Temporary slide bubble detection method and system for physical, chemical and biological experiment assessment

Abstract

The present invention relates to the field of image processing technology, and in particular to a temporary slide bubble detection method and system for physical, chemical, and biological experiment assessment. The method comprises: acquiring a color microscope image of the temporary slide, converting the color microscope image into a smooth grayscale image; determining a gradient transformation image and a distance transformation image based on the smooth grayscale image; performing size transformation on the gradient transformation image and the distance transformation image respectively to form an enhanced image set comprising a plurality of enhanced image pairs, performing logical operations on corresponding pixel points of each enhanced image pair respectively to obtain a mixed heat map set; performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set; removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image. The present invention improves the efficiency of temporary slide bubble detection.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a temporary slide bubble detection method and system for physical, chemical and biological experiment assessment. Background Art

[0002] During the evaluation process of physics, chemistry, and biology experiments, students are required to create temporary slides to observe various cell morphologies. During this process, bubbles often appear due to improper operation, interfering with students' observation of cell structures. Currently, during the evaluation process, teachers often need to manually observe the microscopic images of students' temporary slides for bubbles, which is time-consuming and laborious. Therefore, it is necessary to implement intelligent bubble detection to improve the accuracy, fairness, and efficiency of physics, chemistry, and biology experiment evaluations. Summary of the Invention

[0003] The present invention aims to provide a temporary slide bubble detection method and system for physical, chemical and biological experiment assessment to solve at least one technical problem in the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting bubbles in a temporary slide for physical, chemical, and biological experiment assessment, the method comprising the following steps:

[0006] S100, acquiring a color microscope image of a temporary slide, and converting the color microscope image into a smooth grayscale image;

[0007] S200, determining a gradient transformation image based on the grayscale gradient of the smooth grayscale image, and determining a distance transformation image based on the distance from each pixel in the smooth grayscale image to the nearest background point;

[0008] S300, performing size transformation on the gradient transformed image and the distance transformed image respectively to form an enhanced image set including a plurality of enhanced image pairs, performing logical operations on corresponding pixels of each enhanced image pair respectively to obtain a mixed heat map set; wherein each enhanced image pair has a different size;

[0009] S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set;

[0010] S500 , removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image.

[0011] Optionally, in S100, acquiring a color microscope image of the temporary slide and converting the color microscope image into a smooth grayscale image includes:

[0012] S110, inputting the color microscope image I of the temporary slide rgb , convert the color microscope image into a grayscale image I gray ;

[0013] S120, using median filtering to blur the edges of the grayscale image to obtain a smooth grayscale image I gray ′.

[0014] Optionally, in S200, determining the gradient transformed image based on the grayscale gradient of the smoothed grayscale image includes:

[0015] S211, calculate the smooth grayscale image I gray ′Gray gradient g in the x-axis direction x and the grayscale gradient g in the y-axis direction y ;

[0016] S212, the gray gradient g x and gray gradient g y Superimpose to obtain the gradient image I of the temporary mount grad ;

[0017] S213, gradient image I grad Perform dynamic threshold segmentation to obtain binary image I bin1 ;

[0018] S214, using mean filtering to process the binary image I bin1 Perform edge blur and perform edge blur on the binary image I bin1 Perform bitwise inversion operation to obtain the gradient transformed image I grad′ .

[0019] Optionally, in S200, determining the distance transformation image based on the distance from each pixel in the smoothed grayscale image to the nearest background point includes:

[0020] S221, smoothing grayscale image I gray ' Perform binarization processing to obtain a binary image I bin2 , and for the binary image I bin2 Perform opening operation;

[0021] S222, calculate the binary image I bin2 The distance from each pixel to the nearest background point is used to generate the initial distance transformation image I based on the distance from each pixel to the nearest background point. distance ;

[0022] S223, transform the initial distance image I distance Perform dynamic threshold segmentation and perform bitwise inversion operation to obtain the distance transformation image I distance′ .

[0023] Optionally, in S300, the step of performing size transformation on the gradient transformed image and the distance transformed image to form an enhanced image set including a plurality of enhanced image pairs, and performing logical operations on corresponding pixels of each enhanced image pair to obtain a mixed heat map set includes:

[0024] S310, transforming the gradient image I grad′ and distance transformed image I distance′ As a set of enhanced image pairs of original size, the enhanced image pairs are respectively scaled horizontally, vertically, and overall to obtain three sets of size-transformed enhanced image pairs, and the three sets of size-transformed enhanced image pairs and the enhanced image pairs of original size are combined to form an enhanced image set I;

[0025] S320 , performing a bitwise OR operation on each enhanced image pair in the enhanced image set I to obtain a mixed heat map set H, where the mixed heat map set includes multiple mixed heat maps.

