A method and apparatus for detecting the warp of paperboard

Abstract

The application discloses a paperboard warping degree detection method and device, and relates to the technical field of paperboard surface flatness detection.The paperboard warping degree detection method comprises the following steps of image acquisition, image preprocessing, reflection feature extraction, edge detection, morphological operation, contour analysis and warping degree calculation; the image acquisition is performed by means of a light source and a camera located above the paperboard to be detected to acquire image information of the paperboard; the image preprocessing is performed by converting the acquired image information into a gray-scale image, removing noise and then performing histogram equalization to enhance contrast; the reflection feature extraction is performed by calculating the brightness gradient in the horizontal and vertical directions to obtain a reflection change intensity map, and then performing binarization processing to obtain a reflection feature map; the edge detection is performed by adopting a Canny algorithm to extract a basic edge, and then performing a morphological closing operation on the reflection feature map, and then performing a bit or operation on the basic edge to obtain an enhanced edge; and the morphological operation is performed by performing corrosion operations on the enhanced edge by using different structure elements in sequence to obtain an optimized edge image.

Description

Technical Field

[0001] This application relates to the field of paperboard surface flatness detection technology, and in particular to a method and apparatus for detecting paperboard warpage. Background Technology

[0002] Warping is a common quality defect in cardboard production, directly affecting subsequent processing and product quality. Traditional cardboard warping detection mainly relies on manual visual inspection, which suffers from low efficiency, high subjectivity, and insufficient accuracy.

[0003] Therefore, some devices for detecting the warpage of cardboard have emerged. For example, multiple detection terminals are arranged in a row, and the cardboard is passed through the detection terminals by a conveyor belt. When the cardboard warps, the detection terminals will be displaced, thereby judging the surface condition of the cardboard. However, this method has low detection efficiency, and the results are inaccurate because a certain gap is usually designed between the detection terminals and the cardboard. Summary of the Invention

[0004] This application provides a method and apparatus for detecting the warpage of cardboard, which provides a new, more sensitive and accurate solution for detecting the warpage of cardboard.

[0005] This application provides a method for detecting the warpage of cardboard, including image acquisition, image preprocessing, reflection feature extraction, edge detection, morphological operations, contour analysis, and warpage calculation. Image acquisition involves acquiring image information of the cardboard using a light source and camera positioned above it. Image preprocessing converts the acquired image information into a grayscale image, removes noise, and performs histogram equalization to enhance contrast. Reflection feature extraction calculates the brightness gradients in the horizontal and vertical directions to obtain a reflection intensity map, which is then binarized to obtain a reflection feature map. Edge detection uses the Canny algorithm to extract basic edges and performs morphological closure operations on the reflection feature map. Then, a bitwise OR operation is performed with the base edge to obtain the enhanced edge; morphological operations are performed on the enhanced edge, and different structural elements are eroded sequentially to obtain the optimized edge image; contour analysis is performed to extract the outer contour from the optimized edge image, and the contour with the largest area is selected as the cardboard contour, and then the main straight lines in the contour are detected by Hough transform; warpage calculation is performed, and the two longest detected straight lines are selected as reference lines, and the distance from all contour points to these two reference lines is calculated. According to the reflection intensity at the corresponding position in the reflection feature map, the weighted distance is calculated, and the cardboard length is taken as the maximum side length of the contour bounding box. The warpage output is the ratio of the maximum weighted distance to the cardboard length.

[0006] This application forms a complete technical solution "from image to quantification result" through image acquisition, preprocessing, reflection feature extraction, edge detection, morphological operation, contour analysis, and warp calculation, achieving high-precision and automated detection, replacing manual subjective judgment, and outputting accurate cardboard warp detection results.

[0007] It solves the problems of traditional edge detection being insensitive to subtle warping and easily affected by surface texture; it captures the reflection differences caused by warping of cardboard by extracting reflection features (based on brightness gradient), thereby enhancing the distinguishability of edge information; and it correlates reflection intensity with geometric deviation by weighted distance calculation, making warping measurement more consistent with the actual physical form.

[0008] In some embodiments of this application, the results of warpage are further classified, and the test results are classified into qualified, slight warpage, and severe warpage according to the warpage value, and the test results are output.

[0009] The system categorizes and outputs results for warpage as qualified, slightly warped, and severely warped, enabling direct alignment of these output values ​​with production quality standards. This facilitates rapid product grade determination on the production line, guiding subsequent sorting and rework operations. Simultaneously, it improves quality control efficiency and adapts to the needs of industrialized batch testing.

[0010] In some embodiments of this application, morphological operations include erosion operations of 3×3 structuring elements and dilation operations of 5×5 structuring elements on the enhanced edges.

[0011] It solves the problem of unstable edge optimization effect caused by fuzzy morphological parameters. 3×3 erosion can accurately remove small noisy edges (such as dust and texture interference on cardboard surface), and 5×5 expansion can effectively connect broken edges caused by noise or uneven lighting, balancing "denoising" and "edge integrity". Fixed parameters make the method highly reproducible and facilitate standardized deployment in different scenarios.

