Image analysis system and method of controlling taking of sample images

Abstract

The application provides an image analysis system and a method for controlling a sample image, the system comprising an imaging device, a moving device and an image analysis device, wherein the imaging device comprises an objective lens and an image capturing unit, the image capturing unit captures a sample to be detected on a smear to obtain a first image and acquires first image information of the first image; the image capturing unit captures a region within a field of view on the smear to obtain a second image and acquires second image information of the second image; the moving device is used to drive the smear and / or the objective lens to move; the image analysis device is used to analyze the first and second image information, determine a corresponding position of the second image on the first image, and determine movement information required for the smear and / or the objective lens to move to a target movement position based on the corresponding position. The application identifies the actual field of view position when the second image is captured by determining the corresponding relationship between the second image and the first image, thereby controlling the smear to move to the target movement position, and the method is simple and accurate in positioning.

Description

[0001] This application is a divisional application of Chinese Patent Application No. 202010232109.3. The original application has an application date of March 27, 2020, and the invention is named “Image Analysis System and Method for Controlling Sample Image Shooting”. TECHNICAL FIELD

[0002] The present application relates to the field of image analysis systems, and more particularly, to an image analysis system and a method for controlling sample image shooting. BACKGROUND

[0003] The current image analysis system (e.g., a blood cell digital image analysis system) performs cell analysis in the following process: an image of a target cell is shot with a low-power objective lens (e.g., 10x) to locate the cell (e.g., a white blood cell), and then an image of each cell located by the low-power objective lens is shot using a high-power objective lens (e.g., 100x). However, when shooting an image of one cell with the high-power objective lens and controlling the slide to move to shoot an image of another cell with the high-power objective lens, there is an inherent problem of inaccurate positioning due to mechanical problems such as motor out-of-step or different thread pitches, resulting in the slide failing to accurately move to the target movement position, and thus failing to shoot an image of the target cell. SUMMARY

[0004] To solve the above problems, the present application is proposed. According to an aspect of the present application, an image analysis system is provided, which comprises an imaging device, a moving device, and an image analysis device, wherein: the imaging device comprises an objective lens and an image capturing unit, wherein the image capturing unit shoots a sample to be tested on a slide to obtain a first image, and obtains first image information of the first image; the image capturing unit shoots a region within a field of view on the slide to obtain a second image, and obtains second image information of the second image; the moving device is used to drive the slide and / or the objective lens to move; and the image analysis device is used to: analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; and determine movement information required for the slide and / or the objective lens to move to a target movement position based on the corresponding position.

[0005] According to another aspect of the present application, a sample analysis system is provided, which comprises a blood analysis device, a slide preparation device, an image analysis device, and a control device, wherein the image analysis device comprises an image analysis system as described above.

[0006] According to still another aspect of the present application, there is provided a method for controlling taking sample images by an image analysis system, the method comprising: taking a first image of a sample to be detected on a smear to obtain first image information of the first image; taking a second image of a region within a field of view on the smear to obtain second image information of the second image; analyzing the first image information and the second image information to determine a corresponding position of the second image on the first image; and determining motion information required for the smear and / or the objective lens to move to a target motion position based on the corresponding position.

[0007] According to still another aspect of the present application, there is provided a computer readable storage medium containing computer executable instructions, which when executed by a processor, are capable of performing the above method.

[0008] The image analysis system and the method for controlling taking sample images of the embodiments of the present application can recognize the actual field of view position when taking the second image by determining the corresponding relationship between the second image and the first image, thereby controlling the smear to move to the target motion position. The method is simple and accurate in positioning, and can be implemented by using the existing system without additional devices. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0010] Figure 1 a schematic structural block diagram of an image analysis system according to one embodiment of the present application is shown;

[0011] Figure 2 an exemplary first image according to one embodiment of the present application is shown;

[0012] Figure 3 an exemplary second image according to one embodiment of the present application is shown;

[0013] Figure 4 a schematic diagram of analyzing the first image and the second image by using a sliding window method according to one embodiment of the present application is shown;

[0014] Figure 5 an exemplary integral image according to one embodiment of the present application is shown, in which the coordinates of four vertices of the sliding window are shown;

[0015] Figure 6A schematic diagram showing analysis of a first image and a second image when a sliding window portion is located outside the first image according to an embodiment of the present application;

[0016] Figure 7 A flow chart showing steps of a method for controlling taking sample images for an image analysis system according to an embodiment of the present application;

[0017] Figure 8 A schematic diagram showing the structure of a sample analysis system according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present application more obvious, the following will describe example embodiments according to the present application in detail with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present application.

[0019] In order to solve the above problems, embodiments of the present application provide an image analysis system and a method for controlling taking sample images, the image analysis system comprising an imaging device, a moving device and an image analysis device, wherein: the imaging device comprises an objective lens and an image capturing unit, wherein the image capturing unit takes a sample to be tested on a smear to obtain a first image, and obtains first image information of the first image; the image capturing unit takes a region within a field of view on the smear to obtain a second image, and obtains second image information of the second image; the moving device is used to drive the smear and / or the objective lens to move; and the image analysis device is used to: analyze the first image information and the second image information, determine a corresponding position of the second image on the first image; and based on the corresponding position, determine movement information required for the smear and / or the objective lens to move to a target movement position.

[0020] The image analysis system and the method for controlling taking sample images of the embodiments of the present application identify the actual field of view position when taking the second image by determining the corresponding relationship between the second image and the first image, thereby controlling the smear to move to the target movement position, which is simple in method, accurate in positioning, and can be implemented by using the existing system without additional devices.

[0021] The solutions of the present application will be described in detail below with reference to specific embodiments.

[0022] Embodiment One

[0023] This embodiment provides an image analysis system. Referring toFigure 1 , Figure 1 A schematic structural block diagram of an image analysis system 10 according to an embodiment of the present invention is shown. Figure 1 As shown, the image analysis system 10 may include an imaging device 100, an image analysis device 200, and a moving device 300. The imaging device 100 is used to capture images of a sample to be tested smeared on a smear; the image analysis device 200 is used to analyze images of the sample to be tested (e.g., cells in the sample); and the moving device 300 is used to drive the smear and / or the objective lens of the imaging device 100, causing the smear and / or the objective lens to move, so as to capture images of target cells in a specific area of ​​the sample to be tested on the smear. It should be understood that the moving device 300 may drive only the smear, or only the objective lens, or simultaneously drive both the smear and the objective lens, causing both to move simultaneously; the present invention is not limited in this regard. When the moving device 300 simultaneously drives the smear and the objective lens, it may include a first moving device and a second moving device, respectively used to drive the smear and the objective lens.

[0024] For example, the sample to be tested can be a blood sample, etc., and the present invention is not limited thereto. For example, the sample to be tested can contain various cells, such as white blood cells, neutrophils, red blood cells, etc., and the present invention is not limited thereto.

