CN117974578A

CN117974578A - Photovoltaic glass silk screen edge defect detection method and device and electronic equipment

Info

Publication number: CN117974578A
Application number: CN202410046811.9A
Authority: CN
Inventors: 杨建乔
Original assignee: Luster LightTech Co Ltd
Current assignee: Luster LightTech Co Ltd
Priority date: 2024-01-11
Filing date: 2024-01-11
Publication date: 2024-05-03

Abstract

The application discloses a photovoltaic glass silk-screen edge defect detection method and device and electronic equipment, and belongs to the technical field of image processing. The method comprises the following steps: performing edge recognition on the acquired image to be detected to obtain a photovoltaic glass edge and a silk screen edge; translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge; and detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area. According to the embodiment of the application, the photovoltaic glass edge and the silk-screen edge are automatically identified, and then the detection area is adaptively constructed according to the conditions of the photovoltaic glass edge and the silk-screen edge, so that the detected defect area is more reasonable, the whole is independent of a template image, and the accuracy of detecting the photovoltaic glass silk-screen edge can be improved.

Description

Photovoltaic glass silk screen edge defect detection method and device and electronic equipment

Technical Field

The application belongs to the technical field of image processing, and particularly relates to a photovoltaic glass silk-screen edge defect detection method and device and electronic equipment.

Background

Photovoltaic glass is a special purpose glass and is widely used in solar cell modules and photovoltaic systems. The production process is a complex process flow, wherein silk screen printing is one of the key processes. In the production of photovoltaic glass, the silk screen process is mainly used to print circuit patterns on the glass surface, which patterns can be used for the connection of electrodes and the circuit layout of photovoltaic modules. Edge defects such as uneven edge widths, overprinting or underprinting may lead to reduced photovoltaic glass performance due to the complexity of the screen printing process. Therefore, accurate detection of the integrity and consistency of the screen printed edges is critical to ensuring product quality.

The photovoltaic glass silk-screen edge detection method is generally based on a method for positioning and comparing with a template image, edge features are extracted from the detection image and the template image through an image processing algorithm, and then the silk-screen edge in the detection image is positioned and compared with the template image by utilizing the extracted edge features.

However, the detected image is usually obtained in actual production through the same imaging equipment, and in the equipment, due to the production speed, platform stability and other reasons, the shaking of the silk-screen edge and the imaging difference are generated, and the shaking of the edge cannot be well adapted to illumination, so that a certain difference exists between the detected image and the template image, and the accuracy of detecting the silk-screen edge defect is not high enough.

Disclosure of Invention

The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a method and a device for detecting the edge defects of the silk screen printing of the photovoltaic glass and electronic equipment, so that the accuracy of detecting the edge defects of the silk screen printing of the photovoltaic glass is improved.

In a first aspect, the application provides a method for detecting edge defects of screen printing of photovoltaic glass, which comprises the following steps:

Performing edge recognition on the acquired image to be detected to obtain a photovoltaic glass edge and a silk screen edge;

translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge;

and detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area.

According to the method for detecting the defects of the silk-screen edges of the photovoltaic glass, the edges of the photovoltaic glass and the silk-screen edges are obtained by carrying out edge recognition on the obtained image to be detected; translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge; and detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area. According to the embodiment of the application, the photovoltaic glass edge and the silk-screen edge are automatically identified, and then the detection area is adaptively constructed according to the conditions of the photovoltaic glass edge and the silk-screen edge, so that the detected defect area is more reasonable, the whole is independent of a template image, and the accuracy of detecting the photovoltaic glass silk-screen edge can be improved.

According to one embodiment of the present application, the edge recognition of the acquired image to be detected includes:

calculating gradients of all pixel points in the appointed area of the image to be detected;

the edge of the photovoltaic glass is determined based on the change condition of the gradient of each pixel point.

According to the embodiment, the gradient of each pixel point is calculated, the gradient represents the change condition of the gray value of the pixel in the image, the gradient value is larger at the edge generally, and the position of the edge is located at the outermost edge of the whole photovoltaic glass, so that the position with the larger gradient value can be found by analyzing the change of the gradient, and the position of the edge of the photovoltaic glass can be stably and accurately determined.

