Stone repair scanning method and system

Abstract

Provided in the present invention are a stone repair scanning method and system. The method comprises: controlling a machine end to scan stones at a site to be repaired, and in response to a scanning result of the machine end for any stone determining that the stone is defective, determining the stone as a stone to be repaired, and acquiring a scanned image of the stone to be repaired; performing image recognition on the scanned image, determining a defect contour in the scanned image, and determining scanned repair points located within the defect contour; acquiring repair depths respectively corresponding to the scanned repair points, and on the basis of the repair depths, determining the area volume of a defect area located within the defect contour; if the volume of a repair material carried by the machine end is not less than the area volume, controlling the machine end to fill, with the volume of the repair material, the defect area in the stone to be repaired, so as to obtain a repaired stone; and in response to the machine end sending a repair completion signal, controlling the machine end to perform multi-dimensional repair condition inspection on the repaired stone. The present invention at least improves the stone repair efficiency.

Description

A stone repair scanning method and system Technical Field

[0001] This invention relates to data processing technology, and more particularly to a stone repair scanning method and system. Background Technology

[0002] The tiles on the floor of a shopping mall may develop imperfections due to prolonged foot traffic, such as grooves or cracks. These imperfections can affect the load-bearing capacity of the stone and increase the risk of tripping, falling, and other accidents. Grooves or cracks in the stone can also negatively impact the business's image and customer experience, reducing both the business's reputation and economic benefits. Therefore, cracked tiles should be repaired promptly. Technical issues

[0003] The inventors discovered in their research that existing stone repair methods are mostly done manually, or that existing equipment cannot clearly scan the specific volume of the flawed areas on the stone and repair them in a timely manner, which wastes a certain amount of manpower and time. Technical solutions

[0004] In view of the above problems, the present invention is proposed to provide a stone repair scanning method and system that overcomes or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a stone repair scanning method is provided, comprising the following steps:

[0006] The control machine scans each stone in the site to be repaired. In response to the scanning result of the machine on any of the stones indicating a defect, the stone is identified as the stone to be repaired, and a scan image of the stone to be repaired is acquired.

[0007] Image recognition is performed on the scanned image to determine the blemish contours in the scanned image and to identify each scan repair point located within the blemish contours;

[0008] Obtain the repair depth corresponding to each scan repair point, and determine the area volume of the defect region located in the defect contour based on each repair depth;

[0009] When the volume of the repair material loaded on the machine end is not less than the volume of the area, the machine end is controlled to fill the defective area of ​​the stone to be repaired with the repair material, and the repaired stone is obtained.

[0010] In response to the repair completion signal sent by the machine, the machine is controlled to perform a multi-dimensional inspection of the repaired stone.

[0011] Optionally, in the method according to the present invention, image recognition is performed on the scanned image to determine the blemish contours in the scanned image, and each scan repair point located within the blemish contours is determined, including:

[0012] The scanned image is input into a pre-trained contour recognition model to determine the blemish contours in the scanned image;

[0013] Determine the center point of the defect located in the defect outline, and establish a defect coordinate system based on the center point of the defect;

[0014] Based on the defect coordinate system, a defect coordinate group consisting of each defect coordinate point located in the defect contour is obtained, and the maximum absolute value of the horizontal coordinate and the maximum absolute value of the vertical coordinate in the defect coordinate group are determined.

[0015] The first interval and the second interval are determined based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, respectively.

[0016] Based on the Y-axis and X-axis of the defect coordinate system, first dividing lines with a first interval and second dividing lines with a second interval are generated respectively.

[0017] Obtain the coordinates of each point corresponding to the intersection point between each of the first dividing lines and each of the second dividing lines, and determine each intersection point corresponding to the coordinates of each point in the defect coordinate group as each scan repair point.

[0018] Optionally, in the method according to the present invention, determining the first interval and the second interval based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis respectively includes:

[0019] Retrieve a pre-established quantity partitioning table, wherein the quantity partitioning table includes different numerical ranges and the partitioning intervals corresponding to the different numerical ranges;

[0020] Traverse the quantity division table to determine the first and second numerical intervals, which include the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, and determine the first and second intervals corresponding to the first and second numerical intervals, respectively.

[0021] Optionally, in the method according to the present invention, generating first dividing lines with a first interval and second dividing lines with a second interval based on both sides of the Y-axis and both sides of the X-axis of the defect coordinate system includes:

[0022] A transparent partitioning layer corresponding to the image size is created based on the scanned image;

[0023] In the transparent partitioning layer, first partitioning lines with a first interval and second partitioning lines with a second interval are generated on both sides of the Y-axis and both sides of the X-axis of the defect coordinate system, respectively.

[0024] In response to a modification request from the management terminal, the scanned image with the transparent partition layer is sent to the management terminal for display;

[0025] In response to the interaction of the management terminal with any dividing line in the transparent dividing layer, the dividing line is moved and adjusted in a direction perpendicular to the extension direction of the dividing line.

[0026] Optionally, in the method according to the present invention, obtaining the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines, and determining each intersection point corresponding to each point coordinate in the defect coordinate group as each scan repair point, includes:

[0027] Obtain the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines;

[0028] The intersection points corresponding to the coordinates of each point in the defect coordinate group are summarized to obtain the combination within the region;

[0029] The intersection points corresponding to the coordinates of each point located outside the defect coordinate group are summarized to obtain the outside region combination;

[0030] Each intersection point in the outer region combination that is close to the defect contour is determined as an edge intersection point, and the horizontal and vertical distances between each edge intersection point and the defect contour are obtained respectively.

