A method for monitoring the image quality of a wood grain transfer process for thermal insulation aluminum veneer
By analyzing images during the transfer process of thermally insulated aluminum panels, the transfer defects caused by thermal deformation of the core material were resolved, achieving efficient and accurate quality monitoring and improving the transfer quality.
Patent Information
- Application Number
- CN202511317717.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-16
- Publication Date
- 2025-11-28
- Estimated Expiration
- 2045-09-16
AI Technical Summary
In existing technologies, bulging, deformation, or bubble defects caused by thermal deformation of the core material, foaming shrinkage, and gas release during the wood grain transfer process of insulated aluminum panels affect their service life, and the accuracy and efficiency of manual monitoring methods are insufficient.
Image processing technology is used to acquire images of the thermally insulated aluminum single panel before and after the transfer, perform edge detection and connected component analysis, calculate morphological coefficients and area, determine the degree of thermal deformation of the core material, and combine texture color difference blur value to monitor the transfer quality in real time and adjust process parameters.
This improves the accuracy and efficiency of wood grain transfer quality monitoring for insulated aluminum panels, reduces reliance on manual monitoring, and ensures transfer quality.
Smart Images
Figure CN120807530B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of image data processing, and in particular to an image quality monitoring method for wood grain transfer process of thermal insulation aluminum veneer. BACKGROUND
[0002] Thermal insulation aluminum veneer is a kind of building thermal insulation material, which is often used for building exterior wall. In order to improve the aesthetic appearance of the building exterior wall, people often perform wood grain transfer on the thermal insulation aluminum veneer to obtain thermal insulation aluminum veneer with both aesthetics and practicality.
[0003] The existing problem: currently, the wood grain transfer of the thermal insulation aluminum veneer is mainly performed by heat transfer method. However, due to the existence of the thermal insulation core material in the thermal insulation aluminum veneer, in the process of heat transfer of the thermal insulation aluminum veneer, the thermal deformation, foaming shrinkage and gas release may occur in the core material due to high temperature, which may cause the defects such as bulging, deformation or bubbles in the thermal insulation aluminum veneer after wood grain transfer, thereby affecting the service life of the thermal insulation aluminum veneer. Therefore, it is particularly important to monitor the transfer quality of the thermal insulation aluminum veneer during the wood grain transfer process. At present, the transfer quality of the thermal insulation aluminum veneer is mainly monitored by manual method. However, this method depends on the experience of the monitoring personnel, and the accuracy and efficiency of the monitoring cannot be guaranteed. SUMMARY
[0004] The present application provides an image quality monitoring method for wood grain transfer process of thermal insulation aluminum veneer to solve the existing problem.
[0005] The image quality monitoring method for wood grain transfer process of thermal insulation aluminum veneer provided by the present application adopts the following technical scheme:
[0006] One embodiment of the present application provides an image quality monitoring method for wood grain transfer process of thermal insulation aluminum veneer, which comprises the following steps:
[0007] obtaining a first image and a second image of the thermal insulation aluminum veneer; wherein the first image is an image in the wood grain transfer process of the thermal insulation aluminum veneer, and the second image is an image after the wood grain transfer of the thermal insulation aluminum veneer is completed;
[0008] performing edge detection on the first image to obtain the connected domain of the first image, and determining the core material thermal deformation degree of the first image by using the morphological coefficient of each connected domain and the area of each connected domain;
[0009] obtaining the detection necessary value corresponding to the continuous frame first image based on the core material thermal deformation degree corresponding to the continuous frame first image;
[0010] obtaining the texture color difference blur value of the second image corresponding to the continuous frame first image in the case that the detection necessary value corresponding to the continuous frame first image is within the preset detection necessary value threshold range;
[0011] According to the detection necessary value corresponding to the first image of the continuous frame and the texture color difference blur value of the second image corresponding to the first image of the continuous frame, a wood grain transfer quality detection value of the thermal insulation aluminum veneer is obtained;
[0012] The wood grain transfer process of the thermal insulation aluminum veneer is adjusted by using the wood grain transfer quality detection value of the thermal insulation aluminum veneer.