[0025] The imaging device 100 may include an objective lens unit 110 and an imaging unit 120. The objective lens unit 110 may include a first objective lens and a second objective lens. Exemplarily, the first objective lens may be a low-magnification objective lens, such as a 10x objective lens, and the second objective lens may be a high-magnification objective lens, such as a 100x objective lens. The objective lens unit 110 may also include a third objective lens, such as a 40x objective lens. It should be understood that the terms "low-magnification objective lens" and "high-magnification objective lens" are relative and do not specifically refer to certain magnifications as low-magnification or certain magnifications as high-magnification. The imaging unit 120 may include any camera, video camera, etc., known in the art, such as a CCD camera, a CMOS camera, etc., and this invention does not limit it.

[0026] When the imaging device 100 is equipped with the objective lens, the camera unit 120 captures a first image of the sample to be tested on the smear, acquiring first image information of the first image; then, the camera unit 120 captures a second image of the region within the field of view on the smear, acquiring second image information of the second image. Exemplarily, the camera unit 120 can also acquire the desired field of view location corresponding to a certain region on the first image, referred to herein as the target shooting location. Exemplarily, the image information may include image feature information, pixel information, etc.

[0027] For example, the first and second images can be obtained using different objectives. For instance, the first image can be obtained using a first objective (e.g., a 10x objective), and the second image can be obtained using a second objective (e.g., a 100x objective). Alternatively, a low-power objective can be used to photograph the sample on a smear to obtain the first image (low-power image), and then a high-power objective can be used to photograph each cell in the sample to obtain multiple second images (high-power images). For example, if the first image of a certain object is unclear and a second image needs to be obtained, the first and second images can also be obtained by taking two separate images using the same objective. For example, they can be obtained by taking two separate images using the same high-power objective (e.g., a 100x objective), or they can be obtained by taking two separate images using the same low-power objective (e.g., a 10x objective). This invention does not limit the scope of the invention.

[0028] In the example where the first image is taken with a low-power objective (e.g., 10x objective) and the second image is taken with a high-power objective (e.g., 100x objective), the field of view of the low-power objective is the entire sample to be tested on the smear. Therefore, the first image may include all cells, such as... Figure 2 As shown, the cells in the first image are white blood cells; the field of view of the high-power objective lens is a small area on the smear, so the second image may include one cell, or two or three cells that are close together, or it may not include any cells, such as... Figure 3 The example shown includes two cells.

[0029] For example, when the camera unit 120 finishes photographing one cell and needs to photograph the next, or when the image of the photographed cell is found to be unclear and needs to be re-photographed, the image analysis device 200 can use an image registration method to determine the motion information required for the smear and / or objective lens to move to the corresponding target motion position, so that it can re-photograph after moving to the target motion position. The target motion position is the position to which the smear and / or objective lens needs to be moved when the user wants to capture a clear image of an object. For example, the moving device 300 can drive only the smear to move, or only the objective lens to move, or both to move simultaneously; this invention is not limited in this respect. In the case where the moving device 300 simultaneously drives both the smear and the objective lens to move, the moving device 300 may include a first moving device and a second moving device, respectively used to drive the smear to move and drive the objective lens to move.

[0030] This article uses the example of a 300-unit mobile device driving the movement of a smear. In this case, the image analysis device 200 can use image registration to determine the motion information required for the smear to move to the target motion position, thereby guiding the movement of the smear. The target motion position is the position the smear needs to move to when an image of the target shooting position is to be captured.

[0031] Specifically, the image analysis device 200 may determine the motion information required for the smear to move to the target motion position using an image registration method. This may involve the image analysis device 200 analyzing the first image information and the second image information to determine the corresponding position of the second image on the first image, and based on this corresponding position, determining the motion information required for the smear to move to the target motion position. The corresponding position of the second image on the first image refers to which region of the first image the second image corresponds to.

[0032] In one embodiment, motion information may include the direction and distance of the smear movement. The distance may be in the form of steps. It should be understood that motion information may also include other information about the smear movement, and this invention is not limited thereto.

[0033] In one embodiment, the image analysis device 200 can determine the motion information required for the smear to move to the target motion position based on the corresponding position of the second image on the first image and the target shooting position on the first image. Specifically, the image analysis device 200 can obtain the coordinates of the corresponding position and the coordinates of the target shooting position, subtract the coordinates of the corresponding position and the target shooting position to obtain the coordinate difference, and convert the coordinate difference into the motion information required for the smear. For example, the coordinates of the corresponding position and the coordinates of the target motion position can both be represented by, for example, the number of steps moved by the mobile device, and the coordinates and distances of other positions mentioned herein can also be represented by the number of steps moved by the mobile device.

[0034] Since the corresponding position of the second image on the first image is a small region, the coordinates of a specific point at that position can be selected as the coordinates of the corresponding position, such as the top left corner, top right corner, bottom left corner, bottom right corner, or center point. This invention does not limit this selection. Preferably, the coordinates of the center point of the corresponding position can be selected as the coordinates of the corresponding position.

[0035] For example, an image registration algorithm can be used to analyze the first image information and the second image information to determine the corresponding position of the second image on the first image. For example, the image registration algorithm can include grayscale-based and template-based registration algorithms. Template-based registration algorithms can be called template matching (Blocking Matching), which searches for a sub-image similar to the template image in another image based on a known template image. Grayscale-based matching algorithms can also be called correlation matching algorithms, which use a two-dimensional sliding template for matching. For example, template-based registration algorithms can include, for example, the Mean Absolute Difference (MAD) algorithm, the Sum of Absolute Errors (SAD) algorithm, and the Sum of Squared Errors (SSD) algorithm. For example, the image registration algorithm can also include feature-based registration algorithms, which first extract the features of the image, then generate feature descriptors, and finally match the features between the two images based on the similarity of the feature descriptors. For example, image features can mainly be divided into point, line (edge), and region (surface) features, and can also be divided into local features and global features, with point features and edge features being the most commonly used. For example, point feature-based registration algorithms may include, for instance, Harris, Moravec, KLT, Harr-like, HOG, LBP, SIFT, SURF, BRIEF, SUSAN, FAST, CENSUS, FREAK, BRISK, ORB, optical flow, A-KAZE, etc., while edge feature-based registration algorithms may include, for instance, the LoG operator, Robert operator, Sobel operator, Prewitt operator, Canny operator, etc., and this invention is not limited thereto. It should be understood that other methods can also be used to determine the corresponding position of the second image on the first image, and this invention is not limited thereto.

[0036] An exemplary method for determining the corresponding position of the second image on the first image using an image registration algorithm will be described in detail later.

[0037] In one embodiment, after the smear moves to the desired position based on the motion information, the image analysis device 200 can also determine whether the smear has moved to the target motion position.

