Solder paste state detection method, device and equipment and readable storage medium

Abstract

The invention discloses a solder paste state detection method, device and equipment and a readable storage medium. The method comprises the steps that a to-be-detected solder paste area image and a corresponding template solder paste area image are acquired; the to-be-detected solder paste area image and the template solder paste area image are pseudo depth images; the to-be-detected solder paste area image and the template solder paste area image are converted into a Lab color space, and the similarity between the first color texture feature of the converted to-be-detected solder paste area image and the second color texture feature of the converted template solder paste area image is determined; and determining the state of the to-be-detected solder paste corresponding to the to-be-detected solder paste area image according to the similarity. According to the scheme, the solder paste state is determined based on the color change in the pseudo depth image, the height information participates in solder paste state detection on the basis of the two-dimensional image, the accuracy of solder paste state detection is improved, dependence on a depth camera is not needed, and therefore the solder paste state detection cost can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of solder paste detection, and in particular to a solder paste state detection method, device, equipment and readable storage medium. Background Art

[0002] On a PCB (printed circuit board), all components need to be fixed with solder paste, but the quality of existing solder paste varies greatly, so it is necessary to detect the solder paste status. Visual inspection is becoming the main means of solder paste status inspection due to its good inspection speed and no impact on the production line process.

[0003] Visual inspection combines image processing and other technologies to detect targets. Currently, the core image processing solutions can be divided into two methods: one is solder paste inspection based on no depth information, which is performed on a two-dimensional image. The solder paste area is usually used to evaluate the solder paste status. This method can only be judged on a two-dimensional image and cannot accurately determine the solder paste status. The other is solder paste inspection based on a depth camera, which evaluates the solder paste status from dimensions such as solder paste area and height. However, this method requires depth similarity, so the cost of solder paste status detection is relatively high.

[0004] In summary, how to reduce the cost of solder paste detection and improve the accuracy of solder paste detection is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a solder paste state detection method, device, equipment and readable storage medium, which are used to reduce the cost of solder paste detection and improve the accuracy of solder paste detection.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A solder paste state detection method comprises: obtaining a solder paste area image to be detected and a corresponding template solder paste area image; the solder paste area image to be detected and the template solder paste area image are pseudo depth images; converting the solder paste area image to be detected and the template solder paste area image into Lab color space, determining the similarity between a first color texture feature of the converted solder paste area image to be detected and a second color texture feature of the converted template solder paste area image; and determining the state of the solder paste to be detected corresponding to the solder paste area image to be detected according to the similarity.

[0008] Optionally, determining the similarity between the first color texture feature of the converted solder paste area image to be detected and the second color texture feature of the converted template solder paste area image includes: obtaining a first color matrix corresponding to at least one color channel of the converted solder paste area image to be detected in the Lab color space, and obtaining a second color matrix corresponding to the color channel of the converted template solder paste area image in the Lab color space; the color channel is an a channel and / or a b channel; obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix; determining a first color statistical feature based on the first color symbiosis matrix, and determining a second color statistical feature based on the second color symbiosis matrix; determining the similarity based on the first color statistical feature and the second color statistical feature.

[0009] Optionally, obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix includes: obtaining the first color symbiosis matrix corresponding to the first color matrix in the horizontal direction and the vertical direction respectively, and the second color symbiosis matrix corresponding to the second color matrix in the horizontal direction and the vertical direction respectively.

[0010] Optionally, a first color statistical feature is determined according to the first color symbiosis matrix, and a second color statistical feature is determined according to the second color symbiosis matrix, including: determining a first homogeneity, a first contrast and a first entropy in the horizontal direction and the vertical direction according to the first color symbiosis matrix corresponding to the horizontal direction and the vertical direction respectively; determining a second homogeneity, a second contrast and a second entropy in the horizontal direction and the vertical direction according to the second color symbiosis matrix corresponding to the horizontal direction and the vertical direction respectively.

[0011] Optionally, determining the similarity according to the first color statistical feature and the second color statistical feature includes: determining a first homogeneity average value, a first contrast average value, and a first entropy average value according to the first homogeneity, the first contrast, and the first entropy in the horizontal direction and the first homogeneity, the first contrast, and the first entropy in the vertical direction; determining a second homogeneity average value, a second contrast average value, and a second entropy average value according to the second homogeneity, the second contrast, and the second entropy in the horizontal direction and the second homogeneity, the second contrast, and the second entropy in the vertical direction; determining the similarity according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value, and the second entropy average value.

[0012] Optionally, determining the similarity according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value includes: determining the similarity by using a Euclidean distance calculation method according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value.

[0013] Optionally, before obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix, the method further includes: quantizing the first color matrix and the second color matrix.

[0014] A solder paste state detection device comprises: an acquisition module, used to acquire an image of a solder paste area to be detected and a corresponding image of a template solder paste area; the image of the solder paste area to be detected and the image of the template solder paste area are pseudo depth images; a conversion module, used to convert the image of the solder paste area to be detected and the image of the template solder paste area into a Lab color space, and determine the similarity between a first color texture feature of the converted image of the solder paste area to be detected and a second color texture feature of the converted image of the template solder paste area; and a determination module, used to determine the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected according to the similarity.

[0015] A solder paste state detection device comprises: a memory for storing a computer program; and a processor for implementing the steps of any one of the above-mentioned solder paste state detection methods when executing the computer program.

