Glue path quality detection method, detection device and detection system

Abstract

The invention discloses a glue path quality detection method, a glue path quality detection device and a glue path quality detection system. The glue path quality detection method comprises the following steps: acquiring a glue path binary image, wherein the glue path binary image comprises a glue path area; in the glue path binary image, setting a glue detection area based on a glue path area; setting an end-to-end neglect detection proportion of the glue road area; and performing defect detection on the glue path area in the glue detection area based on the head-tail neglect detection proportion. Therefore, a normal glue path area can be prevented from being misjudged as a defect, and the accuracy of glue path quality detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular to a glue road quality detection method, a glue road quality detection device and a glue road quality detection system. Background Art

[0002] In the automated glue path inspection operation, it is necessary to determine whether there are defects in the glue path after dispensing, such as excess glue defect, insufficient glue defect, broken glue defect, etc. The glue path can be inspected for defects through visual algorithms, but the actual glue path may have inconsistent widths in some areas, which can easily lead to misjudgment. Therefore, how to improve the accuracy of glue path quality inspection is an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a glue road quality detection method, a glue road quality detection device, a glue road quality detection system and a computer-readable storage medium to solve at least one of the above-mentioned technical problems.

[0004] The method for detecting the quality of a rubber road according to the embodiment of the present application comprises:

[0005] Acquire a glue road binary image, wherein the glue road binary image includes a glue road area;

[0006] In the glue path binary image, setting a glue inspection area based on the glue path area;

[0007] Set the head and tail ignore detection ratio of the glue path area;

[0008] Based on the head-to-tail neglected detection ratio, defect detection is performed on the glue path area in the glue inspection area.

[0009] In some embodiments, before the glue inspection area performs defect detection on the glue path area based on the head-tail ignored detection ratio, the glue path quality detection method further includes:

[0010] Determine whether to enable the head and tail ignore detection function;

[0011] When the head-end-ignoring detection function is not enabled, determining a first actual detection area according to the glue detection area;

[0012] Perform defect detection on the glue path area in the first actual detection area;

[0013] The step of performing defect detection on the glue path area in the glue inspection area based on the head-tail ignored detection ratio includes:

[0014] When the head and tail ignoring detection function is turned on, the glue path length of the glue path area in the glue inspection area is calculated;

[0015] Determining a second actual detection area based on the glue path length and the head-to-tail ignored detection ratio;

[0016] The glue path area is inspected for defects in the second actual inspection area.

[0017] In some embodiments, the number of the glue inspection areas is multiple, and the glue path quality inspection method further includes:

[0018] For each of the glue inspection areas, respectively set a defect detection threshold;

[0019] The performing defect detection on the glue path area in the glue inspection area includes:

[0020] In each of the glue inspection areas, defect inspection is performed on the glue path area according to the corresponding defect detection threshold.

[0021] In some embodiments, the glue inspection area includes a central track, the defects include insufficient glue defect, excessive glue defect, glue break defect and glue deviation defect, and in each of the glue inspection areas, defect detection is performed on the glue path area according to the corresponding defect detection threshold, including:

[0022] In the glue inspection area, edge detection is performed on the glue path area based on the central track to obtain a plurality of edge point pairs distributed along both sides of the central track;

[0023] Determine the glue path width corresponding to each edge point pair according to the plurality of edge point pairs;

[0024] Determine the connected domain information of the glue road area according to a connected domain analysis algorithm;

[0025] Detecting the glue path area for the insufficient glue defect, the excessive glue defect, the glue break defect, and the glue deviation defect according to the glue path width, the connected domain information, and the defect detection threshold;

[0026] The glue path information of the glue path area is determined according to the plurality of edge point pairs and the connected domain information, wherein the glue path information includes glue quantity information, glue length information and glue width information.

[0027] In some embodiments, the defect detection threshold includes a low glue defect threshold, a high glue defect threshold, a broken glue defect threshold, and a glue deviation defect threshold, and the detection of the low glue defect, the high glue defect, the broken glue defect, and the glue deviation defect in the glue path area according to the glue path width, the connected domain information, and the defect detection threshold includes:

[0028] Detecting the glue shortage defect in the glue path area according to the glue path width and the glue shortage defect threshold;

[0029] Detecting the multiple glue defects in the glue path area according to the glue path width and the multiple glue defect threshold;

[0030] Detecting the glue break defect in the glue path area according to the glue path width and the glue break defect threshold;

[0031] The glue deviation defect is detected in the glue path area according to the connected domain information and the glue deviation defect threshold.

[0032] In some embodiments, the glue break defect includes a straight glue break defect and an oblique glue break defect, the glue break defect threshold includes a straight glue break defect threshold, and the detection of the glue break defect in the glue path area according to the glue path width and the glue break defect threshold includes:

[0033] Determining whether the glue path width is zero, wherein when there are no edge point pairs on both sides of the center track, the glue path width is zero;

[0034] Obtain the length of the region where the width of the glue path is continuously zero;

[0035] When the length of the region is greater than the straight-mouth glue break defect threshold, it is determined that the straight-mouth glue break defect exists;

[0036] When the glue path width is not zero and there are disconnected glue path areas along the central trajectory, it is determined that the oblique glue break defect exists.

[0037] In some embodiments, after performing defect detection on the glue path area in each of the glue inspection areas according to the corresponding defect detection threshold, performing defect detection on the glue path area in the glue inspection area further includes:

[0038] Determining whether it is necessary to merge defects in a plurality of the glue inspection areas;

[0039] When there is no need to merge defects of the plurality of glue inspection areas, the defect information and the glue path information of each glue inspection area are outputted respectively;

[0040] When it is necessary to merge defects in the plurality of glue inspection areas, determining whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas;

[0041] When the same type of defects in at least two consecutive glue inspection areas are connected among the multiple glue inspection areas, the same type of defects in the at least two glue inspection areas are merged into one of the glue inspection areas, and the defect information and the glue path information of each glue inspection area are output respectively.

[0042] In some embodiments, the determining whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas comprises:

[0043] sequentially determining in each of two adjacent glue inspection areas whether an end point of the last defect in the first glue inspection area is the same as a starting point of the first defect in the second glue inspection area and whether they are of the same type;

[0044] In two adjacent glue inspection areas, when the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area and they are of the same type, it is determined that the defects in the two adjacent glue inspection areas are connected;

[0045] According to the connectivity of the defects in the plurality of glue inspection areas, it is determined whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas.

