in the image, and adjusting the microscope to a target state according to the confidence score, wherein the cell with the highest confidence score is presented in the visual center of the lens in the target state. Therefore, compared with the prior art that a complex focusing algorithm is adopted, the time for adjusting the microscope can be reduced to a certain extent by performing focusing score extraction on the image of the measured object and the confidence score of each cell and adjusting the microscope from the initial state to the target state according to the focusing score and the confidence score, and the time for adjusting the microscope is shorter in the score calculation process, so that the efficiency for adjusting the microscope is improved.

Referring to fig. 2A, fig. 2A is a schematic flow chart illustrating an automatic adjustment method according to an embodiment of the present disclosure. As shown in fig. 2A, the automatic adjustment method includes steps 201 and 203, which are as follows:

201. and adjusting the microscope from the initial state to the reference state according to the initial focusing component of the first image, wherein the first image is an image of the object to be measured, which comprises at least one cell, in the initial state of the microscope.

Optionally, the microscope comprises a stage and a lens. The initial state may include the stage being in an initial stage position and the lens being in an initial lens position. The initial stage position may be understood as the position of the stage when the slide is fixed to the stage, the slide being used to fix the object to be measured, and the initial lens position may be understood as the position of the microscope when the slide is fixed to the stage. The first image can be understood as an image of the object to be measured which is acquired by the lens of the microscope at this time. The object to be tested may be a multicellular organism or a unicellular organism, for example, a cell or a biological tissue placed on a slide glass, which is common in biological experiments of middle school students, and the like, and is not particularly limited herein.

Optionally, the embodiment of the present application further includes extracting an initial focusing point, and one possible method for extracting an initial focusing point of the first image is as follows: and determining a model according to a preset focusing point, and determining an initial focusing point of the first image. The preset focusing score determining model is obtained by training a sample picture through a VGG convolutional neural network model, wherein when the network model is trained, the network model is trained in the forward direction firstly, then the network model is trained in the reverse direction, and finally when the network model converges, the training is completed. The focus score has a value range of [0,1 ]. The larger the value of the focus score is, the sharper the image is, whereas the smaller the value of the focus score is, the more blurred the image is.

Optionally, the reference state includes that the object stage is located at a reference object stage position and the lens is located at a reference lens position, and a possible method for adjusting the microscope to the reference state according to the initial focusing point includes steps a1-a5, which are as follows:

a1, adjusting the lens from the initial lens position to a first lens position according to the initial focusing point, wherein the first lens position is the position where the focusing point of the image of the object to be measured is a first preset focusing point, and the initial focusing point is smaller than the first preset focusing point;

optionally, the value range of the first preset focus score may be [0.19,0.21], and specifically may be, for example, 0.20, 0.21, and the like.

Alternatively, a plurality of intermediate lens positions are included between the initial lens position and the first lens position, and an intermediate lens position can be understood as an intermediate position, i.e. a position reached after the target step size is adjusted for the lens, and a possible method for adjusting the lens from the initial lens position to the first lens position according to the initial focusing fraction includes steps a11-a13, which are specifically as follows:

a11, according to the initial focusing point, adopting a preset lens moving method to move the lens to a first middle lens position, wherein the first middle lens position is a position which is behind and adjacent to the initial lens position in the plurality of middle lens positions;

optionally, one possible method for moving the lens to the first intermediate lens position by using a preset lens moving method includes steps a111-a 112:

a111, determining a formula according to the initial focusing score and a preset step length, and determining a target adjusting step length;

wherein, the preset step length determination formula is as follows:

y＝k(1-0.9x),

wherein y is the adjustment step length, x is the focusing point, and k is the adjustment coefficient. The adjustment coefficient k may be set by an empirical value or historical data, and may be understood as the fastest adjustment coefficient determined by a multiple focusing experiment. According to the above formula for determining the adjustment step length, it can be understood that the adjustment step length for moving the lens next time is determined at each intermediate lens position.

And A122, moving the lens to a first middle lens position by adopting the target adjusting step length.