[0016] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the solder paste state detection method as described in any one of the above items are implemented.

[0017] The present application provides a solder paste status detection method, device, equipment and readable storage medium, wherein the method includes: obtaining an image of a solder paste area to be detected and a corresponding template solder paste area image; the image of the solder paste area to be detected and the image of the template solder paste area are pseudo-depth images; the image of the solder paste area to be detected and the image of the template solder paste area are converted into a Lab color space, and the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the template solder paste area is determined; and the status of the solder paste to be detected corresponding to the image of the solder paste area to be detected is determined according to the similarity.

[0018] The above technical solution disclosed in the present application obtains the image of the solder paste area to be detected and the corresponding template solder paste area image, and both the image of the solder paste area to be detected and the image of the template solder paste area are pseudo-depth images, and the solder paste area in the pseudo-depth image will have a certain color change according to the height change of the solder paste. Then, the acquired image of the solder paste area to be detected and the image of the template solder paste area are converted into the Lab color space to accurately obtain the color change in the image. After the image is converted into the Lab color space, the similarity between the first color texture feature of the converted solder paste area image to be detected and the second color texture feature of the converted template solder paste area image is determined, and the state of the corresponding solder paste to be detected is determined according to the similarity. The above process uses the pseudo-depth image as a carrier to determine the solder paste state based on the color change in the pseudo-depth image, and realizes the involvement of height information in the solder paste state detection on the basis of the two-dimensional image to improve the accuracy of the solder paste state detection, and there is no need to rely on the depth camera to realize the solder paste state detection, so the cost of solder paste state detection can be reduced.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a solder paste status detection method provided in an embodiment of the present application;

[0021] Figure 2 A flow chart for determining the similarity between a first color texture feature and a second color texture feature provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of a solder paste state detection device provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of a solder paste status detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] PCB is an important part of electronic products, and its quality directly affects the overall quality of electronic products. With the improvement of PCBA (Printed Circuit Board Assembly) production process standards, the requirements for the installation of components on PCB are getting higher and higher. On PCB, all components need to be fixed with solder paste, but the quality of existing solder paste is uneven, especially the defect of insufficient solder is difficult to identify.

[0025] At present, the detection of solder paste status is divided into the following types: (1) manual visual judgment; (2) instrument online power-on detection; (3) functional test method; (4) visual inspection method. The first three methods are basically only used for random inspection of some products due to factors such as low efficiency, while the visual inspection method is currently becoming the main detection method due to its good performance, detection speed, and no impact on the production line process.

[0026] In the visual inspection method, the target is detected by integrating image processing and other technologies. The core image processing scheme can basically be divided into two methods according to whether a depth camera is used: one is based on solder paste detection without depth information. Due to the limitation of the image acquisition equipment, the height information of the solder paste cannot be obtained, so it can only be detected on a two-dimensional image, and the solder paste area evaluation is usually used for judgment; the other is based on solder paste detection with height information, which is judged by evaluating the volume of the solder paste from multiple dimensions such as the area and height of the solder paste. The detection scheme based on no depth information can only be judged on a two-dimensional image due to the lack of depth information of the solder paste, and the judgment method is mostly based on the area and shape of the solder paste. The standard state of solder paste includes characteristics such as uniformity, roundness, appropriate size and no cracks, but these characteristics are difficult to obtain on a two-dimensional image. Therefore, the detection scheme based on no depth information cannot accurately determine the state of the solder paste. The detection solution based on depth camera can obtain the depth information of solder paste. In addition to determining the area of ​​solder paste, it can also determine whether the solder paste is full. In other words, increasing the determination of solder paste dimension can improve the accuracy of determination. However, due to the high cost of depth camera, the cost of solder paste detection is relatively high. In addition, the complexity of replacing the detection system of the original production line is also a shortcoming.

[0027] To this end, the present application provides a solder paste status detection method, device, equipment and readable storage medium for reducing the cost of solder paste detection and improving the accuracy of solder paste detection.

[0028] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] See also Figure 1 , which shows a flow chart of a solder paste state detection method provided in an embodiment of the present application. A solder paste state detection method provided in an embodiment of the present application may include:

[0030] S11: Acquire an image of the solder paste area to be detected and a corresponding image of the solder paste area of ​​the template; the image of the solder paste area to be detected and the image of the solder paste area of ​​the template are pseudo depth images.

[0031] It should be noted that the solder paste state detection system may include an image acquisition device and a processing device connected to the image acquisition device. The image acquisition device may be a two-dimensional camera, and the processing device may be a personal computer or the like.

[0032] Among them, the image acquisition device can acquire an image of a PCB containing solder paste to be detected (i.e., an image to be detected, wherein the image to be detected includes a solder paste area to be detected), and send the acquired image to be detected to a processing device. In addition, the image acquisition device can also pre-acquire a template image corresponding to the image to be detected, wherein the template image includes a standard solder paste area (or a template solder paste area) corresponding to the solder paste area to be detected, and can send the acquired template image to the processing device. Of course, the processing device can also obtain the corresponding template image in other ways.