[0013] Further, the first image and the second image of the thermal insulation aluminum veneer are obtained by the following specific steps:
[0014] An original image set is obtained; wherein the original image set includes original images in the wood grain transfer process of the thermal insulation aluminum veneer and original images after the wood grain transfer of the thermal insulation aluminum veneer is completed;
[0015] The brightness of each original image is balanced and the color is corrected to obtain a gray image corresponding to each original image;
[0016] Each gray image is denoised to obtain a denoised image corresponding to each gray image;
[0017] Each denoised image is edge enhanced to obtain an edge enhanced image corresponding to each denoised image;
[0018] Surface distortion of each edge enhanced image is extracted to obtain a pre-processed image of each original image, the pre-processed image of the original image in the wood grain transfer process of the thermal insulation aluminum veneer is taken as the first image of the thermal insulation aluminum veneer, and the pre-processed image of the original image after the wood grain transfer of the thermal insulation aluminum veneer is completed is taken as the second image of the thermal insulation aluminum veneer.
[0019] Further, the first image is edge detected to obtain a connected domain of the first image, and the shape coefficient of each connected domain and the area of each connected domain are used to determine the core material thermal deformation degree of the first image by the following specific steps:
[0020] The first image is edge detected to obtain all connected domains of the first image;
[0021] Based on the gray value of the pixel points in each connected domain, the gray mean value of each connected domain is obtained;
[0022] The edge texture distortion degree of each connected domain is obtained by using the area of each connected domain;
[0023] The shape coefficient of each connected domain is obtained according to the gray mean value of each connected domain and the edge texture distortion degree of each connected domain;
[0024] The core material thermal deformation degree of the first image is determined based on the shape coefficient of each connected domain, the area of each connected domain and the number of connected domains.
[0025] Further, the acquiring of the edge texture distortion degree of each connected domain by using the area of each connected domain comprises the following specific steps:
[0026] The ratio of the area of the minimum circumscribed rectangle to the area of the connected domain is determined as the edge texture distortion degree of each connected domain.
[0027] Further, the acquiring of the morphological coefficient of each connected domain according to the gray mean value of each connected domain and the edge texture distortion degree of each connected domain comprises the following specific steps:
[0028] The ratio of the gray mean value of each connected domain to the edge texture distortion degree of each connected domain is determined as the morphological coefficient of each connected domain.
[0029] Further, the acquiring of the detection necessary value corresponding to the continuous frame first image based on the core material thermal deformation degree corresponding to the continuous frame first image comprises the following specific steps:
[0030] The thermal deformation degree sequence is constituted by using the core material thermal deformation degree corresponding to the continuous frame first image.
[0031] The mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence are acquired, wherein the element represents each thermal deformation degree in the thermal deformation degree sequence.
[0032] The detection necessary value corresponding to the continuous frame first image is determined based on the mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence.
[0033] Further, the acquiring of the texture color difference blur value of the second image corresponding to the continuous frame first image under the condition that the detection necessary value corresponding to the continuous frame first image is in the preset detection necessary value threshold range comprises the following specific steps:
[0034] The detection necessary value corresponding to the continuous frame first image is judged: under the condition that the detection necessary value corresponding to the continuous frame first image is in the preset first detection necessary value threshold range, the wood grain transfer process of the thermal insulation aluminum single board is pre-warned.
[0035] The wood grain transfer process of the thermal insulation aluminum single board is pre-warned under the condition that the detection necessary value corresponding to the continuous frame first image is in the preset first detection necessary value threshold range, which comprises the following specific steps:
[0036] The wood grain transfer process of the thermal insulation aluminum single board is pre-warned under the condition that the detection necessary value corresponding to the continuous frame first image is greater than or equal to the preset first detection necessary value threshold and less than or equal to the preset second detection necessary value threshold.
[0037] In a case where the detection necessary value corresponding to the first image of the continuous frame is in a preset second detection necessary value threshold range, a second image corresponding to the first image of the continuous frame is acquired;
[0038] The specific steps of acquiring the second image corresponding to the first image of the continuous frame in a case where the detection necessary value corresponding to the first image of the continuous frame is in the preset second detection necessary value threshold range include the following steps.