[0031] When the horizontal distance between any of the edge intersection points is less than the first interval under a preset multiple, a first new intersection point parallel to the edge intersection point is generated on the defect contour;

[0032] When the vertical distance between any of the edge intersection points is less than the second interval under a preset multiple, a second new intersection point perpendicular to the edge intersection point is generated on the defect contour;

[0033] The first newly added intersection point and the second newly added intersection point are combined into the region, and each intersection point in the region is determined as a scan repair point.

[0034] Optionally, in the method according to the invention, determining the region volume of the defect area located in the defect contour according to each repair depth includes:

[0035] Establish a virtual blank model and a virtual clone model identical to the virtual blank model;

[0036] Determine the correspondence between the model center point of the virtual blank model and the defect center point, and generate virtual points corresponding to each scan repair point in the virtual blank model based on the correspondence.

[0037] Based on the repair depth corresponding to each scan repair point, the virtual blank model is updated based on each virtual point to obtain a virtual defect model including virtual defect areas.

[0038] The virtual defect model and the virtual clone model are respectively transformed based on the same regular shape to obtain the first model and the second model;

[0039] The volume difference between the first model and the second model is determined, and the volume difference is defined as the volume of the region.

[0040] Optionally, in the method according to the present invention, controlling the machine end to perform multi-dimensional inspection of the repaired stone includes:

[0041] The machine is controlled to acquire images of the repaired stone. Based on the comparison between the acquired images and the scanned images, the repair contour corresponding to the flaw contour in the acquired images is determined.

[0042] Obtain the region pixels of the repair area in the repair contour, and determine the region pixel value corresponding to the region pixels as the first inspection item;

[0043] Identify the scan checkpoints located in the repair area that correspond to each scan repair point, control the machine to scan each scan checkpoint, obtain each check depth corresponding to each scan checkpoint, and determine each check depth as the second check item;

[0044] Perform conformity checks based on the first and second inspection items respectively, and fill the inspection results into a pre-established inspection form.

[0045] Optionally, in the method according to the invention, performing a pass / fail check based on the first inspection item includes:

[0046] In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area.

[0047] The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction.

[0048] Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region;

[0049] Each sub-region pixel in each comparison sub-region is obtained and each sub-region pixel is determined as the comparison pixel.

[0050] The difference between the pixel value of the region and the comparison pixel value of each comparison pixel is calculated to obtain each first absolute difference, and the first preset difference range is retrieved.

[0051] If all first absolute differences are within the first preset difference range, the inspection result of the first inspection item is determined to be qualified.

[0052] If at least one of the first absolute differences is not located within the first preset difference range, the inspection result of the first inspection item is determined to be unqualified.

[0053] Optionally, in the method according to the invention, performing a conformity check based on the second inspection item includes:

[0054] In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area.

[0055] The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction.

[0056] Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region;

[0057] Each sub-region pixel in each comparison sub-region is acquired, and each sub-region pixel is determined as a scan comparison point;

[0058] The machine is controlled to scan each comparison point, obtain the comparison depth corresponding to each comparison point, and calculate the average value based on each comparison depth to obtain the average depth.

[0059] The difference between each inspection depth and the mean depth is calculated to obtain each second absolute difference, and the second preset difference range is retrieved.

[0060] If all second absolute differences are within the second preset difference range, the inspection result of the second inspection item is determined to be qualified.

[0061] If at least one of the second absolute differences is not within the second preset difference range, the inspection result of the second inspection item is determined to be unqualified.

[0062] According to another aspect of the present invention, a stone repair scanning system is provided, comprising: a determination module configured to control a machine terminal to scan each stone in the site to be repaired, and in response to the scanning result of the machine terminal on any of the stones being determined to have a defect, determining the stone as the stone to be repaired, and acquiring a scanned image of the stone to be repaired;

[0063] The recognition module is configured to perform image recognition on the scanned image, determine the blemish contours in the scanned image, and determine each scan repair point located in the blemish contours;

[0064] The volume acquisition module is configured to acquire each repair depth corresponding to each scan repair point, and determine the region volume of the defect area located in the defect contour based on each repair depth.

[0065] The repair module is configured to, when the volume of the repair material carried on the machine end is not less than the volume of the area, control the machine end to fill the defective area of ​​the stone to be repaired with the repair material, so as to obtain a repaired stone including the repaired area.

[0066] The inspection module is configured to respond to a repair completion signal sent by the machine and control the machine to perform a multi-dimensional inspection of the repaired area in the repaired stone. Beneficial effects

[0067] According to the present invention, the server can control the machine to scan each stone in the repair site. In response to the machine's scan result indicating a defect in any stone, the stone is identified as the stone to be repaired, and a scanned image of the stone to be repaired is acquired. Image recognition is then performed on the scanned image to determine the defect contour and identify each repair point located within the defect contour. This allows for the acquisition of repair depths corresponding to each repair point, and the determination of the area volume of the defect region within the defect contour based on each repair depth. When the volume of the repair material carried by the machine is not less than the area volume, the server controls the machine to fill the defect area of ​​the stone to be repaired with the repair material, resulting in a repaired stone. After the machine sends a repair completion signal, the server controls the machine to perform a multi-dimensional repair check on the repaired stone. This invention can quickly determine the defect area and volume of the stone to be repaired, repair it, and perform a multi-dimensional repair check after repair, improving the efficiency of stone repair and largely ensuring the repair effect. Attached Figure Description

[0068] Figure 1 shows a flowchart of a stone repair scanning method according to an embodiment of the present invention;

[0069] Figure 2 shows a schematic diagram of the machine end structure in this embodiment;

[0070] Figures 3-5 show the progress of stone repair in accordance with actual application scenarios;

[0071] Figure 6 shows a structural block diagram of a stone repair scanning system according to another embodiment of the present invention. Embodiments of the present invention

[0072] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0073] The tiles on the floor of a shopping mall may develop imperfections due to prolonged foot traffic, such as grooves or cracks. These imperfections can affect the load-bearing capacity of the stone and increase the risk of tripping, falling, and other accidents. Grooves or cracks in the stone can also negatively impact the business's image and customer experience, reducing both the business's reputation and economic benefits. Therefore, cracked tiles should be repaired promptly.