Extracting the positions of pixel points in the area inside the edge of the photovoltaic glass through preset intervals;

And fitting and correcting the pixel points at the positions to obtain the silk-screen edges.

In this embodiment, the points in the screen printing area are extracted by extracting the pixels at intervals in the area where the edge of the photovoltaic glass is located, which means that each pixel does not need to be extracted, but a pixel at a certain interval can be selected for extraction, so as to reduce the amount of data processed.

According to one embodiment of the present application, the translating the photovoltaic glass edge and the silk-screened edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screened edge includes:

and translating the photovoltaic glass edge towards the silk-screen edge by a first preset distance, and translating the silk-screen edge towards the photovoltaic glass edge by a second preset distance to form a white-reserving detection area surrounded by the translated photovoltaic glass edge and the translated silk-screen edge.

In this embodiment, since there may be burrs on the edge of the photovoltaic glass and excessive pixels on the edge of the screen, the photovoltaic glass edge and the screen edge are translated to form a blank detection area, and defect detection is performed in the blank detection area, so that multiple printing defects can be detected, the over-detection risk is reduced, and the actual defect detection requirement is not affected.

According to one embodiment of the application, the first preset distance is a maximum distance of non-defective photovoltaic glass burrs; the second preset distance is a distance of 1-6 pixels.

And translating the silk-screen edge away from the photovoltaic glass edge by a third preset distance and a fourth preset distance to form a silk-screen detection area surrounded by the translated silk-screen edge.

In this embodiment, since there may be excessive pixels on the screen edge, the screen edge is translated twice to form a screen detection area, and defect detection is performed in the screen detection area, so that fewer defects can be detected, the over-detection risk is reduced, and the actual defect detection requirement is not affected.

According to one embodiment of the present application, the third preset distance is a distance of 1-6 pixels; the fourth preset distance is a distance of 26-38 pixels.

According to one embodiment of the present application, the detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixel in the detection area includes:

performing binarization processing on the detection area based on a preset gray threshold value to obtain a background area and a foreground area of the detection area;

identifying different connected regions in the foreground region;

And screening out the connected region meeting the preset condition as a defect region.

In this embodiment, the detection area is binarized, so that the connected area can be identified in the foreground area, and the connected area meeting the preset condition is a defect area.

In a second aspect, the present application provides a photovoltaic glass silk-screen edge defect detection device, including:

The identification module is used for carrying out edge identification on the acquired image to be detected to obtain a photovoltaic glass edge and a silk screen edge;

the translation module is used for translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge;

And the detection module is used for detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area.

According to the photovoltaic glass silk-screen edge defect detection device, the edge recognition is carried out on the acquired image to be detected, so that the photovoltaic glass edge and the silk-screen edge are obtained; translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge; and detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area. According to the embodiment of the application, the photovoltaic glass edge and the silk-screen edge are automatically identified, and then the detection area is adaptively constructed according to the conditions of the photovoltaic glass edge and the silk-screen edge, so that the detected defect area is more reasonable, the whole is independent of a template image, and the accuracy of detecting the photovoltaic glass silk-screen edge can be improved.

In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for detecting a photovoltaic glass silk-screen edge defect according to the first aspect when executing the computer program.

In a fourth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the photovoltaic glass silk-screen edge defect detection method as described in the first aspect above.

In a fifth aspect, the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method for detecting a photovoltaic glass silk-screen edge defect according to the first aspect.

In a sixth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the photovoltaic glass silk-screen edge defect detection method as described in the first aspect above.

The above technical solutions in the embodiments of the present application have at least one of the following technical effects:

Further, in some embodiments, the gradient of each pixel point is calculated, the gradient represents the change condition of the gray value of the pixel in the image, the gradient value is usually larger at the edge, and the position where the edge is located is the outermost edge of the photovoltaic glass integrally, so that the position where the gradient value is larger can be found by analyzing the change of the gradient, and the position of the edge of the photovoltaic glass can be stably and accurately determined.

