WO2017050088A1 - Method and device for locating electronic component - Google Patents

Abstract

Disclosed is a method for locating an electronic component, comprising the following steps of: performing background modeling on at least two acquired images of a plug-in front board, and acquiring a model of each pixel point of a background model; separately calculating k probability values of k Gaussian distribution functions of a pixel point of the background model, corresponding to each pixel point of an acquired image of a plug-in back board; comparing the k probability values with a preset threshold value one by one, and when any probability value is less than the threshold value, marking the corresponding pixel points as candidate component pixels on the image of the plug-in back board; and communicating the adjacent candidate component pixels on the image of the plug-in back board to form at least one communicated region for locating an electronic component. Also disclosed is a device for locating an electronic component. The present invention realizes rapid location of an electronic component and accelerates the manufacturing speed of a standard format in a circuit board detection process.

Description

Electronic component positioning method and device Technical field

The present invention relates to the field of automatic detection, and in particular, to an electronic component positioning method and apparatus.

Background technique

Automatic optical inspection refers to the use of optical imaging to obtain the surface state of the finished product, and image processing to detect the presence of foreign matter or surface defects on the surface of the finished product. At present, automatic optical inspection is widely used for quality inspection of circuit boards. During the detection, the relevant detecting device automatically scans the circuit board to acquire an image, extracts a partial image of each electronic component, and uses image processing technology to determine whether the electronic components on the circuit board have defects such as mis-insertion, missing insertion or reverse insertion. Finally, the electronic components with suspected defects are displayed or marked for easy viewing and maintenance.

Before detecting defects in electronic components, it is necessary to make a standard layout of the board. In particular, it is necessary to mark the position of each electronic component on the board. The existing solution is to manually set the position of each electronic component on the circuit board, but the manual operation scheme is not only time-consuming but also prone to leakage of electronic components when the number of electronic components is large. Meet the needs of use.

Summary of the invention

In view of the above problems, an object of the present invention is to provide an electronic component positioning method and apparatus that can quickly and accurately locate the positions of all electronic components on an image of a circuit board.

Embodiments of the present invention provide a method for positioning an electronic component, including the following steps:

Background modeling is performed on at least two plug-in front panel images obtained, and a model of each pixel of the background model is obtained, wherein the plug-in front panel image is an image of a circuit board without an electronic component inserted, each pixel point The model consists of k Gaussian distribution functions, and k is an integer greater than one;

Calculating corresponding images of each pixel of the acquired backplane image on the background model respectively k probability values under k Gaussian distribution functions of prime points, wherein the back panel image of the plug-in is an image of a circuit board into which the electronic component is inserted;

Comparing the k probability values with a preset threshold value one by one, and marking a corresponding pixel point as a candidate element pixel on the plug-in back panel image when any one of the probability values is smaller than the threshold value;

An adjacent candidate element pixel is connected to the plug-in rear panel image to form at least one connected region to position the electronic component.

As an improvement of the foregoing solution, the background model is performed on the collected at least two plug-in front panel images according to the Gaussian mixture model, and a model of each pixel point of the background model obtained according to the background model is obtained, including:

x为所述像素点的灰度值，k为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差；Create a model p(x) for each pixel in any of the plug-in front panel images, where

x is the gray value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j respectively represent the weight, mean and covariance of the jth Gaussian model;

The weight, mean and covariance of the model of each pixel that has been established are updated using corresponding pixel points on the front panel image of the other plug-in to obtain the updated model p(x) of each pixel.

As an improvement of the foregoing solution, the k probability values of each of the pixel points of the acquired back-plate image of the acquired plug-in are corresponding to the k-gauss distribution functions of the corresponding pixel points on the background model, specifically:

且1≤j≤k。Calculating, respectively, a probability value p _j (y) of each pixel point y on the image of the back panel of the plug-in under k Gaussian distribution functions of corresponding pixel points of the background model, wherein

And 1 ≤ j ≤ k.

As a modification of the above aspect, the connected area is a rectangle.

As an improvement of the above solution, connecting adjacent candidate element pixels on the back panel image of the plug-in to form at least one connected area to locate an area where the electronic component is located includes:

Calculating an area of the at least one connected region;

Determining whether the area of each connected area is greater than a preset area threshold;

When the area of the connected area is greater than the area threshold, marking the connected area as containing An effective area of the electronic component to locate the electronic component; otherwise, the connected region is marked as an interference region.