In this example, the microscope can be adjusted more accurately by dynamically obtaining the target adjustment step length, so that the accuracy of microscope adjustment can be improved to a certain extent.

A12, acquiring the middle position focusing point of the image of the object to be measured at the first middle lens position, and moving the lens to a second middle lens position by adopting a preset lens moving method according to the middle position focusing point, wherein the second middle lens position is the position which is behind and adjacent to the first middle lens position in the plurality of middle lens positions;

the method for obtaining the intermediate position focusing point may specifically refer to the method for obtaining the initial focusing point.

And A13, moving the lens among a plurality of intermediate lens positions by adopting the lens moving method until the lens is moved to the first lens position.

Alternatively, the method of repeating the above lens shift may be understood as: the method comprises the steps of moving a lens from an initial lens position to a first middle lens position, then moving the lens from the first middle lens position to a second middle lens position, moving the lens to a next middle lens position adjacent to the middle lens position, namely, moving the lens from a current middle lens position to the next middle lens position, wherein the distance between the current lens position and the next middle lens position is a target adjusting step length distance, and when the target adjusting step length is determined, the target adjusting step length needs to be determined according to a focus component of a measured object at the middle position of an image of the current lens position, namely, the target adjusting step length can be dynamically determined. Referring to fig. 2B, as shown in fig. 2B, fig. 2B is a schematic diagram of an adjustment effect for adjusting a lens from an initial position to a first lens position according to an embodiment of the present disclosure. As shown in fig. 2B, in the present exemplary diagram, the adjustment of the lens is shown through the imaging image, when the lens is located at the initial position, the focusing point is lower, the object to be measured is blurred, after the adjustment is performed by the above method, the first lens position is gradually reached, and when the first lens position is reached, the focusing point of the image is increased, and the image is clearer. Different focusing points correspond to different lens positions.

In this example, the lens is adjusted from the initial position to the first lens position by the above method, and the multiple gradual adjustment method is adopted for adjustment, so that the jitter generated during lens adjustment can be reduced to a certain extent, and the accuracy during lens adjustment and the accuracy during image acquisition of the adjusted measured object can be improved.

A2, adjusting the objective table from the initial objective table position to the first objective table position at the first lens position according to a preset adjusting method;

alternatively, one possible method of adjusting the stage from the initial position to the first stage position comprises steps a21-a25 as follows:

a21, acquiring a reference image of the measured object at the first lens position;

alternatively, as shown in fig. 2C, fig. 2C provides a schematic diagram of the effect of moving the stage to the first stage position for the embodiment of the present application. As shown in fig. 2C, since the reference image is acquired through the lens, and the lens is a circular lens, the acquired image is a circular image.

A22, dividing the central point of the reference image according to a preset dividing method to obtain four image blocks, wherein the areas of the four image blocks are the same;

alternatively, the center point of the reference image may be understood as the center of a circle of the circular image. The division of the reference image into four image blocks can be seen in the division method in fig. 2C.

A23, acquiring the focusing point of each image block in the four image blocks;

alternatively, as shown in fig. 2C, the four image blocks may be represented as a first image block, a second image block, a third image block, and a fourth image block. When the focusing time of each image block is obtained and the image is input to the focusing time determination model, the input image is only the image of the image block, and the values of the rest image blocks are 0, as shown in fig. 2D.

A24, determining a target image block from the four image blocks, wherein the target image block is the image block with the highest focusing score;

and A25, moving the objective table along the extension direction of the target ray by a target distance to obtain a first objective table position, wherein the end point of the target ray is the central point of the reference image, the ray is coincident with the symmetry axis of the target image block and is far away from the target image block, the symmetry axis passes through the central point of the reference image, the target distance is one half of the length of the target line segment, and the target line segment is the line segment between the end point of the ray and the intersection point of the ray and the target image block.

Alternatively, as shown in fig. 2C, the direction of movement of the stage is the direction of movement identified in the figure.