Still further, in some embodiments, the screen printing is performed in the area inside the edge of the photovoltaic glass, and the dot positions in the screen printing area are extracted by adopting a method of extracting pixel points at intervals, which means that each pixel point does not need to be extracted, but a pixel point with a certain interval can be selected for extraction, so as to reduce the amount of processed data.

Further, in some embodiments, since burrs may exist on the edge of the photovoltaic glass and excessive pixels may exist on the edge of the screen, the photovoltaic glass edge and the edge of the screen are translated to form a blank detection area, and defect detection is performed in the blank detection area, so that multiple printing defects can be detected, the over-detection risk is reduced, and the actual defect detection requirement is not affected.

Furthermore, in some embodiments, since there may be excessive pixels on the screen edge, the screen edge is translated twice to form a screen detection area, and defect detection is performed in the screen detection area, so that fewer screen defects can be detected, the over-detection risk is reduced, and the actual defect detection requirement is not affected.

Still further, in some embodiments, the detection area is binarized, so that the connected area can be identified in the foreground area, and the connected area meeting the preset condition is a defect area.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the application will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:

Fig. 1 is a schematic flow chart of a method for detecting edge defects of screen printing of photovoltaic glass according to an embodiment of the application;

FIG. 2 is a schematic diagram of an image to be detected according to an embodiment of the present application;

FIG. 3 is a partial enlarged view of an image to be detected according to an embodiment of the present application;

FIG. 4 is a schematic diagram illustrating the division of detection areas according to an embodiment of the present application;

FIG. 5 is a diagram illustrating a second embodiment of the present application for dividing the detection area;

fig. 6 is a schematic structural diagram of a photovoltaic glass silk-screen edge defect detection device according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.

In the silk screen process, first, silk screen molds for printing need to be designed and made, which have fine pores through which ink or other conductive material can be printed on the glass surface. Then, the glass is placed on a printer, and the ink is uniformly printed on the surface of the glass through a screen mold to form a desired circuit pattern. The edge accuracy and integrity of silk screening is critical to the connection of circuits and the performance of photovoltaic modules, and therefore high precision silk screening processes are required to ensure the quality and stability of the pattern.

In addition, the silk screen printing process also involves the steps of ink selection, drying, curing and the like so as to ensure the conductivity and durability of the printed pattern. In the production of photovoltaic glass, the quality of the silk screen printing process directly influences the performance and reliability of photovoltaic products, so that the process parameters are required to be strictly controlled, and the accuracy and stability of the silk screen printing patterns are ensured.

The method based on the positioning comparison with the template image is a common photovoltaic glass silk-screen edge detection technology, and generally comprises the following steps: first, a standard template image is acquired, which contains the desired shape and characteristics of the silk-screened edges. The template image may be acquired by a high resolution imaging device and is typically pre-processed and optimized to ensure its sharpness and accuracy. Next, an image of the photovoltaic glass silk-screen edge to be detected needs to be acquired. The image is usually obtained by the same imaging device in actual production, and may be affected by factors such as illumination, shake, etc., so that a certain difference exists between the image and the template image. For the inspection image and the template image, some preprocessing operations such as denoising, edge enhancement, gray scale adjustment, etc. are generally required to ensure image sharpness and consistency. Edge features are extracted from the detected image and the template image by an image processing algorithm. These features may include information on the shape, curvature, gray level variation, etc. of the edges for subsequent comparison and analysis. And positioning the silk-screen edges in the detection image and comparing the template images by using the extracted edge features. This step typically involves techniques of image registration, feature matching, edge alignment, etc., to ensure that the edge positions of the detected image and the template image are as consistent as possible. And finally, evaluating the quality of the silk-screen edge of the photovoltaic glass according to the positioning comparison result. The integrity, accuracy and consistency of the edges can be judged by the comparison difference, so that quality control and adjustment can be performed.