[0038] For example, the image analysis device 200 can use the above-described method for determining the corresponding position to determine whether the smear has moved to the target movement position. Specifically, after the smear has moved to its position, the camera unit 120 can take another picture of the area within the current field of view on the smear to obtain another second image (hereinafter referred to as the current second image), and acquire the image information of the current second image (hereinafter referred to as the current second image information), such as pixel information, feature information, etc.; then the image analysis device 200 analyzes the current second image information and the first image information to determine the corresponding position of the current second image on the first image (hereinafter referred to as the current corresponding position), and based on the current corresponding position and the target shooting position on the first image, determines whether the smear has moved to the target movement position. For example, any of the above-described image registration algorithms can be used to determine the current corresponding position of the current second image on the first image, that is, which area on the first image the current second image corresponds to. Specifically, if the determined current corresponding position coincides with or substantially coincides with the target shooting position, it can be determined that the smear has moved to the target movement position; otherwise, the smear has not moved to the target movement position. It should be understood that other methods can also be used to determine the current corresponding position of the second image on the first image, and this invention does not limit this method. An exemplary method for determining the current corresponding position of the second image on the first image using an image registration algorithm will be described in detail later.

[0039] When it is determined that the smear has not moved to the target movement position, the image analysis device 200 can re-determine the motion information (hereinafter referred to as current motion information) required to move the smear to the target movement position based on the current corresponding position and the target shooting position. Specifically, the coordinates of both the current corresponding position and the target shooting position can be obtained, and the coordinate difference (hereinafter referred to as current coordinate difference) can be obtained by subtracting the coordinates of the target shooting position from the coordinates of the current corresponding position. This current coordinate difference can then be converted into the current motion information required for the smear to move to the target movement position, such as the current movement direction and movement distance. For example, the coordinates of a specific point at the current corresponding position can be selected as the coordinates of the current corresponding position, such as the upper left corner, upper right corner, lower left corner, lower right corner, or center point of the current corresponding position. This invention does not limit this. Preferably, the coordinates of the center point of the current corresponding position can be selected as the coordinates of the current corresponding position.

[0040] Once the smear has moved to its target position based on the current motion information, the image analysis device 200 re-determines whether the smear has reached the target position. This process is similar to the process described above for determining whether the smear has reached the target position and will not be repeated here. If it is determined that the smear has still not reached the target position, the above process is repeated, and the image analysis device 200 updates the current motion information required for the smear to move to the target position until the smear reaches the target position based on the updated current motion information. The process by which the image analysis device 200 determines the updated current motion information is similar to the process described above for determining motion information and current motion information, and will not be repeated here.

[0041] In one embodiment, the image analysis system 10 further includes an alarm device 400 for issuing alarm information when certain conditions are met. Exemplarily, the alarm information may include sound alarms, graphic alarms, text alarms, etc., and the present invention is not limited thereto.

[0042] In one embodiment, the image analysis device 200 can obtain the number of times the current motion information is updated, and when the number of times the current motion information is updated is greater than or equal to a preset update count threshold, it indicates that a system fault has occurred, and the alarm device 400 is notified to issue an alarm message. For example, the preset update count threshold can be set by the user as needed, such as 3 times, 4 times, 5 times, etc., and this invention does not limit this setting.

[0043] In one embodiment, if the smear still fails to reach the target position after multiple updates of the current motion information, the image analysis device 200 can obtain the total time spent updating the current motion information and the smear movement. If the total time exceeds a preset total time threshold, it indicates a system malfunction, and the alarm device 400 is notified to issue an alarm message. For example, the preset total time threshold can be set by the user as needed, such as 3s, 5s, 10s, etc., and this invention does not limit this setting.

[0044] In one embodiment, if the image analysis device 200 determines that the smear has not moved to the target movement position, it calculates the distance between the current corresponding position and the target shooting position. If the distance is greater than a preset distance threshold, it indicates that a system malfunction has occurred, and the alarm device 400 is notified to issue an alarm message. For example, the preset distance threshold can be set by the user as needed, such as 1mm, 2mm, 3mm, etc., and this invention does not limit this setting.

[0045] In one embodiment, the image analysis device 200 can acquire multiple target shooting locations and multiple corresponding current locations, calculate multiple distances between each target shooting location and its corresponding current location, and if the number of distances greater than a preset distance threshold exceeds a preset quantity threshold, it indicates a system malfunction, and the alarm device 400 is notified to issue an alarm message. For example, the preset quantity threshold can be set by the user as needed, such as 3, 4, 5, etc., and this invention does not limit this.

[0046] In another embodiment, as the smear moves toward the target motion position according to the motion information, the image analysis device 200 can update the motion information required for the smear to move to the target motion position in real time (hereinafter referred to as real-time motion information), so that the smear can reach the target motion position faster and more accurately according to the real-time motion information.

[0047] Specifically, during the movement of the smear towards the target position based on motion information, the camera unit 120 can capture images of the area within the field of view on the smear in real time to obtain multiple second images (referred to herein as real-time second images), and acquire image information of the real-time second images (referred to herein as real-time second image information), such as pixel information, feature information, etc. The image analysis device 200 can analyze the real-time second image information and the first image information of the first image to determine the corresponding position of the real-time second image on the first image (referred to herein as the real-time corresponding position). Exemplarily, any of the above-mentioned image registration algorithms can be used to determine the real-time corresponding position of the real-time second image on the first image, that is, which area of ​​the first image the real-time second image currently corresponds to; this invention does not limit this. It should be understood that other methods can also be used to determine the real-time corresponding position of the real-time second image on the first image; this invention does not limit this. Among them, an exemplary method for determining the real-time corresponding position of the real-time second image on the first image using an image registration algorithm will be described in detail later.

[0048] Then, the image analysis device 200 can update the real-time motion information required for the smear to move to the target motion position based on the real-time corresponding position, until the smear moves to the target motion position according to the updated real-time motion information. For example, the image analysis device 200 can update the real-time motion information required for the smear to move to the target motion position based on the real-time corresponding position and the target shooting position on the first image. Specifically, the image analysis device 200 can obtain the coordinates of both the real-time corresponding position and the target shooting position, subtract the two coordinates to obtain the coordinate difference (referred to herein as the real-time coordinate difference), and convert this real-time coordinate difference into real-time motion information of the smear, thereby updating the real-time motion information in real time, such as the real-time motion direction and real-time motion distance, so that the smear moves according to the updated real-time motion information, thereby guiding the smear to the target motion position faster and more accurately.

[0049] For example, during the movement of the smear towards the target position, if the number of times the camera unit 120 captures a real-time second image and the image analysis device 200 updates the real-time motion information based on the corresponding position of the real-time second image on the first image exceeds a preset real-time number threshold, then the alarm device 400 is notified to issue an alarm message. For example, the preset real-time number threshold can be set by the user as needed, such as 2 times, 3 times, 4 times, 5 times, etc., and the present invention does not limit this.

[0050] In one embodiment, the alarm device 400 issues an alarm message when the smear fails to reach the target movement position within a preset time threshold. Exemplarily, the preset time threshold can be set by the user according to actual needs, such as 3s, 5s, 10s, etc., and this invention does not limit this setting.

