CN114821071A - Method, device and equipment for extracting adhesion bubbles from dynamic ice image - Google Patents

Abstract

The embodiments of the present application disclose a method, a device and a device for extracting adhesion bubbles from a dynamic ice image, which relate to the field of image processing. The method includes: obtaining a distance image according to the minimum distance between the bubble pixels in the preprocessed binary image and the background; performing histogram equalization on the distance image to obtain an adjusted image; and obtaining an image matrix from the adjusted image A numerical value that satisfies a preset condition, and marks the point where the numerical value meeting the preset condition is located in the adjustment image to obtain a marked image; according to the marked point in the marked image, the preprocessing binary value is The image is subjected to watershed transformation to obtain a segmented image of adhering bubbles. The above method can effectively solve the problem of poor effect of dividing the adhering air bubbles in the prior art when extracting adhering air bubbles from a dynamic ice image.

Description

A method, device and device for extracting adhesive bubbles from dynamic ice images

technical field

The present application relates to the technical field of image processing, and more particularly, to a method, device and device for extracting adhesion bubbles from a dynamic ice image.

Background technique

When the aircraft passes through the clouds, the supercooled water droplets may undergo a phase change and cause icing after hitting the airframe. Icing will change the shape of the aircraft and the flow field around it, destroy the aerodynamic performance, reduce the maneuverability and stability, threaten the flight safety, and lead to air accidents in severe cases. The essence of aircraft icing is the dynamic icing process of supercooled water droplets. The supercooled water hits the low-temperature base and freezes, and the ice formed with non-uniformly distributed air bubbles is dynamic ice. The bubbles in the dynamic ice are the fundamental factors that determine the physical properties of the dynamic ice. By analyzing the characteristics of bubble content, distribution, and pore size in the microstructure of dynamic ice, and studying the physical properties of dynamic ice, scientific and effective ice protection measures can be established to ensure the safety of aircraft flight.

To study the characteristics of bubble content, distribution, and pore size in dynamic ice microstructure, it is necessary to obtain bubble images in dynamic ice. However, there are sticky bubbles in dynamic ice. When extracting bubbles from dynamic ice images, it is difficult to extract sticky bubbles. At present, the watershed algorithm based on marker control can be used to segment the adhering bubbles or particles, and this method has a better segmentation effect when the bubbles or particles are of the same size. However, when the size of the adhering air bubbles in the dynamic ice varies greatly, it is difficult to mark the small air bubbles, so it is difficult to divide the adhering small air bubbles. In addition, when large air bubbles with a larger area than the adhering air bubbles exist in the vicinity of the adhering air bubbles in the dynamic ice, it is difficult to mark the adhering air bubbles, and thus it is difficult to segment the adhering air bubbles.

Therefore, in the prior art, when the sticking bubbles are extracted from the dynamic ice image, there is a problem that the effect of dividing the sticking bubbles is poor.

SUMMARY OF THE INVENTION

The inventor of the present application has found through long-term practice that the watershed algorithm based on marker control obtains a distance image according to the minimum distance from the bubble pixel point in the preprocessed binary image to the background, and then marks the distance image. Take marking the point where the local minimum value in the distance image is located as an example. The value in the distance matrix of the distance image is related to the size of the bubble in the distance image. The larger the bubble, the farther the minimum distance between the center of the bubble and the background. , after inversion, the smaller the value of the center part of the bubble in the distance matrix, the lower the brightness of the center of the large bubble in the distance image. When marking the local minimum value in the distance image, in the local area, the value of the central part of the large bubble is smaller than the value of the central part of the small bubble, so the central part of the small bubble will not be marked, and it is difficult to carry out the detection of the small bubbles. segmentation. Based on this, the present application proposes a method for extracting adhesion bubbles from a dynamic ice image. According to the minimum distance between the bubble pixels in the preprocessed binary image and the background, a distance image is obtained; the histogram equalization is performed on the distance image. , adjust the value of the center part of each bubble in the distance matrix of the distance image to obtain an adjustment image; obtain the value that meets the preset condition from the image matrix of the adjustment image, and in the adjustment image Set the point where the numerical value of the condition is located to be marked to obtain a marked image, the marked image includes the marked points of the central part of all the bubbles, and according to the marked points in the marked image, perform watershed transformation on the preprocessed binary image to obtain Segmented image of sticky bubbles. In this way, it can effectively solve the problem of poor effect of dividing the adhering air bubbles in the prior art when extracting adhering air bubbles from a dynamic ice image.