[0012] In some embodiments of this application, reflection feature extraction includes: calculating the brightness gradient in the horizontal and vertical directions; generating a reflection change intensity map based on the gradient magnitude; and performing thresholding on the reflection change intensity map to highlight areas with significant reflection changes.

[0013] It solves the problems of ambiguous logic and difficulty in engineering implementation of reflection feature extraction; the brightness gradient directly reflects the angle change of the cardboard surface caused by warping (the larger the gradient, the more significant the reflection difference), and the thresholding process highlights the core warped area, providing a precise basis for subsequent edge enhancement; it makes the relationship between reflection features and physical warping clearer and improves the robustness of feature extraction.

[0014] In some embodiments of this application, the weighted distance in the warp calculation is: weighted distance = base distance + base distance × reflection intensity + base distance × gradient sensitivity coefficient; the reflection intensity is the reflection characteristic value normalized to the range of 0-1; the gradient sensitivity coefficient ranges from 1.0 to 1.5.

[0015] It solves the problem that traditional geometric distance calculation is insensitive to "reflection anomaly areas"; by weighting the reflection intensity, it amplifies the deviation contribution of the warped core area (where reflection changes drastically), making the quantification results of minor warping (such as 0.1mm level) more significant; the gradient sensitivity coefficient can be adjusted according to the cardboard material (such as surface smoothness), enhancing the method's adaptability to different types of cardboard.

[0016] A cardboard warpage detection device is provided, which uses the above-mentioned cardboard warpage detection method to detect the warpage of cardboard. The cardboard warpage detection device includes a support body, a conveyor belt, a baffle, a diffuse light source, a first bracket, a first image capture unit, a second bracket, and a second image capture unit.

[0017] The support body has a placement area for holding the cardboard to be tested. A conveyor belt is disposed on the support body and located on one side of the placement area. The conveyor belt is used to move the cardboard to be tested along the transport direction of the conveyor belt. A baffle is disposed on the support body and located at the transport end of the conveyor belt. The baffle is used to shield the cardboard to be tested. A diffuse light source is disposed on the baffle, and the light from the diffuse light source is directed toward the cardboard to be tested. A first bracket extends along the transport direction perpendicular to the conveyor belt. The first bracket is disposed on one side of the placement area and located above the conveyor belt. A first image capture unit is disposed on the first bracket. A second bracket extends along the transport direction of the conveyor belt. The second bracket is disposed on one side of the conveyor belt and located above the conveyor belt. A second image capture unit is disposed on the second bracket. The first image capture unit and the second image capture unit are distributed alternately on the surface of the cardboard to be tested along the transport direction perpendicular to the conveyor belt.

[0018] The conveyor belt enables continuous paperboard transport, adapting to assembly line operations; the dual-support + dual-image-capturing elements enable multi-angle image acquisition in both the "vertical transport direction" and "along the transport direction," covering the edges and middle areas of the paperboard and avoiding missed detections from a single angle; the diffused light source provides uniform illumination, reducing specular reflection interference, and works with baffles to fix the paperboard position, ensuring the stability of image acquisition; the paperboard warpage detection device can adapt to and fit into production line operations, improving the accuracy and efficiency of paperboard detection.

[0019] In some embodiments of this application, the cardboard warpage detection device further includes a baffle plate extending along a plane perpendicular to the conveyor belt, the baffle plate being located on one side of the placement area, above the conveyor belt, and on the side of the first support away from the baffle; a gap is provided between the baffle plate and the conveyor belt, the gap between the baffle plate and the conveyor belt being greater than the thickness of one cardboard to be tested and less than the thickness of two cardboards to be tested.

[0020] The baffle can force only one sheet of paper to pass through at a time, ensuring that the image acquisition object is unique, avoiding edge confusion in overlapping areas, and improving the accuracy of contour extraction; the structure is simple and can achieve single-sheet separation without complex sensors, reducing device costs.

[0021] In some embodiments of this application, the cardboard warpage detection device further includes two vertical slide rails, which are mounted on the support body and located on both sides of the conveyor belt. The two ends of the baffle are slidably mounted on the two vertical slide rails. When the cardboard to be tested passes the test, the vertical slide rails drive the baffle to slide upward, and the cardboard to be tested slides off the conveyor belt.

[0022] The combination of vertical slide rails and baffles enables automatic output, solving the efficiency problem of manual sorting after inspection; qualified cardboard flows out automatically, while unqualified cardboard is temporarily stored, reducing manual intervention and improving the automation level of the production line; the slide rail drive has a fast response and can be matched with high-speed conveyor belts (such as 60 meters / minute) to meet high production capacity requirements.

[0023] In some embodiments of this application, the second support is provided with a space for the paperboard to be tested to pass through, and multiple conveyor belts are provided, which are parallel and spaced apart; the paperboard warpage detection device also includes multiple rollers, which are arranged on one side of the baffle, and the multiple rollers are respectively arranged between the multiple conveyor belts. The rotation direction of the rollers is perpendicular to the conveying direction of the conveyor belts, and the rollers send the unqualified paperboard to be tested that is blocked in front of the baffle out from the space on the second support.

