CIS size detection method, computer readable storage medium, equipment and system

Abstract

The invention discloses a CIS size detection method, a computer readable storage medium, equipment and a system, and relates to the technical field of tile detection, and the method comprises the steps: obtaining a tile surface image of a target tile collected by a CIS camera; preprocessing the ceramic tile surface image to generate a reference surface image; constructing a rectangular fitting frame matched with the edge of the target ceramic tile according to the reference surface image; calculating the actual size of the target ceramic tile according to preset calibration parameters and the rectangular fitting frame; and judging whether the target ceramic tile is qualified or not according to the actual size. According to the invention, the size detection of tiles of different specifications can be rapidly realized, and the production efficiency and the flexibility of the equipment are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ceramic tile detection, and in particular to a CIS size detection method, a computer readable storage medium, an equipment and a system. BACKGROUND

[0002] In the production process of ceramic tiles, the uniformity and precision of the size of the ceramic tiles are required to be high, and the size of the ceramic tiles needs to be accurately measured.

[0003] Traditional first and second generation size detection equipment usually adopts four area array cameras to shoot four corners of the ceramic tile. The basic principle is to establish a virtual space in the algorithm, and to realize size detection by calculating the pixels. However, since the ceramic tile production line usually produces products of multiple specifications (such as 600*600, 800*800, 600*1200, 800*1600, etc.), although the traditional first and second generation size detection equipment has high precision and good stability, there are still the following problems when the specification is converted:

[0004] (1) The physical position of the four cameras needs to be adjusted, which is complicated to operate;

[0005] (2) Although an electric adjustment function is added, the limitations are still great.

[0006] Therefore, the traditional size detection equipment has many inconveniences when the specification is converted. SUMMARY

[0007] The technical problem to be solved by the present application is to provide a CIS size detection method, a computer readable storage medium, an equipment and a system, which can quickly realize size detection of ceramic tiles of different specifications, greatly improving the production efficiency and flexibility of the equipment.

[0008] In order to solve the above technical problems, the present application provides a CIS size detection method, comprising: acquiring a ceramic tile surface image of a target ceramic tile collected by a CIS camera; preprocessing the ceramic tile surface image to generate a reference surface image; constructing a rectangular fitting frame matched with the edge of the target ceramic tile according to the reference surface image; calculating the actual size of the target ceramic tile according to the preset calibration parameters and the rectangular fitting frame; and judging whether the target ceramic tile is qualified according to the actual size.

[0009] As an improvement of the above scheme, the step of constructing a rectangular fitting frame matched with the edge of the target ceramic tile according to the reference surface image comprises: detecting the ceramic tile edge of the reference surface image to extract an edge line; detecting a reference straight line in the edge line; filtering the reference straight line in the interior of the edge line; extracting corner point information from the filtered reference straight line; and constructing a rectangular fitting frame according to the corner point information.

[0010] As an improvement of the above-mentioned scheme, the step of calculating the actual size of the target ceramic tile according to the preset calibration parameter and the rectangular fitting frame comprises: calculating the long side pixel length and the short side pixel length of the rectangular fitting frame according to the corner point information of the rectangular fitting frame; and converting the long side pixel length into a long side actual length and converting the short side pixel length into a short side actual length according to the preset calibration parameter.

[0011] As an improvement of the above-mentioned scheme, the step of judging whether the target ceramic tile is qualified according to the actual size comprises: calculating a diagonal actual length according to the long side actual length and the short side actual length; comparing the diagonal actual length with a diagonal standard length of the target ceramic tile to judge whether the target ceramic tile is qualified; and generating an abnormal information if it is judged that the target ceramic tile is not qualified.

[0012] As an improvement of the above-mentioned scheme, before constructing the rectangular fitting frame matched with the edge of the target ceramic tile according to the reference surface image, the method further comprises: judging whether the reference surface image has been subjected to calibration processing; extracting a preset calibration parameter if the reference surface image has been subjected to calibration processing; and calibrating the CIS camera to generate the calibration parameter if the reference surface image has not been subjected to calibration processing.

[0013] As an improvement of the above-mentioned scheme, the step of calibrating the CIS camera to generate the calibration parameter comprises: acquiring a calibration image of a calibration board collected by the CIS camera, the calibration board being provided with a mark segment with a known actual size; measuring a reference size of the mark segment in the calibration image; calculating a pixel actual size corresponding to each pixel point in the calibration image according to the actual size and the reference size; and taking the pixel actual size as the calibration parameter.

