Ceramic tile quality detection method, device, equipment, medium and program
By using conveyor belts and distribution equipment in the tile quality detection system and combining the image group to acquire image groups for detection, the problem of low tile quality detection efficiency in the prior art is solved, and efficient and accurate tile quality detection is achieved.
Patent Information
- Application Number
- CN202411975652.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-04-08
- Estimated Expiration
- 2044-12-31
AI Technical Summary
In the prior art, the quality inspection efficiency of ceramic tile is low and it is difficult to achieve automated inspection.
The tile quality detection system is adopted, which includes a first conveyor belt, a second conveyor belt, a tile distribution device and an image capturing device. By acquiring the initial and target image groups of the tile, initial and target quality detection is performed, and distribution and re-testing is performed based on the detection results.
It achieves efficient completion of tile quality inspection, can quickly identify and eliminate defective products, and improves the accuracy and efficiency of inspection.
Smart Images

Figure CN119771777A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of quality inspection, and in particular to a method, device, equipment, medium and procedure for inspecting the quality of ceramic tiles. Background Art
[0002] Ceramic tiles are a kind of acid- and alkali-resistant porcelain or stone building or decorative material made of refractory metal oxides and semi-metal oxides through a process of grinding, mixing, pressing, glazing and sintering. Their raw materials are mostly made of clay, quartz sand, which are mixed after high temperature and compression, and have very high hardness.
[0003] Evaluating the quality of tiles is a key step in ensuring their performance and beauty. Rigorous quality testing not only ensures that each tile meets high standards of appearance and physical properties, but is also essential to the safety and long-term use of the building. Through a precise testing process, defective products can be effectively identified and eliminated, preventing additional maintenance costs and safety risks caused by tile problems (such as cracks or deformation) in the future.
[0004] Therefore, how to realize automatic detection of tile quality is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention
[0005] The present application provides a ceramic tile quality detection method, device, equipment, medium and program to solve the technical problem of low efficiency of ceramic tile quality detection.
[0006] In a first aspect, the present application provides a tile quality detection method, which is performed by a tile quality detection system, wherein the tile quality detection system includes a first conveyor belt, a second conveyor belt, a tile sorting device, and a camera device.
[0007] The method comprises:
[0008] Acquire an initial image group corresponding to the target tile, wherein the initial image group represents a first basic view of the target tile on the first conveyor belt, and the first basic view can be acquired from a camera device with a shooting direction perpendicular to the first conveyor belt;
[0009] Performing an initial quality detection according to the initial image group to obtain an initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt;
[0010] When the initial quality is unqualified, generating tile distribution equipment operation information, wherein the tile distribution equipment operation information is used to control the tile distribution equipment to distribute the target tile from the first conveyor belt to the second conveyor belt;
[0011] Acquire a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be acquired from a camera device with a shooting direction perpendicular to the second conveyor belt;
[0012] According to the target image group, a target quality detection is performed to obtain a target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile. According to the target image group, a target quality detection is performed to obtain a target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
[0013] Preferably, the initial image group includes at least a first initial main view and a second initial main view, and a first shooting direction corresponding to the first initial main view is opposite to a second shooting direction of the second initial main view.
[0014] The performing of initial quality detection according to the initial image group to obtain the initial quality corresponding to the target tile includes:
[0015] According to the first initial main view, a first positive side length and a first side side length are obtained, wherein the first positive side length represents the length of the side of the target tile that is perpendicular to the first shooting direction, and the first side side length represents the length of the side of the target tile that is not perpendicular to the first shooting direction;
[0016] According to the second initial main view, a second positive side length and a second side side length are obtained, wherein the second positive side length represents the length of the side of the target tile that is perpendicular to the second shooting direction, and the second side side length represents the length of the side of the target tile that is not perpendicular to the second shooting direction;
[0017] According to the first positive side length and the second positive side length, an initial positive side length detection result is obtained;
[0018] According to the first side length and the second side length, an initial side length detection result is obtained;
[0019] The initial quality is obtained according to the initial positive side length detection result and the initial side side length detection result.
[0020] Preferably, the initial image group further includes an initial top view.