[0074] The inventors discovered in their research that existing stone repair methods are mostly done manually, or that existing equipment cannot clearly scan the specific volume of the flawed areas on the stone and repair them in a timely manner, which wastes a certain amount of manpower and time.

[0075] To address the problems existing in the prior art, the inventors proposed the solution of this invention. One embodiment of this invention provides a stone repair scanning method, which can be executed in a computing device.

[0076] Figure 1 shows a flowchart of a stone repair scanning method according to an embodiment of the present invention. As shown in Figure 1, the purpose of this embodiment is to implement a stone repair scanning method, starting from step S102, which includes the following steps:

[0077] The control machine scans each stone in the site to be repaired. In response to the scanning result of the machine on any of the stones indicating a defect, the stone is identified as the stone to be repaired, and a scanned image of the stone to be repaired is acquired.

[0078] For example, in this embodiment, the machine can be understood as a robot with infrared scanning, carrying, and movement capabilities. The server can control the machine to scan all the stones in the area to be repaired, such as scanning floor tiles in a shopping mall. The machine with infrared scanning capabilities can measure the distance between the ground and the sensor in real time. When the infrared measurement result exceeds the normal distance, it means that the machine has scanned a stone with defects such as grooves or cracks. That is, when the machine's scan result for any stone is a confirmed defect, it will identify this stone as the stone to be repaired and simultaneously record the scan image of this stone to be repaired.

[0079] For example, Figure 2 shows a schematic diagram of the machine end in this embodiment. As shown in Figure 2, the machine end includes a machine body 201 and a movable pulley 202. The movable pulley 202 can drive the machine body 201 to move and complete the corresponding scanning work.

[0080] Step S104 includes the following:

[0081] Image recognition is performed on the scanned image to determine the blemish contours in the scanned image, and each scan repair point located in the blemish contours is identified.

[0082] For example, in this embodiment, the server performs image recognition on the scanned image of the stone to be repaired, identifying the outer contour of the flawed area on the stone, i.e., the flaw contour. It then determines each scanned repair point within the flaw contour. Based on the depth of each scanned repair point obtained by the machine through infrared scanning, the distribution of flaws within the flaw contour can be roughly determined, reducing the workload of the server in subsequent steps.

[0083] Furthermore, the aforementioned "performing image recognition on the scanned image, determining the blemish contours in the scanned image, and determining each scan repair point located within the blemish contours" also includes the following steps:

[0084] The scanned image is input into a pre-trained contour recognition model to determine the blemish contours in the scanned image;

[0085] Determine the center point of the defect located in the defect outline, and establish a defect coordinate system based on the center point of the defect;

[0086] Based on the defect coordinate system, a defect coordinate group consisting of each defect coordinate point located in the defect contour is obtained, and the maximum absolute value of the horizontal coordinate and the maximum absolute value of the vertical coordinate in the defect coordinate group are determined.

[0087] The first interval and the second interval are determined based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, respectively.

[0088] Based on the Y-axis and X-axis of the defect coordinate system, first dividing lines with a first interval and second dividing lines with a second interval are generated respectively.

[0089] Obtain the coordinates of each point corresponding to the intersection point between each of the first dividing lines and each of the second dividing lines, and determine each intersection point corresponding to the coordinates of each point in the defect coordinate group as each scan repair point.

[0090] For example, in this embodiment, the contour recognition model can be obtained by training a pre-built image recognition model. Before training, a corresponding contour training sample set can be obtained in advance. The contour training sample set may include multiple contour training images corresponding to different defect contours. After obtaining the corresponding contour training sample set, the pre-built image recognition model can be trained using the contour training sample set to obtain the contour recognition model.

[0091] After obtaining the contour recognition model, the acquired scanned image can be input into the contour recognition model. The contour recognition model will perform contour recognition on the scanned image to determine the flaw contours in the scanned image.

[0092] The server determines the center point of the identified defect contour and establishes a defect coordinate system using this center point as the radii. This coordinate system yields a corresponding defect coordinate set, which contains the coordinates of each scanned repair point within the defect contour. The server then identifies the points with the largest absolute values ​​on both the x and y axes, determining the maximum absolute values ​​of the x and y coordinates. Based on these maximum absolute values, the server determines the first and second intervals. Lines, or dividing lines, are then generated on both sides of the defect coordinate system according to the X and Y axes. Multiple first dividing lines are generated on both sides of the Y-axis at the intervals of the first interval, and multiple second dividing lines are generated on both sides of the X-axis at the intervals of the second interval. At this point, the server can obtain the coordinates of each intersection point between each first dividing line and each second dividing line, and then determine the intersection points corresponding to each point coordinate in the defect coordinate group as each scan repair point, saving the server a certain amount of workload.