[0014] As an improvement of the above-mentioned scheme, the step of pre-processing the ceramic tile surface image to generate the reference surface image comprises: performing a gray processing on the ceramic tile surface image to generate a gray image; performing a filtering processing on the gray image; and performing an edge enhancement processing on the gray image after the filtering processing.

[0015] Correspondingly, the application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to realize the steps of the CIS size detection method.

[0016] Correspondingly, the application further provides a CIS size detection device, which comprises a memory and a processor, and the memory stores a computer program, wherein the processor realizes the steps of the CIS size detection method when the computer program is executed.

[0017] Correspondingly, the application also provides a CIS size detection system, which comprises: a CIS camera, which is used to collect a ceramic tile surface image of a target ceramic tile and a calibration image of a calibration plate; and the CIS size detection device.

[0018] The application has the following beneficial effects:

[0019] The CIS size detection method of the application can realize accurate collection of the ceramic tile surface image by means of the CIS camera. For different specifications of the target ceramic tile, as long as the target ceramic tile is within the shooting range of the CIS camera during the detection process, the CIS camera does not need to be physically adjusted, and only the parameters (such as the edge detection threshold, the calibration parameter and the diagonal line standard length) need to be switched to complete the specification conversion, thereby greatly improving the convenience of use. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a first embodiment flowchart of the CIS size detection method of the application;

[0021] Figure 2 is a second embodiment flowchart of the CIS size detection method of the application;

[0022] Figure 3 is an embodiment structure schematic diagram of the CIS size detection system of the application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be further described in detail below with reference to the drawings. It is hereby declared that the up, down, left, right, front, back, inner and outer directions appearing or about to appear in the text of the application are based on the drawings of the application, and are not specific limitations on the application.

[0024] Referring to Figure 1 , Figure 1 shows a first embodiment flowchart of the CIS size detection method of the application, which comprises:

[0025] S101, acquiring a ceramic tile surface image of a target ceramic tile collected by a CIS camera;

[0026] It should be noted that the CIS (Contact Image Sensor) camera is a linear array structure. When the target ceramic tile passes through the detection area, the target ceramic tile is scanned and photographed by the CIS camera, so that a high-resolution ceramic tile surface image of the target ceramic tile surface can be acquired. Since the CIS camera has the characteristics of 1:1 imaging, the image has no distortion and no edge blurring, and the resolution loss is avoided, so that the accuracy of size detection can be ensured.

[0027] S102, pre-processing the ceramic tile surface image to generate a reference surface image;

[0028] Since the reference surface image may contain noise or other interference factors, it is necessary to perform image preprocessing on the reference surface image. The specific steps include:

[0029] (1) Perform grayscale processing on the image of the tile surface to generate a grayscale image;

[0030] Converting colored tile surface images to grayscale images reduces the amount of data and facilitates subsequent processing.

[0031] (2) Filter the grayscale image;

[0032] By using filtering algorithms, noise in grayscale images can be removed, thereby improving image quality.

[0033] (3) Perform edge enhancement processing on the filtered grayscale image.

[0034] Edge enhancement algorithms can enhance the features of tile edges, making subsequent edge detection easier.

[0035] S103, Construct a rectangular fitting box that matches the edge of the target tile based on the reference surface image;

[0036] Accordingly, the steps of constructing a rectangular fitting box that matches the edge of the target tile based on the reference surface image include:

[0037] (1) Detect the tile edges of the reference surface image to extract the edge lines;

[0038] Edge detection algorithms can be used to find a clear boundary between the tile and the background, thereby determining the edge outline of the tile.

[0039] (2) Detect the reference straight line in the edge line;

[0040] The Hough transform line detection method is used to detect the reference line in the edge line.

[0041] (3) Filter the reference straight line inside the edge line;

[0042] Since the reference line at the edge of the tile is required by this invention, and there may be intersecting reference lines inside the tile, it is necessary to filter out the internal reference lines and retain only the outermost reference line.

[0043] (4) Extract corner information from the filtered baseline line;

[0044] Extract the coordinate information of the four angles from the filtered baseline line.

[0045] (5) Construct a rectangular fitting box based on the corner information.