[0033] Alternatively, the image acquisition device can acquire an image corresponding to the solder paste area to be detected on the PCB (i.e., the image of the solder paste area to be detected, the difference between the image of the solder paste area to be detected and the image to be detected is that the image of the solder paste area to be detected is an image formed by image acquisition of the solder paste area to be detected, and the image to be detected is an image formed by image acquisition of the PCB containing the solder paste to be detected), and send the image of the solder paste area to be detected to the processing device, and the image acquisition device can pre-acquire the corresponding template solder paste area image (the difference between the template solder paste area image and the template image is that the template solder paste area image is an image formed by image acquisition of the standard solder paste area, and the template image is an image formed by image acquisition of the PCB containing the standard solder paste) and send it to the processing device. Of course, the processing device can also obtain the template solder paste area image by other means.

[0034] Whether it is the image to be detected and the template image, or the image of the solder paste area to be detected and the image of the template solder paste area, these images are all pseudo-depth images. In the pseudo-depth image, the solder paste area will have a certain color change according to the change in the height of the solder paste, that is, in the pseudo-depth image, the solder paste area will display different colors in the two-dimensional image according to the height of the solder paste. Therefore, the change in the height of the solder paste can be reflected by the change in color in the pseudo-depth image, so as to accurately and effectively perform solder paste status detection based on this, and since this solder paste status detection method does not need to rely on hardware equipment such as depth cameras, it can reduce the cost of solder paste status detection, and there is no need to replace the detection system of the original production line. In other words, the embodiment of the present application is mainly based on the pseudo-depth image collected in PCB production. The solder paste area has a certain color change according to the change in the height of the solder paste. The solder paste state is determined according to the color change to achieve accurate, effective and low-cost detection of the solder paste state.

[0035] On the basis of the above, when the processing device obtains the image to be detected and the corresponding template image, the image to be detected and the corresponding template image can be identified, the solder paste area to be detected in the image to be detected and the template solder paste area in the corresponding template image can be obtained, and the image of the solder paste area to be detected and the corresponding template solder paste area image can be obtained accordingly, so as to determine the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected based on the corresponding template solder paste area image. When the processing device obtains the image of the solder paste area to be detected and the corresponding template solder paste area image, subsequent detection processing can be performed directly.

[0036] Acquiring an image of the solder paste area to be inspected and an image of the corresponding template solder paste area to participate in solder paste status detection can facilitate reducing the size of the processed image and the amount of data, and can facilitate reducing the impact of other background areas on solder paste status detection, thereby facilitating accurate, fast and efficient determination of the solder paste status.

[0037] S12: Convert the image of the solder paste area to be detected and the image of the template solder paste area to Lab color space, and determine the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the template solder paste area.

[0038] Considering that the images captured by the image acquisition device are generally in RGB (red, green, and blue) format, and due to the characteristics of the captured pseudo-depth image (the solder paste area displays different colors in the two-dimensional image according to the height of the solder paste), in order to reduce the interference of other factors such as brightness, the color change reflecting the change in solder paste height in the two-dimensional image is involved in the solder paste state detection. After obtaining the image of the solder paste area to be detected and the corresponding template solder paste area image, the image of the solder paste area to be detected and the template solder paste area image can be converted into the Lab color space to separate the brightness and color, so that the color information is richer and the color change can be focused, so as to improve the accuracy of solder paste state detection. Among them, the Lab color space is a color-opposition space with dimension L representing brightness, a and b representing color opposition dimensions, a representing the component from green to red, and b representing the component from blue to yellow.

[0039] After the image of the solder paste area to be detected and the corresponding template solder paste area image are converted into the Lab color space, the first color texture feature can be extracted from the image of the solder paste area to be detected converted into the Lab color space, and the second color texture feature can be extracted from the template solder paste area image converted into the Lab color space. The color texture feature is the texture feature generated by color change. Then, the similarity between the first color texture feature of the image of the solder paste area to be detected converted into the Lab color space and the second color texture feature of the template solder paste area image converted into the Lab color space is determined, so as to determine the similarity of the color texture features of the image of the solder paste area to be detected and the corresponding template solder paste area image without relying on hardware equipment such as depth cameras, thereby reducing the cost of solder paste status detection and improving the accuracy of solder paste status detection.

[0040] S13: Determine the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected according to the similarity.

[0041] After determining the similarity between the first color texture feature of the image of the solder paste area to be detected converted into the Lab color space and the second color texture feature of the image of the template solder paste area to be detected converted into the Lab color space, the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected can be determined according to the determined similarity. Among them, the greater the similarity, the more similar the state of the solder paste to be detected is to the state of the template solder paste, that is, the better the state of the solder paste to be detected is (that is, the better the uniformity, roundness, size, etc.); the smaller the similarity, the greater the difference between the state of the solder paste to be detected and the state of the template solder paste, that is, the worse the state of the solder paste to be detected is. Specifically, if the similarity is greater than the preset similarity (the preset similarity can be determined based on experience or in advance through experiments, etc.), it is determined that there is no abnormality in the state of the solder paste. If the similarity is not greater than the preset similarity, it is determined that there is an abnormality in the state of the solder paste.

[0042] Through the above, it is possible to implement solder paste status detection using pseudo-depth images as a carrier in PCB production, and specifically measure the similarity between the solder paste status and the solder paste status of the corresponding standard template, so as to infer whether the solder paste status is abnormal, thereby improving the accuracy of solder paste status detection. Moreover, since there is no need to rely on a depth camera, the cost of solder paste status detection can be reduced.