[0021] Before obtaining an initial positive side length detection result according to the first positive side length and the second positive side length, the method further includes:
[0022] According to the initial top view, a first reference positive side length and a second reference positive side length are obtained;
[0023] According to the first reference positive side length and the second reference positive side length, updating the first positive side length and the second positive side length to obtain a new first positive side length and a new second positive side length;
[0024] The step of obtaining an initial positive side length detection result according to the first positive side length and the second positive side length includes:
[0025] An initial positive side length detection result is obtained according to the new first positive side length and the new second positive side length.
[0026] Preferably, the target image group includes at least a first target main view and a second target main view, and a third shooting direction corresponding to the first target main view is opposite to a fourth shooting direction of the second target main view.
[0027] The performing target quality detection according to the target image group to obtain the target quality corresponding to the target tile includes:
[0028] According to the first target main view, a third positive side length and a third side side length are obtained, wherein the third positive side length represents the length of the side of the target tile that is perpendicular to the third shooting direction, and the third side side length represents the length of the side of the target tile that is not perpendicular to the third shooting direction;
[0029] According to the second target main view, a fourth positive side length and a fourth side length are obtained, wherein the fourth positive side length represents the length of the side of the target tile that is perpendicular to the fourth shooting direction, and the fourth side length represents the length of the side of the target tile that is not perpendicular to the fourth shooting direction;
[0030] According to the third positive side length and the fourth positive side length, a target positive side length detection result is obtained;
[0031] Obtaining a target side length detection result according to the third side length and the fourth side length;
[0032] The target quality is obtained according to the target positive side length detection result and the target side side length detection result.
[0033] Preferably, the target image group also includes a target top view.
[0034] Before obtaining the target positive side length detection result according to the third positive side length and the fourth positive side length, the method further includes:
[0035] According to the target top view, a third reference positive side length and a fourth reference positive side length are obtained;
[0036] According to the third reference positive side length and the fourth reference positive side length, updating the third positive side length and the fourth positive side length to obtain a new third positive side length and a new fourth positive side length;
[0037] The step of obtaining a target positive side length detection result according to the third positive side length and the fourth positive side length includes:
[0038] A target positive side length detection result is obtained according to the new third positive side length and the new fourth positive side length.
[0039] In a second aspect, the present application provides a tile quality detection device, comprising:
[0040] A first acquisition module is used to acquire an initial image group corresponding to a target tile, wherein the initial image group represents a first basic view of the target tile on a first conveyor belt, and the first basic view can be acquired from a camera device with a shooting direction perpendicular to the first conveyor belt;
[0041] A first processing module is configured to perform an initial quality detection based on the initial image group to obtain an initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt; when the initial quality is unqualified, the distribution module is triggered;
[0042] A distribution module, used for generating operation information of a tile distribution device, wherein the operation information of the tile distribution device is used for controlling the tile distribution device to distribute the target tile from the first conveyor belt to the second conveyor belt;
[0043] A second acquisition module is used to acquire a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be acquired from a camera device with a shooting direction perpendicular to the second conveyor belt;
[0044] The second processing module is used to perform target quality detection according to the target image group to obtain the target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
[0045] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
[0046] The memory stores computer-executable instructions;
[0047] The processor executes the computer-executable instructions stored in the memory to implement the tile quality detection method as described in any one of the first aspects.
[0048] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the tile quality detection method as described in any one of the first aspects.
[0049] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the tile quality detection method as described in any one of the first aspects.
[0050] Beneficial effects:
[0051] The tile quality detection method provided in the present application obtains an initial image group corresponding to the target tile to obtain a first basic view with a shooting direction perpendicular to the first conveyor belt; performs an initial quality detection based on the first basic view with a shooting direction perpendicular to the first conveyor belt to obtain the initial quality corresponding to the target tile, so as to determine the appearance quality of the target tile at an angle with a shooting direction perpendicular to the first conveyor belt; generates tile sorting equipment operation information when the appearance quality at an angle with a shooting direction perpendicular to the first conveyor belt is unqualified, so as to control the tile sorting equipment to sort the target tile from the first conveyor belt to the second conveyor belt; obtains a target image group to obtain a second basic view with a shooting direction perpendicular to the second conveyor belt; performs a target quality detection based on the second basic view with a shooting direction perpendicular to the second conveyor belt to obtain the target quality corresponding to the target tile, so as to determine the final appearance quality of the target tile, thereby achieving efficient completion of tile quality detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0053] Figure 1 A structural schematic diagram of a tile quality detection system provided in an embodiment of the present application;
[0054] Figure 2 A schematic diagram of a tile placement position provided in an embodiment of the present application;
[0055] Figure 3 A schematic diagram of a flow chart of a tile quality detection method provided in an embodiment of the present application;
[0056] Figure 4 A schematic diagram of a main view of a tile provided in an embodiment of the present application;
[0057] Figure 5 A schematic top view of a tile provided in an embodiment of the present application;
[0058] Figure 6 A structural schematic diagram of a tile quality detection device provided in an embodiment of the present application;
[0059] Figure 7 A schematic diagram of the structure of an electronic device provided in this application.