[0039] In a case where the detection necessary value corresponding to the first image of the continuous frame is greater than a preset second detection necessary value threshold and less than or equal to a preset third detection necessary value threshold, a second image corresponding to the first image of the continuous frame is acquired.
[0040] The second image is subjected to segmentation and clustering processing to acquire all clustering clusters in the second image.
[0041] Based on the gray value of each pixel point in each clustering cluster, a gray entropy of each clustering cluster is acquired.
[0042] The contrast of the second image is acquired, and the texture color difference blur value of the second image corresponding to the first image of the continuous frame is acquired by using the contrast of the second image, the gray entropy of each clustering cluster and the number of clustering clusters.
[0043] Further, the wood grain transfer process of the thermal insulation aluminum single board is adjusted by using the wood grain transfer quality detection value of the thermal insulation aluminum single board, and the specific steps include the following steps.
[0044] In a case where the wood grain transfer quality detection value of the thermal insulation aluminum single board is greater than or equal to a preset quality detection value threshold, the wood grain transfer of the thermal insulation aluminum single board is stopped.
[0045] In a case where the wood grain transfer quality detection value of the thermal insulation aluminum single board is less than a preset quality detection value threshold, the wood grain transfer process parameters of the thermal insulation aluminum single board are adjusted.
[0046] The technical scheme of the present application has the following advantages: the image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum single board is proposed in the embodiment of the present application, the image during the wood grain transfer process of the thermal insulation aluminum single board and the image after the wood grain transfer is analyzed to obtain the quality monitoring result of the wood grain transfer of the thermal insulation aluminum single board, and the wood grain transfer process is adjusted according to the quality monitoring result, compared with the manual quality monitoring method, the accuracy and efficiency of the wood grain transfer quality monitoring of the thermal insulation aluminum single board can be improved. BRIEF DESCRIPTION OF DRAWINGS
[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required by the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.
[0048] Figure 1 A flow chart of steps of the image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum veneer according to an embodiment of the present application. DETAILED DESCRIPTION
[0049] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the following will combine the drawings and the preferred embodiments to specifically describe the image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum veneer according to the present application, the specific implementation, structure, features and effects thereof, as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.
[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.
[0051] The following will specifically describe the specific scheme of the image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum veneer according to the present application in combination with the drawings.
[0052] Please refer to Figure 1 , which shows a flow chart of steps of the image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum veneer according to an embodiment of the present application. The method comprises the following steps:
[0053] Step S001: acquiring a first image and a second image of the thermal insulation aluminum veneer; wherein the first image is an image in the wood grain transfer process of the thermal insulation aluminum veneer, and the second image is an image after the wood grain transfer of the thermal insulation aluminum veneer is completed.
[0054] The present application provides an image quality monitoring method for the wood grain transfer process of the thermal insulation aluminum veneer. The quality monitoring result of the wood grain transfer of the thermal insulation aluminum veneer is obtained by analyzing the image in the wood grain transfer process and the image after the wood grain transfer is completed, and the wood grain transfer process is adjusted according to the quality monitoring result. Compared with the manual quality monitoring method, the present application can improve the accuracy and efficiency of the wood grain transfer quality monitoring of the thermal insulation aluminum veneer.
[0055] It should be noted that: in this embodiment, the image is first collected, and then preprocessed for subsequent image analysis.
[0056] In this embodiment, a set of original images is obtained; wherein the set of original images includes original images in the wood grain transfer process of the thermal insulation aluminum veneer and original images after the wood grain transfer of the thermal insulation aluminum veneer is completed. The brightness of each original image is balanced and color corrected to obtain a corresponding gray image of each original image. Each gray image is denoised to obtain a corresponding denoised image of each gray image. Each denoised image is edge enhanced to obtain a corresponding edge enhanced image of each denoised image. Surface distortion of each edge enhanced image is extracted to obtain a pre-processed image of each original image. The pre-processed image of the original image in the wood grain transfer process of the thermal insulation aluminum veneer is taken as a first image of the thermal insulation aluminum veneer, and the pre-processed image of the original image after the wood grain transfer of the thermal insulation aluminum veneer is completed is taken as a second image of the thermal insulation aluminum veneer.