In a first aspect, an embodiment of the present application provides a method for extracting adhesion bubbles from a dynamic ice image, the method comprising: S110. Obtain a distance image according to the minimum distance between the bubble pixels in the preprocessed binary image and the background; S120. Perform histogram equalization on the distance image to obtain an adjustment image; S130. Acquire a numerical value that satisfies a preset condition from an image matrix of the adjustment image, and quantify the value that meets the preset condition in the adjustment image Mark the point where the value of , and obtain a marked image; S140. Perform watershed transformation on the preprocessed binary image according to the marked point in the marked image to obtain a segmented image of the adhesion bubbles.

In a second aspect, an embodiment of the present application also provides a system for extracting adhesion bubbles from a dynamic ice image, the system includes a distance acquisition unit, which is configured to, according to the minimum distance from the bubble pixels in the preprocessed binary image to the background, obtaining a distance image; an adjustment unit for performing histogram equalization on the distance image to obtain an adjusted image; a marking unit for obtaining a numerical value that satisfies a preset condition from the image matrix of the adjusted image, and storing the value in the adjusted image In the adjustment image, the point where the value that meets the preset condition is located is marked to obtain a marked image; the watershed transformation unit is used to perform watershed transformation on the marked image according to the marked points in the marked image to obtain adhesion bubbles segmented image.

In a third aspect, embodiments of the present application further provide an electronic device, the electronic device includes one or more processors; a memory; a screen for displaying the images in the foregoing method; one or more application programs, wherein the One or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the aforementioned methods.

To sum up, the present application has at least the following technical effects:

1. Taking the distance transformation of the preprocessed binary image and the inversion of the distance image as an example, the present application performs histogram equalization on the distance image to be marked, so that the center brightness of the large bubbles in the distance image becomes higher, and the small bubbles in the distance image become higher. The brightness of the center of the distance matrix becomes lower, that is, the value of the center part of the large bubble in the distance matrix becomes larger, and the value of the center part of the small bubble becomes smaller. When marking the point where the local minimum value is located, it is avoided due to different bubble sizes. As a result, the numerical value of the central part of the bubble in the local area is different, and the numerical value of the central part of the small bubble is not recognized as a local minimum value, so that the point where the central part of the small bubble is located cannot be marked. Using the method for extracting adhesion bubbles from a dynamic ice image provided by the present application, when the size of the adhesion bubbles in the dynamic ice differs greatly, and when there are larger bubbles with a larger area than the adhesion bubbles near the adhesion bubbles in the dynamic ice, both The point where the center part of the stuck small bubbles is located can be marked, so that the effect of dividing the stuck bubbles is better.

2. The present application directly extracts bubbles from the original image through a preset neural network model, extracts the first intermediate image containing complete large bubbles, and then divides the original image, and uses the preset neural network model to extract from the second segmented image block. Extract the bubbles to obtain a second intermediate image containing complete small bubbles, and perform the OR operation on the first intermediate image and the second intermediate image to obtain a preprocessed binary image that contains both complete large bubbles and complete small bubbles, avoiding dynamic changes. The texture in the ice image is identified as bubbles, the bubble boundary is not clearly identified, a large number of small bubbles will be missed, and there are holes in the extracted large bubbles. The effect of sticking bubbles establishes the foundation.

Therefore, the solution provided by the present application can effectively solve the problem of poor effect of dividing the adhering air bubbles in the prior art when extracting adhering air bubbles from a dynamic ice image.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

1 shows a schematic flowchart of the method for extracting adhesion bubbles from a dynamic ice image provided in Embodiment 1 of the present application;

Fig. 2 shows the micrograph of the sticking bubbles in the dynamic ice provided in Example 1 of the present application;

FIG. 3 shows the original image of the dynamic ice microstructure provided in Example 1 of the present application;

Fig. 4 shows the distance image obtained by performing distance transformation and inversion of the preprocessed binary image provided in Embodiment 1 of the present application;

FIG. 5 shows an adjusted image obtained by performing histogram equalization on the distance image provided by Embodiment 1 of the present application;

6 shows a marked image obtained by marking the point where the local minimum value is located in the adjustment image provided by Embodiment 1 of the present application;

FIG. 7 shows a marked image obtained without performing histogram equalization provided by Embodiment 1 of the present application;

FIG. 8 shows a segmented image of the adhesion bubble obtained by using the histogram equalization provided in Example 1 of the present application;

FIG. 9 shows a segmented image of the adhesion bubble obtained without performing histogram equalization provided in Example 1 of the present application;

10 shows a block diagram of a system for extracting adhesion bubbles from a dynamic ice image provided in Embodiment 2 of the present application;

FIG. 11 shows a block diagram of an electronic device provided in Embodiment 3 of the present application for executing the method for extracting adhesive bubbles from a dynamic ice image according to the embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

At present, the watershed algorithm based on marker control can be used to segment the adhering bubbles or particles, and this method has a better segmentation effect when the bubbles or particles are of the same size. However, when the size of the adhering air bubbles in the dynamic ice varies greatly, it is difficult to mark the small air bubbles, so it is difficult to divide the adhering small air bubbles. In addition, when large air bubbles with a larger area than the adhering air bubbles exist in the vicinity of the adhering air bubbles in the dynamic ice, it is difficult to mark the adhering air bubbles, and thus it is difficult to segment the adhering air bubbles.