[0060] Reference numerals:
[0061] 1-first conveyor belt; 2-second conveyor belt; 3-tile sorting device; 31-rotating shaft; 32-sorting pointer;
[0062] 41-first camera device; 42-second camera device; 43-initial overhead shooting device;
[0063] 51-third camera device; 52-fourth camera device; 53-target overhead shooting device;
[0064] A-position before allocation; A'-position after allocation; 32'-end point of allocation. DETAILED DESCRIPTION
[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0066] First, the terms involved in this application are explained:
[0067] Edge straightness: refers to the straightness of the edge of the tile. Usually a ruler or special measuring tool is used to place the ruler close to the edge of the tile to check and measure the maximum gap between the ruler and the edge. This gap value represents the deviation in edge straightness.
[0068] In the related art, the vertical distance between each point on the edge of the tile and the reference position in the tile image is used to calculate the edge straightness of the tile. The edge straightness refers to the straightness of the edge of the tile. Usually, a ruler or a special measuring tool is used to place the ruler close to the edge of the tile to check and measure the maximum gap between the ruler and the edge. This gap value represents the deviation of the edge straightness. However, it takes a long time.
[0069] Therefore, how to achieve faster tile quality inspection by quickly calculating edge straightness is a technical problem that needs to be solved urgently by those skilled in the art.
[0070] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.
[0071] An embodiment of the present application provides a ceramic tile quality detection method, which is executed by a ceramic tile quality detection system, and the ceramic tile quality detection system is controlled by an electronic device.
[0072] like Figure 1As shown, the tile quality inspection system includes a first conveyor belt 1, a second conveyor belt 2, a tile sorting device 3 and a camera device, wherein:
[0073] The first conveyor belt 1 is used to transfer the tiles that have not been tested for edge straightness to the initial quality testing location, and when the test result shows that the initial quality is unqualified, the tiles that fail the initial quality are transferred to the second conveyor belt 2.
[0074] The second conveyor belt 2 is used to transport tiles that fail to meet the initial quality standards to a target quality inspection location.
[0075] The tile sorting device 3 is used to sort the tiles that are not up to standard in the initial quality from the first conveyor belt 1 to the second conveyor belt 2. The tile sorting device 3 includes a rotating shaft 31 and a sorting pointer 32. When the tile sorting device 3 is started, the sorting pointer 32 changes from a contracted state to an extended state in the figure, and then rotates around the rotating shaft 31 from the position of the sorting pointer 32 in the figure to reach the sorting end point 32'. Then, after the sorting end point 32' changes from an extended state to a contracted state, it rotates around the rotating shaft 31 from the sorting end point 32' to return to the position of the sorting pointer 32 in the figure to complete the tile sorting. Regarding the position of the tiles before and after being sorted, Figure 1 For example, tile A in the figure is the position before being allocated, and tile A' is the position after being allocated. It should be noted that the black dots in tile A and tile A' represent the same corner of the tile. For ease of description, Figure 2 As shown, the four edges of tile A are represented as edges L 1 , side L 2 , side L 3 and side L 4 , the four edges of tile A' are represented as edges side side and edge
[0076] The camera device includes an initial camera group and a target camera group. The initial camera group is used to collect the initial image group corresponding to the target tile; the initial camera group includes a first camera device 41, a second camera device 42 and an initial overhead shooting device 43, the first camera device 41 is used to collect the first initial main view, the second camera device 42 is used to collect the second initial main view, and the initial overhead shooting device 43 is used to collect the initial overhead view. The target camera group is used to collect the target image group corresponding to the target tile; the target camera group includes a third camera device 51, a fourth camera device 52 and a target overhead shooting device 53, the third camera device 51 is used to collect the first target main view, the fourth camera device 52 is used to collect the second target main view, and the target overhead shooting device 53 is used to collect the target overhead view. Figure 1 The shaded area in the figure is an example of the shooting area of the camera device.