[0046] The glue road quality detection device of the embodiment of the present application includes:

[0047] An acquisition module, used for acquiring a binary image of a glue path, wherein the binary image of the glue path includes a glue path area;

[0048] A first setting module, used for setting a glue inspection area based on the glue road area in the glue road binary image;

[0049] The second setting module is used to set the head and tail ignored detection ratio of the glue path area;

[0050] The detection module is used to perform defect detection on the glue path area in the glue inspection area based on the head and tail ignoring detection ratio.

[0051] The glue road quality detection system of the implementation mode of the present application includes one or more processors and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the glue road quality detection method of any of the above implementation modes is implemented.

[0052] The computer-readable storage medium of the embodiment of the present application stores a computer program thereon, and when the program is executed by a processor, the glue path quality detection method of any of the above-mentioned embodiments is implemented.

[0053] In the glue road quality detection method, glue road quality detection device, glue road quality detection system and computer readable storage medium of the embodiment of the present application, by setting the head and tail neglect detection ratio of the glue road area, based on the head and tail neglect detection ratio, the glue road area is inspected for defects in the glue inspection area. In this way, it is possible to prevent the normal glue road area from being misjudged as a defect, and improve the accuracy of the glue road quality detection.

[0054] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0056] Figure 1 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0057] Figure 2 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0058] Figure 3 is a schematic diagram of a binary image of a glue path according to certain embodiments of the present application;

[0059] Figure 4 is a schematic diagram of a glue inspection area provided in a glue path binary image of certain embodiments of the present application;

[0060] Figure 5 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0061] Figure 6 is a schematic diagram of a first actual detection area when the head-end ignoring detection function is not enabled in certain embodiments of the present application;

[0062] Figure 7 is a schematic diagram of a second actual detection area when the head and tail ignored detection ratio is zero in certain embodiments of the present application;

[0063] Figure 8 is a schematic diagram of a second actual detection area when the head and tail ignored detection ratio is 0.1 in some embodiments of the present application;

[0064] Fig. 9 It is a schematic diagram of the detection result of the glue detection area when the head and tail ignoring detection function is not enabled in some embodiments of the present application;

[0065] Fig.10is a schematic diagram of the detection results of the glue detection area when the head and tail ignored detection ratio is zero in certain embodiments of the present application;

[0066] Fig.11 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0067] Fig.12 It is a schematic diagram of a binary image of a glue path in certain embodiments of the present application having multiple glue inspection areas;

[0068] Fig.13 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0069] Fig.14 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0070] Fig.15 It is a schematic diagram of the detection result of glue deficiency defect in certain embodiments of the present application;

[0071] Fig.16 It is a schematic diagram of the detection results of multiple glue defects in certain embodiments of the present application;

[0072] Fig.17 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0073] Fig.18 It is a comparative schematic diagram of a straight-mouth glue break defect and an oblique-mouth glue break defect in certain embodiments of the present application;

[0074] Fig.19 It is a schematic diagram of the detection result of the straight mouth glue break defect in certain embodiments of the present application;

[0075] Fig. 20 It is a schematic diagram of the detection result of the oblique glue break defect in certain embodiments of the present application;

[0076] Fig.21 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0077] Fig. 22 is a schematic diagram of detection results when defect merging is not performed in certain implementation modes of the present application;

[0078] Fig.23 is a schematic diagram of detection results when defects are merged in certain implementation modes of the present application;

[0079] Fig.24 It is a schematic flow chart of a method for detecting the quality of a rubber road according to certain embodiments of the present application;

[0080] Fig.25It is a schematic diagram of a module of a glue road quality detection device according to certain embodiments of the present application;

[0081] Fig.26 is a schematic diagram of a module of a rubber road quality detection system according to certain embodiments of the present application;

[0082] Fig. 27 It is a schematic diagram of the connection status between a computer-readable storage medium and a processor in certain embodiments of the present application. DETAILED DESCRIPTION

[0083] The following is a further description of the embodiments of the present application in conjunction with the accompanying drawings. The same or similar reference numerals in the accompanying drawings represent the same or similar elements or elements with the same or similar functions from beginning to end. In addition, the embodiments of the present application described below in conjunction with the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and cannot be understood as limiting the present application.

[0084] See also Figure 1 and Figure 2 The present application provides a method for detecting the quality of a rubber road, including:

[0085] 010: Get the glue road binary image, which includes the glue road area;

[0086] 020: In the glue path binary image, set the glue inspection area based on the glue path area;

[0087] 030: Set the ratio of the head and tail of the glue path area to ignore detection;

[0088] 040: Based on the ratio of the first and the last ignored detection, defect detection is performed on the glue path area in the glue inspection area.

[0089] In the glue road quality detection method of the embodiment of the present application, by setting the head and tail ignored detection ratio of the glue road area, based on the head and tail ignored detection ratio, the glue road area is detected for defects in the glue inspection area. In this way, it is possible to prevent the normal glue road area from being misjudged as a defect, thereby improving the accuracy of the glue road quality detection.

[0090] Specifically, after gluing products such as smart phones, smart watches, speakers, motors, and lenses, the glue path of the product is photographed to obtain the image to be detected. A series of image preprocessing operations are performed on the image to be detected, such as binarization, to obtain the corresponding glue path binary image. The glue path binary image includes the glue path area, which is the area corresponding to the glue path formed by gluing in the glue path binary image, and the grayscale value is 255. Figure 3 The white area in the figure is the glue path area. The number of the glue path areas can be one or more.

[0091] In the glue path binary image, the glue inspection area (such as Figure 4 As shown in the rectangular box in the middle, in the subsequent defect detection operation, it is only necessary to perform defect detection in the glue inspection area. Since the product glue path can be in various shapes such as annular, linear, S-shaped, etc., the glue path area can also be in various shapes such as annular, linear, S-shaped, etc., and correspondingly, the glue inspection area can be set to different shapes according to different glue path areas. A glue inspection area can include one or more glue path areas.

[0092] After that, the head and tail ignored detection ratio of the glue path area is set. The head and tail ignored detection ratio refers to the ratio of the head sub-area and / or tail sub-area that can be ignored in the glue inspection area. Based on the set head and tail ignored detection ratio, the glue path area is inspected for defects in the glue inspection area.

[0093] For example, if the head and tail ignored detection ratio is set to 0.1, when performing defect detection, the first 10% of the glue path area is taken as the head sub-area, and the last 10% of the glue path area is taken as the tail sub-area. Only the glue path area between the head sub-area and the tail sub-area is tested for defects, and the head sub-area and the tail sub-area do not participate in defect detection. The head and tail ignored detection ratio can be set differently according to the actual situation of the glue path area.