The embodiment of the invention further provides an electronic component positioning device, comprising:

a modeling unit configured to perform background modeling on the acquired at least two plug-in front panel images to obtain a model of each pixel of the background model, wherein the plug-in front panel image is an image of a circuit board without an electronic component inserted The model of each pixel is composed of k Gaussian distribution functions, and k is an integer greater than one;

a probability value calculation unit, configured to respectively calculate k probability values of k Gaussian distribution functions of corresponding pixel points of each pixel point of the acquired plug-in back panel image, wherein the plug-in The board image is an image of a circuit board into which the electronic component is inserted;

a comparing unit, configured to compare the k probability values with a preset threshold one by one, and mark corresponding pixel points as candidates on the plug-in back panel image when any one of the probability values is smaller than the threshold Component pixel

And a positioning unit configured to connect adjacent candidate element pixels on the back panel image of the insert to form at least one connected area to locate an area where the electronic component is located.

As an improvement of the above solution, the modeling unit includes:

x为所述像素点的灰度值，k为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差；a model building unit for establishing a model p(x) for each pixel in any of the plug-in front panel images, wherein

x is the gray value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j respectively represent the weight, mean and covariance of the jth Gaussian model;

The updating unit is configured to update the weight, the mean and the covariance of the model of each pixel that has been established by using corresponding pixel points on the image of the front panel of the other plug-in, and obtain an updated model of each pixel.

且1≤j ≤k。As a modification of the foregoing solution, the probability value calculation unit is specifically configured to separately calculate a probability of each pixel point y on the back panel image of the plug-in under k Gaussian distribution functions of corresponding pixel points of the background model. Value p _j (y), where

And 1 ≤ j ≤ k.

As a modification of the above aspect, the connected area is a rectangle.

As an improvement of the above solution, the positioning unit comprises:

An area calculation unit, configured to calculate an area of the at least one connected area;

a determining unit, configured to determine whether an area of each connected area is greater than a preset area threshold;

a marking unit, configured to mark the connected area as an effective area including an electronic component to locate the electronic component when an area of the connected area is greater than the area threshold; otherwise, marking the connected area as an interference area .

The electronic component positioning method and device provided by the embodiment of the present invention establishes a background model by using a Gaussian mixture model, and then matches each pixel of the background model according to the back panel image of the plug-in, and obtains candidates according to the matching situation. Component pixels, and by connecting adjacent candidate element pixels, position the electronic component in the back panel image of the plug-in, thereby realizing rapid and accurate positioning of the electronic component from the image of the back panel of the plug-in for subsequent Board inspection provides a reliable standard layout.

DRAWINGS

In order to more clearly illustrate the technical solutions of the present invention, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention, which are common in the art. For the skilled person, other drawings can be obtained from these drawings without any creative work.

1 is a flow chart of a method for positioning an electronic component according to an embodiment of the present invention.

2 is a schematic diagram of a front panel of a plug-in according to an embodiment of the present invention.

FIG. 3 is a schematic diagram of a rear panel of a plug-in according to an embodiment of the present invention.

4 is a schematic diagram of positioning an electronic component in an image of a back panel of the plug-in according to an embodiment of the present invention.

FIG. 5 is a flowchart of an electronic component positioning apparatus according to an embodiment of the present invention.

FIG. 6 is a schematic structural view of the modeling unit shown in FIG. 5.

FIG. 7 is another schematic structural view of the positioning unit shown in FIG. 5.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiments of the present invention improve an electronic component positioning method and apparatus for positioning the position of all electronic components on a circuit board by means of automatic positioning. The details are described below separately.

Please refer to FIG. 1. FIG. 1 is a flowchart of a method for positioning an electronic component according to an embodiment of the present invention. The electronic component positioning method can be performed by the electronic component positioning device and includes at least steps S101 to S104. among them,

S101: Perform background modeling on the collected at least two plug-in front panel images to obtain a model of each pixel of the background model, where the plug-in front panel image is an image of a circuit board that is not inserted into the electronic component, and each pixel The model of the point consists of k Gaussian distribution functions, and k is an integer greater than one.

Referring to FIG. 2 together, in the embodiment of the present invention, the front panel image of the plug-in is an image of a circuit board that is not inserted into an electronic component. Wherein, the electronic component positioning device may model the plug-in front panel image by using a Gaussian mixture model to obtain a background model of the plug-in front panel. In the Gaussian mixture model, in order to describe the background and its possible changes, a plurality of background images are required for the background modeling. Therefore, the plug-in front panel image of the present invention is at least two.