[0093] Furthermore, the aforementioned "determining the first interval and the second interval based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis respectively" also includes the following steps:

[0094] Retrieve a pre-established quantity partitioning table, wherein the quantity partitioning table includes different numerical ranges and the partitioning intervals corresponding to the different numerical ranges;

[0095] Traverse the quantity division table to determine the first and second numerical intervals, which include the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, and determine the first and second intervals corresponding to the first and second numerical intervals, respectively.

[0096] For example, in this embodiment, before determining the first interval and the second interval, the server will retrieve a pre-established quantity division table. The quantity division table includes different numerical ranges and the division intervals corresponding to different numerical ranges. The server will determine the numerical range including the maximum absolute value of the horizontal axis in the quantity division table, i.e., the first numerical range, and determine the interval distance corresponding to the first numerical range, i.e., the first interval. Then, the server will find the numerical range including the maximum absolute value of the vertical axis in the quantity division table, i.e., the second numerical range, and determine the interval distance corresponding to the second numerical range, i.e., the second interval. For example, if the unit of the defect coordinate system is mm, when the maximum absolute value of the horizontal axis is determined to be 6mm, the server will find the numerical range containing 6mm in the quantity division table, e.g., [4mm~7mm]. Then, [4mm~7mm] is the first numerical range, and the interval corresponding to this first numerical range is found to be 2mm. Therefore, the first interval of the horizontal axis is 2mm.

[0097] Furthermore, the aforementioned "generating first dividing lines with a first interval and second dividing lines with a second interval based on both sides of the Y-axis and both sides of the X-axis of the defect coordinate system" also includes the following steps:

[0098] A transparent partitioning layer corresponding to the image size is created based on the scanned image;

[0099] In the transparent partitioning layer, first partitioning lines with a first interval and second partitioning lines with a second interval are generated on both sides of the Y-axis and both sides of the X-axis of the defect coordinate system, respectively.

[0100] In response to a modification request from the management terminal, the scanned image with the transparent partition layer is sent to the management terminal for display;

[0101] In response to the interaction of the management terminal with any dividing line in the transparent dividing layer, the dividing line is moved and adjusted in a direction perpendicular to the extension direction of the dividing line.

[0102] For example, in this embodiment, after determining the first and second intervals, the server first creates a transparent partition layer corresponding to the image size of the current scanned image. Within this transparent partition layer, partition lines are generated on both sides according to the X-axis and Y-axis positions. Multiple first partition lines are generated on both sides of the Y-axis according to the interval of the first interval, and multiple second partition lines are generated on both sides of the X-axis according to the interval of the second interval. After the server automatically generates the first and second partition lines, the management terminal can also modify the position of any partition line as needed. When the management terminal issues a modification request, the server sends the scanned image of the transparent partition layer to the management terminal for display. When the management terminal clicks on any partition line in the transparent partition layer, it can move and adjust the partition line along a direction perpendicular to its extension direction, providing flexibility and meeting the customization needs of the management terminal.

[0103] Furthermore, the aforementioned "obtaining the coordinates of each point corresponding to the intersection points between each of the first dividing lines and each of the second dividing lines, and determining the intersection points corresponding to the coordinates of each point in the defect coordinate group as each scan repair point" also includes the following steps:

[0104] Obtain the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines;

[0105] The intersection points corresponding to the coordinates of each point in the defect coordinate group are summarized to obtain the combination within the region;

[0106] The intersection points corresponding to the coordinates of each point located outside the defect coordinate group are summarized to obtain the outside region combination;

[0107] Each intersection point in the outer region combination that is close to the defect contour is determined as an edge intersection point, and the horizontal and vertical distances between each edge intersection point and the defect contour are obtained respectively.

[0108] When the horizontal distance between any of the edge intersection points is less than the first interval under a preset multiple, a first new intersection point parallel to the edge intersection point is generated on the defect contour;

[0109] When the vertical distance between any of the edge intersection points is less than the second interval under a preset multiple, a second new intersection point perpendicular to the edge intersection point is generated on the defect contour;

[0110] The first newly added intersection point and the second newly added intersection point are combined into the region, and each intersection point in the region is determined as a scan repair point.

[0111] For example, in this embodiment, the server obtains the coordinates of each intersection point between the first and second dividing lines, and then divides all intersection points according to their positions. The intersection points corresponding to all points within the defect coordinate group are summarized to obtain a combination within the region; the intersection points corresponding to all points outside the defect coordinate group are summarized to obtain a combination outside the region; furthermore, all intersection points close to the defect outline in the combination outside the region can be identified as edge intersection points, which greatly ensures the integrity of the defect area. Then, the horizontal and vertical distances between each edge intersection point and the defect outline are obtained.

[0112] When the horizontal distance between any edge intersection points is less than a first interval under a preset multiple, such as 0.3, it can be understood that the horizontal distance between the edge intersection point and the defect contour is relatively close in this case, thus generating a first new intersection point parallel to the edge intersection point on the defect contour. Similarly, when the vertical distance between any edge intersection points is less than a second interval under a preset multiple, a second new intersection point perpendicular to the edge intersection point is generated on the defect contour. After generating the first and second new intersection points, the server will summarize the first and second new intersection points into a combination within the region, and determine all intersection points in the combination within the region as each scan repair point. This can maximize the integrity of the defect area during subsequent scanning and reduce the workload of the server.

[0113] Step S106 includes the following:

[0114] Obtain the repair depth corresponding to each scan repair point, and determine the area volume of the defect region located in the defect contour based on each repair depth.

[0115] For example, in this embodiment, the machine can perform infrared scanning on each scan repair point to obtain the depth of each scan repair point, i.e., the repair depth. Then, based on each repair depth, the volume of the defect area in the defect outline can be roughly determined.