[0024] Multiple conveyor belts are spaced apart, with rollers positioned in the gaps and rotating perpendicular to the conveying direction to discharge defective cardboard. The rollers, perpendicular to the conveyor belts, discharge defective cardboard from the side, separating it from the forward flow of qualified cardboard and enabling fully automated sorting. The multiple conveyor belt design prevents cardboard deformation during transport, ensuring morphological stability during inspection.

[0025] In some embodiments of this application, along the direction perpendicular to the conveying plane of the conveyor belt, the distance between the diffuse light source and the upper surface of the cardboard to be tested is greater than 10 mm, the distance between the first image capturing unit and the diffuse light source is greater than 10 mm, and the distance between the second image capturing unit and the diffuse light source is greater than 10 mm.

[0026] The distance between the diffuse light source and the cardboard, and the distance between the image capture element and the light source, are both greater than 10mm. This ensures that the diffuse light source uniformly covers the cardboard surface, avoiding local overexposure or underexposure. At the same time, it ensures that the image capture element (camera) has a complete field of view, clear focus, and reduces edge distortion. It also provides clear parameters for device installation, ensures consistency between different batches of devices, and reduces debugging difficulty. Attached Figure Description

[0027] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of the present invention and do not constitute a limitation on the technical solutions of the present invention.

[0028] Figure 1 This is a schematic flowchart of a paperboard warpage detection method provided in an embodiment of this application.

[0029] Figure 2 This is a schematic diagram of a cardboard warpage detection device provided in an embodiment of this application.

[0030] Figure reference numerals: 01-Image acquisition; 02-Image preprocessing; 03-Reflection feature extraction; 04-Edge detection; 05-Morphological operation; 06-Contour analysis; 07-Warp calculation; 08-Result classification; 1-Supporting body; 11-Placement area; 2-Conveyor belt; 3-Baffle; 4-Diffuse light source; 5-First support; 51-First image capture unit; 6-Second support; 61-Second image capture unit; 7-Guide plate; 8-Vertical slide rail; 9-Roller; A indicates that the second support has a space for the paperboard to be inspected to pass through. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0033] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0034] In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly, for example, they can refer to a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "linked" as used in this application have the meaning of establishing electrical connection. The specific meaning needs to be understood in conjunction with the context.

[0035] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] Warping is a common quality defect in cardboard production, directly affecting subsequent processing and product quality. Traditional cardboard warping detection mainly relies on manual visual inspection, which suffers from low efficiency, high subjectivity, and insufficient accuracy.

[0037] Therefore, some devices for detecting the warpage of cardboard have emerged. For example, multiple detection terminals are arranged in a row, and the cardboard is passed through the detection terminals by a conveyor belt. When the cardboard warps, the detection terminals will be displaced, thereby judging the surface condition of the cardboard. However, this method has low detection efficiency, and the results are inaccurate because a certain gap is usually designed between the detection terminals and the cardboard.

[0038] Therefore, please refer to Figure 1 This application provides a method for detecting the warpage of cardboard, including image acquisition 01, image preprocessing 02, reflection feature extraction 03, edge detection 04, morphological operation 05, contour analysis 06, and warpage calculation 07.

[0039] Image Acquisition 01: Image information of the cardboard is acquired using a light source and camera located above the cardboard to be inspected.

[0040] Image preprocessing 02 converts the acquired image information into a grayscale image, removes noise, and then performs histogram equalization to enhance contrast.

[0041] Reflection feature extraction 03: Calculate the brightness gradient in the horizontal and vertical directions to obtain the reflection change intensity map, and obtain the reflection feature map through binarization.

[0042] Edge detection 04: The Canny algorithm is used to extract the basic edges, and a morphological closure operation is performed on the reflection feature map. Then, a bitwise OR operation is performed with the basic edges to obtain the enhanced edges. Morphological operation 05: Different erosion operations with different structural elements are performed on the enhanced edges to obtain the optimized edge image.

[0043] Contour Analysis 06 extracts the outer contour from the optimized edge image, selects the contour with the largest area as the cardboard contour, and then detects the main straight lines in the contour through Hough transform.

[0044] Warpage Calculation 07: Select the two longest detection lines as reference lines, calculate the distance from all contour points to these two reference lines, calculate the weighted distance based on the reflection intensity at the corresponding position in the reflection feature map, take the maximum side length of the contour bounding box as the cardboard length, and output the warpage as the ratio of the maximum weighted distance to the cardboard length.

[0045] Please refer to Figure 1 This application forms a complete technical solution "from image to quantification result" through image acquisition 01, preprocessing, reflection feature extraction 03, edge detection 04, morphological operation 05, contour analysis 06, and warpage calculation 07, achieving high-precision and automated detection, replacing manual subjective judgment, and outputting accurate cardboard warpage detection results.

[0046] It solves the problems of traditional edge detection being insensitive to minor warping and easily affected by surface texture; it captures the reflection differences caused by warping of cardboard by reflection feature extraction (based on brightness gradient), enhancing the distinguishability of edge information; and it correlates reflection intensity with geometric deviation by weighted distance calculation, making warping measurement more consistent with the actual physical form.