In this example, through moving the objective table, then can move the measured object to the field of vision of camera lens to avoided when adjusting the microscope, to move the measured object outside the field of vision, lead to the circumstances that can't observe the measured object, thereby accuracy when can promote the microscope to a certain extent when adjusting.

A3, acquiring a first focusing point of the image of the object to be measured at the first stage position, and adjusting the lens from the first lens position to a second lens position according to the first focusing point, wherein the second lens position is a position where the focusing point of the image of the object to be measured is a second preset focusing point, and the second preset focusing point is larger than the first preset focusing point;

the value range of the second preset focus score may be [0.69,0.71], and specifically may be 0.70, 0.71, and the like. In the case of movement, the method used is the same as the method described above for moving the lens.

A4, adjusting the objective table from the first objective table position to the second objective table position at the second lens position according to a preset adjusting method, wherein the second objective table position is a reference objective table position;

and A5, acquiring a second focus component of the image of the measured object at the position of the reference object stage, and adjusting the lens from the second lens position to the reference lens position according to the second focus component.

Optionally, the method for adjusting the lens to the reference lens position may refer to the method in step a1, and details are not repeated here.

In this example, the microscope is adjusted first, the focus point of the object to be measured reaches the first preset focus point, the objective table is adjusted again, the object to be measured is moved to the area of the image block with the highest focus point, the lens is adjusted again, the focus point of the object to be measured reaches the second preset focus point, the position of the objective table is adjusted again, the microscope is adjusted from the initial state to the reference state, and the accuracy of the microscope in adjustment can be improved to a certain extent through multiple times of fine adjustment.

202. A second image of the test object is acquired at the reference state, and a confidence score for each of the at least one cell is acquired from the second image.

Alternatively, one possible method of obtaining a confidence score for each cell includes steps B1-B2 as follows:

b1, determining a positioning frame of each cell through a preset network model;

the preset network model can be an improved faster RCNN network model. The improved faster RCNN network model is obtained by replacing a feature extraction network in the traditional faster RCNN network model by a mobileNet network structure. The feature extraction network is replaced through a mobileNet network structure, and the fast RCNN network model is miniaturized, so that the method can be applied to electronic equipment with smaller resources.

And B2, taking the confidence score of the positioning frame of each cell as the confidence score of the corresponding cell.

After the location frame of each cell is determined, the confidence score of each location frame can be obtained through the confidence score determined by the Region pro-social Network (RPN Network) corresponding to the location frame.

203. The microscope was adjusted to the target state according to the confidence score of each cell.

Alternatively, one possible method of adjusting the microscope to a target state based on the confidence score of each cell includes steps C1-C2 as follows:

c1, determining a target cell from the at least one cell, wherein the target cell is the cell with the highest confidence score in the at least one cell;

and C2, moving the object stage from the reference object stage position to the target object stage position, wherein the target object stage position is the position of the target cell at the visual field center of the lens.

Alternatively, referring to fig. 2E, fig. 2E is a schematic diagram of the effect of moving the stage from the reference stage position to the target stage position. As shown in fig. 2E, the highest confidence score is 0.9, and the stage is moved so that the cell corresponding to that confidence score is located at the center of the field of view of the lens.

In one possible example, the embodiments of the present application may also analyze the target cells to determine the name of the object to be detected.

Optionally, the method for determining the name of the measured object may be: in the training process of the preset network model, targets are distinguished according to common cell types of biological experiments, and confidence determined by a positioning frame is as follows: the highest confidence score in the confidence scores of all the common cell types can determine the cell type in the positioning frame according to the cell type corresponding to the confidence score. For example, in the course of performing the experiment on the object to be measured, the confidence score corresponding to "onion epidermal cells" is the highest, and the object to be measured can be determined to be "onion epidermal cells". The recognizable cell types can include plant cells, animal cells including those involved in biological experiments such as onion epidermal cells, onion root tip cells, human blood red cells, etc.