[0077] It should be noted that the first conveyor belt and the second conveyor belt can be intersecting or parallel. The present application takes the intersection as an example, and the first conveyor belt and the second conveyor belt are connected in a Y-shape or a T-shape. At this time, the tile distribution equipment is arranged at the junction of the first conveyor belt and the second conveyor belt.
[0078] The electronic device can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiments of the present application do not limit this.
[0079] like Figure 2 As shown, the method includes steps S201 to S205, wherein:
[0080] S201. Acquire an initial image group corresponding to a target tile, wherein the initial image group represents a first basic view of the target tile on a first conveyor belt, and the first basic view can be acquired from a camera device whose shooting direction is perpendicular to the first conveyor belt.
[0081] Generally, basic views include a front view and a top view of an object. In this embodiment, the first basic view includes a front view and a top view of the target tile on the first conveyor belt.
[0082] It should be noted that the first camera device 41 , the second camera device 42 and the initial overhead shooting device 43 are located on the same plane.
[0083] S202. Perform an initial quality detection based on the initial image group to obtain an initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt.
[0084] S203. When the initial quality is unqualified, generate the tile distribution equipment operation information, wherein the tile distribution equipment operation information is used to control the tile distribution equipment to distribute the target tiles from the first conveyor belt to the second conveyor belt.
[0085] S204, obtaining a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be obtained from a camera device whose shooting direction is perpendicular to the second conveyor belt.
[0086] It should be noted that the third camera device 51 , the fourth camera device 52 and the target overhead shooting device 53 are located on the same plane.
[0087] S205 . Perform target quality detection according to the target image group to obtain the target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
[0088] Specifically, according to the target image group, the edge straightness corresponding to the target tile is obtained; when the edge straightness is greater than a preset edge straightness threshold, the target quality is determined to be unqualified; when the edge straightness is not greater than the preset edge straightness, the target quality is determined to be qualified.
[0089] The tile quality detection method provided in the embodiment of the present application obtains an initial image group corresponding to the target tile to obtain a first basic view with a shooting direction perpendicular to the first conveyor belt; performs an initial quality detection based on the first basic view with a shooting direction perpendicular to the first conveyor belt to obtain the initial quality corresponding to the target tile, so as to determine the appearance quality of the target tile at an angle with a shooting direction perpendicular to the first conveyor belt; generates tile distribution equipment operation information when the appearance quality at an angle with a shooting direction perpendicular to the first conveyor belt is unqualified, so as to control the tile distribution equipment to distribute the target tile from the first conveyor belt to the second conveyor belt; obtains a target image group to obtain a second basic view with a shooting direction perpendicular to the second conveyor belt; performs a target quality detection based on the second basic view with a shooting direction perpendicular to the second conveyor belt to obtain the target quality corresponding to the target tile, so as to determine the final appearance quality of the target tile, thereby achieving efficient completion of tile quality detection.
[0090] In one implementable method, the initial image group includes at least a first initial main view and a second initial main view, and a first shooting direction corresponding to the first initial main view is opposite to a second shooting direction of the second initial main view, wherein a direction in which the first camera device 41 points to the second camera device 42 is the first shooting direction, and a direction in which the second camera device 42 points to the first camera device 41 is the second shooting direction.
[0091] The above S202 performs initial quality detection according to the initial image group to obtain the initial quality corresponding to the target tile, which may specifically include S202-1 to S202-5, wherein:
[0092] S202-1. According to the first initial main view, obtain a first positive side length and a first side side length, wherein the first positive side length represents the length of the side of the target tile that is perpendicular to the first shooting direction, and the first side side length represents the length of the side of the target tile that is not perpendicular to the first shooting direction.
[0093] Specifically, image recognition is performed on the first initial view to obtain Figure 4 The side lengths a1 and a2 are shown, and the side length a1 is the side L 1 The projection length in the first shooting direction, side length a2 is side L 2The projection length in the first shooting direction; then the larger one of the side length a1 and the side length a2 is used as the first positive side length, and the other one is used as the first side length. Figure 4 The dotted line in the figure is the edge L 3 and side L 4 The corresponding edge.
[0094] S202-2. According to the second initial main view, obtain the second positive side length and the second side side length, wherein the second positive side length represents the length of the side of the target tile that is perpendicular to the second shooting direction, and the second side side length represents the length of the side of the target tile that is not perpendicular to the second shooting direction.
