WO2023109446A1

WO2023109446A1 - Conductive particle identification method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023109446A1
Application number: PCT/CN2022/133789
Authority: WO
Inventors: 殷亚男; 朱小明; 张鑫; 匡梦良; 许超
Original assignee: 苏州镁伽科技有限公司
Priority date: 2021-12-16
Filing date: 2022-11-23
Publication date: 2023-06-22
Also published as: CN114359174A; CN114359174B

Abstract

Embodiments of the present invention provide a conductive particle identification method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring an image of a panel to be detected; identifying suspected positive carving parts and suspected negative carving parts in the image on the basis of gray values of pixels in the image; grouping the suspected positive carving parts and the suspected negative carving parts to obtain prediction particles; determining a contrast ratio of the suspected positive carving parts and the suspected negative carving parts in the prediction particles; and at least on the basis of the contrast ratio, identifying a prediction particle that satisfies sensitivity requirements among the prediction particles and identifying the prediction particle as a conductive particle. The interference of imaging noise is avoided, the accuracy of an identification result of the conductive particle is ensured, and possible errors are reduced. Moreover, an algorithm of the technical solution is simple and easy to implement, and the required calculation amount is small, such that the identification efficiency of the conductive particle can be effectively improved. Therefore, the accuracy and efficiency of panel detection are improved, and the user experience is improved.

Description

Conductive particle identification method, device, electronic equipment and storage medium

The present invention claims the priority of the Chinese patent application submitted to the State Intellectual Property Office of the People's Republic of China on December 16, 2021, with the application number 202111545102.8 and the application name "conductive particle identification method, device, electronic equipment and storage medium". The entire contents are incorporated herein by reference.

technical field

The present invention relates to the technical field of panel detection, and more specifically relates to a conductive particle identification method, a conductive particle identification device, an electronic device and a storage medium.

Background technique

Chip On Glass technology (Chip On Glass, referred to as COG) is a technology in which a driving circuit chip is directly bonded to a glass substrate, and is widely used in various display products such as liquid crystal display and electroluminescent technology. In the COG process, the conductive pins of the drive circuit are aligned with the electrodes (bumps) on the glass substrate, and the anisotropic conductive film (ACF) is used as the dielectric material for bonding, which is realized by high temperature and high pressure for a certain period of time. The connection and conduction of the conductive pins of the driving circuit and the electrodes on the glass substrate. Similarly, FPC On Glass (FOG for short) is a technology in which a flexible circuit board (FPC) is directly bound to a glass substrate, and the process is similar to COG. Similarly, chip on flexible substrate technology (Icon on film, COF for short) products are chip packaging products formed by directly packaging semiconductor chips on a flexible substrate, and then bonding the flexible substrate to a glass plate to form a chip package. products, and its manufacturing process is also similar to COG.

The panel inspection technology can be used to detect the indentation of conductive particles in the anisotropic conductive film between the glass electrode and the core electrode including the chip, so as to judge the quality of the panel according to certain standards. The properties of the conductive particles may affect the display function of the panel. Therefore, in the process of testing the panel, it is very important to identify and detect the conductive particles.

In the existing technical solutions for identifying conductive particles, the conductive particles in the image are generally directly identified only by the gray value of the pixels of the image. This is inevitably affected by various imaging noises. As a result, the recognition accuracy of the conductive particles is severely reduced, thereby reducing the accuracy of panel detection and affecting user experience.

Contents of the invention

The present invention has been made in consideration of the above-mentioned problems. According to one aspect of the present invention, a method for identifying conductive particles is provided. The method includes: acquiring an image of the panel to be detected; identifying a suspected intaglio part and a suspected intaglio part in the image based on the gray value of a pixel in the image, and the difference between the gray value of the suspected intaglio part and the gray value of its surrounding area The value is greater than the first predetermined value, and the difference between the gray value of the surrounding area of the suspected intaglio part and the gray value of the suspected intaglio part is greater than the second predetermined value; the suspected intaglio part and the suspected intaglio part are grouped to obtaining predicted particles, wherein each predicted particle includes a suspected inset portion and a suspected inset portion; determining a contrast ratio of the suspected overset portion and the suspected indented portion in the predicted particle; and identifying, based at least on the contrast ratio, in the predicted particle that meets the contrast requirement and identify the predicted particle as a conductive particle.

Exemplarily, based at least on the contrast ratio, identifying a predicted particle that meets the requirements among the predicted particles and identifying the predicted particle as a conductive particle includes: identifying a predicted particle that meets the sensitivity requirement among the predicted particles and identifying the predicted particle based on at least the contrast ratio. The predicted particles are identified as conductive particles, where contrast is positively correlated with sensitivity.

Exemplarily, based at least on the contrast ratio, identifying the predicted particle meeting the sensitivity requirement among the predicted particles and identifying the predicted particle as the conductive particle includes: calculating at least part of the predicted particle according to the contrast between the suspected indented part and the suspected indented part in at least part of the predicted particle Sensitivity of the particles; providing the calculated sensitivity to a user; and setting a sensitivity threshold in response to a setting operation by the user based on the calculated sensitivity; identifying a predicted particle greater than the sensitivity threshold among the predicted particles, and identifying the predicted particle as a conductive particle.

Exemplarily, identifying the suspected embossed part and suspected intaglio part in the image based on the grayscale value of the pixel in the image includes: based on the grayscale value of the pixel in the image, locating the electrode of the panel to be detected in the image; The gray value of the pixel of the electrode is used for image segmentation to identify the suspected positive engraving part and the suspected intaglio engraving part.