[0057] Specifically, an industrial optical camera is installed on the production line of the wood grain transfer of the thermal insulation aluminum veneer. For example, the camera is installed above the transfer channel. Then the angle and distance of the camera are adjusted so that the camera maintains a suitable distance from the workpiece surface. When collecting images, a camera with high resolution and high frame rate is preferred. The original images in the wood grain transfer process and after the wood grain transfer are collected by the set camera.
[0058] The brightness of the original image is balanced and color corrected to eliminate the influence of light source changes.
[0059] Median filtering or Gaussian filtering is used to remove sensor noise and random interference.
[0060] The The operator highlights the wood grain boundary for subsequent detection. The operator is a known technology and will not be described in detail here.
[0061] It should be noted that under the condition of side light / oblique light, abnormal reflection or shadow will appear in the bulge area, and the pre-processing for bulge detection is realized through texture distortion analysis. When the camera is monitoring, an adjustable angle light source is provided to form a 15°-45° oblique incidence between the light and the surface of the thermal insulation aluminum veneer. The bulge or small surface fluctuation will cause local reflection enhancement or shadow to appear. This difference is manifested as high-contrast light and dark changes in the collected image, thereby strengthening the defect features and facilitating the identification of distortion and texture abnormalities in the pre-processing link.
[0062] At this point, the pre-processing of the original images in the wood grain transfer process and after the wood grain transfer is completed is completed.
[0063] Step S002: performing edge detection on the first image to obtain a connected domain of the first image, and determining the core material thermal deformation degree of the first image by using the morphological coefficient of each connected domain and the area of each connected domain.
[0064] It should be noted that there are several quality indicators to be monitored in the process and results of wood grain transfer printing of heat preservation aluminum single board, including the quality of heat preservation aluminum single board in the transfer printing process and the visual quality after the completion of wood grain transfer printing. In order to ensure the quality of wood grain transfer printing, heat transfer printing technology is usually used, however, when dealing with heat preservation aluminum single board material, the heat accumulation effect inside the heat preservation aluminum single board may cause the phenomenon of thermal deformation, foaming shrinkage or gas release of polyurethane and polystyrene, and the visual effect of bulging. When the heat preservation aluminum single board appears bulging, due to the uneven heating of the bulging area and other areas, the heat preservation aluminum single board after wood grain transfer printing has color difference and blur defects. Therefore, the embodiment analyzes the multi-light perspective of multiple images to obtain possible bulging effect and provide early warning information; further, combined with the actual transfer image content, the specific transfer quality result is obtained, which plays the purpose of quality monitoring.
[0065] By analyzing multiple images, the thermal deformation degree of the corresponding internal material of the heat preservation aluminum single board is obtained, and then the necessity of subsequent texture quality detection is determined. First, the bulging rate corresponding to the multiple images is analyzed, and then the core material thermal deformation degree is determined according to the bulging rate. The more obvious the bulging is, the higher the core material expansion degree is, and the more it affects the subsequent wood grain transfer printing texture quality.
[0066] In the embodiment, edge detection is performed on the first image to obtain all connected domains of the first image. Based on the gray value of the pixel points in each connected domain, the gray mean value of each connected domain is obtained. The edge texture distortion degree of each connected domain is obtained by using the area of each connected domain. According to the gray mean value of each connected domain and the edge texture distortion degree of each connected domain, the morphological coefficient of each connected domain is obtained. Based on the morphological coefficient of each connected domain, the area of each connected domain and the number of connected domains, the core material thermal deformation degree of the first image is determined.
[0067] In the embodiment, the minimum circumscribed rectangle of each connected domain is obtained, and the ratio of the area of the minimum circumscribed rectangle to the area of the connected domain is determined as the edge texture distortion degree of each connected domain. The ratio of the gray mean value of each connected domain to the edge texture distortion degree of each connected domain is determined as the morphological coefficient of each connected domain.