[0047] For example, image acquisition 01 acquires image information of the cardboard by using a light source and a camera positioned above the cardboard to be inspected. A diffuse light source is used to provide uniform illumination, avoiding glare interference caused by direct strong light; the camera can shoot vertically or at an angle to ensure complete capture of the cardboard surface features.

[0048] For example, using a ring-shaped LED diffuse light source 4 arranged at a 45° angle, in conjunction with a 2-megapixel industrial camera, images with a resolution of 1920×1080 can be acquired at a working distance of 50cm.

[0049] For example, image preprocessing 02 involves converting the acquired image information into a grayscale image, removing noise, and then performing histogram equalization to enhance contrast. Grayscale conversion reduces computation, Gaussian filtering removes high-frequency noise, and histogram equalization improves the detail differences between bright and dark areas, laying the foundation for subsequent feature extraction.

[0050] For example, a 5×5 Gaussian kernel is used to filter the color image, and the contrast of the grayscale image is enhanced by the cv2.equalizeHist() function, so that the grayscale difference between the edge of the cardboard and the background is increased from 10 to more than 30.

[0051] For example, in reflection feature extraction 03, the intensity map of reflection change is obtained by calculating the brightness gradient in the horizontal and vertical directions. After binarization, the reflection feature map is obtained. The brightness gradient reflects the change in reflection angle caused by warping of the cardboard surface. The larger the gradient, the more obvious the warping. Binarization highlights the areas with significant reflection changes (the core warping area).

[0052] For example, the Sobel operator is used to calculate the horizontal (Gx) and vertical (Gy) gradients, and the gradient magnitude map is generated by √(Gx²+Gy²). A threshold of 30 is set for binarization to obtain the reflection feature map.

[0053] For example, edge detection 04 uses the Canny algorithm to extract the basic edges, performs a morphological closure operation on the reflection feature map, and then performs a bitwise OR operation with the basic edges to obtain enhanced edges. The Canny algorithm extracts complete basic edges, and the reflection feature map is morphologically closed (filling small gaps) and then fused with the basic edges to strengthen the edge signal of the warped region.

[0054] For example, the Canny algorithm sets a low threshold of 50 and a high threshold of 150, and performs a closing operation on the reflection feature map using a 3×3 structuring element, which improves the edge continuity by 40% after fusion.

[0055] For example, morphological operation 05 involves performing erosion and dilation operations on the enhanced edges using different structural elements to obtain an optimized edge image. Erosion removes minor noise edges (such as surface textures), while dilation connects broken but valid edges, balancing edge purity and integrity.

[0056] For example, first erode once with a 3×3 rectangular structuring element to remove noise with a diameter <3 pixels; then expand once with a 5×5 structuring element to connect edges with gaps <5 pixels.

[0057] For example, contour analysis 06 extracts the outer contour from the optimized edge image, selects the contour with the largest area as the cardboard contour, and then uses Hough transform to detect the main straight lines in the contour. The outer contour reflects the overall shape of the cardboard, and the largest area contour is used to filter out background interference; Hough transform identifies ideal straight lines (flat cardboard edges), providing a reference benchmark for warpage calculation 07.

[0058] For example, the cv2.findContours() function can be used to extract contours and filter out contours with an area greater than 10,000 pixels; the Hough transform can be set to a minimum line length of 100 pixels to detect the two long straight lines of the cardboard.

[0059] For example, warpage calculation 07 selects the two longest detection lines as reference lines, calculates the distance from all contour points to these two reference lines, and calculates the weighted distance based on the reflection intensity at the corresponding position in the reflection feature map. The cardboard length is taken as the maximum side length of the contour bounding box, and the warpage output is the ratio of the maximum weighted distance to the cardboard length. The weighted distance amplifies the deviation contribution of the obvious reflection area (warpage core), making subtle warpage easier to quantify; the warpage is expressed as a relative value, eliminating the influence of cardboard size differences.

[0060] For example, if the basic distance of a certain contour point is 0.5mm, the corresponding reflection intensity is 0.8 (after normalization), the gradient sensitivity coefficient is 1.2, and the weighted distance is 0.5 + 0.5 × 0.8 + 0.5 × 1.2 = 1.5mm; the cardboard length is 100mm, and the warpage is 1.5 / 100 = 1.5%.

[0061] For example, Result Classification 08 can classify test results into qualified, slightly warped, and severely warped based on the warp value, and output the test results. This aligns with production standards, facilitating rapid product grade determination and guiding the sorting process.

[0062] For example, by setting thresholds of 0.01 and 0.03, warpage <0.01 is considered acceptable, 0.01-0.03 is considered slight warpage, and ≥0.03 is considered severe warpage.

[0063] Please refer to Figure 1 In some examples, the results of warpage are also classified into categories 08, which classify the test results into qualified, slight warpage, and severe warpage based on the warpage value, and output the test results.