[0051] In one embodiment, the process of using an image registration algorithm to determine the corresponding position of the second image on the first image, the current corresponding position of the second image on the first image, and the real-time corresponding position of the second image on the first image are similar. The following explanation uses the example of using an image registration algorithm to analyze the information of the second image and the information of the first image to determine the corresponding position of the second image on the first image.

[0052] In one embodiment, the image analysis device 200 can extract pixel information or feature information from the first image information and the second image information, and determine the corresponding position of the second image on the first image based on the pixel information or feature information. It should be understood that the image analysis device 200 can also determine the corresponding position of the second image on the first image based on other methods, such as methods based on domain transformation, etc., and this invention does not limit this to such methods.

[0053] For example, when determining the corresponding position of the second image on the first image based on pixel information, the image analysis device 200 can use the pixel information of both the first image and the second image to establish a similarity metric, and determine the corresponding position of the second image on the first image based on the similarity metric.

[0054] To improve the discriminative power of the similarity metric, it can be established based on the average pixel value of the second image and the first image. For example, the similarity metric γ can be established using the following formula:

[0055]

[0056] Where x and y are the coordinates of the pixel, and f(x,y) is the pixel value of each pixel in a certain region of the first image. Let g(x,y) be the average pixel value of all pixels in this region on the first image, and g(x,y) be the pixel value of each pixel on the second image. This represents the average pixel value of all pixels in the second image. It should be understood that f(x,y) can also be used. The second image is represented by g(x,y). The first image is not limited to this one. The formula of this invention can improve the discriminative power of the similarity measurement index, enabling better differentiation between the second image and the first image.

[0057] In one embodiment, the image analysis device 200 may use a sliding window method to analyze the first image and the second image, determine the value of the similarity metric, and thus determine the corresponding position of the second image on the first image.

[0058] Before analyzing the first and second images using the sliding window method, the image analysis device 200 needs to preprocess the first and second images.

[0059] Exemplarily, preprocessing may include resampling the first image and / or the second image to make the first and second images have the same resolution, i.e., the size represented by each pixel in the two images is the same. Resampling may include upsampling and downsampling. Exemplarily, the resolution of the first image may be kept unchanged while the second image is downsampled to the same resolution as the first image, or the resolution of the second image may be kept unchanged while the first image is upsampled to the same resolution as the second image, or both the first and second images may be resampled simultaneously to a certain resolution; this invention is not limited in this regard. The resampling method may employ methods known in the art, such as nearest neighbor interpolation, bilinear interpolation, cubic convolution interpolation, etc.; this invention is not limited in this regard.

[0060] To reduce computational load, preprocessing may further include converting both the first and / or second images to grayscale before resampling. Methods for converting color images to grayscale are well-known and will not be elaborated upon here. It should be understood that preprocessing may also include operations such as image rotation and denoising, which are not limited in this invention.

[0061] Specifically, such as Figure 4 As shown, the sliding window method may include: setting a sliding window and sliding the sliding window along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; during the sliding window process, calculating the value of the similarity metric index of the regions of the second image and the first image located within the sliding window in real time; selecting the maximum value among the similarity metric index values, and the region of the first image within the sliding window corresponding to the maximum value is the corresponding position of the second image on the first image.

[0062] In one embodiment, the predetermined path may include a path from left to right and from top to bottom on the first image. In another embodiment, the predetermined path may include... The predetermined path can be any other suitable path, and this invention does not limit it.

[0063] When the field of view when capturing the second image is at the edge of the field of view when capturing the first image, an edge problem will exist, resulting in a low value for the correlation metric and making it impossible to find the correct corresponding position. Therefore, in one embodiment, if the sliding window portion is located outside the first image, the image analysis device 200 can also calculate the value of the similarity metric based on a preset overlap threshold.

[0064] Specifically, if the ratio of the area of ​​the overlapping portion of the sliding window and the first image to the total area of ​​the sliding window is greater than or equal to the overlap threshold, it indicates that most of the sliding window is within the first image. In this case, the image analysis device 200 can calculate the similarity index between the overlapping portion of the sliding window in the first image and the corresponding portion in the second image. For example... Figure 6 As shown, at this point, only the similarity metric between the dashed area within the sliding window in the first image and the dashed area in the second image is calculated. If the ratio of the area of ​​the overlapping portion of the sliding window and the first image to the total area of ​​the sliding window is less than the overlap threshold, it indicates that only a small portion of the sliding window is within the first image. In this case, the overlap area between the two images is very small, and the accuracy of the similarity metric is low. Therefore, the image analysis device 200 can calculate the similarity metric as zero. The overlap threshold can be set empirically, for example, it can be set to 0.6-0.8, etc., and this invention does not limit this setting.

[0065] Since the similarity metric between the regions of the second image and the first image within the sliding window needs to be recalculated for each pixel the sliding window moves, the computational load is very high due to the large number of locations that need to be traversed. To optimize the computation speed, in one embodiment, the image analysis device 200 can first convert the first and second images to the frequency domain before calculating the similarity metric between the regions of the second image and the first image within the sliding window. Methods for converting the first and second images to the frequency domain can include FFT (Fast Fourier Transform), etc., which will not be elaborated here.

[0066] To optimize computational speed, in another embodiment, the image analysis device 200 can utilize an integral image method to calculate the similarity metric of the regions of the second image and the first image located within a sliding window. First, the image analysis device 200 can construct an array as an integral image, with the same width and height as the first image. Then, this array is assigned values, with each point's value being the sum of pixel values ​​from the top-left corner of the first image to that point within its coverage area. This integral image can then be used to easily calculate the sum of pixel values ​​within the sliding window, thereby conveniently calculating the similarity metric of the regions of the second image and the first image located within the sliding window. Figure 5 As shown in the figure, the sum of the pixel values ​​of all pixels within the sliding window is f(x2,y2)+f(x1,y1)-f(x1,y2)-f(x2,y1), where (x1,y1), (x2,y1), (x1,y2) and (x2,y2) are the coordinates of the four vertices of the sliding window, respectively.

[0067] In one embodiment, the image analysis system 10 may further include a display interface (not shown) for real-time display of the corresponding position, current corresponding position, real-time corresponding position, and target movement position, and may also display the movement path of the smear and / or imaging device in real time. Exemplarily, the display interface may be presented on the display of the image analysis system 10 or on the display of the image analysis device 200, and the present invention is not limited thereto.

[0068] In one embodiment, the image analysis system 10 may further include a smear recognition device, a smear gripping device, and a smear recycling device, wherein the smear recognition device is used to identify the identity information of the smear, the smear gripping device is used to grip the smear from the recognition device onto the moving device 300 for detection, and the smear recycling device is used to place the detected smear. In another embodiment, the image analysis system 10 may further include a smear basket loading device for loading a smear basket containing smears to be tested, and a smear gripping device for gripping the smears to be tested from the smear basket loaded on the smear basket loading device onto the smear recognition device for identification information recognition. It should be understood that the image analysis system 10 may also include other devices known in the art, and the present invention is not limited thereto.