[0095] Similarly, image recognition is performed on the second initial view to obtain the side lengths b1 and b2. The side length b1 is the side length L. 3 The projection length in the second shooting direction, side length b2 is side L 4 The projection length in the second shooting direction; then the larger one of the side length b1 and the side length b2 is used as the second positive side length, and the other one is used as the second side length.
[0096] S202-3. Obtain an initial positive side length detection result according to the first positive side length and the second positive side length.
[0097] When the length of the first positive side is not equal to the length of the second positive side, the side L 2 Or side L 4 There may be a problem of unqualified edge straightness. In this case, the initial positive edge length test result is determined to be unqualified; when the first positive edge length is equal to the second positive edge length, the edge L 2 and side L 4 The edge straightness is qualified, and the initial positive edge length test result is determined to be qualified.
[0098] S202-4. Obtain an initial side length detection result according to the first side length and the second side length.
[0099] When the length of the first side is not equal to the length of the second side, the side L 1 Or side L 3 There may be a problem of unqualified edge straightness, in which case the initial side length test result is determined to be unqualified; when the first side length is equal to the second side length, the side L is characterized 1 and side L 3 There may be a problem with the edge straightness. In this case, the initial side length test result is determined to be qualified.
[0100] S202-5. Obtain initial quality based on initial positive side length detection results and initial side side length detection results.
[0101] When either the initial positive side length detection result or the initial side side length detection result is unqualified, the initial quality is determined to be unqualified and the sorting device 3 needs to be started; conversely, when both the initial positive side length detection result and the initial side side length detection result are qualified, the sorting device 3 does not need to be started.
[0102] In an implementable manner, the initial image group further includes an initial top view, and before obtaining the initial positive side length detection result according to the first positive side length and the second positive side length, S202-3 further includes:
[0103] According to the initial top view, a first reference positive side length and a second reference positive side length are obtained;
[0104] According to the first reference positive side length and the second reference positive side length, the first positive side length and the second positive side length are updated to obtain a new first positive side length and a new second positive side length.
[0105] Specifically, image recognition is performed on the initial top view to obtain the following Figure 5 The first reference positive side length shown Second reference positive side length Among them, for ease of understanding, side A 1 A 3 is the side length of the target tile in the first shooting direction, side A 4 A 6 is the side length of the target tile in the second shooting direction; the first reference positive side length and the first positive side length are averaged to obtain a new first positive side length, and similarly, the second reference positive side length and the second positive side length are averaged to obtain a new second positive side length. The dotted line o is the central axis of the first conveyor belt.
[0106] Correspondingly, according to the first positive side length and the second positive side length, an initial positive side length detection result is obtained, including:
[0107] An initial positive side length detection result is obtained according to the new first positive side length and the new second positive side length.
[0108] In an implementable manner, the target image group includes at least a first target main view and a second target main view, and a third shooting direction corresponding to the first target main view is opposite to a fourth shooting direction of the second target main view.
[0109] The above S205, performing target quality detection according to the target image group to obtain the target quality corresponding to the target tile, may specifically include S205-1 to S205-5, wherein:
[0110] S205-1. According to the first target main view, obtain the third positive side length and the third side side length, wherein the third positive side length represents the length of the side of the target tile that is perpendicular to the third shooting direction, and the third side side length represents the length of the side of the target tile that is not perpendicular to the third shooting direction.
[0111] Specifically, after the target tile is allocated from position A to position A', the first target main view is obtained, and then image recognition is performed on the first target main view to obtain the side length c1 and the side length c2. The side length c1 is the side length of the side L. 2 The projection length in the third shooting direction, side length c2 is side L 3 The projection length in the third shooting direction; then the larger one of the side length c1 and the side length c2 is used as the third positive side length, and the other one is used as the third side length.
[0112] S205-2. According to the second target main view, obtain the fourth positive side length and the fourth side length, wherein the fourth positive side length represents the length of the side of the target tile that is perpendicular to the fourth shooting direction, and the fourth side length represents the length of the side of the target tile that is not perpendicular to the fourth shooting direction.
[0113] Similarly, image recognition is performed on the second target view to obtain the side lengths d1 and d2. The side length d1 is the side length L. 1 The projection length under the fourth shooting direction, the side length d2 is the side L 4 The projection length in the fourth shooting direction; then the larger one of the side length d1 and the side length d2 is used as the fourth positive side length, and the other one is used as the fourth side length.