[0043] The above technical solution disclosed in the embodiment of the present application obtains the image of the solder paste area to be detected and the corresponding template solder paste area image, and both the image of the solder paste area to be detected and the image of the template solder paste area are pseudo-depth images, and the solder paste area in the pseudo-depth image will have a certain color change according to the height change of the solder paste. Then, the acquired image of the solder paste area to be detected and the image of the template solder paste area are converted to the Lab color space to accurately obtain the color change in the image. After the image is converted to the Lab color space, the similarity between the first color texture feature of the converted solder paste area image to be detected and the second color texture feature of the converted template solder paste area image is determined, and the state of the corresponding solder paste to be detected is determined according to the similarity. The above process uses the pseudo-depth image as a carrier to determine the solder paste state based on the color change in the pseudo-depth image, and realizes the involvement of height information in the solder paste state detection on the basis of the two-dimensional image to improve the accuracy of the solder paste state detection, and there is no need to rely on the depth camera to realize the solder paste state detection. Therefore, the cost of solder paste state detection can be reduced.

[0044] See also Figure 2 , which shows a flow chart of determining the similarity between a first color texture feature and a second color texture feature provided by an embodiment of the present application, a solder paste state detection method provided by an embodiment of the present application, determining the similarity between the first color texture feature of the converted solder paste area image to be detected and the second color texture feature of the converted template solder paste area image, may include:

[0045] Obtain a first color matrix corresponding to at least one color channel of the converted image of the solder paste area to be detected in the Lab color space, and obtain a second color matrix corresponding to the color channel of the converted image of the template solder paste area in the Lab color space; the color channel is a channel and / or b channel;

[0046] Obtain a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix;

[0047] Determine a first color statistical feature according to the first color symbiosis matrix, and determine a second color statistical feature according to the second color symbiosis matrix;

[0048] A similarity is determined based on the first color statistical feature and the second color statistical feature.

[0049] In an embodiment of the present application, when determining the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted template solder paste area image, the color co-occurrence matrix can be used to extract color statistical information to measure the color similarity, so as to achieve the similarity measurement of the solder paste area to be detected in the converted image of the solder paste area to be detected and the template solder paste area in the converted template solder paste area, thereby facilitating the determination of defects such as insufficient tin and improving the accuracy of solder paste status detection.

[0050] Specifically, the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the solder paste area of ​​the template may be determined in the following manner:

[0051] Step S101: Obtain a first color matrix corresponding to at least one color channel in the Lab color space of the image of the solder paste area to be detected converted into the Lab color space, wherein the element value at each position in the first color matrix is ​​the color value corresponding to the corresponding pixel point in the image of the solder paste area to be detected converted into the Lab color space in the aforementioned color channel. In addition, obtain a second color matrix corresponding to the template solder paste area image converted into the Lab color space in the aforementioned color channel, wherein the element value at each position in the second color matrix is ​​the color value corresponding to the corresponding pixel point in the template solder paste area image converted into the Lab color space in the aforementioned color channel.

[0052] Wherein, the color channel mentioned above includes at least one of the a channel and the b channel, and the color channel can be selected according to the specific situation. Specifically, when the color channel includes the a channel, the first color matrix corresponding to the a channel of the solder paste area image to be detected converted to the Lab color space can be obtained, and the second color matrix corresponding to the a channel of the template solder paste area image converted to the Lab color space can be obtained. When the color channel includes the b channel, the first color matrix corresponding to the b channel of the solder paste area image to be detected converted to the Lab color space can be obtained, and the second color matrix corresponding to the b channel of the template solder paste area image converted to the Lab color space can be obtained. When the color channel includes the a channel and the b channel, the first color matrix corresponding to the a channel and the first color matrix corresponding to the b channel of the solder paste area image to be detected converted to the Lab color space can be obtained, and the second color matrix corresponding to the a channel and the second color matrix corresponding to the b channel of the template solder paste area image converted to the Lab color space can be obtained.

[0053] When the color channels mentioned above include channel a and channel b, subsequent processing and similarity calculation are performed on channel a and channel b respectively to obtain the similarity corresponding to channel a and the similarity corresponding to channel b. Then, the state of the solder paste can be determined based on the similarities corresponding to the two channels.

[0054] Step S102: Calculate the statistical features according to the color co-occurrence matrix. Here, the co-occurrence matrix is ​​used as an extractor of color perception features. The color co-occurrence matrix is ​​shown in formula (1):

[0055]

[0056] Where d = (Δx, Δy) is the relative distance of (x, y), x and y are spatial coordinates, that is, the position in the color matrix, x is the horizontal position, y is the vertical position, I′ x,y Represents the (x,y) position in the color matrix, I′ x,y =i represents the color value at position (x,y) in the color matrix, I′ (x,y)+d Represents the position (x+△x,y+△y) in the color matrix, I′ (x,y)+d =j represents the color value at the position (x+△x, y+△y) in the color matrix, the values ​​of i and j range from 0 to the maximum color value, W and H represent the number of pixels in the horizontal and vertical directions of the image converted to the Lab color space (or the number of color values ​​in the horizontal and vertical directions of the color matrix).

[0057] Specifically, the first color symbiosis matrix M(X) corresponding to the first color matrix can be obtained based on the above formula (1), and the second color symbiosis matrix M(Y) corresponding to the second color matrix can be obtained based on the above formula (1).

[0058] Step S103: determining a first color statistical feature according to the first color co-occurrence matrix M(X), and determining a second color statistical feature according to the second color co-occurrence matrix M(Y).

[0059] Step S104: determining the similarity between the first color texture feature and the second color texture feature according to the first color statistical feature and the second color statistical feature.