[0046] S104, calculate the actual size of the target tile based on the preset calibration parameters and rectangular fitting frame;

[0047] Accordingly, the steps for calculating the actual size of the target tile based on the preset calibration parameters and the rectangular fitting frame include:

[0048] (1) Calculate the pixel length of the long side and the pixel length of the short side of the rectangular fitting box based on the corner information of the rectangular fitting box;

[0049] (2) Convert the pixel length of the side length to the actual length of the long side according to the preset calibration parameters, and convert the pixel length of the short side to the actual length of the short side.

[0050] It should be noted that the calibration parameters are the actual pixel size corresponding to each pixel in the reference surface image. Therefore, multiplying the side length pixel length by the calibration parameters yields the actual length of the long side of the target tile, and multiplying the short length pixel length by the calibration parameters yields the actual length of the short side of the target tile.

[0051] For example, if the target tile has a side length of 2000 pixels, a short side length of 1500 pixels, and a calibration parameter (i.e., the actual size of each pixel) of 0.1 mm / pixel, then the actual length of the target tile (i.e., the actual length of the long side) is 200 mm, and the actual width (i.e., the actual length of the short side) is 150 mm.

[0052] Therefore, this invention can achieve high-precision measurement of tile size through high-resolution image acquisition and accurate pixel conversion.

[0053] S105, determine whether the target tile is qualified based on its actual size.

[0054] Accordingly, the steps for determining whether a target tile is qualified based on its actual dimensions include:

[0055] (1) Calculate the actual length of the diagonal based on the actual length of the long side and the actual length of the short side;

[0056] (2) Compare the actual length of the diagonal with the standard length of the diagonal of the target tile to determine whether the target tile is qualified;

[0057] (3) If the target tile is determined to be unqualified, an abnormal information is generated.

[0058] Therefore, the CIS size detection method of the present invention achieves accurate acquisition of tile surface images by means of a CIS camera. For target tiles of different specifications, as long as the target tile is within the shooting range of the CIS camera during the detection process, there is no need to adjust the physical position of the CIS camera. Only the parameters (such as edge detection threshold, calibration parameters, and diagonal standard length) need to be switched to complete the specification conversion, which greatly improves the convenience of use.

[0059] See Figure 2 , Figure 2 A flowchart of a second embodiment of the CIS size detection method of the present invention is shown, which includes:

[0060] S201, acquire the tile surface image of the target tile captured by the CIS camera;

[0061] S202, Preprocess the tile surface image to generate a reference surface image;

[0062] S203, determine whether the reference surface image has been calibrated, wherein:

[0063] (1) If the reference surface image has been calibrated, extract the preset calibration parameters;

[0064] (2) If the reference surface image has not been calibrated, the CIS camera is calibrated to generate calibration parameters.

[0065] It should be noted that before performing CIS size detection, the CIS camera needs to be calibrated to determine the actual pixel size corresponding to each pixel in the image.

[0066] In this invention, if the CIS camera has been calibrated and the CIS camera does not subsequently send a position change, the reference surface image acquired by the CIS camera has been calibrated; conversely, if the CIS camera has been calibrated, but the CIS camera subsequently sends a position change, the reference surface image acquired by the CIS camera has not been calibrated, and the CIS camera needs to be calibrated again.

[0067] Accordingly, calibrating the CIS camera is crucial to ensuring measurement accuracy, and the specific steps include:

[0068] (2.1) Obtain the calibration image of the calibration board captured by the CIS camera. The calibration board has marker segments with known actual dimensions.

[0069] The calibration plate has clear scales or markings, and its actual dimensions are known.

[0070] (2.2) Measure the reference dimensions of the marked segments in the calibration image;

[0071] Reference dimensions are in pixels.

[0072] (2.3) Calculate the actual pixel size corresponding to each pixel in the calibration image based on the actual size and the reference size;

[0073] For example, if the actual length of the marker segment in the calibration plate is 100 mm, and the reference length of the marker segment in the calibration image is 1000 pixels, then the actual size of each pixel is 0.1 mm / pixel.

[0074] (2.4) Use the actual pixel size as the calibration parameter.

[0075] S204, Construct a rectangular fitting box that matches the edge of the target tile based on the reference surface image;

[0076] S205, calculate the actual size of the target tile based on the preset calibration parameters and rectangular fitting frame;

[0077] S206, determine whether the target tile is qualified based on its actual size.