[0026] Optionally, in S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set includes:

[0027] S410, after performing erosion, expansion, opening, and closing operations on each mixed heat map in the mixed heat map set H, performing Hough circle detection on each mixed heat map, recording all detected Hough circles, and obtaining a circular edge set;

[0028] S420 , performing size reduction on each circular edge in the circular edge set C to obtain a candidate bubble edge set B, where the candidate bubble edge set B includes a plurality of edges.

[0029] Optionally, in S500, removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image, includes:

[0030] S510 , for each pair of edges in the candidate bubble edge set B, calculating the overlap of the areas within the two edges;

[0031] S520, determining whether the overlap of the areas within the two edges is greater than an overlap threshold; if so, retaining the edge with the larger area; otherwise, retaining both edges to obtain a deduplicated bubble edge set B′;

[0032] S530, filling all edges in the bubble edge set B′ to obtain the bubble segmentation image I mask .

[0033] In a second aspect, an embodiment of the present invention provides a temporary slide bubble detection system for physical, chemical, and biological experiment assessment, the system comprising:

[0034] at least one processor;

[0035] at least one memory for storing at least one program;

[0036] When the at least one program is executed by the at least one processor, the at least one processor implements any one of the methods described above.

[0037] The beneficial effects of the present invention are as follows: the present invention discloses a temporary slide bubble detection method and system for physical, chemical, and biological experiment assessment. The present invention obtains a color microscope image of the temporary slide and converts the color microscope image into a smooth grayscale image; determines a gradient transformation image based on the grayscale gradient of the smooth grayscale image, and determines a distance transformation image based on the distance from each pixel in the smooth grayscale image to the nearest background point; performs size transformation on the gradient transformation image and the distance transformation image respectively to form an enhanced image set comprising multiple enhanced image pairs; performs logical operations on the corresponding pixels of each enhanced image pair to obtain a mixed heat map set; performs image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set; removes duplicates from the candidate bubble edge set to obtain a bubble edge set; fills the bubble edge set to obtain a bubble segmentation image. The present invention can effectively identify bubbles in the microscope image of the temporary slide and intelligently judge the production quality of the temporary slide. The present invention improves the efficiency of temporary slide bubble detection and reduces the reliance on manual labor during physical, chemical, and biological experiment assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 This is a flow chart of a temporary slide bubble detection method for physical, chemical, and biological experiment assessment in an embodiment of the present invention;

[0040] Figure 2 This is a diagram showing the effect of processing a color microscope image in an embodiment of the present invention;

[0041] Figure 3 The diagram is a structural diagram of a temporary slide bubble detection system for physical, chemical, and biological experiment assessment in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other unless there is a conflict.

[0043] The solutions in related technologies have the following problems:

[0044] During the evaluation of physical, chemical, and biological experiments, it is difficult to intelligently determine whether there are bubbles on temporary slides through microscope images.

[0045] How to eliminate the interference of normal cell structures such as cell wall, cell nucleus, vacuole, etc. in temporary slides on bubble detection, and use the morphological characteristics of bubbles to detect them.

[0046] To solve the problems in the background technology, the embodiments of the present invention provide the following technical solutions.

[0047] See Figure 1 and Figure 2 , Figure 1 The present invention provides a temporary slide bubble detection method for physical, chemical and biological experiment assessment, which comprises the following steps:

[0048] S100, acquiring a color microscope image of a temporary slide, and converting the color microscope image into a smooth grayscale image;

[0049] S200, determining a gradient transformation image based on the grayscale gradient of the smooth grayscale image, and determining a distance transformation image based on the distance from each pixel in the smooth grayscale image to the nearest background point;

[0050] S300, performing size transformation on the gradient transformed image and the distance transformed image respectively to form an enhanced image set including a plurality of enhanced image pairs, performing logical operations on corresponding pixels of each enhanced image pair respectively to obtain a mixed heat map set; wherein each enhanced image pair has a different size;

[0051] S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set;

[0052] S500 , removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image.

[0053] In the embodiment provided by the present invention, by using grayscale gradient change, distance transformation, contour fitting, contour deduplication and other technologies to identify bubbles in the microscope image of the temporary slide, the production quality of the temporary slide is intelligently judged, thereby achieving the purpose of intelligent scoring of physical, chemical and biological experiments such as "making and observing temporary slides of plant cells".