[0094] In actual production, the amount of glue is small when starting and falling, which is manifested in the binary image of the glue path as the width of the head sub-region and the tail sub-region of the glue path area is smaller than the middle sub-region of the glue path area (such as Figure 4 If defect detection is performed in the entire glue inspection area, a glue shortage defect (which will be described in detail later) may be detected in the glue inspection area, resulting in a misjudgment. In addition, the size of the glue inspection area may be larger than the size of the glue path area. For example, the length of the glue inspection area is larger than the length of the glue path area. If defect detection is performed in the entire glue inspection area, a glue break defect (which will be described in detail later) may be detected in the glue inspection area, resulting in a misjudgment.

[0095] In the embodiment of the present application, the detection is performed in the glue inspection area based on the head-end ignored detection ratio, and the normal glue road area that may affect the detection result is excluded. In this way, the normal glue road area is prevented from being misjudged as a defect, and the accuracy of glue road quality detection is improved.

[0096] See also Figure 5 In some embodiments, before performing defect detection on the glue path area in the glue inspection area (i.e., 040) based on the head-tail neglect detection ratio, the glue path quality detection method further includes:

[0097] 050: Determine whether to enable the head and tail ignore detection function;

[0098] 060: When the head and tail ignoring detection function is not enabled, determine the first actual detection area according to the glue inspection area;

[0099] 070: Perform defect detection on the glue path area in the first actual detection area;

[0100] Based on the head and tail ignoring detection ratio, perform defect detection on the glue path area in the glue inspection area (i.e., 040), including:

[0101] 041: When the head and tail ignoring detection function is enabled, calculate the glue path length of the glue path area in the glue inspection area;

[0102] 042: Based on the glue path length and the head and tail ignoring detection ratio, determine the second actual detection area;

[0103] 043: Perform defect detection on the glue path area in the second actual detection area.

[0104] Specifically, in actual applications, users can choose to enable or disable the head and tail ignoring detection function according to the actual situation of the glue path area. For example, when both the starting point and the ending point of the glue inspection area belong to the points in the glue path area, or the glue path area in the glue inspection area does not include the glue starting area and the glue dropping area, users can choose not to enable the head and tail ignoring detection function. Conversely, they can choose to enable the head and tail ignoring detection function. The starting point and the ending point of the glue inspection area can be the starting point and the ending point of the central trajectory line of the glue inspection area (which will be introduced in detail later).

[0105] Therefore, before performing defect detection on the glue path area in the glue inspection area based on the head and tail ignoring detection ratio, first determine whether the head and tail ignoring detection function is enabled. When the head and tail ignoring detection function is not enabled, the first actual detection area can be directly determined according to the glue inspection area. For example, directly use the glue inspection area as the first actual detection area (as Figure 6 shown), and perform defect detection on the glue path area in the first actual detection area.

[0106] When the head and tail ignoring detection function is enabled, the second actual detection area needs to be determined according to the glue path area in the glue inspection area. The process of determining the second actual detection area is as follows: Calculate the glue path length of the glue path area in the glue inspection area. The glue path length can be the length of the glue path area along the center line direction of the glue inspection area. Based on the glue path length and the head and tail ignoring detection ratio, the second actual detection area can be determined.

[0107] For example, if the glue path length is L, the starting point of the glue path is x_start, the ending point of the glue path is x_end, and x_start < x_end, when the head and tail ignoring detection ratio is set to 0, then use the starting point and the ending point of the glue path area as the starting point and the ending point of the second actual detection area (as Figure 7When the head and tail ignoring detection ratio is set to 0.1, the starting point of the second actual detection area is x_start+0.1×L, and the end point is x_end–0.1×L (as shown in Figure 8 As shown in FIG. 1 ). The width of the second actual inspection area can be consistent with the width of the glue inspection area. Then, the glue path area is inspected for defects in the second actual inspection area.

[0108] The research found that Figure 3 Take the defect detection of the glue path area in the example as an example. Figure 3 There are no defects in the glue path area. Fig. 9 As shown in the figure, when the head and tail ignoring detection function is not enabled, glue break defects and glue shortage defects will be detected; Fig.10 As shown in the figure, when the head-to-tail ignoring detection function is turned on, but the head-to-tail ignoring detection ratio is 0, the defect of insufficient glue will be detected; when the head-to-tail ignoring detection function is turned on and the head-to-tail ignoring detection ratio is 0.1, no defect will be detected. It can be seen that defect detection of the glue path area based on the head-to-tail ignoring detection ratio can effectively prevent false detection during the glue path quality inspection process.

[0109] See also Figure 2 and Fig.11 In some embodiments, the number of the glue inspection areas is multiple. The glue road quality inspection method also includes:

[0110] 080: For each glue inspection area, set the defect detection threshold separately;

[0111] In the glue inspection area, the glue path area is inspected for defects (i.e. 040), including:

[0112] 044: In each glue inspection area, defect detection is performed on the glue path area according to the corresponding defect detection threshold.

[0113] Specifically, during the defect detection process, it is necessary to set a defect detection threshold as an evaluation indicator for evaluating whether there are defects. However, the shape of the glue path area is complex and changeable, and the glue path width and other dimensions at different locations may be different. Using the same defect detection threshold for a glue path area may result in missed detection and false detection. Therefore, multiple glue detection areas can be set according to the shape of the glue path area, and the sizes of the multiple glue detection areas can be the same or different. Fig.12 As shown, a total of 4 glue inspection areas are set, and the sizes of the 4 glue inspection areas are different.

[0114] For multiple glue inspection areas, different head and tail ignored detection ratios can be set respectively, and defect detection can be performed on the glue path areas respectively. Different defect detection thresholds can also be set for each glue inspection area, so that in each glue inspection area, defect detection can be performed on the glue path area according to the corresponding defect detection threshold. In this way, missed detection and false detection in the glue path quality detection process can be effectively prevented, and the accuracy of glue path quality detection can be further improved.

[0115] See also Fig.13 In some embodiments, the glue inspection area includes a center track. Defects include insufficient glue defect, excessive glue defect, glue break defect and glue deviation defect. In each glue inspection area, defect detection (i.e. 044) is performed on the glue path area according to the corresponding defect detection threshold, including:

[0116] 0441: In the glue inspection area, edge detection is performed on the glue path area based on the center track to obtain multiple edge point pairs distributed on both sides of the center track;

[0117] 0442: Determine the glue path width corresponding to each edge point pair according to multiple edge point pairs;

[0118] 0443: Determine the connected domain information of the rubber road area according to the connected domain analysis algorithm;

[0119] 0444: Detect glue path area defects such as insufficient glue, excessive glue, glue breakage and glue deviation according to glue path width, connected domain information and defect detection threshold;

[0120] 0445: Determine glue path information of the glue path area according to multiple edge point pairs and connected domain information, wherein the glue path information includes glue quantity information, glue length information and glue width information.