[0060] Through the above method, the color co-occurrence matrix is ​​used to extract color statistical information to measure color similarity, thereby realizing similarity measurement of solder paste areas, that is, the perceived similarity of colors is calculated based on color transformation to better measure color changes, thereby better measuring the similarity of solder paste areas, and thus improving the accuracy of solder paste status detection.

[0061] A solder paste state detection method provided in an embodiment of the present application, which obtains a first color symbiosis matrix corresponding to a first color matrix and a second color symbiosis matrix corresponding to a second color matrix, may include:

[0062] A first color co-occurrence matrix corresponding to the first color matrix in the horizontal direction and the vertical direction, and a second color co-occurrence matrix corresponding to the second color matrix in the horizontal direction and the vertical direction are obtained.

[0063] In the embodiment of the present application, considering that the pins used for fixing the solder paste on the PCB are generally placed horizontally, in order to improve the accuracy of solder paste state detection, when obtaining the first color symbiosis matrix corresponding to the first color matrix and the second color symbiosis matrix corresponding to the second color matrix, the first color symbiosis matrix corresponding to the first color matrix in the horizontal direction and the first color symbiosis matrix corresponding to the vertical direction can be obtained, and the second color symbiosis matrix corresponding to the second color matrix in the horizontal direction and the second color symbiosis matrix corresponding to the second color matrix in the vertical direction can be obtained. That is, when the color symbiosis matrix is ​​obtained using formula (1), d = (Δx, Δy) can be specifically: d = (Δx, 0) and d = (0, Δy). Among them, when d = (Δx, 0), the color symbiosis matrix in the horizontal direction is obtained, and Δx can be specifically 1. Of course, the size of Δx can also be adjusted according to the situation of the color matrix. When d = (0, Δy), the color symbiosis matrix in the vertical direction is obtained, and Δy can be specifically 1. Of course, the size of Δx can also be adjusted according to the situation of the color matrix.

[0064] On the basis of the above, the first color statistical features are determined according to the first color symbiosis matrix, and the second color statistical features are determined according to the second color symbiosis matrix, that is: the first color statistical features corresponding to the horizontal and vertical directions are determined according to the first color symbiosis matrices corresponding to the horizontal and vertical directions respectively, and the second color symbiosis matrices corresponding to the horizontal and vertical directions are determined according to the second color symbiosis matrices corresponding to the horizontal and vertical directions respectively, and subsequently the similarity is determined based on the determined color statistical features.

[0065] By obtaining the color co-occurrence matrices corresponding to the horizontal and vertical directions respectively, not only can the color texture features of the solder paste area in the pseudo-depth image be reliably and accurately obtained to improve the accuracy of solder paste state detection, but also the amount of calculation can be reduced and the efficiency of solder paste state detection can be improved.

[0066] Of course, the color co-occurrence matrix in the 45° direction, 135° direction or other directions can also be obtained according to the distribution of solder paste on the pins used to fix components on the PCB, so as to more comprehensively obtain the color texture characteristics of the solder paste area in the pseudo-depth image.

[0067] A solder paste state detection method provided by an embodiment of the present application, determining a first color statistical feature according to a first color symbiosis matrix, and determining a second color statistical feature according to a second color symbiosis matrix, may include:

[0068] Determine the first homogeneity, the first contrast and the first entropy in the horizontal direction and the vertical direction according to the first color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively;

[0069] The second homogeneity, the second contrast and the second entropy in the horizontal direction and the vertical direction are correspondingly determined according to the second color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively.

[0070] Before using the solder paste state detection method provided in the embodiment of the present application to perform state detection, relevant personnel observed the solder pastes in various states on the PCB and the corresponding images of the solder paste area to be detected in the form of pseudo-depth images and found that: when there is a lack of tin, the corresponding image of the solder paste area to be detected is generally of a relatively uniform color tone, and the local color changes repeatedly; when the solder paste state is normal, the corresponding image of the solder paste area to be detected is a smooth transition from a certain color tone to another; when there is a lack of tin, the color tone changes from the top of the solder paste to the bottom of the solder paste in the corresponding image of the solder paste area to be detected are relatively drastic. For this reason, relevant personnel determined through theoretical analysis and comparative experiments that using homogeneity (H), contrast (C) and entropy (E) as color statistical features to participate in solder paste state detection can make the solder paste state detection have relatively good accuracy.

[0071] Therefore, in order to improve the accuracy of solder paste state detection, the processing device is set to specifically determine homogeneity, contrast and entropy when determining color statistical features, so as to utilize these color statistical features to participate in solder paste state detection, thereby improving the accuracy of solder paste state detection. That is, the present application combines three effective statistical features and effectively combines them in a heuristic way to improve the accuracy of solder paste state detection.

[0072] Among them, homogeneity reflects the color uniformity of the local area, that is, high homogeneity indicates that the color variation range is small and the color is relatively consistent. The calculation method of homogeneity is shown in formula (2):

[0073]

[0074] Among them, N k is the maximum color value in the color co-occurrence matrix.