[0068] Specifically, a plurality of first images are obtained, and edge detection is performed on the first images to obtain connected domains composed of a plurality of edges and the size of the connected domains. The edge detection of the operator obtains the connected domains composed of a plurality of edges and the size of the connected domains.
[0069] It should be noted that the morphological characteristics of the bulging are convex or corrugated distortion, which will produce local bright spots under illumination, and the image acquisition will show the texture distortion of the deformation area.
[0070] First, the edge texture distortion degree of each connected domain is calculated , Indicates the first The first frame of the image The edge texture distortion of a connected component represents the ratio between the area of the minimum bounding rectangle of each connected component and the area of the connected component. The higher the ratio, the more regular the shape of the connected component and the lower the degree of edge texture distortion.
[0071] Then calculate the mean gray value of each connected component. , Indicates the first The first frame of the image The average gray value of each connected component The higher the value, the more obvious the bulge shape, meaning the higher the degree of thermal deformation of the core material.
[0072] Finally, the morphological coefficients of each connected component are calculated:
[0073]
[0074] in, Indicates the first The first frame of the image The morphological coefficients of each connected region are used to analyze the degree of thermal deformation of the core material. A higher mean grayscale value in these morphological coefficients indicates a higher degree of bright spots on the bulge, and consequently, a higher degree of thermal deformation of the core material inside the aluminum insulated panel due to heat accumulation.
[0075] Meanwhile, the smaller the ratio of the minimum bounding rectangle of each connected component to the connected component itself, the more irregular the distribution of the edges of the connected components, and the higher the probability of bulging.
[0076] Determine the degree of thermal deformation of the core material:
[0077]
[0078] in, Indicates the first The degree of thermal deformation of the core material corresponding to the frame image; Indicates the first Total number of connected components within a frame image; As a summation coefficient; Indicates the first The first frame of the image The area of each connected region.
[0079] By analyzing each connected component within each frame of the image, a comprehensive evaluation is obtained. Specifically, this evaluation is based on the sum of the areas of the connected components within the frame. The higher the value, the more pronounced the number and size of the bumps caused by thermal effects within the frame.
[0080] At the same time, the normalized connected component morphology coefficients As the sum coefficient, the coefficient is known through the above description, also reflects the real-time connected domain morphological characteristics, and then the corresponding core material thermal deformation degree can be judged.
[0081] When the bulging effect reflected by the sum coefficient is more obvious, the coefficient value in the sum is higher, closer to 1, and the sum result is higher, and the final core material thermal deformation degree is higher.
[0082] Similarly, for the number of connected domains , as the coefficient of the sum result, the purpose of determining the total amount of bulging in the image is achieved by analyzing the total number of connected domains. The more the number of connected domains, the more the total number of bulges, and the higher the deformation degree of the core material caused by heat.
[0083] Step S003: Based on the core material thermal deformation degree corresponding to the continuous frame first image, the detection necessary value corresponding to the continuous frame first image is obtained.
[0084] In this embodiment, the core material thermal deformation degree corresponding to the continuous frame first image is used to form a thermal deformation degree sequence; the mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence are obtained; wherein, the element represents each thermal deformation degree in the thermal deformation degree sequence; based on the mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence, the detection necessary value corresponding to the continuous frame first image is determined.
[0085] It should be noted that: further, after determining the core material thermal deformation degree of a single frame image, in order to analyze whether the deformation degree has the necessity of early warning or the necessity of subsequent wood grain transfer quality detection, it is necessary to continuously monitor and determine the heat accumulation growth reflected by the deformation degree. The higher the heat accumulation growth, the higher the degree of heat affected by the heat preservation aluminum single board at this time.
[0086] Specifically, the continuous multiple frames of side / slant images photographed by the industrial camera are obtained, the corresponding core material thermal deformation degree is obtained, and a thermal deformation degree sequence is formed:
[0087]
[0088] The physical meaning of this sequence is that by showing the core material thermal deformation degree at different times, the change rule is obtained, and then the heat duration and the expansion duration of the internal material of the heat preservation aluminum single board can be analyzed.