[0116] Furthermore, the aforementioned "determining the region volume of the defect area located in the defect contour according to each repair depth" also includes the following steps:

[0117] Establish a virtual blank model and a virtual clone model identical to the virtual blank model;

[0118] Determine the correspondence between the model center point of the virtual blank model and the defect center point, and generate virtual points corresponding to each scan repair point in the virtual blank model based on the correspondence.

[0119] Based on the repair depth corresponding to each scan repair point, the virtual blank model is updated based on each virtual point to obtain a virtual defect model including virtual defect areas.

[0120] The virtual defect model and the virtual clone model are respectively transformed based on the same regular shape to obtain the first model and the second model;

[0121] The volume difference between the first model and the second model is determined, and the volume difference is defined as the volume of the region.

[0122] For example, in this embodiment, the server will create a virtual blank model, and then create a virtual clone model with the same size and shape as the virtual blank model. The center point of the virtual blank model will be aligned with the center point of the defect. Then, virtual points corresponding one-to-one with each scan repair point will be generated in the virtual blank model. The server will update the virtual blank model based on the repair depth corresponding to each scan repair point. That is, after the update, the repair depth of each virtual point is the repair depth corresponding to each scan repair point. The result is a virtual defect model including the virtual defect area.

[0123] The server will transform the virtual defect model and the virtual clone model into models of the same regular shape. For example, it can transform both the virtual defect model and the virtual clone model into a rectangle. After the transformation, the virtual defect model becomes the first model, and the virtual clone model becomes the second model. This allows for a more intuitive calculation of the volume difference between the first model and the second model, and the volume difference is determined as the area volume of the defect.

[0124] Step S108 includes the following:

[0125] When the volume of the repair material loaded on the machine end is not less than the volume of the area, the machine end is controlled to fill the defective area of ​​the stone to be repaired with the repair material, and the repaired stone is obtained.

[0126] For example, in this embodiment, it can be understood that the machine has the function of carrying repair materials. When the volume of the repair materials carried by the machine is not less than the volume of the defective area, that is, the repair materials carried by the machine can completely repair the current defective area, the server can control the machine to repair the defective area in the stone to be repaired, that is, control the machine to fill the defective area in the stone to be repaired with repair materials. After filling, the stone obtained is the repaired stone.

[0127] Step S110 includes the following:

[0128] In response to the repair completion signal sent by the machine, the machine is controlled to perform a multi-dimensional inspection of the repaired stone.

[0129] For example, in this embodiment, once the machine finishes repairing the defective area, it will send a repair completion signal. Upon receiving the repair completion signal, the server will control the machine to perform a multi-dimensional inspection of the repaired stone, ensuring the effectiveness of the repair.

[0130] Furthermore, the aforementioned "controlling the machine to perform multi-dimensional inspections of the repaired stone" also includes the following steps:

[0131] The machine is controlled to acquire images of the repaired stone. Based on the comparison between the acquired images and the scanned images, the repair contour corresponding to the flaw contour in the acquired images is determined.

[0132] Obtain the region pixels of the repair area in the repair contour, and determine the region pixel value corresponding to the region pixels as the first inspection item;

[0133] Identify the scan checkpoints located in the repair area that correspond to each scan repair point, control the machine to scan each scan checkpoint, obtain each check depth corresponding to each scan checkpoint, and determine each check depth as the second check item;

[0134] Perform conformity checks based on the first and second inspection items respectively, and fill the inspection results into a pre-established inspection form.

[0135] For example, in this embodiment, the server controls the machine to perform a multi-dimensional inspection of the repaired stone from two aspects: repair color and repair depth. First, the server controls the machine to re-capture images of the repaired stone, obtaining a captured image of the repaired stone. The captured image is compared with the scanned image of the stone before repair. Based on the comparison results, the repair contour located in the captured image can be determined, and this repair contour corresponds to the flaw contour.

[0136] At this point, the server will obtain the region pixels of the repair area in the repair outline and determine the region pixel value corresponding to the region pixel as the first inspection item. The first inspection item is for the machine to check the repair status of the stone from the dimension of repair color. The server then determines the scan check points located in the repair area that correspond to each scan repair point, and controls the machine to scan each scan check point again to obtain the depth of each scan check point, i.e., the inspection depth. The inspection depth is determined as the second inspection item. The second inspection item is for the machine to check the repair status of the stone from the dimension of repair depth. The server will perform a pass inspection on the stone repair effect based on the first and second inspection items and fill the inspection results into a pre-established inspection form.

[0137] Furthermore, the aforementioned "conformity inspection based on the first inspection item" also includes the following steps:

[0138] In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area.

[0139] The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction.

[0140] Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region;

[0141] Each sub-region pixel in each comparison sub-region is obtained and each sub-region pixel is determined as the comparison pixel.

[0142] The difference between the pixel value of the region and the comparison pixel value of each comparison pixel is calculated to obtain each first absolute difference, and the first preset difference range is retrieved.

[0143] If all first absolute differences are within the first preset difference range, the inspection result of the first inspection item is determined to be qualified.

[0144] If at least one of the first absolute differences is not located within the first preset difference range, the inspection result of the first inspection item is determined to be unqualified.

[0145] For example, in this embodiment, the server first extends a preset distance outward along the repair contour in the acquired image to generate a contrast contour surrounding the repair contour. For example, if the preset distance is 1cm, then a contour surrounding the repair contour is generated by extending a distance of 1cm outward along the repair contour. This contour is the contrast contour, and the area between the contrast contour and the repair contour is the contrast area.