Referring to fig. 3, fig. 3 is a schematic flow chart of another automatic adjustment method according to an embodiment of the present application. As shown in fig. 3, the automatic adjustment method includes steps 301 and 308, which are as follows:

301. adjusting the microscope from an initial state to a reference state according to an initial focusing component of a first image, wherein the first image is an image of a measured object obtained in the initial state of the microscope, and the measured object comprises at least one cell;

wherein, above-mentioned initial condition includes that the objective table is located initial objective table position and the camera lens is located initial camera lens position, and the reference condition includes that the objective table is located reference objective table position and the camera lens is located reference camera lens position, and the microscope includes objective table and camera lens.

302. Adjusting the lens from the initial lens position to a first lens position according to the initial focusing point, wherein the first lens position is a position where the focusing point of the image of the measured object is a first preset focusing point;

wherein the initial focusing point is smaller than the first preset focusing point.

303. Adjusting the objective table from the initial objective table position to the first objective table position at the first lens position according to a preset adjusting method;

304. acquiring a first focusing component of the image of the measured object at the first objective table position, and adjusting the lens from the first lens position to a second lens position according to the first focusing component, wherein the second lens position is a position where the focusing component of the image of the measured object is a second preset focusing component;

the second preset focusing point is larger than the first preset focusing point.

305. In the second lens position, the objective table is adjusted from the first objective table position to a second objective table position according to a preset adjusting method, wherein the second objective table position is a reference objective table position;

306. acquiring a second focus component of the image of the measured object at the position of the reference objective table, and adjusting the lens from the second lens position to the reference lens position according to the second focus component;

307. obtaining a second image of the test object at the reference state, and obtaining a confidence score for each of the at least one cell from the second image;

308. the microscope was adjusted to the target state according to the confidence score of each cell.

Referring to fig. 4, fig. 4 is a schematic flow chart illustrating another automatic adjustment method according to an embodiment of the present disclosure. As shown in fig. 4, the automatic adjustment method includes steps 401 and 405 as follows:

401. adjusting the microscope from an initial state to a reference state according to an initial focusing component of a first image, wherein the first image is an image of a measured object obtained in the initial state of the microscope, and the measured object comprises at least one cell;

wherein the microscope comprises an object stage and a lens.

402. Acquiring a second image of the measured object in a reference state;

403. determining a positioning frame of each cell through a preset network model;

404. Taking the confidence score of the localization frame of each cell as the confidence score of the corresponding cell;

405. the microscope was adjusted to the target state according to the confidence score of each cell.

In this example, the improved faster RCNN network model can be used for a device with smaller resources, so that the practicability of the scheme can be improved to a certain extent.

In accordance with the foregoing embodiments, please refer to fig. 5, fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application, and as shown in the drawing, the terminal includes a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for performing the following steps;

adjusting the microscope from an initial state to a reference state according to an initial focusing component of a first image, wherein the first image is an image of a measured object obtained in the initial state of the microscope, and the measured object comprises at least one cell;

obtaining a second image of the test object at the reference state, and obtaining a confidence score for each of the at least one cell from the second image;

the microscope was adjusted to the target state according to the confidence score of each cell.

In this example, the first image is an image of the object under test, the object under test including at least one cell, taken at the initial state of the microscope by adjusting the microscope from the initial state to a reference state at an initial focus point according to the first image, acquiring a second image of the object under test at the reference state, and acquiring a confidence score for each of the at least one cell from the second image, the microscope is adjusted to the target state based on the confidence score of each cell, and therefore, compared to the prior art, using a complicated focusing algorithm, by performing focus score extraction on an image of a measured object and a confidence score of each cell, and adjusting a microscope from an initial state to a target state according to the focus score and the confidence score, the time required for the score calculation is short, so that the time for adjusting the microscope can be reduced to a certain extent, and the efficiency for adjusting the microscope is improved.