[0054] The present invention has broad application prospects in the fields of physics, chemistry and biology experiment teaching and assessment, improves the efficiency of temporary slide bubble detection, reduces the dependence on manual labor in the physics, chemistry and biology experiment assessment process, reduces the workload of teachers, and is expected to promote the innovation and development of physics, chemistry and biology experiment teaching and assessment methods.

[0055] In some embodiments, in S100, acquiring a color microscope image of the temporary slide and converting the color microscope image into a smooth grayscale image includes:

[0056] S110, inputting the color microscope image I of the temporary slide rgb , convert the color microscope image into a grayscale image I gray ;

[0057] S120, using median filtering to blur the edges of the grayscale image to obtain a smooth grayscale image I gray ′.

[0058] Specifically, the grayscale image is blurred by the mean filter with a filter kernel size of 20 to obtain a smooth grayscale image I gray ′, reducing the influence of the edges of cell structures such as cell wall, nucleus, and vacuole.

[0059] In some embodiments, in S200, determining the gradient transformed image based on the grayscale gradient of the smoothed grayscale image includes:

[0060] S211, calculate the smooth grayscale image I gray ′Gray gradient g in the x-axis direction x and the grayscale gradient g in the y-axis direction y ;

[0061] Specifically, the smooth grayscale image I is calculated by the numpy.gradient function. gray ′Gray gradient g in the x-axis direction x and the grayscale gradient g in the y-axis direction y ;

[0062] S212, the gray gradient g x and gray gradient g y Superimpose to obtain the gradient image I of the temporary mount grad ;

[0063] Specifically, the grayscale gradient g is converted to x and gray gradient g y Superimpose to obtain the gradient image I of the temporary mount grad , further filtering the cell structure and retaining the bubble edge;

[0064] S213, gradient image I grad Perform dynamic threshold segmentation to obtain binary image I bin1 ;

[0065] Specifically, for the gradient image I grad Perform dynamic threshold segmentation to obtain binary image I bin1 ;

[0066] S214, using mean filtering to process the binary image I bin1 Perform edge blur and perform edge blur on the binary image I bin1 Perform bitwise inversion operation to obtain the gradient transformed image I grad′ .

[0067] Specifically, the binary image I is filtered using a mean filter with a filter kernel size of 20. bin1 Perform edge blur and perform edge blur on the binary image I bin1 Perform bitwise inversion operation to obtain the gradient transformed image I grad′ .

[0068] In some embodiments, in S200, determining the distance transformation image based on the distance from each pixel in the smoothed grayscale image to the nearest background point includes:

[0069] S221, smoothing grayscale image I gray ' Perform binarization processing to obtain a binary image I bin2 , and for the binary image I bin2 Perform opening operation;

[0070] Specifically, set the binarization threshold to smooth the grayscale image I gray ' Perform binarization processing to obtain a binary image I bin2 , and for the binary image I bin2 Perform opening operation;

[0071] S222, calculate the binary image I bin2 The distance from each pixel to the nearest background point is used to generate the initial distance transformation image I based on the distance from each pixel to the nearest background point. distance ;

[0072] Specifically, the binary image I is calculated by the cv2.distance Transform function bin2The distance from each pixel to the nearest background point is used to obtain the initial distance transformation image I distance ;

[0073] S223, transform the initial distance image I distance Perform dynamic threshold segmentation and perform bitwise inversion operation to obtain the distance transformation image I distance′ .

[0074] In some embodiments, in S300, the step of performing size transformation on the gradient transformed image and the distance transformed image to form an enhanced image set including multiple enhanced image pairs, and performing logical operations on corresponding pixels of each enhanced image pair to obtain a mixed heat map set includes:

[0075] S310, transforming the gradient image I grad′ and distance transformed image I distance′ As a set of enhanced image pairs of original size, the enhanced image pairs are respectively scaled horizontally, vertically, and overall to obtain three sets of size-transformed enhanced image pairs, and the three sets of size-transformed enhanced image pairs and the enhanced image pairs of original size are combined to form an enhanced image set I;

[0076] Specifically, in the microscope image, the morphological characteristics of the bubble are a circle or an ellipse with a black edge and a bright center. According to the morphological characteristics of the bubble, the horizontal scaling factor of the image is set to α and the vertical scaling factor is set to β, respectively. grad′ and distance transformed image I distance′ Perform three size transformations: horizontal scaling, vertical scaling, and overall scaling, and form an enhanced image set I containing four sets of enhanced image pairs of different sizes together with the original size image.