Specifically, when performing background modeling:

x为所述像素点的灰度值，k为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差。First, create a model p(x) for each pixel in any of the plug-in front panel images, where

x is the gray value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j represent the weight, mean and covariance of the jth Gaussian model, respectively.

x为所述像素点的像素值，k为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差。这里，可视为将所述插件前板图像的一个像素点的像素值表示为k个高斯分布函数的组合，而高斯模型的权重、均值和协方差可先根据经验值进行设置。In the embodiment of the present invention, the electronic component positioning device takes a plug-in front panel image, and creates a model p(x) for each pixel of the plug-in front panel image, wherein

x is the pixel value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j represent the weight, mean and covariance of the jth Gaussian model, respectively. Here, it can be considered that the pixel value of one pixel of the plug-in front panel image is represented as a combination of k Gaussian distribution functions, and the weight, the mean and the covariance of the Gaussian model can be set according to the empirical value.

Then, the weight, mean and covariance of the model of each pixel that has been established are updated by using corresponding pixel points on the image of the other plug-in front panel, and the updated model p(x) of each pixel is obtained.

In the embodiment of the present invention, when a new pixel is added (ie, a new plug-in front panel image is added), the electronic component positioning device respectively separates the pixel value of the new pixel from the pixel of the corresponding background model. The probability of the new pixel value falling into the corresponding Gaussian distribution is calculated simultaneously with the mean μ _j of the k Gaussian distributions of the points, and the matched Gaussian distribution is selected according to the judgment rule. When there is a matching Gaussian distribution, the parameters such as the weight, mean and covariance of these Gaussian distributions need to be updated according to the pixel values of the new pixel points. For a specific calculation process, reference may be made to the parameter update principle of the general Gaussian mixture model, and the present invention will not be described herein.

In the embodiment of the present invention, the electronic component positioning device obtains a model of each pixel point of the background model by the above operation, wherein the model of each pixel point is composed of k Gaussian distribution functions, and k is greater than 1 An integer, and preferably, k ranges from 3 to 5.

S102: Calculate k probability values of k pieces of Gaussian distribution function of corresponding pixel points of each pixel point of the acquired plug-in back panel image, wherein the plug-in back panel image is an inserted electron. An image of the component's board.

Referring to FIG. 3 together, in the embodiment of the present invention, the electronic component positioning device first acquires an image of the back panel of the plug-in, wherein the image of the back panel of the plug-in is an image of a circuit board into which the electronic component is inserted. Then, the electronic component locating device respectively calculates k probability values under k Gaussian distribution functions of corresponding pixel points of the pixel of the plug-in rear panel image on the background model.

然后，所述电子元件定位装置将所述插件后板图像的像素值y分别代入所述的k个高斯分布函数，获得k个概率值，其中，第j个概率值可表示为

For example, assume that the size of the background template and the back panel image of the plug-in are both M×N pixels. Wherein, for each pixel of the background template, it can be represented by k Gaussian distribution functions. When performing the calculation, the electronic component positioning device first reads the pixel value y of the first pixel point (such as the coordinate (1, 1)) of the back panel image of the plug-in, and then the electronic component positioning device reads k Gaussian distribution functions of pixels on the corresponding background model (such as coordinates (1, 1))

Then, the electronic component positioning device substitutes the pixel values y of the back panel image of the plug-in into the k Gaussian distribution functions to obtain k probability values, wherein the j-th probability value can be expressed as

In this way, when the electronic component positioning device traverses all the pixel points on the back panel image and the background template of the plug-in, the k probability values corresponding to each pixel point can be obtained.

S103. Compare the k probability values with a preset threshold one by one, and mark the corresponding pixel points as candidate element pixels on the plug-in backplane image when any of the probability values is smaller than the threshold.

In the embodiment of the present invention, the electronic component positioning device compares the k probability values with a preset threshold one by one, wherein when any of the probability values is less than the threshold, the corresponding pixel points are Marked as candidate element pixels, and when all k probability values are greater than the threshold, the pixel points are marked as background pixels.

S104. Connect adjacent candidate element pixels on the plug-in backplane image to form at least one connected area to locate the electronic component.

Referring to FIG. 4 together, in an embodiment of the present invention, the electronic component positioning device connects adjacent candidate component pixels after marking all the pixels on the back panel image of the plug-in. Wherein, at least one connected area will be formed after the communication, and the connected area is the position where the electronic component is located. Preferably, as a preferred embodiment of the present invention, the shape of the connected region is a rectangle (as shown by three white squares in FIG. 4). Of course, it can be understood that in other embodiments of the present invention, the connected area may also be a circle, a triangle, or other shapes, which is not specifically limited in the present invention.