[0075] Contrast refers to the sum of the differences between the current pixel color and the pixel colors of its surrounding neighborhood. It is calculated as shown in formula (3):

[0076]

[0077] Entropy is the randomness and disorder of color texture, which means color complexity. Its calculation method is shown in formula (4):

[0078]

[0079] Correspondingly, determining the first color statistical feature according to the first color symbiosis matrix and determining the second color statistical feature according to the second color symbiosis matrix can be specifically as follows: determining the first homogeneity, first contrast and first entropy in the horizontal direction according to the first color symbiosis matrix corresponding to the horizontal direction, determining the first homogeneity, first contrast and first entropy in the vertical direction according to the first color symbiosis matrix corresponding to the vertical direction, determining the second homogeneity, second contrast and second entropy in the horizontal direction according to the second color symbiosis matrix corresponding to the horizontal direction, and determining the second homogeneity, second contrast and second entropy in the vertical direction according to the second color symbiosis matrix corresponding to the vertical direction, so as to determine the similarity based on the first homogeneity, first contrast, first entropy, second homogeneity, second contrast and second entropy corresponding to the horizontal and vertical directions respectively, so as to accurately determine the state of the solder paste to be detected based on the similarity.

[0080] Through the above process, it is possible to measure the color statistical characteristics of the solder paste area of ​​the pseudo-depth image without relying on hardware equipment such as a depth camera, thereby accurately determining defects such as insufficient tin.

[0081] A solder paste state detection method provided in an embodiment of the present application, determining similarity according to a first color statistical feature and a second color statistical feature, may include:

[0082] Determine a first homogeneity average value, a first contrast average value, and a first entropy average value according to the first homogeneity, the first contrast, and the first entropy in the horizontal direction and the first homogeneity, the first contrast, and the first entropy in the vertical direction;

[0083] Determine a second homogeneity average value, a second contrast average value, and a second entropy average value according to the second homogeneity, the second contrast, and the second entropy in the horizontal direction and the second homogeneity, the second contrast, and the second entropy in the vertical direction;

[0084] The similarity is determined based on the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value, and the second entropy average value.

[0085] In the embodiment of the present application, the specific process of determining the similarity according to the first color statistical feature and the second color statistical feature may be:

[0086] Step S201: Calculate a first homogeneity average value according to the first homogeneity in the horizontal direction and the first homogeneity in the vertical direction, calculate a first contrast average value according to the first contrast in the horizontal direction and the first contrast in the vertical direction, and calculate a first entropy average value according to the first entropy in the horizontal direction and the first entropy in the vertical direction.

[0087] Alternatively, the first homogeneity, the first contrast and the first entropy in the horizontal direction may be used to form a first statistical feature vector corresponding to the horizontal direction, and the first homogeneity, the first contrast and the first entropy in the vertical direction may be used to form a first statistical feature vector corresponding to the vertical direction. The first average statistical feature vector may be calculated based on the first statistical feature vector corresponding to the horizontal direction and the first statistical feature vector corresponding to the vertical direction. That is, the average statistical feature vector may be calculated using formula (5):

[0088]

[0089] in, is the statistical feature vector formed by combining homogeneity, contrast and entropy in a certain direction, d p Indicates direction, T represents the total number of directions. In the above process, T = 2, representing the horizontal and vertical directions. is the average statistical eigenvector.

[0090] Of course, after respectively calculating the first homogeneity average value, the first contrast average value and the first entropy average value, the first homogeneity average value, the first contrast average value and the first entropy average value may be used to form a first average statistical feature vector.

[0091] Step S202: Calculate a second homogeneity average value according to the second homogeneity in the horizontal direction and the second homogeneity in the vertical direction, calculate a second contrast average value according to the second contrast in the horizontal direction and the second contrast in the vertical direction, and calculate a second entropy average value according to the second entropy in the horizontal direction and the second entropy in the vertical direction.

[0092] Alternatively, the second homogeneity, the second contrast and the second entropy in the horizontal direction may be used to form a second statistical feature vector corresponding to the horizontal direction, and the second homogeneity, the second contrast and the second entropy in the vertical direction may be used to form a second statistical feature vector corresponding to the vertical direction. The second average statistical feature vector may be calculated based on the second statistical feature vector corresponding to the horizontal direction and the second statistical feature vector corresponding to the vertical direction, that is, the above formula (5) may be used for calculation.

[0093] It should be noted that there is no limitation on the execution order of step S201 and step S202, and one of them can be executed first, or both can be executed at the same time.

[0094] Of course, after respectively calculating the second homogeneity average value, the second contrast average value and the second entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value may be formed into a second average statistical feature vector.

[0095] Step S203: Determine similarity based on the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value, and the second entropy average value. After forming a first average statistical feature vector based on the first homogeneity average value, the first contrast average value, and the first entropy average value, and forming a second average statistical feature vector based on the second homogeneity average value, the second contrast average value, and the second entropy average value, the similarity can be determined based on the first average statistical feature vector and the second average statistical feature vector.

[0096] By calculating the average values ​​of the corresponding color statistical features in the horizontal direction and the corresponding color statistical features in the vertical direction, and performing similarity calculation based on the average values ​​of the color statistical features, the accuracy of the similarity calculation can be improved, thereby improving the accuracy of solder paste state detection.

[0097] A solder paste state detection method provided in an embodiment of the present application, which determines similarity according to a first homogeneity average value, a first contrast average value, a first entropy average value, a second homogeneity average value, a second contrast average value, and a second entropy average value, may include:

[0098] The similarity is determined by using the Euclidean distance calculation method according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value.