Exemplarily, identifying the suspected intaglio part and the suspected intaglio part in the image based on the gray value of the pixel in the image includes: locating the electrode of the panel to be detected in the image; and performing image segmentation based on the gray value of the pixel of the electrode , to identify the suspected embossed part and the suspected intaglio part; wherein, locating the electrode of the panel to be detected in the image includes: determining the position of the electrode based on the mark in the image; and adjusting the determined position in response to the user's operation .

Exemplarily, grouping the suspected overcast part and the suspected intaglio part to obtain the predicted particle includes: identifying the suspected overcast part and the suspected intaglio part meeting one or more of the following conditions as a predicted particle: The distance between the suspected overcast part and the suspected intaglio part is within a preset distance range; the arrangement direction of the suspected overcast part and the suspected intaglio part is within a preset angle range.

Exemplarily, grouping the suspected intaglio part and the suspected intaglio part to obtain the predicted particle includes: taking one of the suspected intaglio part and the suspected intaglio part as a reference part, and the other as a pending part, and performing the following operations ; For each reference part, predict the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle, so as to obtain the predicted area; based on the predicted area, determine the undetermined part corresponding to the reference part, so as to be determined by the reference part and the determined The undetermined part of constitutes the prediction particle.

Exemplarily, predicting the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle includes: determining the minimum envelope rectangle of the reference part; and moving the minimum envelope rectangle by k1*d according to the shadow direction of the conductive particle distance to obtain the second rectangle as the prediction area, where k1 represents the first scale factor, and d represents the diameter of the conductive particle.

Exemplarily, predicting the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle includes: calculating the center of the reference part; according to the shadow direction of the conductive particle, calculating the distance from the center of the reference part in the shadow direction as k2 The position of *d, wherein k2 represents the second proportional coefficient, and d represents the diameter of the conductive particle; take the calculated position as the center and k3*d as the side length to determine the square area as the prediction area, wherein k3 represents the third proportional coefficient .

Exemplarily, after identifying the suspected intaglio part and the suspected intaglio part in the image and before grouping the suspected intaglio part and the suspected intaglio part, the method further includes: performing a morphological operation on the image, removing interference regions to Causes the image to display only the identified positive and negative suspects.

According to another aspect of the present invention, a conductive particle identification device is also provided, and the device includes: an acquisition module for acquiring an image of the panel to be detected; The value identifies the suspected Yang engraving part and the suspected Yin engraving part in the image, the difference between the gray value of the suspected Yang engraving part and the gray value of its surrounding area is greater than the first predetermined value, and the gray value of the surrounding area of the suspected Yin engraving part The difference with the gray value of the suspected intaglio part is greater than a second predetermined value; the grouping module is used to group the suspected intaglio part and the suspected intaglio part to obtain predicted particles, wherein each predicted particle includes a suspected intaglio. an inscribed portion and a suspected intaglio portion; a determining contrast module for determining the contrast between the intaglio-suspected portion and the intaglio-likely portion of the predicted particles; and a particle identification module for identifying, based at least on the contrast, those of the predicted particles that meet the contrast requirement A particle is predicted and the predicted particle is identified as a conductive particle.

According to still another aspect of the present invention, there is also provided an electronic device, including a processor and a memory, wherein computer program instructions are stored in the memory, and the computer program instructions are used to perform the above-mentioned conductive particle identification when the processor is run. method.

According to still another aspect of the present invention, there is also provided a storage medium, on which program instructions are stored, and the program instructions are used to execute the method for identifying conductive particles as described above when running.

In the above technical solution, it is fully utilized that each conductive particle includes a positive engraved part and a negative engraved part, and the gray scale of both is different from the gray scale presented by the adhesive in the anisotropic conductive film, Conductive particles are predicted and identified through the relationship between the positive and negative portions of the conductive particles. This avoids interference from imaging noise, ensures the accuracy of the identification result of conductive particles, and reduces possible errors. At the same time, the algorithm of the technical solution is relatively simple, easy to implement, and requires a small amount of calculation, which can effectively improve the identification efficiency of conductive particles. As a result, the accuracy and efficiency of panel detection are improved, and user experience is improved.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail with reference to the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute limitations to the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

FIG. 1 shows a schematic flow chart of a method for identifying conductive particles according to an embodiment of the present invention;

Fig. 2 shows a partial schematic diagram of an image of a panel to be detected according to an embodiment of the present invention;

Fig. 3 shows a schematic flowchart of the steps of identifying suspected intaglio parts and suspected intaglio parts in an image according to an embodiment of the present invention;

Fig. 4 shows a schematic flowchart of the steps of locating the electrodes of the panel to be detected in the image according to one embodiment of the present invention;

Figure 5 shows a schematic diagram of a user interface according to an embodiment of the present invention;

Fig. 6 shows a schematic flow chart of grouping suspected intaglio parts and suspected intaglio parts to obtain predicted particles according to an embodiment of the present invention;

Fig. 7 shows a schematic flowchart of the steps of predicting the area where the undetermined part corresponding to the reference part is located according to an embodiment of the present invention;

Fig. 8 shows a schematic flowchart of the steps of predicting the area where the undetermined part corresponding to the reference part is located according to another embodiment of the present invention;

FIG. 9 shows a schematic flowchart of the steps of identifying predicted particles as conductive particles according to an embodiment of the present invention;

Fig. 10 shows a schematic block diagram of a conductive particle identification device according to an embodiment of the present invention;

Fig. 11 shows a schematic block diagram of an electronic device according to an embodiment of the present invention.