Therefore, in order to solve the above-mentioned defects, an embodiment of the present application provides a method for extracting adhesion bubbles from a dynamic ice image. The method includes: obtaining a distance image according to the minimum distance between the bubble pixels in the preprocessed binary image and the background; Histogram equalization is performed on the distance image, and the value of the center part of each bubble in the distance matrix of the distance image is adjusted to obtain an adjusted image; the value that meets the preset conditions is obtained from the image matrix of the adjusted image, and is stored in the adjusted image. Mark the point where the value that meets the preset condition is located in the adjustment image to obtain a marked image, and the marked image includes the marked points of the central part of all the bubbles. According to the marked points in the marked image, the preset The binary image is processed to perform watershed transformation to obtain a segmented image of adhering bubbles. In this way, it can effectively solve the problem of poor effect of dividing the adhering air bubbles in the prior art when extracting adhering air bubbles from a dynamic ice image.

The method for extracting adhesive bubbles from dynamic ice images involved in the present application will be introduced below.

Example 1

Please refer to FIG. 1 and FIG. 2 , FIG. 1 is a schematic flowchart of a method for extracting adhesion bubbles from a dynamic ice image provided in Example 1 of the present application, and FIG. 2 is a microscopic schematic diagram of adhesion bubbles in dynamic ice. In this embodiment, the method for extracting adhesion bubbles from a dynamic ice image may include the following steps:

Step S110: Obtain a distance image according to the minimum distance from the bubble pixel point in the preprocessed binary image to the background.

As shown in Fig. 3, the original image of the dynamic ice microstructure. By preprocessing the original image, a preprocessed binary image can be obtained.

In Figure 3, the box above shows the situation where the size of the adhesion bubbles in the dynamic ice is quite different. Specifically, three bubbles with different sizes are adhered together. Among the three adhesion bubbles, the uppermost bubble is the largest. , the bubble in the middle is the second largest, and the bubble at the bottom is the smallest.

In Fig. 3, the lower box shows the situation where there are larger bubbles near the sticking bubbles in the dynamic ice, specifically, three bubbles are sticking together, and the diameter of the large bubbles existing nearby is larger than the three sticking Any one of the bubbles, in this case, the size of the three sticking bubbles may be the same or different. For the convenience of description, FIG. 3 shows the situation where the three sticking bubbles are the same size.

As an optional implementation manner, the step S110 further includes a sub-step S111.

Sub-step S111: Perform distance transformation on the preprocessed binary image, and obtain the distance image according to the minimum distance between the bubble pixels in the preprocessed binary image and the background.

In an exemplary embodiment, the distance transformation may be Euclidean distance transformation, Manhattan distance transformation, or other distance transformation methods.

Among them, the larger the bubble in the preprocessed binary image, the greater the minimum distance from the pixel in the center of the bubble to the background, in the distance matrix of the distance image, the larger the value in the center of the bubble, the greater the value of the bubble in the distance image. The center brightness is higher.

As another optional implementation manner, the step S110 further includes a sub-step S112.

Sub-step S112: Perform distance transformation on the preprocessed binary image and invert, and obtain the distance image according to the inverse of the minimum distance between the bubble pixels in the preprocessed binary image and the background.

Among them, the larger the bubble in the preprocessed binary image, the smaller the inverse of the minimum distance between the pixel in the center of the bubble and the background, and in the distance matrix of the distance image, the smaller the value in the center of the bubble, in the distance image The center of the bubble is less bright. As shown in Fig. 4, Fig. 4 is a distance image obtained by performing distance transformation on the preprocessed binary image and inverting it.

It can be seen from Figure 4 that among the three sticking bubbles in the upper frame, the central part of the uppermost bubble has the lowest brightness, the central part of the middle bubble has the second lowest brightness, and the central part of the lowermost bubble has the highest brightness , that is, in the distance matrix of the distance image, the center part of the topmost bubble has the smallest value, the center part of the middle bubble has the second smallest value, and the center part of the bottommost bubble has the largest value.