[0099] In the embodiment of the present application, the similarity can be determined by using the Euclidean distance calculation method according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value. Specifically, after forming a first average statistical feature vector according to the first homogeneity average value, the first contrast average value and the first entropy average value, and forming a second average statistical feature vector according to the second homogeneity average value, the second contrast average value and the second entropy average value, the similarity can be calculated using formula (6):

[0100]

[0101] in, represents the first average statistical eigenvector, represents the second average statistical eigenvector, E s Indicates similarity.

[0102] The above method can simply and quickly calculate the similarity between the first color texture feature of the image of the solder paste area to be detected converted into the Lab color space and the second color texture feature of the template solder paste area image converted into the Lab color space, so as to quickly and efficiently determine the solder paste state.

[0103] A solder paste state detection method provided in an embodiment of the present application may further include, before obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix:

[0104] The first color matrix and the second color matrix are quantized.

[0105] In an embodiment of the present application, considering that the maximum color value in the color matrix may be relatively large and the color level may be relatively large, before obtaining the first color symbiosis matrix corresponding to the first color matrix and the second color symbiosis matrix corresponding to the second color matrix, the first color matrix and the second color matrix may be quantized according to the maximum color value contained in the first color matrix and the second color matrix, or the maximum color level is determined according to the first color matrix and the second color matrix, and the first color matrix and the second color matrix are quantized according to the maximum color level. For example, the maximum color level of the first color matrix and the second color matrix is ​​100. By quantization, the color levels of the first color matrix and the second color matrix can be quantized to level 10, so that the size of the color symbiosis matrix increases from 100 to 10. 2 becomes 10 2 , thereby reducing the size of the color co-occurrence matrix to reduce the amount of calculation and data storage, improve the calculation efficiency and solder paste status detection efficiency, and quantifying the color range of the color matrix can also reduce the interference of factors such as noise to improve the robustness of the measurement indicators.

[0106] It should be noted that, based on the quantization of the first color matrix and the second color matrix, i and j in the color co-occurrence matrix in formula (1) represent the color levels at the corresponding positions, I′ represents the quantized color matrix, W and H represent the number of pixels in the horizontal and vertical directions of the image after the color level of the solder paste area is quantized, and N in formulas (2)-(5) is k It is the maximum color level after quantization.

[0107] The present application also provides a solder paste state detection device, see Figure 3 , which shows a schematic structural diagram of a solder paste state detection device provided in an embodiment of the present application, which may include:

[0108] An acquisition module 31 is used to acquire an image of the solder paste area to be detected and a corresponding image of the solder paste area of ​​the template; the image of the solder paste area to be detected and the image of the solder paste area of ​​the template are pseudo depth images;

[0109] A conversion module 32, used to convert the image of the solder paste area to be detected and the image of the solder paste area of ​​the template into a Lab color space, and determine the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the solder paste area of ​​the template;

[0110] The determination module 33 is used to determine the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected according to the similarity.

[0111] The embodiment of the present application provides a solder paste state detection device, and the conversion module 32 may include:

[0112] A first acquisition submodule is used to acquire a first color matrix corresponding to at least one color channel of the converted solder paste area image to be detected in the Lab color space, and to acquire a second color matrix corresponding to a color channel of the converted template solder paste area image in the Lab color space; the color channel is an a channel and / or a b channel;

[0113] A second acquisition submodule is used to acquire a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix;

[0114] A first determination submodule, configured to determine a first color statistical feature according to a first color symbiosis matrix, and to determine a second color statistical feature according to a second color symbiosis matrix;

[0115] The second determination submodule is configured to determine the similarity according to the first color statistical feature and the second color statistical feature.

[0116] In a solder paste state detection device provided in an embodiment of the present application, the second acquisition submodule may include:

[0117] The acquisition unit is used to acquire a first color symbiosis matrix corresponding to the first color matrix in the horizontal direction and the vertical direction respectively, and a second color symbiosis matrix corresponding to the second color matrix in the horizontal direction and the vertical direction respectively.

[0118] In a solder paste state detection device provided in an embodiment of the present application, the first determination submodule may include:

[0119] A first determining unit, configured to determine first homogeneity, first contrast and first entropy in the horizontal direction and in the vertical direction according to first color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively;

[0120] The second determination unit is used to determine the second homogeneity, the second contrast and the second entropy in the horizontal direction and the vertical direction according to the second color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively.

[0121] In a solder paste state detection device provided in an embodiment of the present application, the second determination submodule may include:

[0122] A third determining unit is used to determine a first homogeneity average value, a first contrast average value, and a first entropy average value according to the first homogeneity, the first contrast, and the first entropy in the horizontal direction and the first homogeneity, the first contrast, and the first entropy in the vertical direction;

[0123] a fourth determining unit, configured to determine a second homogeneity average value, a second contrast average value, and a second entropy average value according to the second homogeneity, the second contrast, and the second entropy in the horizontal direction and the second homogeneity, the second contrast, and the second entropy in the vertical direction;

[0124] The fifth determining unit is used to determine the similarity according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value.

[0125] In a solder paste state detection device provided by an embodiment of the present application, the fifth determination unit may include:

[0126] The determination subunit is used to determine the similarity by using the Euclidean distance calculation method according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value.

[0127] In a solder paste state detection device provided in an embodiment of the present application, the conversion module 32 may further include:

[0128] The quantization submodule is used to quantize the first color matrix and the second color matrix before obtaining the first color symbiosis matrix corresponding to the first color matrix and the second color symbiosis matrix corresponding to the second color matrix.