The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It is understood that the terminal includes corresponding hardware structures and/or software modules for performing the respective functions in order to implement the above-described functions. Those of skill in the art will readily appreciate that the present application is capable of hardware or a combination of hardware and computer software implementing the various illustrative elements and algorithm steps described in connection with the embodiments provided herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the terminal may be divided into the functional units according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

In accordance with the above, please refer to fig. 6, fig. 6 is a schematic structural diagram of an automatic adjusting device according to an embodiment of the present application. The automatic adjustment device comprises a first adjustment unit 601, an acquisition unit 602 and a second adjustment unit 603, wherein,

a first adjusting unit 601, configured to adjust the microscope from an initial state to a reference state according to an initial focusing score of a first image, where the first image is an image of a measured object obtained in the initial state of the microscope, and the measured object includes at least one cell;

an obtaining unit 602, configured to obtain a second image of the measured object in the reference state, and obtain a confidence score of each cell of the at least one cell from the second image;

a second adjusting unit 603 for adjusting the microscope to a target state according to the confidence score of each cell.

Optionally, the microscope includes an object stage and a lens, the initial state includes that the object stage is located at an initial object stage position and the lens is located at an initial lens position, the reference state includes that the object stage is located at a reference object stage position and the lens is located at a reference lens position, the microscope is adjusted from the initial state to the reference state according to the initial focusing point of the first image, and the first adjusting unit 601 is specifically configured to:

adjusting the lens from the initial lens position to a first lens position according to the initial focusing point, wherein the first lens position is a position where the focusing point of the image of the measured object is a first preset focusing point, and the initial focusing point is smaller than the first preset focusing point;

adjusting the objective table from the initial objective table position to the first objective table position at the first lens position according to a preset adjusting method;

acquiring a first focusing point of an image of a measured object at a first objective table position, and adjusting a lens from a first lens position to a second lens position according to the first focusing point, wherein the second lens position is a position where the focusing point of the image of the measured object is a second preset focusing point, and the second preset focusing point is larger than the first preset focusing point;

in the second lens position, the objective table is adjusted from the first objective table position to a second objective table position according to a preset adjusting method, wherein the second objective table position is a reference objective table position;

and acquiring a second focus component of the image of the measured object at the position of the reference object stage, and adjusting the lens from the second lens position to the reference lens position according to the second focus component.

Optionally, in the first lens position, in terms of adjusting the object stage from the initial object stage position to the first object stage position according to a preset adjustment method, the first adjustment unit 601 is specifically configured to:

acquiring a reference image of a measured object at a first lens position;

dividing the central point of the reference image according to a preset dividing method to obtain four image blocks, wherein the areas of the four image blocks are the same;

acquiring a focusing score of each image block in the four image blocks;

moving the objective table along the extension direction of the target ray by a target distance to obtain the position of a first objective table, wherein the endpoint of the target ray is the central point of the reference image, the target ray is overlapped with the symmetry axis of the target image block and is far away from the target image block, the symmetry axis passes through the central point of the reference image, the target distance is one half of the length of the target line segment, and the target line segment is the line segment between the endpoint of the ray and the intersection point of the target ray and the target image block.

Optionally, in terms of obtaining the confidence score of each cell from the second image, the obtaining unit 602 is specifically configured to:

determining a positioning frame of each cell through a preset network model;

the confidence score of the localization box of each cell was taken as the confidence score of the corresponding cell.

Optionally, a plurality of intermediate lens positions are included between the initial lens position and the first lens position, and in terms of adjusting the lens from the initial lens position to the first lens position according to the initial focusing fraction, the first adjusting unit 601 is specifically configured to:

acquiring a middle position focusing point of an image of a measured object at a first middle lens position, and moving a lens to a second middle lens position by adopting a preset lens moving method according to the middle position focusing point, wherein the second middle lens position is a position which is behind and adjacent to the first middle lens position in the plurality of middle lens positions;

by adopting the method for moving the lens, the lens is moved among a plurality of intermediate lens positions until the lens is moved to the first lens position.