It can be seen from Figure 4 that the brightness of the central part of the three sticking bubbles in the lower box and the larger bubbles existing nearby is the same and higher than that of the larger bubbles existing nearby. The brightness of , that is, in the distance matrix of the distance image, the value of the central part of the three sticking bubbles is the same and higher than the value of the central part of the larger bubble that exists nearby.

In this embodiment of the present application, the negation may also be performed after step S120.

Step S120: Perform histogram equalization on the range image to obtain an adjusted image.

Taking the preprocessed binary image to distance transform and inversion to obtain the distance image as an example, the histogram equalization is performed on the distance image in this case, so that the center brightness of large bubbles in the distance image becomes higher, and the small bubbles in the distance image are brighter. The brightness of the center of the distance matrix becomes lower, that is, the value of the center part of the large bubble in the distance matrix becomes larger, and the value of the center part of the small bubble becomes smaller, so as to obtain the adjusted image. As shown in FIG. 5 , FIG. 5 is an adjusted image obtained by performing histogram equalization on the distance image.

As can be seen from Figure 5, among the three sticking bubbles in the box above, the central parts of the three sticking bubbles have the same brightness, that is, in the image matrix of the adjusted image, the central parts of the three sticking bubbles have the same value big.

It can be seen from Figure 5 that among the three sticking bubbles in the lower box and the larger bubbles existing nearby, the brightness of the central part of the three sticking bubbles is as high as the brightness of the central part of the larger bubble existing nearby, and also That is, in the image matrix of the adjusted image, the value of the central part of the three stuck bubbles is as large as the value of the central part of the larger bubble that exists nearby.

Step S130: Acquire a numerical value that satisfies a preset condition from the image matrix of the adjustment image, and mark the point where the numerical value meeting the preset condition is located in the adjustment image to obtain a marked image.

As an optional implementation manner, if the step S110 includes the sub-step S111, and the preset condition is a local maximum value, the step S130 includes the sub-step S131.

Sub-step S131: Obtain the local maximum value from the image matrix of the adjustment image, and mark the point where the local maximum value is located in the adjustment image to obtain the marked image.

The local maximum value may be: in the image matrix of the adjusted image, the maximum value of the value in the local area. Wherein, the local area can be the area that just covers the largest bubble in the adjusted image, such as the box shown in Figure 5, or it can be a slightly larger area than the area that just covers the largest bubble in the adjusted image, This application does not limit this.

Iteratively calculate the local area in the image matrix of the adjusted image, and obtain the local maxima during each iteration calculation.

After the adjustment image is obtained by performing histogram equalization on the distance image, the brightness of the central part of the bubble in the local area of the adjusted image is consistent, and the value of the central part of the bubble in the local area of the image matrix of the adjusted image is consistent. Therefore, each The values of the central part of each bubble are the maximum values in the local area, and the point where the central part of each bubble is located can be marked.

If the histogram equalization is not performed, the local maximum value is directly obtained from the distance matrix of the distance image obtained by the distance transformation of the preprocessed binary image, and the point where the local maximum value is located is marked in the distance image. Since the brightness of the central part of the bubble in the local area of the distance image is inconsistent, the value of the central part of the bubble in the local area of the distance matrix of the distance image is also inconsistent. Therefore, only the bubble with the largest value in the central part can be marked. Bubbles whose values in the central part are not the largest are omitted.

As another optional implementation manner, if the step S110 includes the sub-step S112, and the preset condition is a local minimum value, the step S130 includes the sub-step S132.

Sub-step S132: Obtain the local minimum value from the image matrix of the adjusted image, and mark the point where the local minimum value is located in the adjusted image to obtain the marked image.

The local minima may be: in the image matrix of the adjusted image, the minimum value of the values in the local area. Wherein, for the local area and the content of obtaining the local minimum value, reference may be made to the local area and the content of obtaining the local maximum value in sub-step S131, which will not be repeated in this application.

After the adjustment image is obtained by performing histogram equalization on the distance image, the brightness of the central part of the bubble in the local area of the adjusted image is consistent, and the value of the central part of the bubble in the local area of the image matrix of the adjusted image is consistent. Therefore, each The values of the central part of each bubble are the minimum values in the local area, and the point where the central part of each bubble is located can be marked.

As shown in FIG. 6 , FIG. 6 is a marked image obtained using the method of the present application.

It can be seen from FIG. 6 that, among the three sticking bubbles in the above box, the points where the central parts of the three sticking bubbles are located are marked.