Detailed ways

In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only some embodiments of the present invention, rather than all embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments described here. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative effort shall fall within the protection scope of the present invention.

Fig. 1 shows a schematic flowchart of a method 100 for identifying conductive particles according to an embodiment of the present invention. As shown in FIG. 1 , the method 100 includes the following steps.

Step S110, acquiring an image of the panel to be inspected.

The image of the panel to be inspected may be an original image collected by an image acquisition device such as a camera in the panel inspection system, or an image obtained after preprocessing the original image. The preprocessing operations may include all operations for clearer panel detection. For example, preprocessing operations may include denoising operations such as filtering. The image may contain all or some of the electrodes in the panel to be inspected.

Step S130 , identifying suspected intaglio parts and suspected intaglio parts in the image based on grayscale values of pixels in the image. The difference between the gray value of the suspected embossed part and the suspected intaglio part and the gray value of the surrounding area is greater than a predetermined value. Specifically, the difference between the gray value of the suspected intaglio part and the gray value of its surrounding area is greater than the first predetermined value, and the difference between the gray value of the surrounding area of the suspected intaglio part and the gray value of the suspected intaglio part greater than the second predetermined value.

Fig. 2 shows a partial schematic diagram of an image of a panel to be inspected according to an embodiment of the present invention. The image of the panel to be inspected includes an electrode area 210 , such as the light gray rectangular area in FIG. 2 . The electrode region includes one or more conductive particles 220 . Conductive particles generally include an etched portion and an engraved portion. The embossed part and the negative part are generated due to the following phenomenon: when using, for example, a differential interference microscope (DIC) for imaging, the height difference between the conductive particles relative to the electrode is converted into a grayscale difference, As a result, the brightness of high places is enhanced, and the brightness of low places is reduced, thereby forming a contrast between light and dark, and enhancing the three-dimensional effect. The brightness of the embossed part is higher than that of the surrounding area, and the brightness of the intaglio part is lower than that of the surrounding area. This surrounding region is a region where the binder in the simple anisotropic conductive film is located. Referring to FIG. 2 , it is easy to see that the image includes a suspected embossed part 222 and a suspected intaglio part 221 . The suspected embossed part 222 and the suspected intaglio part 221 are parts with a relief shape, and the remaining smooth parts are the surrounding areas of the conductive particles. The suspected inscription part 222 is brighter than its surrounding area, and the difference between the gray value of the suspected inscription part 222 and the gray value of its surrounding area is greater than a first predetermined value. The suspected intaglio portion 221 is darker than its surrounding area, and the difference between the gray value of the surrounding area of the suspected intaglio portion 221 and the gray value of the suspected intaglio portion 221 is greater than a second predetermined value. The first predetermined value and the second predetermined value may be different due to differences in contrast of images. For example, the first predetermined value and the second predetermined value can be 30 and 20 respectively, that is to say, the gray value of the suspected intaglio part is at least 30 greater than the gray value of its surrounding area, and the surrounding area of the suspected intaglio part is larger than that of the surrounding area. Its own grayscale value is at least 20 greater. Any image segmentation method may be utilized to identify the suspected intaglio and suspected intaglio portions in the image. For example, image segmentation based on threshold, image segmentation based on gray histogram, etc. It can be understood that, in step S130 , the suspected embossed portion and the suspected indented portion are identified based on the gray value, which may not be the embossed portion and the indented portion of the real conductive particles. However, the suspected overset portion includes the overset portion of the real conductive particles, and the suspected intaglio portion includes the undercut portion of the real conductive particle. In other words, the suspected Yang engraving part includes the true Yang engraving part and the misrecognized false Yang engraving part, and the suspected intaglio part includes the true Yin engraving part and the misidentified false Yin engraving part.

Step S150, grouping suspected intaglio parts and suspected intaglio parts to obtain predicted particles. Each of the predicted particles includes a suspected overhang part and a suspected undercut part.

For example and not limitation, the suspected embossed parts and suspected intaglio parts on the panel to be inspected may be grouped by dividing the image into regions. Each group includes a suspected intaglio part and a suspected intaglio part, which constitute a predicted particle. If in the same image area, only one suspected embossed part and one suspected intaglio part are included, then it is a group. If there are multiple suspected intaglio parts and multiple suspected intaglio parts in the same image area, a suspected intaglio part and a suspected intaglio part with the closest distance can be regarded as a group according to the principle of proximity.

Step S170, determining the contrast between the suspected intaglio part and the suspected intaglio part in the predicted particle.

According to the gray value of the suspected embossed part and the gray value of the suspected intaglio part in the predicted particles, the contrast between the two is determined. From an image perspective, contrast is a measure of the different brightness levels of pixels. It can be understood that the larger the contrast value is, the more obvious the difference between the suspected embossed portion and the suspected intaglio portion is. Exemplarily, the gray value of the brightest pixel in the suspected intaglio portion can be subtracted from the grayscale value of the darkest pixel in the suspected intaglio portion, and the resulting difference can be used as the contrast between the suspected intaglio portion and the suspected intaglio portion .

For the conductive particles in the image of the panel to be detected, the contrast between the positive and negative parts can directly reflect the sensitivity of the conductive particles. That is, the contrast of the conductive particles is positively correlated with the sensitivity in a non-linear manner.

Step S190, at least based on the contrast ratio, identifying the predicted particles meeting the requirements among the predicted particles and identifying the predicted particles as conductive particles.