Optionally, in terms of moving the lens to the first intermediate lens position by using a preset lens moving method according to the initial focusing point, the first adjusting unit 601 is specifically configured to:

moving the lens to a first intermediate lens position by adopting a target adjustment step length;

the preset step length determination formula is as follows:

y＝k(1-0.9x)，

Optionally, in terms of adjusting the microscope to the target state according to the confidence score of each cell, the second adjusting unit 602 is specifically configured to:

determining a target cell from the at least one cell, the target cell being the cell with the highest confidence score of the at least one cell;

the stage is moved from the reference stage position to a target stage position, which is a position where the target cell is located at the center of the field of view of the lens.

Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the automatic adjustment methods as described in the above method embodiments.

Embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program causes a computer to execute part or all of the steps of any one of the automatic adjustment methods as described in the above method embodiments.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.

The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a read-only memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and the like.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash memory disks, read-only memory, random access memory, magnetic or optical disks, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An automatic adjustment method, comprising:

adjusting the microscope to a target state according to the confidence score of each cell;

the microscope comprises an object stage and a lens, the initial state comprises that the object stage is located at an initial object stage position and the lens is located at an initial lens position, the reference state comprises that the object stage is located at a reference object stage position and the lens is located at a reference lens position, and the microscope is adjusted from the initial state to the reference state according to the initial focusing component of the first image, and the method comprises the following steps:

2. The method of claim 1, wherein adjusting the stage from the initial stage position to a first stage position in the first lens position according to a predetermined adjustment method comprises:

acquiring a reference image of the measured object at the first lens position;

acquiring a focusing score of each image block in the four image blocks;

3. The method of claim 1 or 2, wherein said obtaining a confidence score for each of said at least one cell from said second image comprises:

determining a positioning frame of each cell through a preset network model;

4. The method of claim 1 or 2, wherein the initial lens position and the first lens position include a plurality of intermediate lens positions therebetween, and wherein adjusting the lens from the initial lens position to the first lens position according to the initial focus fraction comprises:

5. The method according to claim 4, wherein the moving the lens to a first intermediate lens position according to the initial focusing point by a preset lens moving method comprises:

the preset step length determination formula is as follows:

y＝k(1-0.9x)，

6. The method of claim 5, wherein said adjusting said microscope to a target state based on said confidence score for each cell comprises:

7. The method of claim 6, further comprising:

8. An automatic adjustment device, which is characterized by being applied to a microscope, comprises a first adjustment unit, an acquisition unit and a second adjustment unit, wherein,

the second adjusting unit is used for adjusting the microscope to a target state according to the confidence score of each cell;

the microscope includes an object stage and a lens, the initial state includes that the object stage is located at an initial object stage position and the lens is located at an initial lens position, the reference state includes that the object stage is located at a reference object stage position and the lens is located at a reference lens position, the microscope is adjusted from the initial state to the reference state according to an initial focusing component of the first image, and the first adjusting unit is specifically configured to:

9. The apparatus according to claim 8, wherein in the first lens position, the stage is adjusted from the initial stage position to a first stage position according to a preset adjustment method, and the first adjustment unit is specifically configured to:

acquiring a reference image of the measured object at the first lens position;

acquiring a focusing score of each image block in the four image blocks;

10. The apparatus according to claim 8 or 9, wherein in the obtaining of the confidence score for each cell from the second image, the obtaining unit is specifically configured to:

determining a positioning frame of each cell through a preset network model;

11. The apparatus according to claim 8 or 9, wherein the initial lens position and the first lens position include a plurality of intermediate lens positions therebetween, and the first adjusting unit is specifically configured to, in the adjusting the lens from the initial lens position to the first lens position according to the initial focus fraction:

12. The apparatus according to claim 11, wherein in the aspect that the lens is moved to the first intermediate lens position by adopting a preset lens moving method according to the initial focusing score, the first adjusting unit is specifically configured to:

the preset step length determination formula is as follows:

y＝k(1-0.9x)，

13. The apparatus according to claim 12, wherein in said adjusting the microscope to a target state according to the confidence score of each cell, the second adjusting unit is specifically configured to:

14. The device according to claim 13, wherein the automatic adjustment device is further specifically configured to:

15. A terminal, comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.

16. A computer-readable storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method according to any of claims 1-7.