[0064] The results of warpage are classified into 08 categories and output as qualified, slightly warped, and severely warped. This output value can be directly linked to the production quality standards, making it easy for the production line to quickly determine the product grade and guide subsequent sorting, rework and other operations. At the same time, it improves the efficiency of quality control and meets the needs of industrial batch testing.

[0065] Please refer to Figure 1In some examples, morphological operation 05 includes erosion of the enhanced edges by a 3×3 structuring element and dilation of the edges by a 5×5 structuring element.

[0066] It solves the problem of unstable edge optimization effect caused by fuzzy morphological parameters. 3×3 erosion can accurately remove small noisy edges (such as dust and texture interference on cardboard surface), and 5×5 expansion can effectively connect broken edges caused by noise or uneven lighting, balancing "denoising" and "edge integrity". Fixed parameters make the method highly reproducible and facilitate standardized deployment in different scenarios.

[0067] In some examples, reflection feature extraction 03 includes: calculating the brightness gradient in the horizontal and vertical directions; generating a reflection change intensity map based on the gradient magnitude; and thresholding the reflection change intensity map to highlight areas with significant reflection changes.

[0068] It solves the problems of ambiguity and difficulty in engineering implementation in the 03 logic of reflection feature extraction; the brightness gradient directly reflects the angle change of the cardboard surface caused by warping (the larger the gradient, the more significant the reflection difference), and the thresholding process highlights the core warped area, providing a precise basis for subsequent edge enhancement; it makes the relationship between reflection features and physical warping clearer and improves the robustness of feature extraction.

[0069] In some examples, the weighted distance calculated in warp calculation 07 is: weighted distance = base distance + base distance × reflection intensity + base distance × gradient sensitivity coefficient; the reflection intensity is the reflection feature value normalized to the range of 0-1; the gradient sensitivity coefficient ranges from 1.0 to 1.5.

[0070] It solves the problem that traditional geometric distance calculation is insensitive to "reflection anomaly areas"; by weighting the reflection intensity, it amplifies the deviation contribution of the warped core area (where reflection changes drastically), making the quantification results of minor warping (such as 0.1mm level) more significant; the gradient sensitivity coefficient can be adjusted according to the cardboard material (such as surface smoothness), enhancing the method's adaptability to different types of cardboard.

[0071] This application provides an embodiment one, a method for detecting the warpage of cardboard, applicable to ordinary kraft paper.

[0072] Image Acquisition 01: Images were acquired using a 16-megapixel camera at a distance of 60cm, using a 45° ring diffuse light source 4 (800 lux).

[0073] Preprocessing: 5×5 Gaussian filtering and histogram equalization expand the grayscale range to 0-255.

[0074] Reflection Feature Extraction 03: Sobel operator calculates gradient, threshold 25 generates reflection feature map.

[0075] Edge detection 04: Canny threshold (40, 120), the reflection feature map is fused with the basic edge after a 3×3 closing operation.

[0076] Morphological operation 05: 3×3 erosion once, 5×5 expansion once.

[0077] Contour Analysis 06: Extract the maximum contour, and use Hough transform to detect the two longest straight lines (length > 200 pixels).

[0078] Warpage Calculation 07: Gradient sensitivity coefficient 1.1, cardboard length is taken as the long side of the boundary frame, output warpage.

[0079] Classification: Thresholds 0.01 and 0.03, output acceptable / slight / severe warping results.

[0080] This application provides a second embodiment of a method for detecting the warpage of cardboard, applicable to corrugated cardboard.

[0081] Image Acquisition 01: Increase the light source intensity to 1500 lux, shorten the camera exposure time to 10 ms, and reduce texture interference.

[0082] Preprocessing: 7×7 Gaussian filter to remove corrugated texture noise.

[0083] Reflection Feature Extraction 03: Increase the threshold to 40 to filter out false reflection changes caused by texture.

[0084] Edge Detection 04: Canny threshold (60, 180) enhances edge anti-interference capability.

[0085] Morphological operation 05: 3×3 erosion twice to remove more texture edges.

[0086] Contour Analysis 06: Hough Transform minimum line length set to 300 pixels to adapt to larger corrugated cardboard sizes.

[0087] Warp Calculation 07: Gradient sensitivity coefficient increased to 1.4, amplifying the real warp signal.

[0088] Classification: Same as Example 1, with the addition of "Retest" level (warpage 0.025-0.03).

[0089] To facilitate industrial production and improve the efficiency and accuracy of cardboard warpage detection, this application also provides a cardboard warpage detection device. The device employs the aforementioned cardboard warpage detection method for cardboard warpage detection. Please refer to [link / reference needed]. Figure 2 The cardboard warpage detection device includes a support body 1, a conveyor belt 2, a baffle 3, a diffuse light source 4, a first bracket 5, a first image capture unit 51, a second bracket 6, and a second image capture unit 61.

[0090] Please refer to Figure 2 The support body 1 has a placement area 11 for holding the cardboard to be tested. The conveyor belt 2 is disposed on the support body 1 and located on one side of the placement area 11. The conveyor belt 2 is used to move the cardboard to be tested along the transport direction of the conveyor belt 2.