[0089] If the sequence presents a trend of only increasing but not decreasing in a period of time, it can be explained that the heat accumulation effect in the heat preservation aluminum single board continues to increase, and the necessity of early warning and subsequent transfer texture quality detection is also higher.
[0090] Analyze the detection necessary value:
[0091]
[0092] wherein, indicates that the heat insulation aluminum veneer is analyzed in the time interval [0, ] after analysis, the corresponding analysis and detection necessary value. indicates the average value of the core material thermal deformation degree in the time interval; indicates the total amount of time participating in the calculation.
[0093] It should be noted that each time corresponds to a frame of the first image, so according to the core material thermal deformation degree of the continuous frame of the first image, the detection necessary value corresponding to the continuous frame of the first image can be obtained.
[0094] indicates that the core material thermal deformation degree corresponding to the time frame before and after is calculated by difference, and then summed to obtain the thermal deformation degree growth. If it continues to grow, the difference result is always greater than 0, and the summation result is also greater; on the contrary, the difference result is always less than 0, and the summation result is also smaller.
[0095] The former calculates the average of the core material thermal deformation degree in the interval, which aims to quantify the specific size of the deformation degree. The higher the average value, the higher the corresponding core material thermal deformation degree, and the higher the necessity of its early warning and subsequent quality detection.
[0096] Step S004: In the case that the detection necessary value corresponding to the continuous frame of the first image is in the preset detection necessary value threshold range, the texture color difference blur value of the second image corresponding to the continuous frame of the first image is obtained.
[0097] In this embodiment, the detection necessary value corresponding to the continuous frame of the first image is judged: in the case that the detection necessary value corresponding to the continuous frame of the first image is in the preset first detection necessary value threshold range, the wood grain transfer process of the heat insulation aluminum veneer is warned; in the case that the detection necessary value corresponding to the continuous frame of the first image is in the preset second detection necessary value threshold range, the second image corresponding to the continuous frame of the first image is obtained; the second image is segmented and clustered to obtain all the clustering clusters in the second image; based on the gray value of the pixel points in each clustering cluster, the gray entropy of each clustering cluster is obtained; the contrast of the second image is obtained, and the texture color difference blur value of the second image corresponding to the continuous frame of the first image is obtained by using the contrast of the second image, the gray entropy of each clustering cluster and the number of clustering clusters.
[0098] It should be noted that the preset first detection necessary value threshold range and the preset second detection necessary value threshold range are set according to specific circumstances, which are not limited here.
[0099] In the embodiment, when the detection necessary value corresponding to the first image of the continuous frames is greater than or equal to a preset first detection necessary value threshold and less than or equal to a preset second detection necessary value threshold, a wood grain transfer process of the thermal insulation aluminum veneer is warned. When the detection necessary value corresponding to the first image of the continuous frames is greater than the preset second detection necessary value threshold and less than or equal to a preset third detection necessary value threshold, a second image corresponding to the first image of the continuous frames is acquired.
[0100] It should be noted that the preset first detection necessary value threshold, the preset second detection necessary value threshold and the preset third detection necessary value threshold are set according to specific conditions, which are not limited here.
[0101] Specifically, when the detection necessary value is in the range [0.4, 0.6], it is considered that there may be a certain degree of slight bulging, but it does not affect the wood grain transfer quality, and a warning process is performed at this time; further, when the detection necessary value is in the range (0.6, 1], it is considered that the bulging effect caused by the internal heat accumulation effect of the thermal insulation aluminum veneer will affect the transfer texture quality.
[0102] Further, the thermal insulation aluminum veneer and its transfer image that need to be detected are obtained, that is, the second image is analyzed.
[0103] It should be noted that when the bulging area is unevenly heated, it will cause local transfer temperature to be insufficient or too high, and its corresponding visual performance feature is that the wood grain texture color exists abnormal distribution relative to the surrounding area, which is manifested as being too deep (temperature is too high) or too shallow (temperature is too low), and the feature is color difference of the transfer result. Moreover, the texture boundary is blurred, and "blurred texture" appears. Therefore, when the wood grain transfer image exists the detection necessity, the visual feature of the above color difference blur exists, which can indicate that the wood grain transfer quality reflected by the image quality monitoring result is low at this time.