As can be seen from Figure 6, among the three sticking bubbles in the lower box and the larger bubbles existing nearby, the point where the center part of the three sticking bubbles is located and the point where the center part of the larger bubble existing nearby are both marked out.

If the histogram equalization is not performed, the local minimum value is directly obtained from the distance matrix of the distance image as shown in Figure 4, and the point where the local minimum value is located is marked in the distance image. The brightness of the central part of the bubble in the area is inconsistent, and the value of the central part of the bubble in the local area of the distance matrix from the image is also inconsistent. Therefore, only the bubble with the smallest value in the central part can be marked, and the value in the central part is not. The smallest bubbles will be missed. If the histogram equalization is not performed, the resulting marked image is shown in Figure 7.

As can be seen from Figure 7, among the three sticking bubbles in the upper box, only the point where the center of the uppermost and largest bubble is located is marked, and the second largest bubble in the middle and the smallest bubble at the bottom are marked. The points where the center part is located are all omitted.

As can be seen from Figure 7, among the three sticking bubbles in the box below and the larger bubbles existing nearby, only the point where the center part of the larger bubble existing nearby is marked, and the center part of the three sticking bubbles is located points are missed.

Step S140: Perform watershed transformation on the preprocessed binary image according to the marked points in the marked image, to obtain a segmented image of the adhering bubbles.

As an optional implementation manner, if the step S110 includes the sub-step S111, the step S140 includes the sub-step S141.

Sub-step S141: Perform watershed transformation on the preprocessed binary image according to the marked points in the marked image to obtain a watershed segmentation line based on the marked points, and perform an OR operation on the watershed segmentation line and the preprocessed binary image , to obtain a segmented image of the sticking bubbles.

In the embodiment of the present application, since the point where the center of each bubble is located is marked, according to the marked point of each bubble, watershed transformation is performed on the preprocessed binary image, and the watershed dividing line of each bubble can be obtained, The adhering bubbles are segmented by ORing the watershed dividing line of each bubble with the preprocessed binary image.

As another optional implementation manner, if the step S110 includes the sub-step S112, the step S140 includes the sub-step S142.

Sub-step S142: According to the marked points in the marked image, perform watershed transformation on the preprocessed binary image to obtain a watershed segmentation line based on the marked points, invert the watershed segmentation line, and combine with the preprocessed binary image. The graph is ORed to obtain a segmented image of the adhering bubbles.

In the embodiment of the present application, since the point where the center of each bubble is located is marked, according to the marked point of each bubble, watershed transformation is performed on the preprocessed binary image, and the watershed dividing line of each bubble can be obtained, Invert the watershed dividing line of each bubble, and then perform OR operation with the preprocessed binary image to segment the adhering bubbles.

As shown in FIG. 8 , FIG. 8 is a segmented image of adhering bubbles obtained using the method of the present application.

It can be seen from Fig. 8 that, among the three adhesion bubbles in the box above, all three adhesion bubbles are divided.

It can be seen from Fig. 8 that among the three adhesion bubbles in the box below, all three adhesion bubbles are divided.

If the histogram equalization is not performed, the obtained segmented image of the adhering bubbles is shown in FIG. 9 .

As can be seen from Figure 9, among the three sticking bubbles in the upper box, since only the point where the center part of the uppermost bubble is located is marked, neither the center bubble nor the point where the center part of the lowermost bubble is located is not marked. Marked so that only the top bubble is split, the middle and bottom bubbles are not split and still stick together.

It can be seen from FIG. 9 that, among the three sticking bubbles in the box below, since the point where the central part of the three sticking bubbles is not marked, the three sticking bubbles are not divided and are still sticking together.

By performing histogram equalization on the distance image to be marked, the present application avoids that the value of the central part of the bubble in the local area is different due to the different size of the bubble, and does not recognize the value of the central part of the small bubble as satisfying the preset value condition, so that the point where the center part of the small bubble is located cannot be marked. Using the method for extracting adhesion bubbles from a dynamic ice image provided by the present application, when the size of the adhesion bubbles in the dynamic ice differs greatly, and when there are larger bubbles with a larger area than the adhesion bubbles near the adhesion bubbles in the dynamic ice, both The point where the center part of the stuck small bubbles is located can be marked, so that the effect of dividing the stuck bubbles is better.

In an exemplary embodiment, steps S101 to S104 are further included before the step S110.

Step S101 : extracting bubbles from the original image through a preset neural network model to obtain a first intermediate image.

In the embodiment of the present application, the original image of the dynamic ice may be a microscopic image, or an image obtained by capturing the dynamic ice with a mobile phone camera, and the original image may be a color image or a grayscale image.