In another embodiment of the present invention, pixel points that are originally background pixels are sometimes erroneously calculated as candidate element pixels due to problems such as accuracy of the algorithm or parameter errors. At this time, it may cause The position where the electronic component does not exist originally forms a connected region. In order to prevent the above, the electronic component positioning device can be set as follows:

First, an area of the at least one connected region is calculated.

Secondly, it is determined whether the area of each connected area is greater than a preset area threshold.

Finally, when the area of the connected area is larger than the area threshold, the connected area is marked as an effective area including an electronic component; otherwise, the connected area is marked as an interference area not including an electronic component.

In this way, the areas of communication having a small area are excluded, that is, the interference areas caused by calculation accuracy or error are excluded, and the connected areas are all areas including electronic components.

In summary, the electronic component positioning method provided by the embodiment of the present invention obtains a background model by using a Gaussian mixture model, and then matches each pixel of the background model according to the back panel image of the plug-in to obtain a candidate component pixel. And by connecting adjacent candidate element pixels, the position of the electronic component is located in the back panel image of the plug-in, thereby realizing the position of the electronic component quickly and accurately from the image of the back panel of the plug-in, and providing for subsequent board inspection. Reliable standard layout.

Please refer to FIG. 5. FIG. 5 is a structural diagram of an electronic component positioning apparatus according to an embodiment of the present invention. The electronic component positioning device 100 can be used to execute the electronic component positioning method described above, and at least includes a modeling unit 10, a probability value calculation unit 20, a comparison unit 30, and a positioning unit 40, wherein:

The modeling unit 10 is configured to perform background modeling on the collected at least two plug-in front panel images to obtain a model of each pixel point of the background model, wherein the plug-in front panel image is a circuit without an electronic component inserted The image of the plate, the model of each pixel consists of k Gaussian distribution functions, and k is an integer greater than one.

In an embodiment of the invention, the front panel image of the plug-in is an image of a circuit board that is not inserted into an electronic component. In order to locate the position of the electronic component from the circuit board, the modeling unit 10 may first acquire at least two plug-in front panel images as background images. The modeling unit 10 may model the plug-in front panel image by using a Gaussian mixture model to obtain a background model of the plug-in front panel. The Gaussian mixture model requires multiple background images in order to characterize the background and its possible changes during background modeling. The plug-in front panel image of the present invention is at least two.

Please refer to FIG. 6 in detail. Specifically, the modeling unit 10 includes a model establishing unit 11 and an updating unit 12, where:

x为所述像素点的灰度值，a为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差。The model establishing unit 11 is configured to establish a model p(x) for each pixel in any of the plug-in front panel images, where

x is the gray value of the pixel, a is the number of Gaussian models, and ω _j , μ _j , C _j represent the weight, mean and covariance of the jth Gaussian model, respectively.

x为所述像素点的像素值，k为高斯模型的个数，ω_j，μ_j，C_j分别表示第j个高斯模型的权重、均值和协方差。这里，可视为将所述插件前板图像的一个像素点的像素值表示为k个高斯分布函数的组合，而高斯模型的权重、均值和协方差可先根据经验值进行设置。In the embodiment of the present invention, the model establishing unit 11 takes a plug-in front panel image and creates a model p(x) for each pixel of the plug-in front panel image, where

x is the pixel value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j represent the weight, mean and covariance of the jth Gaussian model, respectively. Here, it can be considered that the pixel value of one pixel of the plug-in front panel image is represented as a combination of k Gaussian distribution functions, and the weight, the mean and the covariance of the Gaussian model can be set according to the empirical value.

The updating unit 12 is configured to update the weight, the mean and the covariance of the model of each pixel that has been established by using corresponding pixel points on the image of the front panel of the other plug-in to obtain a model of each pixel after the update. p(x).

In the embodiment of the present invention, when a new pixel is added (ie, a new plug-in front panel image is added), the updating unit 12 separates the pixel values of the new pixel from the k-gauss distribution described above. Compared with the mean μ _j , the probability that the new pixel value falls into the corresponding Gaussian distribution is calculated at the same time, and the matched Gaussian distribution is selected according to the judgment rule. When there is a matching Gaussian distribution, the parameters such as the weight, mean and covariance of these Gaussian distributions need to be updated according to the pixel values of the new pixel points. For a specific calculation process, reference may be made to the parameter update principle of the general Gaussian mixture model, and the present invention will not be described herein.