However, the detected image is usually obtained in actual production through the same imaging equipment, and in the equipment, due to the production speed, platform stability and other reasons, the shaking of the silk-screen edge and the imaging difference are generated, and the shaking of the edge cannot be well adapted to illumination, so that a certain difference exists between the detected image and the template image, and the accuracy of the silk-screen edge detection is not high enough.

According to the application, if the detection area can be adaptively constructed according to the glass edge condition, the detected defect area can be more reasonable, and the whole detection area is independent of the template image, so that the problem that the accuracy of silk-screen edge detection caused by positioning comparison through the template image in the prior art is not high enough is hopefully solved.

The method, the device and the electronic equipment for detecting the edge defects of the photovoltaic glass screen printing provided by the embodiment of the application are described in detail through specific embodiments and application scenes thereof by combining the accompanying drawings.

The method for detecting the edge defects of the photovoltaic glass screen printing can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet having a touch sensitive surface (e.g., a touch screen display and/or a touch pad). It should also be appreciated that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or a touch pad).

In the following various embodiments, a terminal including a display and a touch sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

The implementation main body of the photovoltaic glass silk-screen edge defect detection method provided by the embodiment of the application can be electronic equipment or a functional module or a functional entity capable of realizing the photovoltaic glass silk-screen edge defect detection method in the electronic equipment, and the electronic equipment provided by the embodiment of the application comprises, but is not limited to, a mobile phone, a tablet computer, a camera, a wearable device and the like.

As shown in fig. 1, the method for detecting the edge defect of the photovoltaic glass screen printing comprises the following steps: step 110, step 120 and step 130.

And 110, carrying out edge recognition on the acquired image to be detected to obtain a photovoltaic glass edge and a silk screen edge.

The image to be detected can be obtained through imaging equipment in the actual production of the photovoltaic glass, and the image to be detected comprises the photovoltaic glass and a circuit pattern (namely silk screen) formed by printing on the surface of the photovoltaic glass, as shown in fig. 2.

In the image to be detected, as shown in fig. 3, fig. 3 is a partial enlarged view of the upper left corner of fig. 2, and in fig. 3, it can be seen that the image to be detected includes photovoltaic glass, silk screen printing, background area, etc., and there are many silk screen printing patterns on the photovoltaic glass, the silk screen printing does not cover the photovoltaic glass completely, some white areas exist between the photovoltaic glass edge and the silk screen printing edge, if the defect of the silk screen printing edge of the photovoltaic glass is detected, it is necessary to determine the photovoltaic glass edge and the silk screen printing edge first, and then detect whether the defect exists on the silk screen printing edge.

In the embodiment of the application, the acquired image to be detected can be subjected to edge recognition through an image processing technology, for example, the image to be detected is subjected to edge recognition through an edge detection algorithm, such as a Canny algorithm, a Sobel algorithm, a differential edge detection algorithm, a Robert algorithm, a laplace edge detection algorithm and the like. Of course, edge recognition can be performed on the image to be detected in a machine learning mode, for example, an edge detection model is trained in advance, the image to be detected is input into the edge detection model, and the photovoltaic glass edge and the silk screen edge are obtained based on the output of the edge detection model. Any manner can be selected by a person skilled in the art according to the need to perform edge recognition on the image to be detected, and the embodiment of the application is not limited to this.

In the embodiment of the application, the outer edge of the photovoltaic glass is automatically identified through edge identification, so that the range of the photovoltaic glass can be accurately positioned, and a reference is provided for subsequent silk-screen edge detection. How to identify the outer edge of the photovoltaic glass is illustrated by one example: because the photovoltaic glass edge is longer and possibly has bending, a segmented edge detection method based on sobel can be adopted, so that a more closely-adhered glass outer edge is obtained, and the determination of the edge of the inner fringe of the glass is carried out according to the gradient change and the gradient change by adopting the edge detection method based on sobel.