[0091] The baffle 3 is installed on the support body 1 and is located at the end of the conveyor belt 2. The baffle 3 is used to cover the cardboard to be inspected.

[0092] A diffuse light source 4 is placed on the baffle 3, and the light from the diffuse light source 4 is directed toward the cardboard to be tested.

[0093] The first support 5 extends along the conveying direction perpendicular to the conveyor belt 2. The first support 5 is disposed on one side of the placement area 11 and is located above the conveyor belt 2.

[0094] The first image capture unit 51 is mounted on the first bracket 5.

[0095] The second support 6 extends along the conveying direction of the conveyor belt 2, and is located on one side of the conveyor belt 2, above the conveyor belt 2.

[0096] The second image capture unit 61 is disposed on the second support 6. The first image capture unit 51 and the second image capture unit 61 are distributed at intervals along the conveying direction perpendicular to the conveyor belt 2 and projected onto the surface of the cardboard to be inspected.

[0097] Please refer to Figure 2 The conveyor belt 2 enables continuous paperboard transport, adapting to assembly line operations; the dual brackets and dual image capture elements enable multi-angle image acquisition 01 in both the "vertical transport direction" and "along the transport direction," covering the edges and middle areas of the paperboard and avoiding missed detections from a single angle; the diffuse light source 4 provides uniform illumination, reducing specular reflection interference, and works with the baffle 3 to fix the paperboard position, ensuring the stability of the image acquisition 01; the paperboard warpage detection device can adapt to and fit into production line operations, improving the accuracy and efficiency of paperboard detection.

[0098] For example, the support body 1 may have a placement area 11 for holding the cardboard to be tested. Providing a stable mounting base, the placement area 11 ensures the cardboard is fixed in position during testing. For instance, an aluminum alloy frame may be used, and the placement area 11 is a flat 500×500mm surface covered with anti-slip rubber.

[0099] For example, the conveyor belt 2 is disposed on the support body 1 and located on one side of the placement area 11, for moving the cardboard to be inspected along the transport direction. The conveyor belt 2 enables continuous transport of cardboard and is suitable for production line operations. For example, the conveyor belt 2 can be composed of three synchronous belts with a width of 50 mm, a spacing of 100 mm, and a running speed of 30 m / min.

[0100] For example, a baffle 3 is disposed on the support body 1 at the end of the conveyor belt 2 to shield the cardboard to be inspected. This temporarily blocks the cardboard 7, ensuring its stable position during inspection. For instance, the baffle 3 can be made of acrylic sheet, 100mm high, with a 5mm gap between its bottom and the surface of the conveyor belt 2.

[0101] For example, the diffuse light source 4 is disposed on the baffle 3, with the light directed toward the cardboard to be inspected. The diffuse light source 4 is used to provide uniform diffuse illumination, enhancing the differences in reflective characteristics of the cardboard surface. For example, the diffuse light source 4 can be a ring-shaped LED diffuse light source 4 with a color temperature of 6500K, a light intensity of 1000 lux, and a diameter of 150mm.

[0102] For example, the first bracket 5 extends along a direction perpendicular to the conveyor belt 2, is located on one side of the placement area 11 and above the conveyor belt 2, and the first image capturing element is disposed on the first bracket 5. The first bracket 5 and the first image capturing element can realize image acquisition 01 perpendicular to the conveying direction, covering the edge features in the width direction of the cardboard.

[0103] For example, the first bracket 5 can be made of aluminum profile with a length of 800mm; the first image capturing element is a 12-megapixel camera with an 8mm lens, and the shooting direction is perpendicular to the conveyor belt 2.

[0104] For example, the second support 6 extends along the direction of the conveyor belt 2, is located on one side of the conveyor belt 2 and above the conveyor belt 2; the second image capture unit 61 is mounted on the second support 6 and is distributed at intervals with the first image capture element in the vertical conveying direction. The second support 6 and the second image capture unit 61 can realize image acquisition 01 along the conveying direction, covering the edge features of the cardboard along its length, and forming multi-angle acquisition with the first camera.

[0105] For example, the second bracket 6 is 1000mm long, and the second image capture unit 61 is the same model camera, which is 300mm apart from the first camera in the width direction.

[0106] For example, the baffle plate 7 extends along a plane perpendicular to the conveyor belt 2, located on one side of the placement area 11 and on the side of the first support 5 away from the baffle plate 3; the gap between the baffle plate 7 and the conveyor belt 2 is greater than the thickness of one sheet of paperboard and less than the thickness of two sheets of paperboard. The baffle plate 7 can prevent multiple sheets of paperboard from stacking into the detection area, ensuring that each detection object is unique.

[0107] For example, the baffle plate 7 is made of stainless steel and has a gap of 0.5 mm between it and the conveyor belt 2 (when the plate thickness is 0.3 mm).

[0108] For example, two vertical slide rails 8 are mounted on the support body 1, located on both sides of the conveyor belt 2, with baffles 3 slidably mounted on the slide rails at both ends; when a paperboard is qualified, the slide rails drive the baffles 3 to rise and release it. The vertical slide rails 8 can realize the automatic raising and lowering of the baffles 3, and complete the automatic release of qualified paperboards in conjunction with the detection results. For example, the vertical slide rails 8 can be selected with a slide rail stroke of 50mm, driven by a servo motor, and a response time of <0.5s.