As mentioned earlier, contrast is a measure of the different brightness levels of pixels. Exemplarily, in the predicted particle, the contrast between the suspected intaglio part and the suspected intaglio part can be considered as a conductive particle if it meets the preset conditions, for example, when the contrast ratio of the suspected intaglio part and the suspected intaglio part in the predicted particle is greater than 40 , the predicted particle can be identified as a conductive particle. That is, in step S190 , among the predicted particles, the predicted particles that meet the contrast requirement can be directly identified as conductive particles. For example, particles whose contrast is higher than the contrast threshold are conductive particles that meet the contrast requirements; otherwise, they are not conductive particles.

As mentioned earlier, contrast is positively related to sensitivity. The contrast between the suspected intaglio portion and the suspected intaglio portion of the predicted particle can represent the sensitivity of the predicted particle to a certain extent. Exemplarily, in one embodiment, step S190 may include, based at least on the contrast ratio, identifying a predicted particle meeting the sensitivity requirement among the predicted particles and identifying the predicted particle as a conductive particle. Thus, the predicted particles that meet the sensitivity requirements can be identified simply based on the contrast, and these predicted particles are the conductive particles. Sensitivity requirements can meet the factory settings for the conductive particle detection function of most panels to be tested, or can be customized and modified by the user through the user interface. For example, particles whose sensitivity is higher than the sensitivity threshold are conductive particles that meet the sensitivity requirements; otherwise, they are not conductive particles. Sensitivity is more sensitive to users, and identifying conductive particles through sensitivity requirements can bring users a better experience.

Fig. 3 shows a schematic flowchart of the step S130 of identifying suspected intaglio parts and suspected intaglio parts in an image according to an embodiment of the present invention. As shown in Fig. 3, step S130 may include the following steps.

Step S131 , based on the gray value of the pixel in the image, locate the electrode of the panel to be inspected in the image.

Referring to Fig. 2 again, the light gray rectangular area in Fig. 2 is the electrode area of the panel to be tested, and the surrounding area of the electrode area is dark gray, obviously the two are obviously different. Therefore, for example, according to the difference in the gray value of the pixels in the image, the edge of the electrode of the panel to be detected can be determined, thereby realizing the positioning of the electrode.

Step S132 , image segmentation is performed based on the gray value of the pixel of the electrode, so as to identify suspected positive engraving parts and suspected intaglio engraving parts.

Exemplarily, the image segmentation can be performed according to the change of the gray value of the pixel of the electrode. According to Figure 2, it is not difficult to see that in most areas of the image, the gray value of the pixel does not fluctuate much. However, if the gray value suddenly becomes larger or smaller in a certain area, then the area is a part suspected of being engraved in relief or a part suspected of intaglio. Image segmentation can be performed for electrode regions on the image. The image segmentation operation can be realized by using the method of edge detection, a plurality of pixels whose gray values suddenly become larger are taken as the boundary, and the area inside the boundary is identified as a suspected inscription part. Similarly, a plurality of pixels whose gray value suddenly becomes smaller is used as a boundary, and an area inside the boundary is identified as a suspected intaglio portion.

Since the effective conductive particles are all distributed in the electrodes, and the distinction between the suspected positive engraving part and the suspected intaglio part is mainly related to the gray value of the pixel, in the above technical solution, the electrodes are positioned first, and then image segmentation is performed in the electrodes. According to the technical solution described above, the accuracy of the identified suspected sun-engraved parts and suspected intaglio-engraved parts can be guaranteed to a great extent. Moreover, the identification operation is simple and the feasibility is high.

It can be understood that, before identifying the conductive particles, the position of the electrode can be firstly located in the acquired image, and then the suspected embossed portion and the suspected intaglio portion on the electrode can be identified. The detection frame can be drawn automatically or manually for the electrode of the panel to be detected in the image, and the drawn detection frame coincides with the boundary of the electrode in the image as much as possible. In one embodiment, when identifying conductive particles, it is generally considered that the position of the detection frame is the position of the electrode in the image. However, due to various errors, the drawn detection frame often cannot completely coincide with the electrodes in the image. In this way, if the detection frame does not coincide with the boundary of the electrode, the detection result will be affected. How to locate the position of the electrode in the image will be specifically introduced below.

In another embodiment, step S130 identifying the suspected intaglio part and the suspected intaglio part in the image based on the gray value of the pixel in the image may further include: locating the electrode of the panel to be detected in the image, and based on the pixel of the electrode The gray value of the image is segmented to identify the suspected positive engraving part and the suspected intaglio part. Wherein, locating the electrodes of the panel to be detected in the image may include: determining the positions of the electrodes based on the marks in the images, and then adjusting the determined positions in response to user operations.

Specifically, FIG. 4 shows a schematic flowchart of the steps of locating the electrodes of the panel to be inspected in the image according to an embodiment of the present invention. As shown in FIG. 4 , locating the electrodes of the panel to be inspected in the image can be realized through the following steps S131a and S131b.

Step S131a, based on the markers in the image, determine the position of the electrodes.

Exemplarily, marks may be set on the panel to be tested, and the marks are usually set on both sides of the electrode area. The location of the electrodes can be determined based on the markers in the image. For example, markers include left markers and right markers. The area between the left and right marks is where the electrodes are located. Labels in images can be obtained, for example, by human or machine annotation. After the position of the mark in the image is determined, the position of the detection frame relative to the mark can be determined, such as the coordinates of the upper left vertex of the detection frame, so that the position and boundary of the detection frame can be determined.

Step S131b, adjusting the determined position in response to the user's operation.