[0069] Example 2

[0070] This embodiment provides a sample analysis system A, referencing... Figure 8 , Figure 8 A schematic diagram of the structure of a sample analysis system A according to an embodiment of the present invention is shown. Figure 8 As shown, the sample analysis system A may include a blood analysis device A100, a smear preparation device A200, an image analysis device A300, and a control device A400. The blood analysis device A110 is used to perform routine blood tests on the sample to be tested; the smear preparation device A200 is used to prepare a smear of the sample to be tested; the image analysis device A300 is used to capture and analyze images of the sample on the smear; and the control device A400 is communicatively connected to the blood analysis device A100, the smear preparation device A200, and the image analysis device A300. The sample analysis system A may also include a transmission track connecting each device and a feeding mechanism for each device, etc., but to avoid unnecessarily obscuring the invention, these will not be described in detail here.

[0071] The image analysis device A300 can be the image analysis system 10 according to Embodiment 1 of the present invention. The structure of the image analysis system 10 is described in Embodiment 1 and will not be repeated here.

[0072] Example 3

[0073] This embodiment provides a method for controlling the acquisition of sample images in an image analysis system. (Reference) Figure 7 , Figure 7 A flowchart illustrating the steps of a method 700 for controlling the capture of sample images in an image analysis system according to an embodiment of the present invention is shown.

[0074] like Figure 7 As shown, method 700 may include the following steps:

[0075] Step S710: Take a picture of the sample to be tested on the smear to obtain a first image, and obtain the first image information of the first image; take a picture of the area within the field of view on the smear to obtain a second image, and obtain the second image information of the second image.

[0076] For example, the sample to be tested can be a blood sample, etc., and the present invention is not limited thereto. For example, the sample to be tested can contain various cells, such as white blood cells, neutrophils, red blood cells, etc., and the present invention is not limited thereto. For example, the image information can include image feature information, pixel information, etc.

[0077] For example, the first and second images can be obtained using different objectives. For instance, the first image can be obtained using a first objective (e.g., a 10x objective), and the second image can be obtained using a second objective (e.g., a 100x objective). Alternatively, a low-power objective can be used to photograph the sample on a smear to obtain the first image (low-power image), and then a high-power objective can be used to photograph each cell in the sample to obtain multiple second images (high-power images). For example, if the first image of a certain object is unclear and a second image needs to be obtained, the first and second images can also be obtained by taking two separate images using the same objective. For example, they can be obtained by taking two separate images using the same high-power objective (e.g., a 100x objective), or they can be obtained by taking two separate images using the same low-power objective (e.g., a 10x objective). This invention does not limit the scope of the invention.

[0078] In the example where the first image is taken with a low-power objective (e.g., a 10x objective) and the second image is taken with a high-power objective (e.g., a 100x objective), the field of view of the low-power objective is all the samples to be tested on the entire smear, so the first image may include all cells; the field of view of the high-power objective is a small area on the smear, so the second image may include one cell, or two or three cells when they are close together, or it may not include any cells.

[0079] Step S720: Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image. The corresponding position of the second image on the first image refers to which region of the first image the second image corresponds to.

[0080] For example, an image registration algorithm can be used to analyze the second image information and the first image information to determine the corresponding position of the second image on the first image. For example, the image registration algorithm can include grayscale-based and template-based registration algorithms. Template-based registration algorithms can be called template matching (Blocking Matching), which searches for a sub-image similar to the template image in another image based on a known template image. Grayscale-based matching algorithms can also be called correlation matching algorithms, which use a two-dimensional sliding template for matching. For example, template-based registration algorithms can include, for example, the Mean Absolute Difference (MAD) algorithm, the Sum of Absolute Errors (SAD) algorithm, and the Sum of Squared Errors (SSD) algorithm. For example, the image registration algorithm can also include feature-based registration algorithms, which first extract the features of the image, then generate feature descriptors, and finally match the features between the two images based on the similarity of the feature descriptors. For example, image features can mainly be divided into point, line (edge), and region (surface) features, and can also be divided into local features and global features, with point features and edge features being the most commonly used. For example, point feature-based registration algorithms may include, for instance, Harris, Moravec, KLT, Harr-like, HOG, LBP, SIFT, SURF, BRIEF, SUSAN, FAST, CENSUS, FREAK, BRISK, ORB, optical flow, A-KAZE, etc., while edge feature-based registration algorithms may include, for instance, the LoG operator, Robert operator, Sobel operator, Prewitt operator, Canny operator, etc., and this invention is not limited thereto. It should be understood that other methods can also be used to determine the corresponding position of the second image on the first image, and this invention is not limited thereto.

[0081] The process of analyzing the second image information and the first image information using an image registration algorithm to determine the corresponding position of the second image on the first image may include: extracting pixel information or feature information from the first image information and the second image information, and determining the corresponding position of the second image on the first image based on the pixel information or feature information. It should be understood that other methods can also be used to determine the corresponding position of the second image on the first image, such as methods based on domain transformation, and this invention does not limit this approach.

[0082] For example, determining the corresponding position of the second image on the first image based on pixel information may include: establishing a similarity metric using the pixel information of both the first and second images, and determining the corresponding position of the second image on the first image based on the similarity metric.

[0083] To improve the discriminative power of the similarity metric, method 700 may include establishing a similarity metric based on the average pixel values ​​of the second image and the first image. For example, the similarity metric γ can be established using the following formula:

[0084]

[0085] Where x and y are the coordinates of the pixel, and f(x,y) is the pixel value of each pixel in a certain region of the first image. Let g(x,y) be the average pixel value of all pixels in this region on the first image, and g(x,y) be the pixel value of each pixel on the second image. This represents the average pixel value of all pixels in the second image. It should be understood that f(x,y) can also be used. The second image is represented by g(x,y). The first image is not limited to this one. The formula of this invention can improve the discriminative power of the similarity measurement index, enabling better differentiation between the second image and the first image.

[0086] For example, a sliding window method can be used to analyze the first image and the second image to determine the value of the similarity metric, thereby determining the corresponding position of the second image on the first image.

[0087] Before analyzing the first and second images using the sliding window method, preprocessing of the first and second images is required.

[0088] Exemplarily, preprocessing may include resampling the first image and / or the second image to make the first and second images have the same resolution, i.e., the size represented by each pixel in the two images is the same. Resampling may include upsampling and downsampling. Exemplarily, the resolution of the first image may be kept unchanged while the second image is downsampled to the same resolution as the first image, or the resolution of the second image may be kept unchanged while the first image is upsampled to the same resolution as the second image, or both the first and second images may be resampled simultaneously to a certain resolution; this invention is not limited in this regard. The resampling method may employ methods known in the art, such as nearest neighbor interpolation, bilinear interpolation, cubic convolution interpolation, etc.; this invention is not limited in this regard.

[0089] To reduce computational load, preprocessing may also include converting both the first and second images to grayscale before resampling them. Methods for converting color images to grayscale are well-known and will not be elaborated upon here.