In the embodiment of the present invention, the modeling unit 10 obtains a model of each pixel point of the background model by the above operation, wherein the model of each pixel point is composed of k Gaussian distribution functions, and k is greater than 1 An integer, and preferably, k ranges from 3 to 5.

The probability value calculation unit 20 is configured to respectively calculate k probability values of k Gaussian distribution functions of corresponding pixel points of each pixel point of the acquired plug-in back panel image, where The back panel image of the plug-in is an image of a board into which the electronic component is inserted.

In the embodiment of the present invention, the probability value calculation unit 20 first acquires an image of the back panel of the plug-in, wherein the image of the back panel of the plug-in is an image of a circuit board into which the electronic component is inserted. Then, the probability value calculation unit 20 respectively calculates k probability values under k Gaussian distribution functions of corresponding pixel points of the pixel of the plug-in back panel image on the background model.

然后，所述概率值计算单元20将所述插件后板图像的像素值y分布代入所述的k个高斯分布函数，获得k个概率值，其中，第j个概率值可表示为

For example, assume that the size of the background template and the back panel image of the plug-in are both M×N pixels. Wherein, for each pixel of the background template, it can be represented by k Gaussian distribution functions. When performing the calculation, the probability value calculation unit 20 first reads the pixel value y of the first pixel point (such as the coordinate (1, 1)) of the plug-in back panel image, and then the probability value calculation unit 20 Read k Gaussian distribution functions of pixels on the corresponding background model (such as coordinates (1, 1))

Then, the probability value calculation unit 20 substitutes the pixel value y distribution of the plug-in back panel image into the k Gaussian distribution functions to obtain k probability values, wherein the j-th probability value can be expressed as

In this way, when the probability value calculation unit 20 traverses all the pixel points on the back panel image and the background template of the plug-in, the k probability values corresponding to each pixel point can be obtained.

The comparing unit 30 is configured to compare the k probability values with a preset threshold one by one, and when the probability value is less than the threshold, the corresponding pixel points are displayed on the plug-in back panel image. Marked as candidate element pixels.

In the embodiment of the present invention, the comparing unit 30 compares the k probability values one by one with a preset threshold, wherein when any one of the probability values is less than the threshold, the comparing unit 30 Corresponding pixel points are labeled as candidate element pixels, and when all k probability values are greater than the threshold, then comparison unit 30 marks the pixel points as background pixels.

The positioning unit 40 is configured to connect adjacent candidate element pixels on the back panel image of the plug-in. At least one connected region is formed to position the electronic component.

In an embodiment of the invention, the positioning unit 40 connects adjacent candidate element pixels after marking all the pixels on the back panel image of the plug-in. Wherein, at least one connected area will be formed after the communication, and the connected area is the position where the electronic component is located. Preferably, as a preferred embodiment of the present invention, the shape of the connected region is a rectangle. Of course, it can be understood that in other embodiments of the present invention, the connected area may also be a circle, a triangle, or other shapes, which is not specifically limited in the present invention.

Referring to FIG. 7 together, in another embodiment of the present invention, due to problems such as the accuracy of the algorithm or the parameter error, the pixel points which are originally background pixels are sometimes erroneously calculated as candidate element pixels. At this time, a connection region may be formed at a position where the electronic component is not originally present. In order to prevent the above situation, the positioning unit 40 may include:

The area calculating unit 41 is configured to calculate an area of the at least one connected area.

The determining unit 42 is configured to determine whether an area of each connected area is greater than a preset area threshold.

The marking unit 43 is configured to mark the connected area as an effective area including an electronic component when an area of the connected area is larger than the area threshold; otherwise, mark the connected area as an interference area not including an electronic component .

In this way, the positioning unit 40 excludes those connected areas having a small area, that is, excludes interference areas caused by calculation accuracy or error, and ensures that the connected areas are all areas including electronic components.

In summary, the electronic component positioning apparatus 100 according to the embodiment of the present invention obtains a background model by using a Gaussian mixture model, and then matches each pixel of the background model according to the back panel image of the plug-in to obtain a candidate component. Pixels, and by connecting adjacent candidate element pixels, position the electronic component in the back panel image of the plug-in, thereby realizing the position of the electronic component quickly and accurately from the image of the back panel of the plug-in, for subsequent board detection Provide a reliable standard layout.

The above disclosure is only a preferred embodiment of the present invention, and of course, the scope of the present invention is not limited thereto, and those skilled in the art can understand all or part of the process of implementing the above embodiments, and according to the present invention. The equivalent changes required are still within the scope of the invention.