[0114] S205-3. Obtain a target positive side length detection result according to the third positive side length and the fourth positive side length.
[0115] When the length of the third positive side is not equal to the length of the fourth positive side, the side L 1 Or side L 3 There may be a problem of unqualified edge straightness. In this case, the target positive side length test result is determined to be unqualified; when the third positive side length is equal to the fourth positive side length, it indicates that the edge L 1 and side L 3 The edge straightness is qualified, and the target positive side length detection result is determined to be qualified.
[0116] S205-4. Obtain a target side length detection result according to the third side length and the fourth side length.
[0117] When the length of the third side is not equal to the length of the fourth side, the side L 2 Or side L 4 There may be a problem of unqualified edge straightness. In this case, the target side length test result is determined to be unqualified; when the length of the third side is equal to the length of the fourth side, it indicates that the edge L 2 and side L 4 There may be a problem with the straightness of the edge. In this case, the target side length test result is determined to be qualified.
[0118] S205-5. Obtain target quality according to the target positive side length detection result and the target side side length detection result.
[0119] When either the target positive side length detection result or the target side side length detection result is unqualified, the target quality is determined to be unqualified; conversely, when both the target positive side length detection result and the target side side length detection result are qualified, the target quality is determined to be qualified.
[0120] In an implementable manner, the target image group also includes a target top view, and the above S205-3, before obtaining the target positive side length detection result according to the third positive side length and the fourth positive side length, further includes:
[0121] According to the target top view, a third reference positive side length and a fourth reference positive side length are obtained;
[0122] According to the third reference positive side length and the fourth reference positive side length, the third positive side length and the fourth positive side length are updated to obtain a new third positive side length and a new fourth positive side length.
[0123] Specifically, image recognition is performed on the initial top view to obtain the following Figure 4 The first reference positive side length shown Second reference positive side length Among them, for ease of understanding, side A 1 A 3 is the side length of the target tile in the first shooting direction, side A 4 A 6 is the side length of the target tile under the second shooting direction; the first reference positive side length and the first positive side length are averaged to obtain a new first positive side length, and similarly, the second reference positive side length and the second positive side length are averaged to obtain a new second positive side length.
[0124] Correspondingly, according to the third positive side length and the fourth positive side length, the target positive side length detection result is obtained, including:
[0125] According to the new third positive side length and the new fourth positive side length, the target positive side length detection result is obtained.
[0126] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.
[0127] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
[0128] Figure 6 A structural diagram of a tile quality detection device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the tile quality detection device 40 provided in the embodiment of the present application includes:
[0129] A first acquisition module 401 is used to acquire an initial image group corresponding to the target tile, wherein the initial image group represents a first basic view of the target tile on the first conveyor belt, and the first basic view can be acquired from a camera device with a shooting direction perpendicular to the first conveyor belt;
[0130] The first processing module 402 is used to perform an initial quality detection based on the initial image group to obtain the initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt; when the initial quality is unqualified, the distribution module 403 is triggered;
[0131] The distribution module 403 is used to generate the operation information of the tile distribution equipment, wherein the operation information of the tile distribution equipment is used to control the tile distribution equipment to distribute the target tile from the first conveyor belt to the second conveyor belt;
[0132] A second acquisition module 404 is used to acquire a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be acquired from a camera device with a shooting direction perpendicular to the second conveyor belt;
[0133] The second processing module 405 is used to perform target quality detection according to the target image group to obtain the target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
[0134] In a possible implementation, the initial image group includes at least a first initial main view and a second initial main view, and a first shooting direction corresponding to the first initial main view is opposite to a second shooting direction of the second initial main view. The first processing module 402, when performing initial quality detection according to the initial image group to obtain the initial quality corresponding to the target tile, is used to:
[0135] According to the first initial main view, a first positive side length and a first side side length are obtained, wherein the first positive side length represents the length of the side of the target tile that is perpendicular to the first shooting direction, and the first side side length represents the length of the side of the target tile that is not perpendicular to the first shooting direction;
[0136] According to the second initial main view, a second positive side length and a second side side length are obtained, wherein the second positive side length represents the length of the side of the target tile that is perpendicular to the second shooting direction, and the second side side length represents the length of the side of the target tile that is not perpendicular to the second shooting direction;
[0137] According to the first positive side length and the second positive side length, an initial positive side length detection result is obtained;
[0138] According to the first side length and the second side length, an initial side length detection result is obtained;
[0139] The initial quality is obtained according to the initial positive side length detection results and the initial side side length detection results.