[0121] Specifically, defects include any one or more of insufficient glue defect, excessive glue defect, broken glue defect and glue deviation defect. Excess glue defect means that the actual glue path partially overflows the edge of the template glue path. Insufficient glue defect means that the actual glue path is less than the template glue path. Broken glue defect means that the template glue path is connected, but the actual glue path is disconnected. Glue deviation defect means that the actual glue path deviates from the template glue path in whole or in part.

[0122] The glue inspection area includes the center track (that is, the center line mentioned above). In the glue inspection area, edge detection is performed on the glue path area on both sides of the center track along a direction perpendicular to the center track. It should be noted that the center track can be a straight line or a curve. When the center track is a curve, the direction perpendicular to the center track is also the normal direction of the center track. For annular or S-shaped special-shaped glue path areas, edge detection is performed along the direction perpendicular to the center track, which can more accurately capture the edge of the special-shaped glue path, thereby improving the accuracy of subsequent defect detection.

[0123] The two sides of the center track are divided into the left side and the right side. Starting from any point on the center track, the edge detection of the glue path is performed to the left along the direction perpendicular to the center track. The point that transitions from light (grayscale value is 255) to dark (grayscale value is 0) is the left edge point; the edge detection of the glue path is performed to the right along the direction perpendicular to the center track. The point that transitions from light to dark is the right edge point. A left edge point and a corresponding right edge point constitute an edge point pair distributed along the two sides of the center track.

[0124] The width of the glue path corresponding to each edge point pair can be calculated based on multiple edge point pairs. For example, the distance between the left edge point and the right edge point can be calculated to obtain the corresponding glue path width. The connected domain information of the glue path area can be determined based on the connected domain analysis algorithm, and the connected domain analysis algorithm can use the Blob analysis algorithm. The connected domain analysis algorithm can be used to analyze one or more regions composed of adjacent pixels with the same grayscale value in the glue inspection area to obtain connected domain information, wherein the region composed of pixels with a grayscale value of 255 is the glue path area.

[0125] Afterwards, the glue path area can be detected for insufficient glue defects, excessive glue defects, glue break defects, and glue deviation defects based on the glue path width, connected domain information, and defect detection threshold. The glue path information of the glue path area can be determined based on multiple edge point pairs and connected domain information, where the glue path information includes glue quantity information, glue length information, and glue width information. The glue quantity information can evaluate the glue quantity of the glue dispensed, the glue length information can evaluate the length of the glue dispensed, and the glue width information can evaluate the width of the glue dispensed, thereby determining whether secondary glue filling or correction is required.

[0126] The glue quantity information can be calculated based on the connected domain information. Based on the connected domain information, the area of ​​the glue path area in the glue inspection area is calculated. When the glue inspection area includes multiple glue path areas, the total area of ​​the multiple glue path areas is calculated to obtain the glue quantity information.

[0127] The glue length information is the total length of the glue path area in multiple glue inspection areas, which can be calculated based on the edge point pairs. Each edge point pair corresponds to a track point on the central track. The distance between every two continuous and adjacent track points is calculated. The sum of all distances is the glue length information. It can be understood that the two track points on both sides of the glue break defect are not continuous track points and do not participate in the glue length calculation.

[0128] The glue width information includes the maximum glue path width, the minimum glue path width and the average glue path width in each glue inspection area. After determining the glue path width corresponding to each edge point pair, the maximum glue path width and the minimum glue path width can be directly obtained. The average glue path width can be obtained by calculating the average value of the glue path widths corresponding to multiple edge point pairs in each glue inspection area.

[0129] The following is a detailed introduction to the detection of insufficient glue defects, excessive glue defects, broken glue defects and glue deviation defects.

[0130] See also Fig.14 In some embodiments, the defect detection threshold includes a low glue defect threshold, a high glue defect threshold, a broken glue defect threshold, and a glue deviation defect threshold. According to the glue path width, the connected domain information, and the defect detection threshold, the glue path area is detected for low glue defects, high glue defects, broken glue defects, and glue deviation defects (i.e., 0444), including:

[0131] 04441: Detect glue shortage defects in the glue path area based on the glue path width and glue shortage defect threshold;

[0132] 04442: Detect multiple glue defects in the glue path area based on the glue path width and multiple glue defect threshold;

[0133] 04443: Detect glue break defects in the glue path area based on the glue path width and glue break defect threshold;

[0134] 04444: Detect glue deviation defects in the glue path area based on the connected domain information and glue deviation defect threshold.

[0135] Specifically, the low glue defect threshold includes a first glue path width threshold, a first glue path length threshold and a first glue path area threshold. The low glue defect in the glue path area can be detected based on the glue path width, the first glue path width threshold, the first glue path length threshold and the first glue path area threshold. According to the glue path width corresponding to each edge point pair, the area where the glue path widths of multiple consecutive edge point pairs are less than the first glue path width threshold is extracted as the first glue path area. Calculate the first glue path length of the first glue path area. If the first glue path length is greater than the first glue path length threshold, calculate the first glue path area of ​​the first glue path area; if the first glue path area is greater than the first glue path area threshold, determine that the first glue path area has a low glue defect, and mark the low glue defect area, such as Fig.15 As shown in area A.

[0136] The glue defect point set can be determined based on multiple edge point pairs located in the same glue defect area. After the glue defect point set is determined, the glue defect information can be obtained, including the starting point, end point, length, height, glue defect point set and defect area of ​​the glue defect. In this way, it is convenient to perform secondary glue filling or correction based on the size information.

[0137] The multiple glue defect thresholds include the second glue road width threshold, the second glue road length threshold and the second glue road area threshold. The multiple glue defects in the glue road area can be detected according to the glue road width, the second glue road width threshold, the second glue road length threshold and the second glue road area threshold. According to the glue road width corresponding to each edge point pair, the area where the glue road widths of multiple consecutive edge point pairs are less than the second glue road width threshold is extracted as the second glue road area. The second glue road length of the second glue road area is calculated. If the second glue road length is greater than the second glue road length threshold, the second glue road area of ​​the second glue road area is calculated. If the second glue road area is greater than the second glue road area threshold, it is determined that the second glue road area has multiple glue defects, and the multiple glue defect area is marked, such as Fig.16 As shown in area B.