Exemplarily, the user can observe the image of the panel to be inspected as shown in FIG. 2 through the user interface. And the user can also use an input device such as a mouse or a keyboard to trigger a "calibration button" (not shown in the figure) in the user interface. After the calibration button is triggered, in response to the user's operation, the boundary of the electrode in the image can be determined through the gray value difference. At this time, since the boundary of the electrode and the boundary of the detection frame have been determined, the distance between the boundaries of the two can also be determined, so in response to the user's operation, the boundary of the detection frame can be moved to a position that coincides with the boundary of the electrode in the image , to adjust the positions of the electrodes determined above.

Therefore, the position of the electrode can be quickly identified based on the marked points in the image, and the accuracy of the electrode position can be ensured through human-computer interaction operation. At the same time, the user's operation is simple and does not bring extra work to the user.

Exemplarily, after step S130 identifying the suspected intaglio portion and the suspected intaglio portion in the image and before step S150 grouping the suspected intaglio portion and the suspected intaglio portion, the above method 100 may further include: step S140, Morphological operations are performed on the image, and the interference area is removed so that the image only shows the identified suspected sun-engraved part and suspected intaglio-engraved part.

Exemplarily, morphological operations may include, for example, dilation, erosion, and the like. Specifically, for the dilation operation, a structural element can be used to scan each pixel in the image of the panel to be detected, and a logical "OR" operation can be performed between each pixel in the structural element and the pixels covered by it. If both are 0, then 0 for that pixel, 1 otherwise. On the contrary, the erosion operation can use a structural element to scan each pixel in the image, and use each pixel in the structural element to perform a logical "AND" operation with the pixels covered by it. If they are all 1, the pixel is 1, otherwise is 0. Normally, these two operations are performed sequentially.

Thus, the image of the panel to be inspected is smoothed. Not only can the interference area be eliminated, that is, the noise points smaller than the structural elements in the image can be eliminated, so that the image only shows the identified suspected embossed parts and suspected intaglio parts. It is also possible to ideally increase the suspected intaglio portion and the suspected intaglio portion in the image, thereby obtaining better predicted particles.

Exemplarily, the step S150 of grouping the suspected intaglio parts and the suspected intaglio parts to obtain predicted particles may be specifically implemented through the following scheme. Group suspected overlay parts and suspected undercut parts that meet one or more of the following conditions into a group and identify them as a predicted particle: Condition 1, the distance between the suspected overlay part and the suspected undercut part is within the predicted within the set range; condition 2, the angle between the arrangement directions of the suspected sun-engraved part and the suspected intaglio-engraved part is within the preset angle range.

According to the foregoing, multiple suspected sun-cut parts and suspected intaglio parts may have been identified. The distance between each suspected overcast part and each suspected intaglio part can be calculated separately. Then compare the obtained multiple distances with the set preset distance range. When the obtained distance is within the preset distance range, the suspected inset part and the suspected intaglio part corresponding to the distance can be identified as a predicted particle. Fig. 5 shows a schematic diagram of a user interface according to an embodiment of the present invention. Users can perform human-computer interaction through the user interface. In an embodiment, the preset range can be set by adjusting the operable control "distance between Yin and Yang" in Figure 5, for example, setting the operable control "distance between Yin and Yang" to 5, which is the maximum value of the preset distance range is 5, which means that when the distance between the suspected intaglio part and the suspected intaglio part is less than or equal to 5 pixels, the two can be identified as a predicted particle. The value can be adjusted by operating the arrow behind the operable control "Yin-Yang engraving distance". Operating the up arrow can increase the maximum value of the preset distance range, and operating the down arrow can decrease the maximum value of the preset distance range.

Alternatively, after a plurality of suspected intaglio parts and suspected intaglio parts are identified, the arrangement direction of each suspected intaglio part and each suspected intaglio part may be respectively determined. For an electrode, the signal flow direction of the electrode is usually its length direction. For the conductive particles therein, the arrangement direction of the embossed parts and the incised parts is also from top to bottom or from bottom to top. Therefore, by connecting the center of each suspected intaglio portion with the center of each suspected intaglio portion, the angle between the connecting line and the vertical line can be calculated. Afterwards, the calculated included angle is compared with the preset angle range, and when the obtained included angle is within the preset angle range, the suspected inscription part and the suspected intaglio part corresponding to the included angle can be identified as one predicted particles. Similarly, the preset angle range can be set differently according to user requirements. In the above two embodiments, a predicted particle includes a suspected intaglio part and a suspected intaglio part.

The above technical solution identifies predicted particles based on the distance between the suspected intaglio portion and the suspected intaglio portion and/or the arrangement direction of the two. The implementation scheme is not only simple in logic and easy to realize, but also the identified predicted particles are more accurate.

FIG. 6 shows a schematic flowchart of grouping suspected intaglio parts and suspected intaglio parts to obtain predicted particles in step S150 according to an embodiment of the present invention. In this embodiment, one of the suspected intaglio portion and the suspected intaglio portion is taken as a reference portion, and the other is a pending portion, and the following steps as shown in FIG. 6 are performed. It can be understood that any one of the suspected sun-engraved portion and the suspected intaglio-engraved portion can be used as a reference portion, and if the reference portion is determined, the remaining one is determined as a pending portion.

Step S151 , for each reference part, predict the area where the part to be determined corresponding to the reference part is located according to the shadow direction of the conductive particles, so as to obtain the predicted area.