[0104] The texture color difference blur of the first image corresponding to the wood grain transfer completion frame image is determined. The wood grain transfer color difference is visually manifested as a certain area clustering cluster gray difference in the image. Therefore, first, the image is segmented and clustered by a superpixel segmentation algorithm to obtain a plurality of clustering clusters, and the gray entropy in the clustering cluster is acquired. .
[0105] It should be noted that the superpixel segmentation algorithm and the calculation of the gray entropy in the clustering cluster are known technologies, which are not specifically introduced here. The gray entropy in the clustering cluster indicates the gray dispersion degree in a clustering cluster. The more dispersed, the more color distribution jumps, and the more likely the transfer color difference and blur effect appear.
[0106] Then, the first image corresponding to the wood grain transfer completion frame image is acquired. The contrast within the second image frame; the higher this value, the more obvious the color difference after the wood grain transfer.
[0107] Therefore, we can obtain the following at this point:
[0108]
[0109] in, Indicates the first Texture chromatic aberration blur value of the second image frame; Indicates the first The contrast of the second image in frame 2; Indicates the first The total number of clusters in the second frame of the image; Indicates the first The second image below frame The grayscale entropy of each cluster. Within a frame, the higher the contrast and the greater the color range, the more monotonous the wood grain transfer result of the insulated aluminum panel. Conversely, a large color range indicates color difference problems caused by uneven transfer temperature. Furthermore, the higher the grayscale entropy within each cluster, the greater the corresponding ambiguity and color difference.
[0110] It should be noted that when the required detection value corresponding to the first image in a series of frames is large, the second image corresponding to the first image in that series of frames is obtained. This second image corresponds to the first image in the series of frames. The first image is the image during the wood grain transfer process, and the second image is the image corresponding to that image after the transfer is complete.
[0111] Step S005: Obtain the wood grain transfer quality detection value of the thermal insulation aluminum panel based on the detection necessary value corresponding to the first image of the consecutive frames and the texture color difference blur value of the second image corresponding to the first image of the consecutive frames.
[0112] By combining the necessary test values, the wood grain transfer quality test values are obtained:
[0113]
[0114] in, This indicates the wood grain transfer quality test value. The higher the value, the worse the wood grain transfer effect, and the more necessary it is to issue an alarm for core material abnormalities.
[0115] Step S006: Adjust the wood grain transfer process of the insulated aluminum panel using the quality inspection value of the wood grain transfer.
[0116] In the case that the wood grain transfer quality detection value of the heat preservation aluminum veneer in the embodiment is greater than or equal to the preset quality detection value threshold, the wood grain transfer of the heat preservation aluminum veneer is stopped; in the case that the wood grain transfer quality detection value of the heat preservation aluminum veneer is less than the preset quality detection value threshold, the wood grain transfer process parameters of the heat preservation aluminum veneer are adjusted.
[0117] It should be noted that the preset quality detection value threshold is set according to specific circumstances, which is not limited here.
[0118] Specifically, when the quality detection value is greater than or equal to 60%, the bump effect causes high wood grain texture color difference ambiguity, the alarm level is high, and the wood grain transfer is stopped; when the quality detection value is less than 60%, the alarm level is low, the wood grain transfer is suspended, and the process parameters are adjusted to reduce the wood grain transfer defects caused by heat accumulation effect.
[0119] Thus far, the present application is completed.
[0120] In summary, in the embodiment of the present application, an image quality monitoring method for wood grain transfer process of heat preservation aluminum veneer is proposed, which analyzes the images in the wood grain transfer process of heat preservation aluminum veneer and the images after wood grain transfer is completed, obtains the quality monitoring result of wood grain transfer of heat preservation aluminum veneer, and adjusts the wood grain transfer process according to the quality monitoring result. Compared with the manual quality monitoring method, the embodiment of the present application can improve the accuracy and efficiency of wood grain transfer quality monitoring of heat preservation aluminum veneer.