[0146] The server can determine the horizontal and vertical contrast lengths of the comparison area, compare the two lengths, select the longest contrast length, and determine its corresponding direction as the division direction. Then, based on this division direction, the comparison area is divided into equally spaced regions, resulting in various comparison sub-regions. At this point, the server can obtain the pixels of any sub-region within each comparison sub-region and identify each sub-region's pixels as the comparison pixels.

[0147] Next, the difference between the region pixel value and the comparison pixel value of each comparison pixel is calculated. The absolute value of the difference calculation result is the first absolute difference, thus obtaining each first absolute difference. A first preset difference range is then retrieved. The first preset difference range can be freely set by the management terminal, for example, the first preset difference range is [0~30]. If all the first absolute differences are within the first preset difference range, it means that the difference between the region pixel value and the comparison pixel value is not large, and at this time, the inspection result of the first inspection item can be determined to be qualified. If one or more of the first absolute differences are not within the first preset difference range, it means that the difference between the region pixel value and the comparison pixel value is too large, and at this time, the inspection result of the first inspection item can be determined to be unqualified.

[0148] In this embodiment, the server compares the color of the stone outside the repair area with the color of the stone within the repair area, and checks the repair status from the perspective of repair color based on the comparison results. A first preset difference range is set, which can greatly improve the accuracy of the inspection results.

[0149] Furthermore, the aforementioned "conformity inspection based on the second inspection item" also includes the following steps:

[0150] In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area.

[0151] The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction.

[0152] Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region;

[0153] Each sub-region pixel in each comparison sub-region is acquired, and each sub-region pixel is determined as a scan comparison point;

[0154] The machine is controlled to scan each comparison point, obtain the comparison depth corresponding to each comparison point, and calculate the average value based on each comparison depth to obtain the average depth.

[0155] The difference between each inspection depth and the mean depth is calculated to obtain each second absolute difference, and the second preset difference range is retrieved.

[0156] If all second absolute differences are within the second preset difference range, the inspection result of the second inspection item is determined to be qualified.

[0157] If at least one of the second absolute differences is not within the second preset difference range, the inspection result of the second inspection item is determined to be unqualified.

[0158] For example, in this embodiment, the server first extends a preset distance outward along the repair contour in the acquired image to generate a contrast contour surrounding the repair contour. For example, if the preset distance is 1cm, then a contour surrounding the repair contour is generated by extending a distance of 1cm outward along the repair contour. This contour is the contrast contour, and the area between the contrast contour and the repair contour is the contrast area.

[0159] The server can determine the horizontal contrast length and the vertical contrast length in the contrast area, compare the two lengths, select the longest contrast length, and determine its corresponding direction as the division direction. Then, based on the division direction, the contrast area is divided into equally spaced regions, resulting in contrast sub-regions. At this point, the server can acquire the pixels of any sub-region within each contrast sub-region and determine these pixels as the respective scan contrast points.

[0160] The server controls the machine to scan each comparison point, obtaining the depth of each comparison point. The average depth of all comparison depths is then calculated. Next, the difference between each inspection depth and the average depth is calculated. The absolute value of the difference is the second absolute difference, resulting in a second absolute difference. A second preset difference range is then retrieved. This second preset difference range can be freely set by the management end, for example, [0mm~2mm]. If the second absolute difference is within the second preset difference range, it indicates that the inspection depth and the average depth are not significantly different, and the inspection result of the second inspection item can be determined as qualified. If one or more second absolute differences are not within the second preset difference range, it indicates that the inspection depth and the average depth are significantly different, and the inspection result of the second inspection item can be determined as unqualified. In this embodiment, the server can check the repair status from the dimension of repair depth based on the difference results. Setting the second preset difference range largely ensures the objectivity of the inspection results.

[0161] For example, Figures 3-5 are schematic diagrams of the progress of stone repair in actual application scenarios. Figure 3 shows the stone before repair, where the flawed areas in the stone can be clearly seen; Figure 4 shows the stone during repair, where the flawed areas in the stone have been filled; and Figure 5 shows the stone after repair, where the flawed areas in the stone have been completely repaired.

[0162] According to the present invention, the server can control the machine to scan each stone in the repair site. In response to the machine's scan result indicating a defect in any stone, the stone is identified as the stone to be repaired, and a scanned image of the stone to be repaired is acquired. Image recognition is then performed on the scanned image to determine the defect contour and identify each repair point located within the defect contour. This allows for the acquisition of repair depths corresponding to each repair point, and the determination of the area volume of the defect region within the defect contour based on each repair depth. When the volume of the repair material carried by the machine is not less than the area volume, the server controls the machine to fill the defect area of ​​the stone to be repaired with the repair material, resulting in a repaired stone. After the machine sends a repair completion signal, the server controls the machine to perform a multi-dimensional repair check on the repaired stone. This invention can quickly determine the defect area and volume of the stone to be repaired, repair it, and perform a multi-dimensional repair check after repair, improving the efficiency of stone repair and largely ensuring the repair effect.

[0163] Another embodiment of the present invention provides a stone repair scanning system, and Figure 6 is a corresponding system block diagram. The system includes:

[0164] The determination module is configured to control the machine terminal to scan each stone in the site to be repaired. In response to the scanning result of the machine terminal on any of the stones being determined to have a defect, the stone is determined to be the stone to be repaired, and a scan image of the stone to be repaired is acquired.