[0077] S320 , performing a bitwise OR operation on each enhanced image pair in the enhanced image set I to obtain a mixed heat map set H, where the mixed heat map set includes multiple mixed heat maps.

[0078] Where H = {h1,h2,h3,h4};

[0079] h i It is a mixed heat map. The calculation formula of the mixed heat map is:

[0080] In some embodiments, in S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set includes:

[0081] S410, after performing erosion, expansion, opening, and closing operations on each mixed heat map in the mixed heat map set H, performing Hough circle detection on each mixed heat map, recording all detected Hough circles, and obtaining a circular edge set;

[0082] Specifically, each mixed heat map in the mixed heat map set H is subjected to image morphological operations such as corrosion, expansion, opening, and closing to remove the influence of noise. Then, the minimum radius is set to 10, the maximum radius is set to 120, the number of votes is set to 70, and the minimum spacing is set to 70. Hough circle detection is performed on each mixed heat map in the mixed heat map set H, and all detected Hough circles are recorded to obtain the circular edge set C = {c1, c2, ..., c n}, where c i =(x i ,y i ,r i ), (x i ,y i ) is the coordinate of the circle center, r i is the radius.

[0083] S420 , performing size reduction on each circular edge in the circular edge set C to obtain a candidate bubble edge set B, where the candidate bubble edge set B includes a plurality of edges.

[0084] Specifically, for a circular edge c in the circular edge set C i , the coordinates of the center of the ellipse obtained after size reduction (x i ′,y i ′) and the length of the major and minor axes They are:

[0085] (x i ′,y i ′)=(x i / α,y i / β);

[0086]

[0087] Resize each circular edge in the circular edge set C to obtain the candidate bubble edge set B = {b1, b2, ..., b n},in

[0088] In some embodiments, in S500, removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image, includes:

[0089] S510 , for each pair of edges in the candidate bubble edge set B, calculating the overlap of the areas within the two edges;

[0090] Specifically, the candidate bubble edge set B is subjected to edge deduplication based on the degree of overlap. For each pair of edges b in the candidate bubble edge set B, i and b j , calculate the overlap of the areas within the two edges Overlap ij , the calculation formula is:

[0091]

[0092] Among them, Area(b i ) means b i Area(b j ) means b j Area(b i )∩Area(b j ) represents the area where two contours intersect;

[0093] S520, determining whether the overlap of the areas within the two edges is greater than an overlap threshold; if so, retaining the edge with the larger area; otherwise, retaining both edges to obtain a deduplicated bubble edge set B′;

[0094] S530, filling all edges in the bubble edge set B′ to obtain the bubble segmentation image I mask .

[0095] Specifically, let the overlap threshold be ε. When the overlap between two edges is greater than ε, only the edge with the larger area is retained to obtain the deduplicated bubble edge set B′. Then, fill all the edges in the bubble edge set B′ to obtain the bubble segmentation image I mask .

[0096] It can be seen from the above embodiments that the present invention has the following advantages over the prior art:

[0097] 1. The present invention obtains a hybrid thermal map by combining the gradient grayscale image corresponding to the microscope image of the temporary slide with the distance transformation image to reduce the influence of cell structure on bubble detection and extract the edge contour information of the retained bubble;

[0098] 2. The present invention utilizes the morphological characteristics of bubbles to design different scale transformations for the mixed heat map and obtains multiple approximate edge contours of the bubbles through Hough circle fitting;

[0099] 3. The present invention filters the overlapping edge contours by calculating the overlap of the edge contours, retains the edge contour that best covers the area where the largest bubble is located, and fills the edge contours to obtain a bubble segmentation image, thereby improving the accuracy of bubble detection.