How to identify a silk-screen edge is illustrated in one example: since there may be burrs, defects, etc. on the silk-screen edges, it is generally recommended to perform a search according to the line fitting method of the points, for example: according to the position of the glass edge, the inward area is a screen printing edge detection area, point position extraction is carried out by adopting a method of spacing points, fitting and correction are carried out in sections, and therefore, more accurate and reliable predicted screen printing edges are obtained.

And 120, translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge.

In the embodiment of the application, burrs may exist on the edge of the photovoltaic glass, burrs, excessive pixels and the like may exist on the edge of the silk screen, and if the defect detection is directly carried out on the edge of the silk screen, the burrs, the excessive pixels and the like may be mistakenly detected as defects, so that the problem of overdetection exists. Therefore, in the embodiment of the application, the photovoltaic glass edge and the silk-screen edge can be translated first, for example, the photovoltaic glass edge is directed towards the silk-screen edge, and then the silk-screen edge is directed towards the photovoltaic glass edge, so as to avoid factors such as burrs, excessive pixels and the like, and a detection area is obtained, and if silk-screen ink exists in the detection area, the silk-screen edge has the defect of multiple prints. Of course, the silk-screen edge can be translated for multiple times towards the direction away from the photovoltaic glass edge, so that factors such as burrs, excessive pixels and the like are avoided, a detection area is obtained, and if the silk-screen pattern is missing or incomplete in the area, the defect that the silk-screen edge generates few prints is indicated. Of course, other detection regions may be generated by other translation methods, as shown in fig. 4, and different detection regions may be generated by different translation methods.

And 130, detecting the photovoltaic glass silk-screen edge defect based on the pixel attribute of the pixels in the detection area.

In the embodiment of the application, the pixel attribute may be information for representing the pixel feature, for example, may be a position, a color, a gray value, and the like of the pixel. After the detection area is obtained, detecting defects of the silk-screen edge of the photovoltaic glass based on pixel attributes of pixels in the detection area, for example, if silk-screen ink exists in an extension area of the silk-screen edge, the defects of multiple prints generated on the silk-screen edge are indicated; the absence or incompleteness of the silk-screen pattern in the inner region of the silk-screen edge indicates that the silk-screen edge has a defect of less printing.

In the embodiment of the application, the defects of the silk-screen edges of the photovoltaic glass can be detected by an image processing technology. For example, photovoltaic glass silk-screen edge defects may be detected by texture analysis methods, which may detect defective areas by analyzing texture features in the image, which typically include gray level co-occurrence matrix (GLCM), wavelet transforms, and the like. The defects of the photovoltaic glass silk screen edge can also be detected by a color-based method, and for color images, the defects can be detected by utilizing color information, such as threshold segmentation, color feature extraction and the like of a color space. Machine learning algorithms, such as Support Vector Machines (SVMs), convolutional Neural Networks (CNNs), etc., may also be utilized to learn the characteristics of defects from the image and perform defect detection. Or screening the detection area based on the detection method of the blob analysis, and setting a fixed gray threshold according to the gray distribution of the whole white-keeping area and the silk-screen area to perform blob detection and the like. The man skilled in the art can select any mode to detect the defects of the silk-screen edges of the photovoltaic glass according to the actual requirements.

According to the method for detecting the defects of the silk-screen edges of the photovoltaic glass, the edges of the photovoltaic glass and the silk-screen edges are obtained by carrying out edge recognition on the obtained image to be detected; translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge; detecting a photovoltaic glass silk-screen edge defect based on pixel attributes of pixels in the detection region. According to the embodiment of the application, the photovoltaic glass edge and the silk-screen edge are automatically identified, and then the detection area is adaptively constructed according to the conditions of the photovoltaic glass edge and the silk-screen edge, so that the detected defect area is more reasonable, the whole is independent of a template image, and the accuracy of detecting the photovoltaic glass silk-screen edge can be improved.

In some embodiments, performing edge recognition on the acquired image to be detected includes:

Calculating gradients of all pixel points in a designated area of the image to be detected;

Gradients represent the change in gray values of pixels in an image, with the gradient values typically being larger at the edges. Therefore, the change of the gradient can be analyzed to find the position where the gradient value is large, thereby determining the outer edge position of the glass. Generally, the change in the gradient value forms a peak at the location of the outer edge of the photovoltaic glass.