[0129] The present application also provides a solder paste state detection device, see Figure 4 , which shows a schematic structural diagram of a solder paste state detection device provided in an embodiment of the present application, which may include:

[0130] A memory 41, used for storing computer programs;

[0131] The processor 42, when used to execute the computer program stored in the memory 41, can implement the following steps:

[0132] The image of the solder paste area to be detected and the corresponding image of the template solder paste area are obtained; the image of the solder paste area to be detected and the image of the template solder paste area are pseudo depth images; the image of the solder paste area to be detected and the image of the template solder paste area are converted into Lab color space, and the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the template solder paste area is determined; the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected is determined according to the similarity.

[0133] The present application also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following steps can be implemented:

[0134] The image of the solder paste area to be detected and the corresponding image of the template solder paste area are obtained; the image of the solder paste area to be detected and the image of the template solder paste area are pseudo depth images; the image of the solder paste area to be detected and the image of the template solder paste area are converted into Lab color space, and the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the template solder paste area is determined; the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected is determined according to the similarity.

[0135] The description of the relevant parts of a solder paste state detection device, equipment and readable storage medium provided in the embodiments of the present application can be found in the detailed description of the corresponding parts of a solder paste state detection method provided in the embodiments of the present application, and will not be repeated here.

[0136] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any readable storage medium for use by an instruction execution system, device or equipment (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or equipment and execute instructions), or in combination with these instruction execution systems, devices or equipment. For the purpose of this specification, "readable storage medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or equipment, or in combination with these instruction execution systems, devices or equipment. More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the readable storage medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0137] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0139] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0140] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0141] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting solder paste status, characterized in that: include: Acquire an image of the solder paste area to be detected and a corresponding image of the solder paste area of ​​the template; the image of the solder paste area to be detected and the image of the solder paste area of ​​the template are pseudo depth images; Convert the to-be-detected solder paste region image and the template solder paste region image into Lab color space, and determine the similarity between the first color texture feature of the converted to-be-detected solder paste region image and the second color texture feature of the converted template solder paste region image; The state of the solder paste to be detected corresponding to the image of the solder paste area to be detected is determined according to the similarity.

2. The solder paste state detection method according to claim 1, characterized in that: Determining the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the solder paste area of ​​the template includes: Obtain a first color matrix corresponding to at least one color channel of the converted solder paste area image to be detected in the Lab color space, and obtain a second color matrix corresponding to the color channel of the converted template solder paste area image in the Lab color space; the color channel is a channel and / or b channel; Obtain a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix; Determine a first color statistical feature according to the first color symbiosis matrix, and determine a second color statistical feature according to the second color symbiosis matrix; The similarity is determined according to the first color statistical feature and the second color statistical feature.

3. The solder paste state detection method according to claim 2, characterized in that: Obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix, including: A first color co-occurrence matrix corresponding to the first color matrix in the horizontal direction and the vertical direction, and a second color co-occurrence matrix corresponding to the second color matrix in the horizontal direction and the vertical direction are obtained.

4. The solder paste state detection method according to claim 3, characterized in that: Determining a first color statistical feature according to the first color symbiosis matrix, and determining a second color statistical feature according to the second color symbiosis matrix, comprises: Determine the first homogeneity, the first contrast and the first entropy in the horizontal direction and the vertical direction according to the first color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively; The second homogeneity, the second contrast and the second entropy in the horizontal direction and the vertical direction are correspondingly determined according to the second color co-occurrence matrices corresponding to the horizontal direction and the vertical direction respectively.

5. The solder paste state detection method according to claim 4, characterized in that: Determining the similarity according to the first color statistical feature and the second color statistical feature includes: Determine a first homogeneity average value, a first contrast average value, and a first entropy average value according to the first homogeneity, the first contrast, and the first entropy in the horizontal direction and the first homogeneity, the first contrast, and the first entropy in the vertical direction; Determine a second homogeneity average value, a second contrast average value, and a second entropy average value according to the second homogeneity, the second contrast, and the second entropy in the horizontal direction and the second homogeneity, the second contrast, and the second entropy in the vertical direction; The similarity is determined according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value, and the second entropy average value.

6. The solder paste state detection method according to claim 5, characterized in that: Determining the similarity according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value, and the second entropy average value includes: The similarity is determined by using a Euclidean distance calculation method according to the first homogeneity average value, the first contrast average value, the first entropy average value, the second homogeneity average value, the second contrast average value and the second entropy average value.

7. The solder paste state detection method according to any one of claims 2 to 6, characterized in that: Before obtaining a first color symbiosis matrix corresponding to the first color matrix and a second color symbiosis matrix corresponding to the second color matrix, the method further includes: The first color matrix and the second color matrix are quantized.

8. A solder paste state detection device, characterized in that: include: An acquisition module, used to acquire an image of the solder paste area to be detected and a corresponding image of the solder paste area of ​​the template; the image of the solder paste area to be detected and the image of the solder paste area of ​​the template are pseudo depth images; A conversion module, used to convert the image of the solder paste area to be detected and the image of the solder paste area of ​​the template into a Lab color space, and determine the similarity between the first color texture feature of the converted image of the solder paste area to be detected and the second color texture feature of the converted image of the solder paste area of ​​the template; A determination module is used to determine the state of the solder paste to be detected corresponding to the image of the solder paste area to be detected according to the similarity.

9. A solder paste state detection device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the solder paste status detection method as described in any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the solder paste status detection method according to any one of claims 1 to 7 are implemented.

Images