[0138] The multi-glue defect point set can be determined based on multiple edge point pairs located in the same multi-glue defect area. After determining the multi-glue defect point set, the multi-glue defect information can be obtained, including the starting point, end point, length, height, multi-glue defect point set and defect area of ​​the multi-glue defect. In this way, it is convenient to perform secondary glue filling or correction based on the size information.

[0139] The glue deviation defect threshold represents the minimum allowable glue deviation. The glue deviation defect can be detected in the glue path area according to the connected domain information and the glue deviation defect threshold. In each inspection area, when there is no glue break defect in the glue inspection area, the glue inspection area only includes one glue path area, and the connected domain centroid of the glue path area, that is, the average value of the coordinates of multiple glue path pixel points, is calculated to obtain the centroid of multiple glue path pixel points. When there is a glue break defect in the glue inspection area, the glue inspection area includes multiple glue path areas, and the connected domain centroid of each glue path area is calculated separately, and then the average value of the centroid coordinates of the multiple glue path areas is calculated to obtain the centroid of multiple glue path pixel points.

[0140] Before detecting glue deviation defects, it is necessary to determine the detection benchmark for glue deviation defects. The detection benchmark can be any one or more of the benchmark points, benchmark lines, and benchmark profiles. For example, only the benchmark points can be used as the detection benchmark, or only the benchmark lines can be used as the detection benchmark, or only the benchmark profile can be used as the detection benchmark. Any two of the benchmark points, benchmark lines, and benchmark profiles can also be used as the detection benchmarks. The benchmark points, benchmark lines, and benchmark profiles can also be used as the detection benchmarks at the same time. The benchmark points and benchmark lines are suitable for measuring the overall glue deviation of the glue path, and the benchmark profile is suitable for measuring the different glue deviations of each segmented glue inspection area.

[0141] Calculate the first minimum distance between the centroid and the detection benchmark. For example, when the detection benchmark includes a benchmark point, calculate the distance between the centroid and the benchmark point, which is the first minimum distance. When the detection benchmark includes a baseline, make a perpendicular line from the centroid to the baseline, and the distance between the perpendicular point and the centroid is the first minimum distance. Determine the relationship between the first minimum distance and the adhesive deviation defect threshold. When the first minimum distance is less than or equal to the adhesive deviation defect threshold, determine that there is no adhesive deviation defect in the inspection area. When the first minimum distance is greater than the adhesive deviation defect threshold, determine that there is an adhesive deviation defect in the inspection area. The first minimum distance can be output as adhesive deviation defect information.

[0142] The glue breaking defect can be further divided into two situations for detection. The glue breaking defect is described in detail below.

[0143] See also Fig.17 In some embodiments, the glue break defect includes a straight glue break defect and an oblique glue break defect. The glue break defect threshold includes a straight glue break defect threshold. The glue break defect detection (i.e., 04443) is performed on the glue path area according to the glue path width and the glue break defect threshold, including:

[0144] 044431: Determine whether the glue path width is zero. When there are no edge point pairs on both sides of the center track, the glue path width is zero;

[0145] 044432: Get the length of the area where the glue path width is continuously zero;

[0146] 044433: When the area length is greater than the straight-mouth glue break defect threshold, it is determined that a straight-mouth glue break defect exists;

[0147] 044434: When the glue path width is not zero and there are unconnected glue path areas along the center trajectory, it is determined that there is an oblique glue break defect.

[0148] Specifically, the glue break defect includes a straight glue break defect and an oblique glue break defect. Fig.18 As shown in the figure, a straight-mouth glue break defect refers to a defect where the glue break is perpendicular to the glue path direction, and there are no edge point pairs on both sides of the center track corresponding to the position with an oblique glue break defect. An oblique glue break defect refers to a defect where the glue break is not perpendicular to the glue path direction, and there is an edge point or an edge point pair on both sides of the center track corresponding to the position with an oblique glue break defect. The glue break defect threshold includes a straight-mouth glue break defect threshold, and the straight-mouth glue break defect threshold represents the minimum allowable glue break length.

[0149] The process of detecting straight-mouth glue break defects and oblique-mouth glue break defects is as follows: Determine whether the glue path width is zero. It can be understood that the glue path width is calculated based on the edge point pairs. If there are edge point pairs on both sides of the center track, the glue path width is not zero. Therefore, when there are no edge point pairs on both sides of the center track, the glue path width is zero. Obtain the area length of the area where the glue path width is continuously zero in the glue inspection area, and determine the relationship between the area length and the straight-mouth glue break defect threshold. When the area length is less than the straight-mouth glue break defect threshold, it means that there is no straight-mouth glue break defect in the area. When the area length is greater than the straight-mouth glue break defect threshold, it is determined that there is a straight-mouth glue break defect in the area, and the straight-mouth glue break defect area is marked, such as Fig.19 As shown in area C.

[0150] Based on the straight-mouth glue break defect area, the straight-mouth glue break defect point set can be determined. After the straight-mouth glue break defect point set is determined, the starting point, end point, length, straight-mouth glue break defect point set and defect area of ​​the straight-mouth glue break defect can be obtained. In this way, it is convenient to perform secondary glue filling or correction according to the size information.

[0151] When the glue path width is not zero and there is a disconnected glue path area along the center track, it is determined that there is an oblique glue break defect and the oblique glue break defect area is marked, such as Fig. 20 As shown in the middle area D. Any connected domain analysis algorithm can be used to determine whether there is a disconnected glue path area along the central track, and there is no limitation here.

[0152] Based on the oblique-mouth glue break defect area, the straight-mouth glue break defect point set can be determined. After the straight-mouth glue break defect point set is determined, the starting point, end point, length, oblique-mouth glue break defect point set and defect area of ​​the oblique-mouth glue break defect can be obtained. In this way, it is convenient to perform secondary glue filling or correction according to the size information.

[0153] It should be noted that in actual production, the severity of glue break defects is greater than that of glue deficiency defects. If glue break defects are detected only based on whether the glue path width is zero, only straight glue break defects can be detected, and oblique glue break defects will be detected as glue deficiency defects, resulting in missed detection.

[0154] In the implementation manner of the present application, adding the detection of the oblique glue break defect can effectively prevent the oblique glue break defect from being detected as a glue deficiency defect and caused by missed detection, thereby improving the accuracy of glue path quality detection.