In addition, as the position of the edge of the photovoltaic glass is at the outermost edge of the whole photovoltaic glass, the appointed area can be the area of the periphery of the photovoltaic glass, and the gradient change of each pixel point in the appointed area is only needed to be analyzed, so that the calculation resource is not needed to be wasted to calculate the gradient of all the pixel points in the image to be detected.

extracting the positions of pixel points in the region inside the edge of the photovoltaic glass through preset intervals;

and fitting and correcting the pixel points at the position to obtain the silk-screen edge.

In the detection of the silk-screen edge, firstly, a silk-screen area can be determined according to the position of the edge of the photovoltaic glass, and the area of the photovoltaic glass, which is inwards, is determined as the area where the silk-screen is located. The pixel point locations within the silk-screen area can then be extracted using a method of spacing points. This means that each pixel does not need to be extracted, but rather pixels at intervals can be selected for extraction to reduce the amount of data processed.

Next, after the positions of the pixels are extracted, the pixels at these positions may be fitted and corrected in segments. Specifically, the extracted pixel points can be divided into a plurality of segments, and then each segment of pixel points is fitted to obtain more accurate and reliable silk-screen edge positions. This can be achieved by fitting a curve or a straight line to better describe the shape of the silk-screened edge.

In some embodiments, translating the photovoltaic glass edge and the silk-screened edge to obtain a detection region formed by the translated photovoltaic glass edge and the translated silk-screened edge, comprising:

And translating the photovoltaic glass edge towards the silk-screen edge by a first preset distance, and translating the silk-screen edge towards the photovoltaic glass edge by a second preset distance to form a white-remaining detection area surrounded by the translated photovoltaic glass edge and the translated silk-screen edge.

In this embodiment, a detection area may be defined based on the identified photovoltaic glass edges and silk-screened edges: the detection area (the area between the inner edge of the glass and the silk screen edge) remains white.

As shown in fig. 5, the photovoltaic glass edge may be translated toward the silk-screen edge by a first preset distance, the silk-screen edge may be translated toward the photovoltaic glass edge by a second preset distance, and the vertex position may be modified according to the intersection point thereof, so as to form a white-remaining detection area surrounded by the translated photovoltaic glass edge and the translated silk-screen edge. The translated photovoltaic glass edge is used as the outer edge of the white-keeping detection area, and the translated silk-screen edge is used as the inner edge of the white-keeping detection area. The outer edge of the blank detection area represents a side close to the photovoltaic glass edge before translation, the inner edge of the blank detection area represents a side far away from the photovoltaic glass edge before translation, and the photovoltaic glass edge and the silk screen edge are not intersected when the photovoltaic glass edge and the silk screen edge are translated, so that a certain distance is kept between the photovoltaic glass edge and the silk screen edge all the time.

In the blank detection area, there is normally no screen ink, and if there is screen ink in this area, this indicates that the screen edge has a multi-printed defect.

In some embodiments, the first preset distance and the second preset distance are not preferably too large or too small. Preferably, the first preset distance is a maximum distance of the non-defective photovoltaic glass burrs, for example, the first preset distance can be a distance of 2 pixels, a distance of 3 pixels, a distance of 5 pixels, and the like; the second preset distance is a distance of 1-6 pixels, preferably a distance of 2 pixels, and of course, may be any one of a distance of 1 pixel, a distance of 3 pixels, a distance of 4 pixels, a distance of 5 pixels, and a distance of 6 pixels. Therefore, the influence of factors such as burrs, excessive pixels and the like in the detection process can be eliminated as much as possible, and the risks of over-detection and omission are reduced.

In this embodiment, another detection area may be defined based on the identified silk-screened edge: screen detection area (screen edge inward fixed distance).