Exemplarily, taking the suspected intaglio part as a reference part, the suspected intaglio part is a pending part. The shadow direction of the conductive particles can be set by using the operable control "Shadow Direction" in the user interface as shown in Figure 5, wherein it can be set as "upper shadow" or "lower shadow" (not shown in the figure). Wherein, "upper shadow" means that for a conductive particle, its incised part is located above the positive inscribed part, and in the image it is shown that the upper part is dark and the lower part is bright, that is, the shadow is on the upper part of the particle. The meaning of the "Shadow below" setting can be understood by reading the description of "Shadow above", so I won't repeat it here. In the case of a known reference part, such as a suspected intaglio part, the area where the suspected intaglio part corresponding to the suspected intaglio part can be predicted according to the shadow direction of the set conductive particles.

Step S152, based on the prediction area, determine the undetermined part corresponding to the reference part, so that the prediction particle is composed of the reference part and the determined undetermined part.

The undetermined portion corresponding to the reference portion can be determined within the prediction area. In the above example where the suspected intaglio part is the reference part, the suspected intaglio part corresponding to the suspected intaglio part can be determined in the obtained prediction area. If the predicted area does not contain the suspected intaglio part, then there is no predicted particle. Conversely, if the predicted area contains a suspected intaglio part, then the suspected intaglio part can form a predicted particle with the suspected intaglio part.

Thus, the predicted particle can be directly determined through the shadow direction of the conductive particle based on the imaging rule of the conductive particle. The method is simple and easy to implement. Moreover, the user can set the shadow direction of the conductive particles differently according to the actual acquisition of the image of the panel to be inspected, so that accurate identification of the predicted particles can be realized for different images.

Fig. 7 shows a schematic flow chart of predicting the area of the undetermined part corresponding to the reference part in step S151 according to an embodiment of the present invention. As shown in Fig. 7, step S151 may be implemented through the following steps.

Step S151a, determine the minimum enveloping rectangle of the reference part.

Still take the reference part as an example that is suspected to be inscribed in relief. Among them, the part suspected of being engraved in relief may be an irregular figure, for which the minimum envelope rectangle can be determined by algorithms such as OpenCV. This application does not set any limitation on the algorithm for calculating the minimum envelope rectangle, and any existing or future algorithm that can determine the minimum envelope rectangle of the reference part is within the protection scope of this application.

In step S151b, according to the shadow direction of the conductive particles, the minimum enclosing rectangle is moved by a distance of k1*d to obtain a second rectangle as a prediction area. Where k1 represents the first proportionality coefficient, and d represents the diameter of the conductive particles.

According to the shadow direction of the aforementioned conductive particles, for example, if it is set to "upper shadow", the second rectangle obtained after moving the determined minimum envelope rectangle upward by a distance of k1*d is used as the predicted area. If it is set to "lower shadow", the second rectangle obtained by moving the determined minimum envelope rectangle downward by a distance of k1*d is used as the prediction area. It can be understood that the user can set k1 to any value between 0.5-1 according to actual needs, so as to ensure the rationality of the prediction area.

In the above technical solution, the conditions for identifying the suspected intaglio part and the suspected intaglio part as a predicted particle are added, that is, the limitation of the diameter of the conductive particle and the direction of the shadow. This avoids the phenomenon that multiple suspected positive engraved parts and multiple suspected indented engraved parts are misidentified as one predicted particle when their distances are close, thereby ensuring the accuracy and reliability of the obtained predicted particles.

Fig. 8 shows a schematic flowchart of the steps of predicting the area where the undetermined part corresponding to the reference part is located according to another embodiment of the present invention. As shown in FIG. 8, step S151 may also be implemented through the following steps.

Step S151c, calculate the center of the reference part.

Still taking the example that the reference part is a suspected inscription part, the center of the suspected inscription part can be calculated. In this application, the algorithm for calculating the center of the reference part is not limited in any way, and any existing or future calculation method or scheme that can realize the calculation of the center of the reference part is within the scope of protection of this application.

Step S151d, according to the shadow direction of the conductive particle, calculate the position of the distance k2*d from the center of the reference part in the shadow direction. Where k2 represents the second proportionality coefficient, and d represents the diameter of the conductive particles.

Exemplarily, for example, if the shadow direction of the conductive particles is set to "upper shadow", then the calculated position above the reference part and the distance from the center of the reference part is k2*d, which can be represented by position coordinates. Similar to k1, users can set k2 to any value between 0.5 and 1 according to actual needs to ensure the rationality of the prediction area.

In step S151e, a square area is determined with the calculated position as the center and k3*d as the side length as the predicted area, where k3 represents the third scale factor.

Taking the position obtained by the above calculation as the center and k3*d as the side length, a square area can be determined as the prediction area. In this prediction area, the undetermined portion, which in the above example is the suspected inlay portion, is determined. Wherein, k3 can also be set to any reasonable value between 0.7-1.3.

As an alternative implementation of the above-mentioned technical solution, this solution not only ensures the accuracy of the obtained predicted particles, but also avoids the complicated operation of calculating the minimum enclosing rectangle of the geometric image, and it is simpler to replace it with an algorithm and easier to implement s solution.

Fig. 9 shows a schematic flowchart of the step S190 of identifying predicted particles as conductive particles according to an embodiment of the present invention. As shown in FIG. 9, step S190 may include the following steps.

Step S191 , calculating the sensitivity of at least part of the predicted particles according to the contrast between the suspected intaglio part and the suspected intaglio part in at least part of the predicted particles.

As mentioned earlier, the contrast of conductive particles is positively correlated with its sensitivity. Based on the mathematical relationship between the two, its sensitivity can be calculated from the contrast of the conductive particles.

Step S192, providing the calculated sensitivity to the user.