[0109] For example, the guide roller 9 is located on one side of the baffle 3, between multiple conveyor belts 2, and rotates perpendicular to the conveyor belts 2. It is used to discharge defective cardboard. The guide roller 9 can discharge defective cardboard from the side, realizing automatic sorting. For example, three rubber guide rollers 9 with a diameter of 30 mm, a rotation speed of 100 r / min, and a gap of 1 mm between them and the conveyor belts 2 can be selected.

[0110] For example, the distance between the diffuse light source 4 and the upper surface of the cardboard is >10mm, and the distance between the image capturing element and the light source is >10mm. The first and second image capturing elements can be at the same height or at different heights. This height difference avoids uneven lighting or image blurring caused by excessively close proximity, ensuring image quality. For instance, the diffuse light source 4 is 10mm from the cardboard, and the camera is 10mm from the light source.

[0111] Please refer to Figure 2 In some examples, the cardboard warpage detection device also includes a baffle 7, which extends along a plane perpendicular to the conveyor belt 2. The baffle 7 is located on one side of the placement area 11, above the conveyor belt 2, and on the side of the first support 5 away from the baffle 3. A gap is provided between the baffle 7 and the conveyor belt 2. The gap between the baffle 7 and the conveyor belt 2 is greater than the thickness of one cardboard to be tested and less than the thickness of two cardboards to be tested.

[0112] The baffle 7 can force only one baffle to pass through at a time, ensuring that the image acquisition object is unique, avoiding edge confusion in overlapping areas, and improving the accuracy of contour extraction; the structure is simple and can achieve single-sheet separation without complex sensors, reducing device cost.

[0113] Please refer to Figure 2 In some examples, the cardboard warpage detection device also includes two vertical slide rails 8, which are mounted on the support body 1 and located on both sides of the conveyor belt 2. The two ends of the baffle 3 are slidably mounted on the two vertical slide rails 8. When the cardboard to be tested passes the test, the vertical slide rails 8 drive the baffle 3 to slide upward, and the cardboard to be tested slides off the conveyor belt 2.

[0114] The combination of vertical slide rail 8 and baffle 3 enables automatic output, solving the efficiency problem of manual sorting after inspection; qualified cardboard flows out automatically, while unqualified cardboard is temporarily stored, reducing manual intervention and improving the automation level of the production line; the slide rail drive has a fast response and can be matched with high-speed conveyor belt 2 (such as 60 meters / minute) to meet high capacity requirements.

[0115] Please refer to Figure 2 In some examples, the second support 6 is provided with space for the passage of the cardboard to be tested. Figure 2 (As shown in area A), multiple conveyor belts 2 are configured, and the multiple conveyor belts 2 are parallel and spaced apart; the cardboard warpage detection device also includes multiple rollers 9 ( Figure 2 (The number 9 represents the installation area only and is not shown in the specific structural diagram). The roller 9 is set on one side of the baffle 3. Multiple rollers 9 are respectively set between multiple conveyor belts 2. The rotation direction of the roller 9 is perpendicular to the conveying direction of the conveyor belt 2. The roller 9 can send out the unqualified paperboard to be tested from the space inside the second bracket 6 when it is blocked in front of the baffle 3.

[0116] Multiple conveyor belts 2 are spaced apart, with rollers 9 located in the gaps and rotating perpendicular to the conveying direction to discharge defective cardboard. The rollers 9 are perpendicular to the direction of the conveyor belts 2, which can discharge defective cardboard from the side, separating it from the forward flow of qualified cardboard, thus achieving fully automatic sorting; the design of multiple conveyor belts 2 avoids deformation of cardboard during conveying, ensuring morphological stability during inspection.

[0117] Please refer to Figure 2 In some examples, along the direction perpendicular to the conveying plane of conveyor belt 2, the distance between the diffuse light source 4 and the upper surface of the cardboard to be inspected is greater than 10 mm, the distance between the first image capturing unit 51 and the diffuse light source 4 is greater than 10 mm, and the distance between the second image capturing unit 61 and the diffuse light source 4 is greater than 10 mm. Figure 2 The positions of the first image capture unit 51 and the second image capture unit 61 are shown in the diagram. The actual height needs to be adjusted during installation to obtain the required image and light information.

[0118] The distance between the diffuse light source 4 and the cardboard, and the distance between the image capturing element and the light source, are both greater than 10mm. This ensures that the light from the diffuse light source 4 evenly covers the surface of the cardboard, avoiding local overexposure or underexposure. At the same time, it ensures that the field of view of the image capturing element (camera) is complete, the focus is clear, and edge distortion is reduced. It also provides clear parameters for device installation, ensures the consistency of different batches of devices, and reduces the difficulty of debugging.