[0165] The recognition module is configured to perform image recognition on the scanned image, determine the blemish contours in the scanned image, and determine each scan repair point located in the blemish contours;

[0166] The volume acquisition module is configured to acquire each repair depth corresponding to each scan repair point, and determine the region volume of the defect area located in the defect contour based on each repair depth.

[0167] The repair module is configured to, when the volume of the repair material carried on the machine end is not less than the volume of the area, control the machine end to fill the defective area of ​​the stone to be repaired with the repair material, so as to obtain a repaired stone including the repaired area.

[0168] The inspection module is configured to respond to a repair completion signal sent by the machine and control the machine to perform a multi-dimensional inspection of the repaired area in the repaired stone.

[0169] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing preferred embodiments of the invention.

[0170] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0171] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0172] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0173] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0174] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0175] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0176] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0177] Although the invention has been described with respect to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and edibility purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative rather than restrictive, and the scope of the invention is defined by the appended claims.

Claims

1. A method of stone restoration scanning, the method comprising: Includes the following steps: The control machine scans each stone in the site to be repaired. In response to the scanning result of the machine on any of the stones indicating a defect, the stone is identified as the stone to be repaired, and a scan image of the stone to be repaired is acquired. Image recognition is performed on the scanned image to determine the blemish contours in the scanned image and to identify each scan repair point located within the blemish contours; Obtain the repair depth corresponding to each scan repair point, and determine the area volume of the defect region located in the defect contour based on each repair depth; When the volume of the repair material loaded on the machine end is not less than the volume of the area, the machine end is controlled to fill the defective area of ​​the stone to be repaired with the repair material, and the repaired stone is obtained. In response to the repair completion signal sent by the machine, the machine is controlled to perform a multi-dimensional inspection of the repaired stone. The process includes performing image recognition on the scanned image to determine the contours of defects in the scanned image and identifying each scan repair point located within the defect contours, including: The scanned image is input into a pre-trained contour recognition model to determine the blemish contours in the scanned image; Determine the center point of the defect located in the defect outline, and establish a defect coordinate system based on the center point of the defect; Based on the defect coordinate system, a defect coordinate group consisting of each defect coordinate point located in the defect contour is obtained, and the maximum absolute value of the horizontal coordinate and the maximum absolute value of the vertical coordinate in the defect coordinate group are determined. The first interval and the second interval are determined based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, respectively. Based on the Y-axis and X-axis of the defect coordinate system, first dividing lines with a first interval and second dividing lines with a second interval are generated respectively. Obtain the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines, and determine each intersection point corresponding to each point coordinate in the defect coordinate group as each scan repair point; The determination of the region volume of the defect area located in the defect contour based on each repair depth includes: Establish a virtual blank model and a virtual clone model identical to the virtual blank model; Determine the correspondence between the model center point of the virtual blank model and the defect center point, and generate virtual points corresponding to each scan repair point in the virtual blank model based on the correspondence. Based on the repair depth corresponding to each scan repair point, the virtual blank model is updated based on each virtual point to obtain a virtual defect model including virtual defect areas. The virtual defect model and the virtual clone model are respectively transformed based on the same regular shape to obtain the first model and the second model; Determine the volume difference between the first model and the second model, and define the volume difference as the volume of the region; The control system performs multi-dimensional inspections of the repaired stone, including: The machine is controlled to acquire images of the repaired stone. Based on the comparison between the acquired images and the scanned images, the repair contour corresponding to the flaw contour in the acquired images is determined. Obtain the region pixels of the repair area in the repair contour, and determine the region pixel value corresponding to the region pixels as the first inspection item; Determine the scanning checkpoints located in the repair area that correspond to each scanning repair point, control the machine to scan each scanning checkpoint, obtain each inspection depth corresponding to each scanning checkpoint, and determine each inspection depth as the second inspection item; Perform conformity checks based on the first and second inspection items respectively, and fill the inspection results into a pre-established inspection form.

2. The stone repair scanning method according to claim 1, characterized in that, Determining the first interval and the second interval based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, respectively, includes: Retrieve a pre-established quantity partitioning table, wherein the quantity partitioning table includes different numerical ranges and the partitioning intervals corresponding to the different numerical ranges; Traverse the quantity division table to determine the first and second numerical intervals, which include the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, and determine the first and second intervals corresponding to the first and second numerical intervals, respectively.

3. The stone repair scanning method according to claim 1, characterized in that, Based on the Y-axis and X-axis of the defect coordinate system, first dividing lines with a first interval and second dividing lines with a second interval are generated respectively, including: A transparent partitioning layer corresponding to the image size is created based on the scanned image; In the transparent partitioning layer, first partitioning lines with a first interval and second partitioning lines with a second interval are generated on both sides of the Y-axis and both sides of the X-axis of the defect coordinate system, respectively. In response to a modification request from the management terminal, the scanned image with the transparent partition layer is sent to the management terminal for display; In response to the interaction of the management terminal with any dividing line in the transparent dividing layer, the dividing line is moved and adjusted in a direction perpendicular to the extension direction of the dividing line.

4. The stone repair scanning method according to claim 1, characterized in that, Obtain the coordinates of each point corresponding to the intersection point between each of the first dividing lines and each of the second dividing lines, and determine the intersection points corresponding to the coordinates of each point in the defect coordinate group as each scan repair point, including: Obtain the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines; The intersection points corresponding to the coordinates of each point in the defect coordinate group are summarized to obtain the combination within the region; The intersection points corresponding to the coordinates of each point located outside the defect coordinate group are summarized to obtain the outside region combination; Each intersection point in the outer region combination that is close to the defect contour is determined as an edge intersection point, and the horizontal and vertical distances between each edge intersection point and the defect contour are obtained respectively. When the horizontal distance between any of the edge intersection points is less than the first interval under a preset multiple, a first new intersection point parallel to the edge intersection point is generated on the defect contour; When the vertical distance between any of the edge intersection points is less than the second interval under a preset multiple, a second new intersection point perpendicular to the edge intersection point is generated on the defect contour; The first newly added intersection point and the second newly added intersection point are combined into the region, and each intersection point in the region is determined as a scan repair point.