As an optional implementation manner, if the size of the original image is equal to the preset size, a preset neural network model is used to extract bubbles from the original image to obtain the first intermediate image.

As another optional implementation manner, if the size of the original image is not equal to the preset size, the size of the original image is adjusted to the preset size, and the preset neural network model is used to adjust the size from The bubbles are extracted from the original image of the preset size to obtain a first extracted image, and the first extracted image is restored to the size of the original image to obtain the first intermediate image.

Wherein, if the size of the original image is smaller than the preset size, the size of the original image is enlarged to the preset size, and a preset neural network model is used to extract bubbles from the original image enlarged to the preset size to obtain the first extraction image, and reduce the first extracted image to the size of the original image to obtain a first intermediate image.

If the size of the original image is larger than the preset size, reducing the size of the original image to the preset size, and extracting bubbles from the original image reduced to the preset size through a preset neural network model to obtain a first extracted image, and enlarge the first extracted image to the size of the original image to obtain a first intermediate image.

As another optional implementation manner, if the size of the original image is smaller than the preset size, the bubbles are extracted from the original image through a preset neural network model to obtain the first intermediate image.

The preset size may be a size set according to computer resource constraints, such as 256*256 or 512*512.

The method of enlarging or reducing the original image may be an interpolation method, and the method of reducing the first extracted image to the size of the original image or enlarging the first extracted image to the size of the original image may also be an interpolation method.

By adjusting the original image to the preset size when the size of the original image is not equal to the preset size, it is avoided that the image recognition cannot be performed on the original image due to the limitation of computer resources, and the first extracted image is restored to the size of the original image, Avoid loss of accuracy of the first intermediate image due to resizing.

In this embodiment of the present application, the preset neural network model may be a U-net network model with an attention mechanism, an R2U-net model, or other neural network models, which are not limited in this application.

The present application extracts bubbles from dynamic ice images through a preset neural network model, which avoids the problems of identifying textures in dynamic ice images as bubbles and unclear bubble boundary recognition, and provides a basis for better extraction of bubbles.

As an optional implementation manner, if the shape of the original image does not meet the input shape of the preset neural network model, fill the original image with the input shape of the preset neural network model, and then perform the steps S101.

，并通过所述预设神经网络模型分别从所述n个第二分割图像块中提取气泡，得到n个第二提取图像块。Step S102: Divide the original image into n second divided image blocks, and

, and extract bubbles from the n second segmented image blocks respectively through the preset neural network model to obtain n second extracted image blocks.

In this application, by dividing the dynamic ice image into second segmented image blocks of smaller size, and using a preset neural network model to extract bubbles from each of the second segmented image blocks, it is avoided that the size of the original image is too large and the size of the bubbles is too small to be missed. air bubbles to make the extracted air bubbles more effective.

Step S103: splicing the n second extracted image blocks into a second intermediate image according to the sequence of division positions, and the sequence of division positions is that when the original image is divided into the n second divided image blocks, The arrangement sequence of the position of each second divided image block in the original image.

In this embodiment of the present application, the step of acquiring the first intermediate image may be performed first, and then the step of acquiring the second intermediate image may be performed, or the step of acquiring the second intermediate image may be performed first, and then the step of acquiring the first intermediate image may be performed, The steps of acquiring the first intermediate image and the steps of acquiring the second intermediate image may also be performed simultaneously.

Step S104: Perform OR operation on the first intermediate image and the second intermediate image to obtain a preprocessed binary image.

Specifically, the small bubbles in the first intermediate image are omitted, and the large bubbles in the second intermediate image have holes. The first intermediate image and the second intermediate image are ORed to make up for the missing small bubbles and large bubbles. A preprocessed binary image is obtained, and the preprocessed binary image contains complete small bubbles and complete large bubbles.

As an optional implementation manner, an open operation is performed on the preprocessed binary image obtained in step S104 to obtain a preprocessed binary image after noise removal.

The present application directly extracts bubbles from the original image through a preset neural network model, extracts a first intermediate image containing complete large bubbles, then divides the original image, and extracts bubbles from the second segmented image block through a preset neural network model , obtain a second intermediate image containing complete small bubbles, and perform OR operation on the first intermediate image and the second intermediate image to obtain a preprocessed binary image containing both complete large bubbles and complete small bubbles, so that the preprocessed binary image The effect of the extracted bubbles is better, which lays a foundation for improving the effect of dividing and adhering bubbles.

Example 2

Please refer to FIG. 10 , which is a structural block diagram of a system 1000 for extracting adhesion bubbles from a dynamic ice image provided in Embodiment 2 of the present application. The system may include: a distance acquisition unit 1010 , an adjustment unit 1020 , a marking unit 1030 , and a watershed transformation unit 1040 .