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Claims (10)

An electronic component positioning method, comprising the steps of: Background modeling is performed on at least two plug-in front panel images obtained, and a model of each pixel of the background model is obtained, wherein the plug-in front panel image is an image of a circuit board without an electronic component inserted, each pixel point The model consists of k Gaussian distribution functions, and k is an integer greater than one; Calculating k probability values under k Gaussian distribution functions of corresponding pixel points of the acquired plug-in back panel image respectively, wherein the plug-in back panel image is inserted into the electronic component An image of the board; Comparing the k probability values with a preset threshold value one by one, and marking a corresponding pixel point as a candidate element pixel on the plug-in back panel image when any one of the probability values is smaller than the threshold value; An adjacent candidate element pixel is connected to the plug-in rear panel image to form at least one connected region to position the electronic component. The electronic component positioning method according to claim 1, wherein the background modeling is performed on at least two plug-in front panel images according to a Gaussian mixture model, and each pixel of the background model obtained according to the background modeling is obtained. Point model, including: Create a model p(x) for each pixel in any of the plug-in front panel images, where

x is the gray value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j respectively represent the weight, mean and covariance of the jth Gaussian model; The weight, mean and covariance of the model of each pixel that has been established are updated using corresponding pixel points on the front panel image of the other plug-in to obtain the updated model p(x) of each pixel. The electronic component positioning method according to claim 2, wherein said calculating, respectively, each pixel point of the acquired plug-in rear panel image is under a k Gaussian distribution function of a corresponding pixel point on said background model k probability values, specifically: Calculating, respectively, a probability value p _j (y) of each pixel point y on the image of the back panel of the plug-in under k Gaussian distribution functions of corresponding pixel points of the background model, wherein

And 1 ≤ j ≤ k. The electronic component positioning method according to claim 1, wherein the communication area is a rectangle. The electronic component positioning method according to any one of claims 1 to 4, wherein adjacent candidate element pixels are connected to the plug-in rear panel image to form at least one connected region to position the electronic component. include: Calculating an area of the at least one connected region; Determining whether the area of each connected area is greater than a preset area threshold; When the area of the connected area is greater than the area threshold, the connected area is marked as an effective area containing electronic components to locate the electronic component; otherwise, the connected area is marked as an interference area. An electronic component positioning device, comprising: a modeling unit configured to perform background modeling on the acquired at least two plug-in front panel images to obtain a model of each pixel of the background model, wherein the plug-in front panel image is an image of a circuit board without an electronic component inserted The model of each pixel is composed of k Gaussian distribution functions, and k is an integer greater than one; a probability value calculation unit, configured to respectively calculate k probability values of k Gaussian distribution functions of corresponding pixel points of each pixel point of the acquired plug-in back panel image, wherein the plug-in The board image is an image of a circuit board into which the electronic component is inserted; a comparing unit, configured to compare the k probability values with a preset threshold one by one, and mark corresponding pixel points as candidates on the plug-in back panel image when any one of the probability values is smaller than the threshold Component pixel And a positioning unit configured to connect adjacent candidate element pixels on the back panel image of the insert to form at least one connected area to locate the electronic component. The electronic component positioning device according to claim 6, wherein the modeling unit comprises: a model building unit for establishing a model p(x) for each pixel in any of the plug-in front panel images, wherein

x is the gray value of the pixel, k is the number of Gaussian models, and ω _j , μ _j , C _j respectively represent the weight, mean and covariance of the jth Gaussian model; And an updating unit, configured to update, by using corresponding pixel points on other front panel images, weights, mean values, and covariances of the model of each pixel that has been established, to obtain an updated model p(x) of each pixel point. ). The electronic component positioning device according to claim 7, wherein the probability value calculation unit is configured to separately calculate a corresponding pixel of each pixel point y on the background image of the plug-in rear panel image. The probability value p _j (y) of the k Gaussian distribution functions of the points, where

And 1 ≤ j ≤ k. The electronic component positioning device according to claim 6, wherein the communication region is rectangular. The electronic component positioning device according to any one of claims 6 to 9, wherein the positioning unit comprises: An area calculation unit, configured to calculate an area of the at least one connected area; a determining unit, configured to determine whether an area of each connected area is greater than a preset area threshold; a marking unit, configured to mark the connected area as an effective area including an electronic component to locate the electronic component when an area of the connected area is greater than the area threshold; otherwise, marking the connected area as an interference area .

Images