[0090] Specifically, the sliding window method may include: setting a sliding window and sliding the sliding window along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; during the sliding window process, calculating in real time the value of the similarity metric index of the regions of the second image and the first image located within the sliding window; selecting the maximum value among the similarity metric index values, and the region of the first image within the sliding window corresponding to the maximum value is the corresponding position of the second image on the first image.

[0091] In one embodiment, the predetermined path may include a path from left to right and from top to bottom on the first image. In another embodiment, the predetermined path may include... The predetermined path can be any other suitable path, and this invention does not limit it.

[0092] When the field of view when capturing the second image is at the edge of the field of view when capturing the first image, an edge problem will exist, resulting in a low value for the relevance metric and making it impossible to find the correct corresponding position. Therefore, in one embodiment, if the sliding window portion is located outside the first image, method 700 may further include: calculating the value of the similarity metric based on a preset overlap threshold.

[0093] Specifically, if the ratio of the area of ​​the overlapping portion of the sliding window and the first image to the total area of ​​the sliding window is greater than or equal to the overlap threshold, it indicates that most of the sliding window is within the first image. In this case, method 700 may include calculating the similarity metric between the overlapping portion of the sliding window in the first image and the corresponding portion in the second image. If the ratio of the overlapping portion of the sliding window and the first image to the total area of ​​the sliding window is less than the overlap threshold, it indicates that only a small portion of the sliding window is within the first image. In this case, the overlap area between the two images is very small, and the accuracy of the similarity metric is low. Therefore, method 700 may include setting the similarity metric to zero. The overlap threshold can be set empirically, for example, it can be set to 0.6-0.8, etc., and this invention does not limit it.

[0094] Since the similarity metric between the regions of the second image and the first image within the sliding window needs to be recalculated for each pixel the sliding window slides, the computational load is very high due to the large number of locations that need to be traversed. To optimize the computation speed, in one embodiment, method 700 may further include: first converting the first image and the second image to the frequency domain, and then calculating the similarity metric between the regions of the second image and the first image within the sliding window. The method for converting the first image and the second image to the frequency domain can be FFT (Fast Fourier Transform), etc., which will not be elaborated here.

[0095] To optimize computation speed, in another embodiment, method 700 may include: using an integral image method to calculate the similarity metric of the regions of the second image and the first image located within a sliding window. First, an array can be constructed as an integral image, with the same width and height as the first image. Then, this array is assigned values, where the value of each point is the sum of the pixel values ​​of all pixels within the coverage area from the top-left vertex of the first image to that point. Then, the sum of the pixel values ​​of all pixels within the sliding window can be easily calculated using this integral image, thereby conveniently calculating the similarity metric of the regions of the second image and the first image located within the sliding window.

[0096] Step S730: Based on the corresponding position of the second image on the first image, determine the motion information required for the smear to move to the target motion position.

[0097] The corresponding position of the second image on the first image is the area on the first image that the second image corresponds to, and the target motion position is the position to which the smear needs to be moved when the user wants to take a clear image of a certain area.

[0098] In one embodiment, motion information may include the direction and distance of the smear movement. The distance may be in the form of steps. It should be understood that motion information may also include other information about the smear movement, and this invention is not limited thereto.

[0099] For example, the target shooting position on the first image can be obtained, and based on the corresponding position of the second image on the first image and the target shooting position, the motion information required for the smear to move to the target movement position can be determined. Specifically, the coordinates of both the corresponding position and the target shooting position can be obtained, the coordinate difference can be obtained by subtracting the coordinates of the corresponding position from the coordinates of the target shooting position, and the coordinate difference can be converted into the motion information required for the smear, such as the movement direction and movement distance. Both the coordinates of the corresponding position and the coordinates of the target movement position can be represented, for example, by the number of steps moved by the mobile device, and the coordinates of other positions mentioned herein can also be represented by the number of steps moved by the mobile device.

[0100] Since the corresponding position of the second image on the first image is a small region, the coordinates of a specific point at that position can be selected as the coordinates of the corresponding position, such as the top left corner, top right corner, bottom left corner, bottom right corner, or center point. This invention does not limit this selection. Preferably, the coordinates of the center point of the corresponding position can be selected as the coordinates of the corresponding position.

[0101] It should be understood that when photographing target cells, the smear can be moved, the imaging device can be moved, or both can be moved simultaneously for focusing; this invention does not limit this. In this embodiment, the movement of the smear is used as an example for illustration.

[0102] Specifically, in one embodiment, after the smear has moved to its designated position according to the motion information, method 700 may further include: determining whether the smear has moved to the target motion position. Specifically, a current second image can be obtained by capturing a region within the current field of view on the smear; current second image information, such as pixel information and feature information, can be acquired; then, the current second image information and the first image information are analyzed to determine the current corresponding position of the current second image on the first image, and based on the current corresponding position and the target shooting position on the first image, it is determined whether the smear has moved to the target motion position. Exemplarily, any of the above image registration algorithms can be used to determine the current corresponding position of the current second image on the first image, i.e., which region on the first image the current second image corresponds to. Specifically, if the determined current corresponding position coincides with or substantially coincides with the target shooting position, it can be determined that the smear has moved to the target motion position; otherwise, the smear has not moved to the target motion position. It should be understood that other methods can also be used to determine the current corresponding position of the current second image on the first image, and this invention does not limit this method. One exemplary method for determining the current corresponding position of the second image on the first image using an image registration algorithm is similar to the method described above for determining the corresponding position of the second image on the first image, and will not be repeated here.

[0103] When it is determined that the smear has not moved to the target movement position, method 700 may further include: determining the current motion information required to move the smear to the target movement position based on the current corresponding position and the target shooting position. Specifically, the coordinates of both the current corresponding position and the target shooting position can be obtained, the coordinates of the target shooting position can be subtracted from the coordinates of the current corresponding position to obtain the current coordinate difference, and the current coordinate difference can be converted into the current motion information required for the smear to move to the target movement position, such as the current movement direction and movement distance. For example, the coordinates of a specific point on the current corresponding position can be selected as the coordinates of the current corresponding position, such as the upper left corner, upper right corner, lower left corner, lower right corner, center point, etc. of the current corresponding position; this invention does not limit this. Preferably, the coordinates of the center point of the current corresponding position can be selected as the coordinates of the current corresponding position.

[0104] Once the smear has moved to its target position based on the current motion information, method 700 may further include: re-determining whether the smear has moved to the target position. This process is similar to the process described above for determining whether the smear has moved to the target position, and will not be repeated here. If it is determined that the smear has still not moved to the target position, the above process is repeated, updating the current motion information required to move the smear to the target position, until the smear moves to the target position based on the updated current motion information.

[0105] In one embodiment, method 700 may further include issuing an alarm message when certain conditions are met. Exemplarily, the alarm message may include an audible alarm, a graphic alarm, a text alarm, etc., and this invention is not limited thereto.