As shown in fig. 5, the screen printing edge may be translated twice, and the screen printing edge is translated away from the photovoltaic glass edge by a third preset distance and translated by a fourth preset distance, so as to obtain a screen printing detection area surrounded by the translated screen printing edge, wherein one translated screen printing edge is used as an inner edge of the screen printing detection area, and the other translated screen printing edge is used as an outer edge of the screen printing detection area.

In the screen detection area, which is normally full of screen ink, if there is a missing or incomplete screen pattern in the area, this indicates that the screen edge has a few printed defects.

In some embodiments, the third preset distance and the fourth preset distance are not preferably too large or too small. Preferably, the third preset distance is a distance of 1-6 pixels, preferably a distance of 2 pixels, and of course, the third preset distance can be any one of a distance of 1 pixel, a distance of 3 pixels, a distance of 4 pixels, a distance of 5 pixels and a distance of 6 pixels; the fourth preset distance is a distance of 26-38 pixels, preferably a distance of 32 pixels, and of course, may be a distance of 26 pixels, a distance of 28 pixels, a distance of 30 pixels, a distance of 36 pixels, a distance of 38 pixels, or the like. Therefore, the influence of factors such as burrs, excessive pixels and the like in the detection process can be eliminated as much as possible, and the risks of over-detection and omission are reduced.

In some embodiments, detecting a photovoltaic glass silk-screened edge defect based on pixel attributes of pixels in a detection region includes:

Identifying different connected regions in the foreground region;

In this embodiment, the image may also be subjected to preprocessing, such as graying, denoising, etc., before the binarization processing is performed on the detection area, and then a fixed gray threshold value is set. The selection of this gray threshold may be predetermined by experimentation based on the gray distribution of the image and the characteristics of the target area.

Then, the detection area is subjected to binarization processing by using a preset gray threshold value, and a target area (such as a defect) and a background in the detection area are separated. This results in a binary image in which the target area is marked as foreground (typically white) and the background is marked as background (typically black).

And then carrying out connected region analysis on the foreground region to identify different connected regions in the image. The connected region refers to a region in the image, which is composed of adjacent pixels, and the pixels are spatially connected to form a whole. By way of example, after converting the detection area into a binarized image, the pixels in the foreground area may be marked as1, the pixels in the background area may be marked as 0, then each pixel in the image may be scanned row by row starting from the upper left corner of the image, for a pixel having a value of 1, checking whether the pixels adjacent in each direction thereof have been re-marked, if there are pixels already marked in the adjacent pixels, marking the current pixel as the same mark as the adjacent pixels, if there are pixels not marked in the adjacent pixels, marking the current pixel as a new mark, continuing to scan the next row of the image, repeating the above steps until the entire image is scanned, the same marked pixel points belonging to the same connected region, so that different connected regions in the image may be identified.

Finally, according to the characteristics (such as size, shape and the like) of the defects, the connected regions meeting the conditions are screened out as defect regions. This may be achieved by setting some threshold or rule, such as screening out connected areas with areas larger than a certain threshold as defects.

According to the photovoltaic glass silk-screen edge defect detection method provided by the embodiment of the application, the execution main body can be a photovoltaic glass silk-screen edge defect detection device. In the embodiment of the application, the photovoltaic glass silk-screen edge defect detection device provided by the embodiment of the application is described by taking the method for executing the photovoltaic glass silk-screen edge defect detection by the photovoltaic glass silk-screen edge defect detection device as an example.

The embodiment of the application also provides a device for detecting the edge defect of the photovoltaic glass screen printing.

As shown in fig. 6, the photovoltaic glass silk screen edge defect detection device includes:

The identifying module 610 is configured to perform edge identification on the acquired image to be detected, so as to obtain a photovoltaic glass edge and a silk-screen edge;

the translation module 620 is configured to translate the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge;

The detection module 630 is configured to detect a photovoltaic glass silk-screen edge defect based on a pixel attribute of a pixel in the detection area.