Exemplarily, the sensitivity obtained by the above calculation may be provided to the user through a user interface, so that the user may perform subsequent operations based on the sensitivity. It can be understood that the data can be provided to the user in the form of calculated sensitivity probability distribution data, so that the user can have a clearer understanding of the sensitivity of the predicted particles in the current image.

Step S193 , setting a sensitivity threshold in response to a user's setting operation based on the calculated sensitivity.

The user can use the operable control "sensitivity" in the user interface as shown in Figure 5 to set the sensitivity requirement. For example, increasing the sensitivity threshold by operating the up arrow and decreasing the sensitivity threshold by operating the down arrow. In one embodiment of the present application, the sensitivity threshold can be set to any integer between 0-100, and the user can customize it according to needs. The "27" shown in Figure 5 is only exemplary and does not constitute a Definition of sensitivity thresholds in applications. In this step, the user can set different sensitivity thresholds according to the requirements of the panel to be detected. Assuming that the quality requirements of the panel to be detected are relatively high, a higher sensitivity threshold can be set based on the currently calculated sensitivity; otherwise, vice versa.

Step S194, identifying a predicted particle larger than the sensitivity threshold among the predicted particles, and identifying the predicted particle as a conductive particle.

As mentioned above, the larger the value of the sensitivity of the predicted particle, the more likely the predicted particle is a conductive particle. For example, when the sensitivity obtained through calculation is greater than the sensitivity threshold set by the user, the predicted particle may be identified as a conductive particle. On the contrary, it is not a conductive particle.

According to the above technical solution, the sensitivity of the predicted particle can be calculated based on the contrast between the suspected inscription part and the suspected intaglio part of the predicted particle, and then can be provided to the user, so that the user can set the sensitivity threshold to identify the predicted particle. In this solution, the user can customize the sensitivity threshold based on the current image of the panel to be detected to meet the needs of different users. Ideal identification of predicted particles can be achieved based on the calculated sensitivity of predicted particles and the set sensitivity threshold.

According to another aspect of the present invention, a device for identifying conductive particles is also provided. Fig. 10 shows a schematic block diagram of a conductive particle identification device 1000 according to an embodiment of the present invention. As shown in FIG. 10 , the device 1000 includes an acquisition module 1010 , an embossed intaglio identification module 1020 , a grouping module 1030 , a contrast determination module 1040 and a particle identification module 1050 .

The acquisition module 1010 is used to acquire the image of the panel to be inspected.

The embossed intaglio identifying module 1020 is configured to identify suspected intaglio parts and suspected intaglio parts in the image based on gray values of pixels in the image. The difference between the gray value of the suspected positive engraved part and the gray value of its surrounding area is greater than the first predetermined value, and the difference between the gray value of the suspected engraved part's surrounding area and the gray value of the suspected engraved part is greater than the second predetermined value. predetermined value.

The grouping module 1030 is used for grouping suspected intaglio parts and suspected intaglio parts to obtain predicted particles. Wherein each predicted particle includes a suspected overhang part and a suspected undercut part.

The determining contrast module 1040 is used to determine the contrast between the suspected intaglio portion and the suspected intaglio portion in the predicted particles.

The particle identification module 1050 is configured to identify a predicted particle meeting the sensitivity requirement among the predicted particles based at least on the contrast ratio and identify the predicted particle as a conductive particle. The contrast is positively correlated with the sensitivity.

According to still another aspect of the present invention, an electronic device is also provided. Fig. 11 shows a schematic block diagram of an electronic device 1100 according to an embodiment of the present invention. As shown in FIG. 11 , the electronic device 1100 includes a processor 1110 and a memory 1120 . Wherein, the memory 1120 stores computer program instructions, and the computer program instructions are used to execute the conductive particle identification method 100 as described above when the computer program instructions are executed by the processor 1110 .

According to still another aspect of the present invention, a storage medium is also provided. Program instructions are stored on the storage medium, and the program instructions are used to execute the conductive particle identification method 100 as described above when running. The storage medium may include, for example, a storage unit of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory , or any combination of the above storage media. The computer readable storage medium can be any combination of one or more computer readable storage medium.

Those of ordinary skill in the art can understand the specific implementation schemes of the above-mentioned conductive particle identification device, electronic equipment and storage medium by reading the relevant description of the above-mentioned conductive particle identification method, and for the sake of brevity, details are not repeated here.

Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-described example embodiments are exemplary only and are not intended to limit the scope of the invention thereto. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another device, or some features may be omitted, or not implemented.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be understood that in the description of the exemplary embodiments of the invention, in order to streamline the disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure , or in its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the corresponding claims reflect, the inventive point lies in that the corresponding technical problem can be solved by using less than all features of a single disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

It will be appreciated by those skilled in the art that all features disclosed in this specification (including accompanying claims, abstract and drawings) and all features of any method or apparatus so disclosed may be used in any combination, except where the features are mutually exclusive. process or unit. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to realize some or all functions of some modules in the conductive particle identification device according to the embodiment of the present invention. The present invention can also be implemented as an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

The above is only a specific embodiment of the present invention or a description of the specific embodiment, and the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily Any changes or substitutions that come to mind should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

A method for identifying conductive particles, characterized in that the method comprises:

Obtain the image of the panel to be detected;