5. The stone repair scanning method according to claim 1, characterized in that, Based on the first inspection item, a conformity check is performed, including: In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area. The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction. Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region; Each sub-region pixel in each comparison sub-region is obtained and each sub-region pixel is determined as the comparison pixel. The difference between the pixel value of the region and the comparison pixel value of each comparison pixel is calculated to obtain each first absolute difference, and the first preset difference range is retrieved. If all first absolute differences are within the first preset difference range, the inspection result of the first inspection item is determined to be qualified. If at least one of the first absolute differences is not located within the first preset difference range, the inspection result of the first inspection item is determined to be unqualified.

6. The stone repair scanning method according to claim 1, characterized in that, Based on the second inspection item, a conformity check is performed, including: In the acquired image, a contrast contour is generated by extending a preset distance outward along the repair contour, and the area between the contrast contour and the repair contour is defined as the contrast area. The horizontal and vertical comparison lengths of the comparison area are determined in the horizontal and vertical directions, respectively, and the direction corresponding to the longest of the horizontal and vertical comparison lengths is determined as the division direction. Based on the division direction, the comparison region is divided into equally spaced regions to obtain each comparison sub-region; Each sub-region pixel in each comparison sub-region is acquired, and each sub-region pixel is determined as a scan comparison point; The machine is controlled to scan each comparison point, obtain the comparison depth corresponding to each comparison point, and calculate the average value based on each comparison depth to obtain the average depth. The difference between each inspection depth and the mean depth is calculated to obtain each second absolute difference, and the second preset difference range is retrieved. If all second absolute differences are within the second preset difference range, the inspection result of the second inspection item is determined to be qualified. If at least one of the second absolute differences is not within the second preset difference range, the inspection result of the second inspection item is determined to be unqualified.

7. A stone restoration scanning system, characterized by, include: The determination module is configured to control the machine terminal to scan each stone in the site to be repaired. In response to the scanning result of the machine terminal on any of the stones being determined to have a defect, the stone is determined to be the stone to be repaired, and a scan image of the stone to be repaired is acquired. The recognition module is configured to perform image recognition on the scanned image, determine the blemish contours in the scanned image, and determine each scan repair point located in the blemish contours; The volume acquisition module is configured to acquire each repair depth corresponding to each scan repair point, and determine the region volume of the defect area located in the defect contour based on each repair depth. The repair module is configured to, when the volume of the repair material carried on the machine end is not less than the volume of the area, control the machine end to fill the defective area of ​​the stone to be repaired with the repair material, so as to obtain a repaired stone including the repaired area. The inspection module is configured to respond to the repair completion signal sent by the machine terminal and control the machine terminal to perform a multi-dimensional inspection of the repaired area in the repaired stone. The process includes performing image recognition on the scanned image to determine the contours of defects in the scanned image and identifying each scan repair point located within the defect contours, including: The scanned image is input into a pre-trained contour recognition model to determine the blemish contours in the scanned image; Determine the center point of the defect located in the defect outline, and establish a defect coordinate system based on the center point of the defect; Based on the defect coordinate system, a defect coordinate group consisting of each defect coordinate point located in the defect contour is obtained, and the maximum absolute value of the horizontal coordinate and the maximum absolute value of the vertical coordinate in the defect coordinate group are determined. The first interval and the second interval are determined based on the maximum absolute value of the horizontal axis and the maximum absolute value of the vertical axis, respectively. Based on the Y-axis and X-axis of the defect coordinate system, first dividing lines with a first interval and second dividing lines with a second interval are generated respectively. Obtain the coordinates of each point corresponding to each intersection point between each of the first dividing lines and each of the second dividing lines, and determine each intersection point corresponding to each point coordinate in the defect coordinate group as each scan repair point; The determination of the region volume of the defect area located in the defect contour based on each repair depth includes: Establish a virtual blank model and a virtual clone model identical to the virtual blank model; Determine the correspondence between the model center point of the virtual blank model and the defect center point, and generate virtual points corresponding to each scan repair point in the virtual blank model based on the correspondence. Based on the repair depth corresponding to each scan repair point, the virtual blank model is updated based on each virtual point to obtain a virtual defect model including virtual defect areas. The virtual defect model and the virtual clone model are respectively transformed based on the same regular shape to obtain the first model and the second model; Determine the volume difference between the first model and the second model, and define the volume difference as the volume of the region; The control system performs multi-dimensional inspections of the repaired stone, including: The machine is controlled to acquire images of the repaired stone. Based on the comparison between the acquired images and the scanned images, the repair contour corresponding to the flaw contour in the acquired images is determined. Obtain the region pixels of the repair area in the repair contour, and determine the region pixel value corresponding to the region pixels as the first inspection item; Identify the scan checkpoints located in the repair area that correspond to each scan repair point, control the machine to scan each scan checkpoint, obtain each check depth corresponding to each scan checkpoint, and determine each check depth as the second check item; Perform conformity checks based on the first and second inspection items respectively, and fill the inspection results into a pre-established inspection form.

Images