According to the photovoltaic glass silk-screen edge defect detection device, the edge recognition is carried out on the acquired image to be detected, so that the photovoltaic glass edge and the silk-screen edge are obtained; translating the photovoltaic glass edge and the silk-screen edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk-screen edge; detecting a photovoltaic glass silk-screen edge defect based on pixel attributes of pixels in the detection region. According to the embodiment of the application, the photovoltaic glass edge and the silk-screen edge are automatically identified, and then the detection area is adaptively constructed according to the conditions of the photovoltaic glass edge and the silk-screen edge, so that the detected defect area is more reasonable, the whole is independent of a template image, and the accuracy of detecting the photovoltaic glass silk-screen edge can be improved.

In some embodiments, the identification module 610 is further configured to:

calculating the gradient of each pixel point in the image to be detected;

In some embodiments, the identification module 610 is further configured to:

In some embodiments, translation module 620 is further configured to:

In some embodiments, the first predetermined distance is a maximum distance of non-defective photovoltaic glass burrs; the second preset distance is a distance of 1-6 pixels.

In some embodiments, translation module 620 is further configured to:

In some embodiments, the third predetermined distance is a distance of 1-6 pixels; the fourth preset distance is a distance of 26-38 pixels.

In some embodiments, the detection module 630 is further configured to:

Identifying different connected regions in the foreground region;

The photovoltaic glass silk-screen edge defect detection device in the embodiment of the application can be electronic equipment, and also can be a component in the electronic equipment, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. The electronic device may be a Mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a Mobile internet appliance (Mobile INTERNET DEVICE, MID), an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a robot, a wearable device, an ultra-Mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), etc., and may also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a Television (TV), a teller machine, a self-service machine, etc., which are not particularly limited in the embodiments of the present application.

The photovoltaic glass silk screen edge defect detection device in the embodiment of the application can be a device with an operating system. The operating system may be a microsoft (Windows) operating system, an Android operating system, an IOS operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.

In some embodiments, as shown in fig. 7, an electronic device 700 is further provided in the embodiments of the present application, which includes a processor 701, a memory 702, and a computer program stored in the memory 702 and capable of running on the processor 701, where the program when executed by the processor 701 implements the processes of the embodiments of the method for detecting edge defects of silk-screen glass on photovoltaic glass, and the same technical effects can be achieved, and for avoiding repetition, a detailed description is omitted herein.

The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.

The embodiment of the application also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, realizes the processes of the photovoltaic glass silk-screen edge defect detection method embodiment, and can achieve the same technical effects, and in order to avoid repetition, the description is omitted here.

The processor is a processor in the electronic device in the above embodiment. Readable storage media include computer readable storage media such as computer readable memory ROM, random access memory RAM, magnetic or optical disks, and the like.

The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the computer program realizes the photovoltaic glass silk-screen edge defect detection method when being executed by a processor.

The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the embodiment of the method for detecting the edge defects based on the photovoltaic glass screen printing, and the same technical effects can be achieved, so that repetition is avoided, and the description is omitted.

It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.

The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.

In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.

Claims

1. The method for detecting the edge defect of the screen printing of the photovoltaic glass is characterized by comprising the following steps of:

2. The method according to claim 1, wherein the performing edge recognition on the acquired image to be detected includes:

3. The method according to claim 1, wherein the performing edge recognition on the acquired image to be detected includes:

4. The method of claim 1, wherein translating the photovoltaic glass edge and the silk screened edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk screened edge comprises:

5. The method of claim 4, wherein the first predetermined distance is a maximum distance of non-defective photovoltaic glass burrs; the second preset distance is a distance of 1-6 pixels.

6. The method of claim 1, wherein translating the photovoltaic glass edge and the silk screened edge to obtain a detection area formed by the translated photovoltaic glass edge and the translated silk screened edge comprises:

7. The method of claim 6, wherein the third predetermined distance is a distance of 1-6 pixels; the fourth preset distance is a distance of 26-38 pixels.

8. The method of claim 1, wherein detecting photovoltaic glass silk-screened edge defects based on pixel attributes of pixels in the detection region comprises:

identifying different connected regions in the foreground region;

9. The utility model provides a photovoltaic glass silk screen printing edge defect detection device which characterized in that includes:

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-8 when the program is executed by the processor.