[0106] In one embodiment, method 700 may further include: obtaining the number of times the current motion information is updated, and when the number of times the current motion information is updated is greater than or equal to a preset update count threshold, indicating a system malfunction, and issuing an alarm message. For example, the preset update count threshold can be set by the user as needed, such as 3 times, 4 times, 5 times, etc., and this invention does not limit this setting.

[0107] In one embodiment, if the smear still fails to reach the target movement position after multiple updates of the current motion information, method 700 may further include: obtaining the total time spent updating the current motion information and the smear movement process; and if the total time exceeds a preset total time threshold, indicating a system malfunction, and issuing an alarm message. For example, the preset total time threshold can be set by the user as needed, such as 3s, 5s, 10s, etc., and this invention does not limit this setting.

[0108] In one embodiment, if it is determined that the smear has not moved to the target movement position, the distance between the current corresponding position and the target shooting position is calculated. If the distance is greater than a preset distance threshold, it indicates that the system has malfunctioned, and an alarm message is issued. For example, the preset distance threshold can be set by the user as needed, such as 1mm, 2mm, 3mm, etc., and the present invention does not limit it in this way.

[0109] In one embodiment, method 700 may further include: acquiring multiple target shooting locations and multiple corresponding current locations; calculating multiple distances between each target shooting location and its corresponding current location; and issuing an alarm message if the number of distances greater than a preset distance threshold exceeds a preset quantity threshold. For example, the preset quantity threshold can be set by the user as needed, such as 3, 4, 5, etc., and this invention does not limit this.

[0110] In another embodiment, during the process of the smear moving toward the target motion position according to the motion information, method 700 may further include: updating the real-time motion information required for the smear to move to the target motion position in real time, so that the smear can reach the target motion position faster and more accurately according to the real-time motion information.

[0111] Specifically, during the movement of the smear towards the target position based on motion information, a real-time second image can be obtained by capturing images of the area within the field of view on the smear. Real-time second image information, such as pixel information and feature information, is then acquired. This real-time second image information is then analyzed in conjunction with the first image information of the first image to determine the real-time corresponding position of the second image on the first image. For example, any of the image registration algorithms described above can be used to determine the real-time corresponding position of the second image on the first image, i.e., which region of the first image the second image currently corresponds to. This invention does not limit this method. It should be understood that other methods can also be used to determine the real-time corresponding position of the second image on the first image, and this invention does not limit these methods. One exemplary method for determining the real-time corresponding position of the second image on the first image using an image registration algorithm is similar to the method described above for determining the corresponding position of the second image on the first image, and will not be repeated here.

[0112] Then, method 700 may further include: updating the real-time motion information required for the smear to move to the target motion position based on the real-time corresponding position, until the smear moves to the target motion position according to the real-time motion information. For example, the real-time motion information required for the smear to move to the target motion position can be updated in real time based on the real-time corresponding position and the target shooting position on the first image. Specifically, the coordinates of the real-time corresponding position and the target shooting position can be obtained, the real-time coordinate difference can be obtained by subtracting the two coordinates, and this real-time coordinate difference can be converted into real-time motion information of the smear, thereby updating the real-time motion information in real time, such as the real-time motion direction and real-time motion distance, so that the smear moves according to the updated motion information, thereby guiding the smear to the target motion position faster and more accurately.

[0113] For example, during the movement of the smear towards the target position, if the number of times a real-time second image is captured and the real-time motion information is updated based on the corresponding position of the real-time second image on the first image exceeds a preset real-time number threshold, an alarm message is issued. For example, the preset real-time number threshold can be set by the user as needed, such as 2 times, 3 times, 4 times, 5 times, etc., and the present invention does not limit it in this way.

[0114] In one embodiment, an alarm can be issued if the smear fails to reach the target position within a preset time threshold. For example, the preset time threshold can be set by the user according to actual needs, such as 3s, 5s, 10s, etc., and this invention does not limit this setting.

[0115] In one embodiment, method 700 may further include: displaying in real time the corresponding position, current corresponding position, real-time corresponding position and target motion position on the display of image analysis system 10 or on the display of image analysis device 200, and may also display the motion path of the smear in real time.

[0116] Example 4

[0117] This embodiment provides a computer-readable medium storing a computer program that, when executed, performs the methods described in the above embodiments. Any tangible, non-transitory computer-readable medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions may be loaded onto a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to form a machine, such that instructions executing on the computer or other programmable data processing apparatus can generate means for implementing a specified function. These computer program instructions may also be stored in a computer-readable storage medium that can instruct the computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable storage medium can form an article of manufacture including means for implementing the specified function. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable apparatus to produce a computer-implemented process, such that instructions executing on the computer or other programmable apparatus can provide steps for implementing the specified function.

[0118] Technical effects of the present invention:

[0119] The image analysis system and method for controlling the capture of sample images according to embodiments of the present invention identify the actual field of view position when capturing the second image by determining the correspondence between the second image and the first image, thereby controlling the smear to move to the target movement position. The method is simple, the positioning is accurate, and it can be implemented using existing systems without the need for additional devices.

[0120] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0121] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0122] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0123] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0124] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0125] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0126] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An image analysis system, characterized in that, The image analysis system includes an imaging device, a moving device, and an image analysis device. The imaging device includes an objective lens, wherein: The imaging device is used to capture a sample to be tested on a smear under a first field of view to obtain a first image, thereby obtaining first image information of the first image; and to capture a sample to be tested on the smear under a second field of view to obtain a second image, thereby obtaining second image information of the second image. The moving device is used to drive the smear and / or the objective lens to move; after the imaging device takes a picture of the sample to be tested on the smear in the first field of view to obtain the first image, the moving device drives the smear and / or the objective lens to move so that the imaging device takes a picture of the sample to be tested on the smear in the second field of view to obtain the second image; The image analysis device is used for: Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image; and Determine whether the corresponding position coincides with or substantially coincides with the target shooting position of the second image on the first image; When it is determined that the corresponding position coincides with or substantially coincides with the target shooting position, the target image of the sample to be tested is determined based on the second image; When it is determined that the corresponding position does not coincide with or substantially coincide with the target shooting position, based on the corresponding position and the target shooting position, motion information required for the smear and / or the objective lens to move to the target motion position is determined, so that the moving device drives the smear and / or the objective lens to move to the target motion position according to the motion information, and the imaging device captures the sample to be tested on the smear under the current second field of view to obtain the current second image, so as to obtain the current second image information of the current second image.

2. The image analysis system according to claim 1, characterized in that, During the process of the moving device driving the smear and / or the objective lens to move toward the target motion position according to the motion information, the image analysis device is further configured to: The real-time motion information required for the smear and / or the objective lens to move to the target motion position is updated in real time, so that the moving device drives the smear and / or the objective lens to move to the target motion position according to the real-time motion information.