[0155] See also Figure 2 and Fig.21 In some embodiments, after performing defect detection on the glue path area according to the corresponding defect detection threshold value (i.e., step 044) in each glue inspection area, performing defect detection on the glue path area in the glue inspection area (i.e., step 040) further includes:

[0156] 045: Determine whether it is necessary to merge defects in multiple glue inspection areas;

[0157] 046: When there is no need to merge defects in multiple glue inspection areas, the defect information and glue path information of each glue inspection area are output separately;

[0158] 047: When it is necessary to merge defects in multiple glue inspection areas, determine whether there are defects of the same type in at least two consecutive glue inspection areas among the multiple glue inspection areas that are connected;

[0159] 048: When there are defects of the same type in at least two continuous glue inspection areas among multiple glue inspection areas that are connected, the defects of the same type in at least two glue inspection areas that are connected are merged into one of the glue inspection areas, and the defect information and glue path information of each glue inspection area are output respectively.

[0160] Specifically, when setting the glue inspection area, a defect may be divided into at least two glue inspection areas. When performing defect detection, two adjacent glue inspection areas may detect connected defects of the same type. The user can choose whether to merge the connected defects of the same type according to actual needs. Therefore, after defect detection is performed on the glue path area according to the corresponding defect detection threshold in multiple glue inspection areas, it is determined whether it is necessary to merge the defects detected in multiple glue inspection areas.

[0161] When it is not necessary to merge defects in multiple glue inspection areas, the defect information and glue path information detected in each glue inspection area are output respectively. When it is necessary to merge defects in multiple glue inspection areas, it is determined whether there are defects of the same type in at least two consecutive glue inspection areas that are connected, that is, whether there are defects that can be merged.

[0162] When there are defects of the same type in at least two consecutive glue inspection areas among multiple glue inspection areas that are connected, it means that there are defects that can be merged in the at least two glue inspection areas. The defects of the same type that are connected in the at least two glue inspection areas are merged into one of the glue inspection areas, and the defect is deleted in the other glue inspection areas. In one example, there are connected defects of insufficient glue in three consecutive glue inspection areas. The insufficient glue defect is merged into the first glue inspection area among the three glue inspection areas, and the insufficient glue defect is deleted in the second and third glue inspection areas. After the defects are merged, the defect information and glue path information of each glue inspection area are output respectively.

[0163] like Fig. 22 As shown in FIG. 1 , there are connected glue deficiency defects in area E and area F. When it is not necessary to merge defects in multiple glue inspection areas, the two glue deficiency defects are output in the two glue inspection areas respectively. When it is necessary to merge defects in multiple glue inspection areas, the two glue deficiency defects are merged into one glue deficiency defect, as shown in FIG. Fig.23 As shown in area G in the middle, the output is in a glue inspection area.

[0164] In the implementation manner of the present application, after the detection is completed, the connected defects of the same type are merged, so that the actual size and shape of the defects can be accurately determined, which is convenient for subsequent secondary glue filling or correction. Each defect is recorded only once, which can eliminate the repeated and redundant information generated by partition detection and avoid false alarms and missed alarms.

[0165] See also Fig.24 In some embodiments, determining whether there are defects of the same type in at least two consecutive glue inspection areas among the plurality of glue inspection areas are connected (i.e., 047) includes:

[0166] 0471: In each of two adjacent glue inspection areas, determine whether the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area, and whether they are of the same type;

[0167] 0472: In two adjacent glue inspection areas, when the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area and they are of the same type, the defects in the two adjacent glue inspection areas are determined to be connected;

[0168] 0473: According to the connectivity of defects in multiple glue inspection areas, determine whether there are defects of the same type in at least two consecutive glue inspection areas in the multiple glue inspection areas that are connected.

[0169] Specifically, for multiple glue inspection areas, it is determined in turn whether the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area in each of the two adjacent glue inspection areas, and whether they are of the same type. When the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area in two adjacent glue inspection areas, and they are of the same type, it is determined that the defects in the two adjacent glue inspection areas are connected. Among them, the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area, which means that the last defect in the first inspection area is connected to the first defect in the second glue inspection area; at this time, if the types of the two defects are the same, it means that the two defects can be merged.

[0170] It should be noted that among multiple glue inspection areas, there may be defects of the same type in multiple continuous glue inspection areas that are connected. Therefore, it is necessary to further determine whether there are defects of the same type in at least two continuous glue inspection areas that are connected among the multiple glue inspection areas according to the connectivity of the defects in the multiple glue inspection areas. For example, glue inspection area 1 is adjacent to glue inspection area 2, and glue inspection area 2 is adjacent to glue inspection area 3. There are defects of the same type that are connected between glue inspection area 1 and glue inspection area 2, and there are defects of the same type that are connected between glue inspection area 2 and glue inspection area 3. Then, there are defects of the same type that are connected between glue inspection area 1, glue inspection area 2, and glue inspection area 3. In this way, all connected defects of the same type in multiple glue inspection areas can be determined.

[0171] See also Fig.25 , the embodiment of the present application also provides a glue road quality detection device 100. The glue road quality detection device 100 includes an acquisition module 10, a first setting module 20, a second setting module 30 and a detection module 40. The acquisition module 10 is used to acquire a binary image of the glue road, and the binary image of the glue road includes a glue road area. The first setting module 20 is used to set a glue inspection area based on the glue road area in the binary image of the glue road. The second setting module 30 is used to set a head and tail ignored detection ratio of the glue road area. The detection module 40 is used to perform defect detection on the glue road area in the glue inspection area based on the head and tail ignored detection ratio.

[0172] In some embodiments, before performing defect detection on the glue path area in the glue inspection area based on the head-to-tail ignoring detection ratio, the detection module 40 is further used to determine whether the head-to-tail ignoring detection function is turned on; when the head-to-tail ignoring detection function is not turned on, determine the first actual detection area according to the glue inspection area; and perform defect detection on the glue path area in the first actual detection area. The detection module 40 is specifically used to calculate the glue path length of the glue path area in the glue inspection area when the head-to-tail ignoring detection function is turned on; determine the second actual detection area based on the glue path length and the head-to-tail ignoring detection ratio; and perform defect detection on the glue path area in the second actual detection area.

[0173] In some embodiments, there are multiple glue inspection areas. The detection module 40 is also used to set a defect detection threshold for each glue inspection area. The detection module 40 is specifically used to perform defect detection on the glue path area in each glue inspection area according to the corresponding defect detection threshold.