A suspected intaglio portion and a suspected intaglio portion in the image are identified based on grayscale values of pixels in the image, the difference between the grayscale value of the suspected intaglio portion and the grayscale value of its surrounding area is greater than a first A predetermined value, the difference between the gray value of the surrounding area of the suspected inscribed part and the gray value of the suspected inscribed part is greater than a second predetermined value;

grouping the suspected intaglio part and the suspected intaglio part to obtain predicted particles, wherein each predicted particle includes a suspected intaglio part and a suspected intaglio part;

determining the contrast between the suspected overprinted portion and the suspected indented portion of the predicted particle; and

Based at least on the contrast, a qualified one of the predicted particles is identified and identified as a conductive particle.
The method of claim 1, wherein said identifying qualified predicted particles among said predicted particles and identifying the predicted particles as conductive particles based at least on said contrast ratio comprises:

Identifying one of the predicted particles that meets a sensitivity requirement and identifying the predicted particle as a conductive particle based at least on the contrast ratio, wherein the contrast ratio is positively correlated with the sensitivity.
The method according to claim 2, wherein said identifying a predicted particle meeting a sensitivity requirement among said predicted particles based at least on said contrast ratio and identifying the predicted particle as a conductive particle comprises:

calculating the sensitivity of at least some of the predicted particles according to the contrast between the suspected intaglio portion and the suspected intaglio portion of the at least some of the predicted particles;

providing the calculated sensitivity to the user; and

setting a sensitivity threshold in response to a user setting operation based on the calculated sensitivity;

A predicted particle larger than the sensitivity threshold among the predicted particles is identified, and the predicted particle is identified as a conductive particle.
The method according to claim 1, wherein the identifying the suspected intaglio part and the suspected intaglio part in the image based on the gray value of the pixel in the image comprises:

locating electrodes of the panel to be inspected in the image based on grayscale values of pixels in the image; and

Image segmentation is performed based on gray values of pixels of the electrodes to identify the suspected intaglio portion and the suspected intaglio portion.
The method according to claim 1, wherein the identifying the suspected intaglio part and the suspected intaglio part in the image based on the gray value of the pixel in the image comprises:

locating electrodes of the panel to be inspected in the image; and

performing image segmentation based on the gray value of the pixel of the electrode to identify the suspected embossed part and the suspected intaglio part;

Wherein, the positioning of the electrodes of the panel to be detected in the image includes:

determining the location of the electrodes based on markers in the image; and

The determined position is adjusted in response to a user's operation.
The method according to claim 1, wherein said grouping said suspected intaglio parts and said suspected intaglio parts to obtain predicted particles comprises:

A suspected overlay part and a suspected intaglio part meeting one or more of the following conditions are identified as a predicted particle:

The distance between the suspected overcast part and the suspected intaglio part is within the preset distance range;

The arrangement direction of the suspected sun-engraved portion and the suspected intaglio-engraved portion is within a preset angle range.
The method according to claim 1, wherein said grouping said suspected intaglio parts and said suspected intaglio parts to obtain predicted particles comprises:

Taking one of the suspected intaglio portion and the suspected intaglio portion as a reference portion, and the other as a pending portion, perform the following operations;

For each reference part, predict the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle, so as to obtain the predicted area;

Based on the predicted area, determine the undetermined part corresponding to the reference part, so that the predicted particle is composed of the reference part and the determined undetermined part.
The method according to claim 7, wherein said predicting the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle comprises:

determining a minimum enclosing rectangle for the reference portion; and

According to the shadow direction of the conductive particles, move the minimum envelope rectangle by a distance of k1*d to obtain a second rectangle as the prediction area, where k1 represents the first proportional coefficient, and d represents the distance of the conductive particles diameter.
The method according to claim 7, wherein said predicting the area where the undetermined part corresponding to the reference part is located according to the shadow direction of the conductive particle comprises:

calculating the center of the reference portion;

According to the shadow direction of the conductive particles, calculate the position of k2*d from the center of the reference part in the shadow direction, where k2 represents the second proportionality factor, and d represents the diameter of the conductive particles;

A square area is determined with the calculated position as the center and k3*d as the side length as the prediction area, where k3 represents a third scale factor.
The method of claim 1 , wherein after identifying the suspected intaglio portion and the suspected intaglio portion in the image and before said grouping the suspected inset portion and the suspected intaglio portion, The method also includes:

A morphological operation is performed on the image, and interference regions are eliminated so that the image only displays the identified suspected intaglio parts and suspected intaglio parts.
A conductive particle identification device, characterized in that the device comprises:

Obtaining module, for obtaining the image of panel to be detected;

An embossed intaglio identification module, configured to identify a suspected intaglio part and a suspected intaglio part in the image based on the gray value of a pixel in the image, the gray value of the suspected embossed part and its surrounding area The difference in grayscale value is greater than a first predetermined value, and the difference between the grayscale value of the surrounding area of the suspected intaglio part and the grayscale value of the suspected intaglio part is greater than a second predetermined value;

A grouping module, configured to group the suspected intaglio parts and the suspected intaglio parts to obtain predicted particles, wherein each predicted particle includes a suspected intaglio part and a suspected intaglio part;

determining a contrast module, configured to determine the contrast between the suspected overcast part and the suspected intaglio part in the predicted particle; and

A particle identification module, configured to identify a predicted particle meeting the contrast requirement among the predicted particles based at least on the contrast ratio and identify the predicted particle as a conductive particle.
An electronic device, characterized by comprising a processor and a memory, wherein computer program instructions are stored in the memory, and the computer program instructions are used to execute any one of claims 1 to 10 when run by the processor. The conductive particle identification method described in the item.
A storage medium, characterized in that program instructions are stored on the storage medium, and the program instructions are used to execute the conductive particle identification method according to any one of claims 1 to 10 when running.