3. The image analysis system according to claim 2, characterized in that, During the process of the moving device driving the smear and / or the objective lens to move toward the target moving position according to the motion information, the imaging device is also used to take real-time pictures of the sample to be tested on the smear under the second field of view to obtain a real-time second image, so as to obtain the real-time second image information of the real-time second image; The image analysis device is further configured to analyze the first image information and the real-time second image information to determine the real-time corresponding position of the real-time second image on the first image; and to update the real-time motion information in real time based on the real-time corresponding position and the target shooting position.

4. The image analysis system according to claim 1, characterized in that, The image analysis device is also used for: The first image information and the current second image information are analyzed to determine the current corresponding position of the current second image on the first image, and the smear and / or the objective lens are determined to have moved to the target movement position based on the current corresponding position. If the smear and / or the objective lens moves to the target movement position, then the target image of the sample to be tested is determined based on the current second image; If the smear and / or the objective lens does not move to the target motion position, then based on the current corresponding position and the target shooting position, the updated current motion information required for the smear and / or the objective lens to move to the target motion position is determined, so as to drive the smear and / or the objective lens to move to the target motion position according to the updated current motion information.

5. The image analysis system according to claim 4, characterized in that, The image analysis system also includes an alarm device for issuing alarm information; Specifically, the alarm device issues the alarm information when the number of updates to the current motion information is greater than or equal to a preset update number threshold, when the total time spent on updating the current motion information and the movement of the smear and / or the objective lens exceeds a preset total time threshold, or when the distance between the current corresponding position and the target shooting position exceeds a preset distance threshold.

6. The image analysis system according to claim 1, characterized in that, The objectives include low-power objectives and high-power objectives; The first image was captured under the low-power objective lens, and the second image was captured under the high-power objective lens.

7. The image analysis system according to claim 1, characterized in that, The region of the sample to be tested within the second field of view is a part of the region of the sample to be tested within the first field of view.

8. The image analysis system according to any one of claims 1-7, characterized in that, The image analysis system further includes a display interface, which is used to display at least one of the following: The corresponding position, the target shooting position, the target movement position, the movement path of the smear and / or the objective lens, and the alarm information.

9. A method for controlling the capture of sample images in an image analysis system, characterized in that, The method includes: The sample to be tested on the smear is photographed under a first field of view to obtain a first image, and the first image information of the first image is acquired; The sample to be tested on the smear is photographed under a second field of view to obtain a second image, and the second image information of the second image is acquired; After the imaging device captures the sample to be tested on the smear in the first field of view to obtain the first image, the smear and / or objective lens are driven to move so that the imaging device captures the sample to be tested on the smear in the second field of view to obtain the second image. Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image; and Determine whether the corresponding position coincides with or substantially coincides with the target shooting position of the second image on the first image; When it is determined that the corresponding position coincides with or substantially coincides with the target shooting position, the target image of the sample to be tested is determined based on the second image; When it is determined that the corresponding position does not coincide with or substantially coincide with the target shooting position, based on the corresponding position and the target shooting position, the motion information required for the smear and / or the objective lens to move to the target motion position is determined, so as to drive the smear and / or the objective lens to move to the target motion position according to the motion information, and to capture the sample to be tested on the smear under the current second field of view to obtain the current second image, and to acquire the current second image information of the current second image.

10. The method according to claim 9, characterized in that, The method further includes: during the process of driving the smear and / or the objective lens to move towards the target motion position according to the motion information, updating in real time the real-time motion information required for the smear and / or the objective lens to move to the target motion position; and The smear and / or the objective lens are driven to move to the target motion position based on the real-time motion information.

11. The method according to claim 10, characterized in that, The real-time motion information required for the smear and / or the objective lens to move to the target motion position includes: The sample to be tested on the smear is photographed in real time under the second field of view to obtain a real-time second image, and the real-time second image information of the real-time second image is acquired. Analyze the first image information and the real-time second image information to determine the real-time corresponding position of the real-time second image on the first image; and The real-time motion information is updated in real time based on the real-time corresponding position and the target shooting position.

12. The method according to claim 9, characterized in that, The method further includes: The first image information and the current second image information are analyzed to determine the current corresponding position of the current second image on the first image, and the smear and / or the objective lens are determined to have moved to the target movement position based on the current corresponding position. If the smear and / or the objective lens moves to the target movement position, then the target image of the sample to be tested is determined based on the current second image; If the smear and / or the objective lens does not move to the target motion position, then based on the current corresponding position and the target shooting position, the updated current motion information required for the smear and / or the objective lens to move to the target motion position is determined, so as to drive the smear and / or the objective lens to move to the target motion position according to the updated current motion information.

13. The method according to claim 9, characterized in that, The step of analyzing the first image information and the second image information to determine the corresponding position of the second image on the first image includes: An image registration algorithm is used to analyze the first image information and the second image information to determine the corresponding position of the second image on the first image.

14. The method according to claim 13, characterized in that, The step of analyzing the first image information and the second image information using an image registration algorithm to determine the corresponding position of the second image on the first image includes: Extract pixel information or feature information from the first image information and the second image information; and The corresponding position of the second image on the first image is determined based on the pixel information or the feature information.

15. The method according to claim 14, characterized in that, Determining the corresponding position of the second image on the first image based on the pixel information includes: A similarity metric is established using the pixel information of the first image and the pixel information of the second image, and the corresponding position of the second image on the first image is determined based on the similarity metric.

16. The method according to claim 15, characterized in that, Determining the corresponding position of the second image on the first image based on the similarity metric includes: The value of the similarity metric is determined using the sliding window method to determine the corresponding position of the second image on the first image.

17. The method according to claim 16, characterized in that, The step of determining the value of the similarity metric using the sliding window method to determine the corresponding position of the second image on the first image includes: The first image and the second image are preprocessed, the preprocessing including resampling the first image and / or the second image so that the first image and the second image have the same resolution; A sliding window is set up and slides along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; During the sliding process of the sliding window, the value of the similarity metric index of the regions of the second image and the first image located within the sliding window is calculated in real time; Select the maximum value among the values ​​of the similarity metric; and The region of the first image within the sliding window corresponding to the maximum value is determined as the corresponding position of the second image on the first image.

18. An image analysis system, characterized in that, The image analysis system includes an imaging device, a moving device, an image analysis device, and an alarm device. The imaging device includes an objective lens, wherein: The imaging device is used to capture a sample to be tested on a smear under a first field of view to obtain a first image, thereby obtaining first image information of the first image; and to capture a sample to be tested on the smear under a second field of view to obtain a second image, thereby obtaining second image information of the second image. The moving device is used to drive the smear and / or the objective lens to move; after the imaging device takes a picture of the sample to be tested on the smear in the first field of view to obtain the first image, the moving device drives the smear and / or the objective lens to move so that the imaging device takes a picture of the sample to be tested on the smear in the second field of view to obtain the second image; The image analysis device is used for: Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image; and Obtain the distance between the corresponding position and the target shooting position of the second image on the first image; When the distance exceeds a preset distance threshold, the alarm device issues an alarm message.

Images