[0174] In some embodiments, the glue inspection area includes a center track. Defects include insufficient glue defects, excessive glue defects, broken glue defects, and glue deviation defects. The detection module 40 is specifically used to perform edge detection on the glue path area in the glue inspection area based on the center track to obtain multiple edge point pairs distributed along both sides of the center track; determine the glue path width corresponding to each edge point pair based on the multiple edge point pairs; determine the connected domain information of the glue path area based on the connected domain analysis algorithm; detect insufficient glue defects, excessive glue defects, broken glue defects, and glue deviation defects in the glue path area based on the glue path width, connected domain information, and defect detection thresholds; determine the glue path information of the glue path area based on the multiple edge point pairs and the connected domain information, wherein the glue path information includes glue quantity information, glue length information, and glue width information.

[0175] In some embodiments, the defect detection threshold includes a low glue defect threshold, a high glue defect threshold, a broken glue defect threshold, and a biased glue defect threshold. The detection module 40 is specifically used to detect low glue defects in the glue path area according to the glue path width and the low glue defect threshold; to detect high glue defects in the glue path area according to the glue path width and the high glue defect threshold; to detect broken glue defects in the glue path area according to the glue path width and the broken glue defect threshold; and to detect biased glue defects in the glue path area according to the connected domain information and the biased glue defect threshold.

[0176] In some embodiments, the glue breaking defect includes a straight glue breaking defect and an oblique glue breaking defect. The glue breaking defect threshold includes a straight glue breaking bias defect threshold. The detection module 40 is specifically used to determine whether the glue path width is zero, wherein when there are no edge point pairs on both sides of the center track, the glue path width is zero; obtain the area length of the area where the glue path width is continuously zero; when the area length is greater than the straight glue breaking defect threshold, it is determined that a straight glue breaking defect exists; when the glue path width is not zero and there are unconnected glue path areas along the center track, it is determined that an oblique glue breaking defect exists.

[0177] In certain embodiments, in each glue inspection area, after defect detection is performed on the glue path area according to the corresponding defect detection threshold, the detection module 40 is specifically used to determine whether it is necessary to merge defects in multiple glue inspection areas; when it is not necessary to merge defects in multiple glue inspection areas, the defect information and glue path information of each glue inspection area are output separately; when it is necessary to merge defects in multiple glue inspection areas, determine whether there are continuous connections of defects of the same type in at least two glue inspection areas among the multiple glue inspection areas; when there are continuous connections of defects of the same type in at least two glue inspection areas among the multiple glue inspection areas, merge the defects of the same type in at least two glue inspection areas into one of the glue inspection areas, and output the defect information and glue path information of each glue inspection area separately.

[0178] In some embodiments, the detection module 40 is specifically used to determine in turn whether, in each two adjacent glue inspection areas, the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area, and whether they belong to the same type; when, in two adjacent glue inspection areas, the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area, and they belong to the same type, it is determined that the defects in the two adjacent glue inspection areas are connected; based on the connectivity of the defects in multiple glue inspection areas, it is determined whether there are continuous connections of defects of the same type in at least two of the multiple glue inspection areas.

[0179] It should be pointed out that the explanation of the glue path quality detection method in the aforementioned embodiment is also applicable to the glue path quality detection device 100 in the embodiment of the present application, and will not be elaborated here.

[0180] See also Fig.26 The embodiment of the present application also provides a glue road quality detection system 200. The glue road quality detection system 200 includes one or more processors 110 and a memory 120. The memory 120 stores a computer program, and when the computer program is executed by the processor 110, the glue road quality detection method of any of the above embodiments is implemented.

[0181] For example, when the computer program is executed by the processor 110, the following glue road quality detection method is implemented:

[0182] 010: Get the glue road binary image, which includes the glue road area;

[0183] 020: In the glue path binary image, set the glue inspection area based on the glue path area;

[0184] 030: Set the ratio of the head and tail of the glue path area to ignore detection;

[0185] 040: Based on the ratio of the first and the last ignored detection, defect detection is performed on the glue path area in the glue inspection area.

[0186] For another example, when the computer program is executed by the processor 110, the following glue path quality detection method is implemented:

[0187] 050: Determine whether to enable the head and tail ignore detection function;

[0188] 060: When the head and tail ignoring detection function is not enabled, the first actual detection area is determined according to the glue detection area;

[0189] 070: Defect detection of the glue path area in the first actual detection area;

[0190] Based on the ratio of ignored detection at the beginning and end, defect detection is performed on the glue path area in the glue inspection area (i.e. 040), including:

[0191] 041: When the head and tail ignore detection function is turned on, calculate the glue path length of the glue path area in the glue inspection area;

[0192] 042: Determine the second actual detection area based on the length of the glue path and the ratio of the first and last ignored detections;

[0193] 043: Perform defect detection on the glue path area in the second actual detection area.

[0194] It should be pointed out that the explanations and descriptions of the glue road quality detection method and the glue road quality detection device 100 in the aforementioned embodiments are also applicable to the glue road quality detection system 200 of the embodiments of the present application, and will not be elaborated here.

[0195] See also Fig. 27 The embodiment of the present application further provides a computer-readable storage medium 300 on which a computer program 310 is stored. When the program is executed by the processor 320, the method for detecting the quality of the adhesive path in any of the above embodiments is implemented.

[0196] For example, when the computer program 310 is executed by the processor 320, the following glue path quality detection method is implemented:

[0197] 010: Get the glue road binary image, which includes the glue road area;

[0198] 020: In the glue path binary image, set the glue inspection area based on the glue path area;

[0199] 030: Set the ratio of the head and tail of the glue path area to ignore detection;

[0200] 040: Based on the ratio of the first and the last ignored detection, defect detection is performed on the glue path area in the glue inspection area.

[0201] For another example, when the computer program 310 is executed by the processor 320, the following glue path quality detection method is implemented:

[0202] 050: Determine whether to enable the head and tail ignore detection function;

[0203] 060: When the head and tail ignoring detection function is not enabled, the first actual detection area is determined according to the glue detection area;

[0204] 070: Defect detection of the glue path area in the first actual detection area;

[0205] Based on the ratio of ignored detection at the beginning and end, defect detection is performed on the glue path area in the glue inspection area (i.e. 040), including:

[0206] 041: When the head and tail ignore detection function is turned on, calculate the glue path length of the glue path area in the glue inspection area;

[0207] 042: Determine the second actual detection area based on the length of the glue path and the ratio of the first and last ignored detections;

[0208] 043: Perform defect detection on the glue path area in the second actual detection area.

[0209] It should be pointed out that the explanations and descriptions of the glue path quality detection method and the glue path quality detection device 100100 in the aforementioned embodiments are also applicable to the computer-readable storage medium 300 of the embodiments of the present application, and will not be elaborated here.