The distance obtaining unit 1010 is configured to obtain a distance image according to the minimum distance from the bubble pixel point in the preprocessed binary image to the background.

The adjustment unit 1020 is configured to perform histogram equalization on the distance image to obtain an adjusted image.

The marking unit 1030 is configured to obtain a numerical value satisfying a preset condition from the image matrix of the adjustment image, and mark the point where the numerical value meeting the preset condition is located in the adjustment image to obtain a marked image.

The watershed transformation unit 1040 is configured to perform watershed transformation on the marked image according to the marked points in the marked image, so as to obtain a segmented image of adhering bubbles.

As an optional implementation manner, the distance obtaining unit 1010 includes a first distance obtaining sub-unit, configured to perform distance transformation on the preprocessed binary image, according to the distance from the bubble pixels in the preprocessed binary image to The minimum distance from the background to obtain the distance image.

The marking unit 1030 includes a first marking sub-unit, which is used to obtain a local maximum value from the image matrix of the adjustment image, and mark the point where the local maximum value is located in the adjustment image to obtain: the marked image.

The watershed transformation unit 1040 includes a first watershed transformation sub-unit, configured to perform watershed transformation on the preprocessed binary image according to the marked points in the marked image, to obtain a watershed segmentation line based on the marked points, and convert the The watershed dividing line is ORed with the preprocessed binary image to obtain the segmented image of the adhering bubbles.

As another optional implementation manner, the distance obtaining unit 1010 further includes a second distance obtaining subunit, configured to perform distance transformation and inversion on the preprocessed binary image, according to the preprocessed binary image The inverse of the minimum distance from the bubble pixel point to the background to obtain the distance image.

The marking unit 1030 further includes a second marking sub-unit, configured to obtain a local minimum value from the image matrix of the adjusted image, and mark the point where the local minimum value is located in the adjusted image, The marked image is obtained.

The watershed transformation unit 1040 includes a second watershed transformation subunit, which is configured to perform watershed transformation on the preprocessed binary image according to the marked points in the marked image, so as to obtain a watershed segmentation line based on the marked points, and convert the The watershed dividing line is inverted and ORed with the preprocessed binary image to obtain the segmented image of the adhering bubbles.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the system and unit described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically alone, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules.

Example 3

Please refer to FIG. 11 , which is a structural block diagram of an electronic device 1100 according to Embodiment 3 of the present application. The electronic device 1100 in the present application may include one or more of the following components: a memory 1110, a processor 1120, a screen 1130, and one or more application programs, wherein the one or more application programs may be stored in the memory 1110 and configured For execution by the one or more processors 1120, one or more programs are configured to perform the methods as described in the foregoing method embodiments.

The memory 1110 may include random access memory (Random Access Memory, RAM), or may include read-only memory (Read-Only Memory, ROM). Memory 1110 may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 1110 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a histogram equalization function, etc.), for implementing the following Instructions of various method embodiments, etc. The storage data area may also store data (such as image matrix data, etc.) created by the electronic device 1100 in use.

The processor 1120 may include one or more processing cores. The processor 1120 uses various interfaces and lines to connect various parts of the entire electronic device 1100, and executes by running or executing the instructions, programs, code sets or instruction sets stored in the memory 1110, and calling the data stored in the memory 1110. Various functions of the electronic device 1100 and processing data. Optionally, the processor 1120 may use at least one of digital signal processing (Digital Signal Processing, DSP), field-programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). It is implemented in a hardware form. The processor 1120 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a modem, and the like. Among them, the CPU mainly handles the operating system and application programs; the modem is used to handle wireless communication. It can be understood that, the above-mentioned modem may not be integrated into the processor 1120, and is implemented by a communication chip alone.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (9)

1. A method of extracting stuck bubbles from a dynamic ice image, the method comprising:

s110, obtaining a distance image according to the minimum distance from a bubble pixel point in the preprocessed binary image to the background;

s120, carrying out histogram equalization on the distance image to obtain an adjusted image;

s130, obtaining a numerical value meeting a preset condition from an image matrix of the adjusted image, and marking a point where the numerical value meeting the preset condition is located in the adjusted image to obtain a marked image;

s140, performing watershed transformation on the preprocessed binary image according to the mark points in the mark image to obtain a segmented image with adhered bubbles.