[0078] Therefore, the CIS size detection method of the present invention can realize the size detection of tiles of different specifications simply by switching parameters (such as edge detection threshold, calibration parameters, and standard diagonal length), which greatly improves production efficiency and equipment flexibility.

[0079] Accordingly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described CIS size detection method.

[0080] Meanwhile, the present invention also provides a CIS size detection device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described CIS size detection method.

[0081] See Figure 3 , Figure 3 The specific structure of the CIS size detection system of the present invention is shown, which includes a CIS camera and a CIS size detection device, specifically:

[0082] CIS camera 1 is used to acquire images of the surface of the target tile 3 and the calibration image of the calibration plate;

[0083] The CIS size inspection device 2 includes a memory and a processor. The memory stores a computer program, wherein the processor executes the computer program to implement the steps of the above-described CIS size inspection method.

[0084] Therefore, by cooperating with the CIS camera 1 and the CIS size detection device 2, the target tile 3 can be scanned and photographed to obtain a high-resolution tile surface image of the target tile 3. Combined with the precise CIS size detection method, high-precision measurement of the tile size can be achieved.

[0085] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting the dimensions of a CIS (Computer Integrated System), characterized in that, include: Acquire the surface image of the target tile captured by the CIS camera; The tile surface image is preprocessed to generate a reference surface image; A rectangular fitting box matching the edge of the target tile is constructed based on the reference surface image; The actual size of the target tile is calculated based on the preset calibration parameters and the rectangular fitting frame; The suitability of the target tile is determined based on its actual dimensions.

2. The CIS size detection method as described in claim 1, characterized in that, The step of constructing a rectangular fitting box that matches the edge of the target tile based on the reference surface image includes: Detect the tile edges in the reference surface image to extract edge lines; Detect the reference straight line in the edge line; Filter the reference straight lines that are inside the edge lines; Extract corner information from the filtered baseline line; A rectangular fitting box is constructed based on the corner point information.

3. The CIS size detection method as described in claim 1, characterized in that, The step of calculating the actual size of the target tile based on the preset calibration parameters and the rectangular fitting frame includes: The pixel length of the long side and the pixel length of the short side of the rectangular fitting box are calculated based on the corner point information of the rectangular fitting box. The pixel length of the side is converted into the actual length of the long side according to the preset calibration parameters, and the pixel length of the short side is converted into the actual length of the short side.

4. The CIS size detection method as described in claim 3, characterized in that, The step of determining whether the target tile is qualified based on the actual size includes: Calculate the actual length of the diagonal based on the actual length of the longer side and the actual length of the shorter side; The actual length of the diagonal is compared with the standard length of the diagonal of the target tile to determine whether the target tile is qualified. If the target tile is determined to be substandard, an error message is generated.

5. The CIS size detection method as described in claim 1, characterized in that, Before constructing a rectangular fitting box that matches the edge of the target tile based on the reference surface image, the method further includes: Determine whether the reference surface image has been calibrated. If the reference surface image has been calibrated, then the preset calibration parameters are extracted; If the reference surface image has not been calibrated, the CIS camera is calibrated to generate calibration parameters.

6. The CIS size detection method as described in claim 5, characterized in that, The steps for calibrating a CIS camera to generate calibration parameters include: Acquire a calibration image of a calibration board captured by a CIS camera, wherein the calibration board has marker segments of known actual size; Measure the reference size of the marked segment in the calibration image; Based on the actual size and the reference size, calculate the actual pixel size corresponding to each pixel in the calibration image; The actual size of the pixel is used as the calibration parameter.

7. The CIS size detection method as described in claim 1, characterized in that, The step of preprocessing the tile surface image to generate a reference surface image includes: The image of the tile surface is converted to grayscale to generate a grayscale image; The grayscale image is filtered. Edge enhancement processing is performed on the filtered grayscale image.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the CIS size detection method according to any one of claims 1 to 7.

9. A CIS dimensional inspection device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the CIS size detection method according to any one of claims 1 to 7.

10. A CIS dimensional inspection system, characterized in that, include: CIS camera, used to acquire surface images of the target ceramic tile and calibration images of the calibration plate; The CIS size detection device as described in claim 9.

Images