[0140] In a possible implementation, the initial image group further includes an initial top view, and the device 40 further includes a first correction module;
[0141] The first correction module is used to:
[0142] According to the initial top view, a first reference positive side length and a second reference positive side length are obtained;
[0143] According to the first reference positive side length and the second reference positive side length, the first positive side length and the second positive side length are updated to obtain a new first positive side length and a new second positive side length;
[0144] Accordingly, the second processing module 405, when executing to obtain the initial positive side length detection result according to the first positive side length and the second positive side length, is used to:
[0145] An initial positive side length detection result is obtained according to the new first positive side length and the new second positive side length.
[0146] In a possible implementation, the target image group includes at least a first target main view and a second target main view, and a third shooting direction corresponding to the first target main view is opposite to a fourth shooting direction of the second target main view.
[0147] The second processing module 405, when performing target quality detection according to the target image group to obtain the target quality corresponding to the target tile, is used to:
[0148] According to the first target main view, a third positive side length and a third side side length are obtained, wherein the third positive side length represents the length of the side of the target tile that is perpendicular to the third shooting direction, and the third side side length represents the length of the side of the target tile that is not perpendicular to the third shooting direction;
[0149] According to the second target main view, a fourth positive side length and a fourth side length are obtained, wherein the fourth positive side length represents the length of the side of the target tile that is perpendicular to the fourth shooting direction, and the fourth side length represents the length of the side of the target tile that is not perpendicular to the fourth shooting direction;
[0150] According to the third positive side length and the fourth positive side length, a target positive side length detection result is obtained;
[0151] Obtaining a target side length detection result according to the third side length and the fourth side length;
[0152] The target quality is obtained according to the target positive side length detection results and the target side side length detection results.
[0153] In a possible implementation, the target image group further includes a target top view, and the device 40 further includes a second correction module;
[0154] The second correction module is used to:
[0155] According to the target top view, a third reference positive side length and a fourth reference positive side length are obtained;
[0156] According to the third reference positive side length and the fourth reference positive side length, the third positive side length and the fourth positive side length are updated to obtain a new third positive side length and a new fourth positive side length;
[0157] Accordingly, the second processing module 405, when executing the method of obtaining the target positive side length detection result according to the third positive side length and the fourth positive side length, is used to:
[0158] According to the new third positive side length and the new fourth positive side length, the target positive side length detection result is obtained.
[0159] The tile quality detection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.
[0160] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.
[0161] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.
[0162] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to a transistor, a memristor, etc.
[0163] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Preferably, the electronic device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.
[0164] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.
[0165] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0166] If not otherwise specified, the processor 501 may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not otherwise specified, the memory 502 may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.
[0167] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.
[0168] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above redundant field updating method for a distributed system is implemented.
[0169] An embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the above redundant field updating method for a distributed system.
[0170] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for detecting tile quality, characterized in that: The process is performed by a tile quality detection system, which includes a first conveyor belt, a second conveyor belt, a tile sorting device, and a camera device. The method comprises: Acquire an initial image group corresponding to the target tile, wherein the initial image group represents a first basic view of the target tile on the first conveyor belt, and the first basic view can be acquired from a camera device with a shooting direction perpendicular to the first conveyor belt; Performing an initial quality detection according to the initial image group to obtain an initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt; When the initial quality is unqualified, generating tile distribution equipment operation information, wherein the tile distribution equipment operation information is used to control the tile distribution equipment to distribute the target tile from the first conveyor belt to the second conveyor belt; Acquire a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be acquired from a camera device with a shooting direction perpendicular to the second conveyor belt; According to the target image group, a target quality detection is performed to obtain a target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
2. The ceramic tile quality detection method according to claim 1, characterized in that: The initial image group includes at least a first initial main view and a second initial main view, wherein a first shooting direction corresponding to the first initial main view is opposite to a second shooting direction of the second initial main view, The performing of initial quality detection according to the initial image group to obtain the initial quality corresponding to the target tile includes: According to the first initial main view, a first positive side length and a first side side length are obtained, wherein the first positive side length represents the length of the side of the target tile that is perpendicular to the first shooting direction, and the first side side length represents the length of the side of the target tile that is not perpendicular to the first shooting direction; According to the second initial main view, a second positive side length and a second side side length are obtained, wherein the second positive side length represents the length of the side of the target tile that is perpendicular to the second shooting direction, and the second side side length represents the length of the side of the target tile that is not perpendicular to the second shooting direction; According to the first positive side length and the second positive side length, an initial positive side length detection result is obtained; According to the first side length and the second side length, an initial side length detection result is obtained; The initial quality is obtained according to the initial positive side length detection result and the initial side side length detection result.