2. The method of extracting stuck bubbles from a dynamic ice image of claim 1, wherein the step S110 comprises:

performing distance transformation on the preprocessed binary image, and obtaining the distance image according to the minimum distance from a bubble pixel point in the preprocessed binary image to a background;

the preset condition is a local maximum, and the step S130 includes:

acquiring the local maximum value from the image matrix of the adjusted image, and marking the point of the local maximum value in the adjusted image to obtain a marked image;

the step S140 includes:

and carrying out watershed transformation on the preprocessed binary image according to the mark points in the marked image to obtain a watershed segmentation line based on the mark points, and carrying out OR operation on the watershed segmentation line and the preprocessed binary image to obtain a segmented image with adhered bubbles.

3. The method of extracting stuck bubbles from a dynamic ice image of claim 1, wherein the step S110 comprises:

performing distance transformation and negation on the preprocessed binary image, and obtaining the distance image according to the inverse number of the minimum distance from the bubble pixel point in the preprocessed binary image to the background;

the preset condition is a local minimum, and the step S130 includes:

acquiring the local minimum value from an image matrix of the adjusted image, and marking a point where the local minimum value is located in the adjusted image to obtain a marked image;

the step S140 includes:

and carrying out watershed transformation on the preprocessed binary image according to the mark points in the marked image to obtain a watershed segmentation line based on the mark points, negating the watershed segmentation line, and carrying out OR operation on the watershed segmentation line and the preprocessed binary image to obtain a segmented image adhered with bubbles.

4. The method of extracting stuck bubbles from a dynamic ice image of any of claims 2 to 3, wherein the distance transform is a Euclidean distance transform or a Manhattan distance transform.

5. The method of extracting stuck bubbles from a dynamic ice image of claim 1, further comprising, before the step S110:

extracting bubbles from the original image through a preset neural network model to obtain a first intermediate image;

the original image is divided into n second divided image blocks, an

Respectively extracting bubbles from the n second divided image blocks through the preset neural network model to obtain n second extracted image blocks;

splicing the n second extracted image blocks into a second intermediate image according to a segmentation position arrangement sequence, wherein the segmentation position arrangement sequence is an arrangement sequence of positions of each second segmentation image block in the original image when the original image is segmented into the n second segmentation image blocks;

and performing OR operation on the first intermediate image and the second intermediate image to obtain a preprocessed binary image.

6. A system for extracting stuck bubbles from a dynamic ice image, comprising:

the distance acquisition unit is used for obtaining a distance image according to the minimum distance from the bubble pixel point in the preprocessed binary image to the background;

the adjusting unit is used for carrying out histogram equalization on the distance image to obtain an adjusted image;

the marking unit is used for acquiring a numerical value meeting a preset condition from the image matrix of the adjusted image, and marking a point where the numerical value meeting the preset condition is located in the adjusted image to obtain a marked image;

and the watershed transformation unit is used for carrying out watershed transformation on the marked image according to the mark points in the marked image to obtain a segmented image adhered with bubbles.

7. The system for extracting adhered bubbles from a dynamic ice image according to claim 6, wherein the distance obtaining unit comprises a first distance obtaining subunit, configured to perform distance transformation on the preprocessed binary image, and obtain the distance image according to a minimum distance from a bubble pixel point in the preprocessed binary image to a background;

the marking unit comprises a first marking subunit, which is used for acquiring a local maximum value from an image matrix of the adjustment image and marking a point of the local maximum value in the adjustment image to obtain a marked image;

the watershed transform unit comprises a first watershed transform subunit, and is used for performing watershed transform on the preprocessed binary image according to the mark points in the marked image to obtain a watershed segmentation line based on the mark points, and performing OR operation on the watershed segmentation line and the preprocessed binary image to obtain a segmented image with adhered bubbles.

8. The system for extracting adhered bubbles from a dynamic ice image according to claim 6, wherein the distance obtaining unit further comprises a second distance obtaining subunit, configured to perform distance transformation and inversion on the preprocessed binary image, and obtain the distance image according to an inverse number of a minimum distance from a bubble pixel point in the preprocessed binary image to a background;

the marking unit further comprises a second marking subunit, configured to obtain a local minimum value from the image matrix of the adjustment image, and mark a point in the adjustment image where the local minimum value is located, to obtain the marked image;

the watershed transform unit comprises a second watershed transform subunit, and is used for performing watershed transform on the preprocessed binary image according to the mark points in the marked image to obtain a watershed segmentation line based on the mark points, negating the watershed segmentation line, and performing OR operation on the watershed segmentation line and the preprocessed binary image to obtain a segmented image adhered with bubbles.

9. An electronic device, comprising:

one or more processors;

a memory;

a screen for displaying an image in the method of any one of claims 1-5;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-5.

Images