[0210] In summary, in the glue road quality detection method, glue road quality detection device 100, glue road quality detection system 200 and computer readable storage medium 300 of the embodiments of the present application, by setting the head and tail ignored detection ratio of the glue road area, based on the head and tail ignored detection ratio, the glue road area is detected for defects in the glue inspection area. In this way, it is possible to prevent the normal glue road area from being misjudged as a defect, thereby improving the accuracy of the glue road quality detection.

[0211] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0212] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0213] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a computer-readable storage medium can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0214] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0215] A person of ordinary skill in the art will appreciate that all or part of the steps carried by the method for implementing the above-mentioned embodiment can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment. In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0216] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application. The scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for detecting the quality of a rubber road, characterized in that: include: Acquire a glue road binary image, wherein the glue road binary image includes a glue road area; In the glue path binary image, setting a glue inspection area based on the glue path area; Set the head and tail ignore detection ratio of the glue path area; Based on the head-to-tail neglected detection ratio, defect detection is performed on the glue path area in the glue inspection area.

2. The method for detecting the quality of the rubber road according to claim 1, characterized in that: Before the glue inspection area performs defect detection on the glue path area based on the head-to-tail neglected detection ratio, the glue path quality detection method further includes: Determine whether to enable the head and tail ignore detection function; When the head-end-ignoring detection function is not enabled, determining a first actual detection area according to the glue detection area; Perform defect detection on the glue path area in the first actual detection area; The step of performing defect detection on the glue path area in the glue inspection area based on the head-tail ignored detection ratio includes: When the head and tail ignoring detection function is turned on, the glue path length of the glue path area in the glue inspection area is calculated; Determining a second actual detection area based on the glue path length and the head-to-tail ignored detection ratio; The glue path area is inspected for defects in the second actual inspection area.

3. The method for detecting the quality of the rubber road according to claim 1, characterized in that: The number of the glue inspection areas is multiple, and the glue road quality inspection method further includes: For each of the glue inspection areas, respectively set a defect detection threshold; The performing defect detection on the glue path area in the glue inspection area includes: In each of the glue inspection areas, defect inspection is performed on the glue path area according to the corresponding defect detection threshold.

4. The method for detecting the quality of the rubber road according to claim 3, characterized in that: The glue inspection area includes a central track, the defects include insufficient glue defect, excessive glue defect, glue break defect and glue deviation defect, and in each glue inspection area, defect detection is performed on the glue path area according to the corresponding defect detection threshold, including: In the glue inspection area, edge detection is performed on the glue path area based on the central track to obtain a plurality of edge point pairs distributed along both sides of the central track; Determine the glue path width corresponding to each edge point pair according to the plurality of edge point pairs; Determine the connected domain information of the glue road area according to a connected domain analysis algorithm; Detecting the glue path area for the insufficient glue defect, the excessive glue defect, the glue break defect, and the glue deviation defect according to the glue path width, the connected domain information, and the defect detection threshold; The glue path information of the glue path area is determined according to the plurality of edge point pairs and the connected domain information, wherein the glue path information includes glue quantity information, glue length information and glue width information.

5. The method for detecting the quality of the rubber road according to claim 4, characterized in that: The defect detection threshold includes a low glue defect threshold, a high glue defect threshold, a broken glue defect threshold, and a glue deviation defect threshold. The detection of the low glue defect, the high glue defect, the broken glue defect, and the glue deviation defect in the glue path area according to the glue path width, the connected domain information, and the defect detection threshold includes: Detecting the glue shortage defect in the glue path area according to the glue path width and the glue shortage defect threshold; Detecting the multiple glue defects in the glue path area according to the glue path width and the multiple glue defect threshold; Detecting the glue break defect in the glue path area according to the glue path width and the glue break defect threshold; The glue deviation defect is detected in the glue path area according to the connected domain information and the glue deviation defect threshold.

6. The method for detecting the quality of the rubber road according to claim 5, characterized in that: The glue break defect includes a straight glue break defect and an oblique glue break defect, the glue break defect threshold includes a straight glue break defect threshold, and the glue break defect detection on the glue path area according to the glue path width and the glue break defect threshold includes: Determining whether the glue path width is zero, wherein when there are no edge point pairs on both sides of the center track, the glue path width is zero; Obtain the length of the region where the width of the glue path is continuously zero; When the length of the region is greater than the straight-mouth glue break defect threshold, it is determined that the straight-mouth glue break defect exists; When the glue path width is not zero and there are disconnected glue path areas along the central trajectory, it is determined that the oblique glue break defect exists.

7. The method for detecting the quality of the rubber road according to claim 4, characterized in that: After performing defect detection on the glue path area according to the corresponding defect detection threshold in each of the glue inspection areas, performing defect detection on the glue path area in the glue inspection area further includes: Determining whether it is necessary to merge defects in a plurality of the glue inspection areas; When there is no need to merge defects of the plurality of glue inspection areas, the defect information and the glue path information of each glue inspection area are outputted respectively; When it is necessary to merge defects in the plurality of glue inspection areas, determining whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas; When the same type of defects in at least two consecutive glue inspection areas are connected among the multiple glue inspection areas, the same type of defects in the at least two glue inspection areas are merged into one of the glue inspection areas, and the defect information and the glue path information of each glue inspection area are output respectively.

8. The method for detecting the quality of the rubber road according to claim 7, characterized in that: The determining whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas comprises: sequentially determining in each of two adjacent glue inspection areas whether an end point of the last defect in the first glue inspection area is the same as a starting point of the first defect in the second glue inspection area and whether they are of the same type; In two adjacent glue inspection areas, when the end point of the last defect in the first glue inspection area is the same as the starting point of the first defect in the second glue inspection area and they are of the same type, it is determined that the defects in the two adjacent glue inspection areas are connected; According to the connectivity of the defects in the plurality of glue inspection areas, it is determined whether the defects of the same type in at least two consecutive glue inspection areas are connected among the plurality of glue inspection areas.

9. A rubber road quality detection device, characterized in that: include: An acquisition module, used for acquiring a binary image of a glue path, wherein the binary image of the glue path includes a glue path area; A first setting module, used for setting a glue inspection area based on the glue road area in the glue road binary image; The second setting module is used to set the head and tail ignored detection ratio of the glue path area; The detection module is used to perform defect detection on the glue path area in the glue inspection area based on the head and tail ignoring detection ratio.

10. A rubber road quality detection system, characterized in that: The glue road quality detection system includes one or more processors and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the glue road quality detection method described in any one of claims 1 to 8 is implemented.

Images