[0100] and Figure 1 Corresponding to the method, refer to Figure 3 The embodiment of the present invention provides a temporary slide bubble detection system for physical, chemical and biological experiment assessment, comprising:

[0101] at least one processor;

[0102] at least one memory for storing at least one program;

[0103] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0104] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0105] Those skilled in the art will appreciate that all or some of the methods disclosed above, the system can be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data) and is volatile and non-volatile, removable and non-removable media. Computer storage media includes but is not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0106] The above is a specific description of the preferred implementation of the present disclosure, but the present disclosure is not limited to the above-mentioned implementation mode. Technical personnel familiar with the art can also make various equivalent modifications or substitutions without violating the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A temporary slide bubble detection method for physical, chemical and biological experiment assessment, characterized in that: The method comprises the following steps: S100, acquiring a color microscope image of a temporary slide, and converting the color microscope image into a smooth grayscale image; S200, determining a gradient transformation image based on the grayscale gradient of the smooth grayscale image, and determining a distance transformation image based on the distance from each pixel in the smooth grayscale image to the nearest background point; S300, performing size transformation on the gradient transformed image and the distance transformed image respectively to form an enhanced image set including a plurality of enhanced image pairs, performing logical operations on corresponding pixels of each enhanced image pair respectively to obtain a mixed heat map set; wherein each enhanced image pair has a different size; S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set; S500 , removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image.

2. The method according to claim 1, characterized in that In S100, the step of acquiring a color microscope image of a temporary slide and converting the color microscope image into a smooth grayscale image includes: S110, inputting the color microscope image I of the temporary slide rgb , convert the color microscope image into a grayscale image I gray ; S120, using median filtering to blur the edges of the grayscale image to obtain a smooth grayscale image I gray ′.

3. The method according to claim 2, characterized in that In S200, determining a gradient transformed image based on the grayscale gradient of the smoothed grayscale image includes: S211, calculate the smooth grayscale image I gray ′Gray gradient g in the x-axis direction x and the grayscale gradient g in the y-axis direction y ; S212, the gray gradient g x and gray gradient g y Superimpose to obtain the gradient image I of the temporary mount grad ; S213, gradient image I grad Perform dynamic threshold segmentation to obtain binary image I bin1 ; S214, using mean filtering to process the binary image I bin1 Perform edge blur and perform edge blur on the binary image I bin1 Perform bitwise inversion operation to obtain the gradient transformed image I grad′ .

4. The method according to claim 3, characterized in that In S200, determining a distance transformation image based on the distance from each pixel in the smoothed grayscale image to the nearest background point includes: S221, smoothing grayscale image I gray ' Perform binarization processing to obtain a binary image I bin2 , and for the binary image I bin2 Perform opening operation; S222, calculate the binary image I bin2 The distance from each pixel to the nearest background point is used to generate the initial distance transformation image I based on the distance from each pixel to the nearest background point. distance ; S223, transform the initial distance image I distance Perform dynamic threshold segmentation and perform bitwise inversion operation to obtain the distance transformation image I distance′ .

5. The method according to claim 4, characterized in that In S300, the gradient transformation image and the distance transformation image are resized to form an enhanced image set including multiple enhanced image pairs, and logical operations are performed on corresponding pixels of each enhanced image pair to obtain a mixed heat map set, including: S310, transforming the gradient image I grad′ and distance transformed image I distance′ As a set of enhanced image pairs of original size, the enhanced image pairs are respectively scaled horizontally, vertically, and overall to obtain three sets of size-transformed enhanced image pairs, and the three sets of size-transformed enhanced image pairs and the enhanced image pairs of original size are combined to form an enhanced image set I; S320 , performing a bitwise OR operation on each enhanced image pair in the enhanced image set I to obtain a mixed heat map set H, where the mixed heat map set includes multiple mixed heat maps.

6. The method according to claim 5, characterized in that In S400, performing image morphological operations, Hough circle detection, and shape restoration on the mixed heat map set to obtain a candidate bubble edge set includes: S410, after performing erosion, expansion, opening, and closing operations on each mixed heat map in the mixed heat map set H, performing Hough circle detection on each mixed heat map, recording all detected Hough circles, and obtaining a circular edge set; S420 , performing size reduction on each circular edge in the circular edge set C to obtain a candidate bubble edge set B, where the candidate bubble edge set B includes a plurality of edges.

7. The method according to claim 6, characterized in that In S500, the step of removing duplicates from the candidate bubble edge set to obtain a bubble edge set, and filling the bubble edge set to obtain a bubble segmentation image includes: S510 , for each pair of edges in the candidate bubble edge set B, calculating the overlap of the areas within the two edges; S520, determining whether the overlap of the areas within the two edges is greater than an overlap threshold; if so, retaining the edge with the larger area; otherwise, retaining both edges to obtain a deduplicated bubble edge set B′; S530, filling all edges in the bubble edge set B′ to obtain the bubble segmentation image I mask .

8. A temporary slide bubble detection system for physical, chemical and biological experiment assessment, characterized by: The system comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

Images