3. The ceramic tile quality detection method according to claim 2, characterized in that: The initial image set also includes an initial top view, Before obtaining an initial positive side length detection result according to the first positive side length and the second positive side length, the method further includes: According to the initial top view, a first reference positive side length and a second reference positive side length are obtained; According to the first reference positive side length and the second reference positive side length, updating the first positive side length and the second positive side length to obtain a new first positive side length and a new second positive side length; Correspondingly, obtaining an initial positive side length detection result according to the first positive side length and the second positive side length includes: An initial positive side length detection result is obtained according to the new first positive side length and the new second positive side length.
4. The ceramic tile quality detection method according to claim 1, characterized in that: The target image group includes at least a first target main view and a second target main view, a third shooting direction corresponding to the first target main view is opposite to a fourth shooting direction of the second target main view, The performing target quality detection according to the target image group to obtain the target quality corresponding to the target tile includes: According to the first target main view, a third positive side length and a third side side length are obtained, wherein the third positive side length represents the length of the side of the target tile that is perpendicular to the third shooting direction, and the third side side length represents the length of the side of the target tile that is not perpendicular to the third shooting direction; According to the second target main view, a fourth positive side length and a fourth side length are obtained, wherein the fourth positive side length represents the length of the side of the target tile that is perpendicular to the fourth shooting direction, and the fourth side length represents the length of the side of the target tile that is not perpendicular to the fourth shooting direction; According to the third positive side length and the fourth positive side length, a target positive side length detection result is obtained; Obtaining a target side length detection result according to the third side length and the fourth side length; The target quality is obtained according to the target positive side length detection result and the target side side length detection result.
5. The method for detecting tile quality according to claim 4, characterized in that: The target image group also includes a target top view. Before obtaining the target positive side length detection result according to the third positive side length and the fourth positive side length, the method further includes: According to the target top view, a third reference positive side length and a fourth reference positive side length are obtained; According to the third reference positive side length and the fourth reference positive side length, updating the third positive side length and the fourth positive side length to obtain a new third positive side length and a new fourth positive side length; Correspondingly, obtaining the target positive side length detection result according to the third positive side length and the fourth positive side length includes: A target positive side length detection result is obtained according to the new third positive side length and the new fourth positive side length.
6. A tile quality detection device, characterized in that: include: A first acquisition module is used to acquire an initial image group corresponding to a target tile, wherein the initial image group represents a first basic view of the target tile on a first conveyor belt, and the first basic view can be acquired from a camera device with a shooting direction perpendicular to the first conveyor belt; A first processing module is configured to perform an initial quality detection based on the initial image group to obtain an initial quality corresponding to the target tile, wherein the initial quality represents the appearance quality of the target tile when the shooting direction is perpendicular to the first conveyor belt; when the initial quality is unqualified, the distribution module is triggered; A distribution module, used for generating operation information of a tile distribution device, wherein the operation information of the tile distribution device is used for controlling the tile distribution device to distribute the target tile from the first conveyor belt to the second conveyor belt; A second acquisition module is used to acquire a target image group, wherein the target image group represents a second basic view of the target tile on the second conveyor belt, and the second basic view can be acquired from a camera device with a shooting direction perpendicular to the second conveyor belt; The second processing module is used to perform target quality detection according to the target image group to obtain the target quality corresponding to the target tile, wherein the target quality represents the appearance quality of the target tile.
7. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.
9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Methods for measuring the shape of rectangular plates and methods for correcting the relative position of camera units.
CN102301201A
Method for measuring flatness of plate material, device for measuring flatness of plate material, and production method for steel plate
CN105229413A
Hand recognition method based on image edge line curvature and distance features
CN106446911A
Detection system and method for bending degree of refractory brick based on structured light visual sense
CN110470241A
Vision inspection system for ceramic tiles
CN201819669U