[0119] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0120] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting the warp of paperboard, characterized in that The method comprises: image acquisition, image information of the paperboard is acquired by a light source and a camera located above the paperboard to be detected; image preprocessing, the acquired image information is converted into a grayscale image, and after removing noise, histogram equalization is performed to enhance contrast; reflection feature extraction, the intensity of reflection change is obtained by calculating the brightness gradient in the horizontal and vertical directions, and a reflection feature map is obtained by binary processing; edge detection, the basic edge is extracted by using the Canny algorithm, and a morphological closing operation is performed on the reflection feature map, and then a bit or operation is performed with the basic edge to obtain an enhanced edge; morphological operation, corrosion operations of different structure elements are performed on the enhanced edge to obtain an optimized edge image; contour analysis, the outer contour is extracted from the optimized edge image, the largest area contour is selected as the paperboard contour, and then the main straight lines in the contour are detected by Hough transform; warping degree calculation, the two longest detected straight lines are selected as reference lines, the distances of all contour points to the two reference lines are calculated, the weighted distance is calculated according to the reflection intensity of the corresponding position in the reflection feature map, the length of the paperboard is taken as the maximum side length of the contour bounding box, and the warping degree is output as the ratio of the maximum weighted distance to the length of the paperboard.

2. The paperboard warp detection method of claim 1, wherein, The method further comprises classifying the result of the warping degree, dividing the detection result into qualified, slight warping and severe warping according to the warping degree value, and outputting the detection result.

3. The paperboard warping degree detection method according to claim 1 or 2, wherein the morphological operation comprises a corrosion operation of a 3*3 structure element on the enhanced edge and a dilation operation of a 5*5 structure element.

4. The paperboard warping degree detection method according to claim 1 or 2, wherein the reflection feature extraction comprises: calculating the brightness gradient in the horizontal and vertical directions; generating a reflection change intensity map based on the gradient amplitude; performing threshold processing on the reflection change intensity map to highlight the significant reflection change region. The paperboard warping degree detection method according to any one of claims 1-4 is used for paperboard warping degree detection, and the paperboard warping degree detection device comprises: a support body having a placing area for containing the paperboard to be detected, 5. A paperboard warp detection apparatus characterized by, a conveying belt arranged on the support body and located on one side of the placing area, the conveying belt being used for moving the paperboard to be detected along the conveying direction of the conveying belt; a baffle arranged on the support body, the baffle being located at the conveying end of the conveying belt, and the baffle being used for shielding the paperboard to be detected; a diffuse light source arranged on the baffle, the light of the diffuse light source being directed towards the paperboard to be detected; a first support extending perpendicular to the conveying direction of the conveying belt, the first support being arranged on one side of the placing area and located above the conveying belt; a first image capturing unit arranged on the first support; a second support extending along the conveying direction of the conveying belt, the second support being arranged on one side of the conveying belt, and the second support being located above the conveying belt; a second image capturing unit arranged on the second support, the first image capturing unit and the second image capturing unit being distributed at intervals on the surface of the paperboard to be detected in a direction perpendicular to the conveying direction of the conveying belt. ​ ​ 6.The paperboard warping degree detection device according to claim 5, characterized in that, the paperboard warping degree detection device further comprises a paperboard blocking plate, the paperboard blocking plate extends along a plane perpendicular to the plane on which the conveying belt is located, the paperboard blocking plate is located on one side of the placement area, the paperboard blocking plate is located above the conveying belt, and the paperboard blocking plate is located on the side of the first support away from the blocking plate; a gap is arranged between the paperboard blocking plate and the conveying belt, the gap between the paperboard blocking plate and the conveying belt is greater than the thickness of one paperboard to be detected and less than the thickness of two paperboards to be detected. 7.The paperboard warping degree detection device according to claim 5, characterized in that, the paperboard warping degree detection device further comprises two vertical sliding rails, the two vertical sliding rails are arranged on the support body, the two vertical sliding rails are located on both sides of the conveying belt, and the two ends of the blocking plate are slidingly arranged on the two vertical sliding rails; when the paperboard to be detected is detected to be qualified, the vertical sliding rails drive the blocking plate to slide upwards, and the paperboard to be detected slides out of the conveying belt. 8.The paperboard warping degree detection device according to claim 7, characterized in that, the second support is provided with a space for passing the paperboard to be detected, and the conveying belt is provided in a plurality of forms, and the plurality of conveying belts are parallel and spaced apart; the paperboard warping degree detection device further comprises a plurality of row rollers, the row rollers are arranged on one side of the blocking plate, the plurality of row rollers are arranged between the plurality of conveying belts respectively, the rotation direction of the row rollers is perpendicular to the conveying direction of the conveying belt, and the row rollers send the unqualified paperboard to be detected in front of the blocking plate out of the space on the second support. 9.The paperboard warping degree detection device according to claim 5, characterized in that, in the direction perpendicular to the conveying plane of the conveying belt, the distance between the diffuse light source and the upper surface of the paperboard to be detected is greater than 10 mm, the distance between the first image capturing unit and the diffuse light source is greater than 10 mm, and the distance between the second image capturing unit and the diffuse light source is greater than 10 mm.

Images