[0121] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.
Claims
1. A method for monitoring the image quality of a wood grain transfer process for heat- treated aluminum veneer, characterized by, The method comprises the following steps: Obtaining a first image and a second image of the heat preservation aluminum veneer; wherein the first image is an image in the wood grain transfer process of the heat preservation aluminum veneer, and the second image is an image after the wood grain transfer of the heat preservation aluminum veneer is completed; Edge detection is performed on the first image to obtain a connected domain of the first image, and the degree of core material thermal deformation of the first image is determined by using a morphological coefficient of each connected domain and an area of each connected domain; Based on the degree of core material thermal deformation corresponding to the continuous frame first image, a detection necessary value corresponding to the continuous frame first image is obtained; In the case that the detection necessary value corresponding to the continuous frame first image is in a preset detection necessary value threshold range, a texture color difference blur value of the second image corresponding to the continuous frame first image is obtained; According to the detection necessary value corresponding to the continuous frame first image and the texture color difference blur value of the second image corresponding to the continuous frame first image, a wood grain transfer quality detection value of the heat preservation aluminum veneer is obtained; The wood grain transfer process of the heat preservation aluminum veneer is adjusted by using the wood grain transfer quality detection value of the heat preservation aluminum veneer.
2. The method of claim 1, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of obtaining the first image and the second image of the heat preservation aluminum veneer include the following: Obtaining an original image set; wherein the original image set includes original images in the wood grain transfer process of the heat preservation aluminum veneer, and original images after the wood grain transfer of the heat preservation aluminum veneer is completed; Brightness equalization and color correction are performed on each original image to obtain a gray image corresponding to each original image; Noise removal processing is performed on each gray image to obtain a denoising image corresponding to each gray image; Edge enhancement is performed on each denoising image to obtain an edge enhanced image corresponding to each denoising image; Surface distortion extraction is performed on each edge enhanced image to obtain a preprocessed image of each original image, and the preprocessed image of the original image in the wood grain transfer process of the heat preservation aluminum veneer is taken as the first image of the heat preservation aluminum veneer, and the preprocessed image of the original image after the wood grain transfer of the heat preservation aluminum veneer is completed is taken as the second image of the heat preservation aluminum veneer.
3. The method of claim 2, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of performing edge detection on the first image to obtain the connected domain of the first image, and determining the degree of core material thermal deformation of the first image by using the morphological coefficient of each connected domain and the area of each connected domain include the following: Edge detection is performed on the first image to obtain all connected domains of the first image; Based on the gray value of the pixel points in each connected domain, the gray mean value of each connected domain is obtained; By using the area of each connected domain, the edge texture distortion degree of each connected domain is obtained; According to the gray mean value of each connected domain and the edge texture distortion degree of each connected domain, the morphological coefficient of each connected domain is obtained; Based on the morphological coefficient of each connected domain, the area of each connected domain and the number of connected domains, the degree of core material thermal deformation of the first image is determined.
4. The method of claim 3, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of obtaining the edge texture distortion degree of each connected domain by using the area of each connected domain include the following: The minimum circumscribed rectangle of each connected domain is obtained, and the ratio of the area of the minimum circumscribed rectangle to the area of the connected domain is determined as the edge texture distortion degree of each connected domain.
5. The method of claim 3, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of obtaining the morphological coefficient of each connected domain according to the gray mean value of each connected domain and the edge texture distortion degree of each connected domain include the following: The ratio of the gray mean value of each connected domain to the edge texture distortion degree of each connected domain is determined as the morphological coefficient of each connected domain.
6. The method of claim 5, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of obtaining the detection necessary value corresponding to the continuous frame first image based on the core material thermal deformation degree corresponding to the continuous frame first image include the following: A thermal deformation degree sequence is constructed by using the core material thermal deformation degree corresponding to the continuous frame first image; The mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence are obtained; wherein, the element represents each thermal deformation degree in the thermal deformation degree sequence; Based on the mean value of all elements, the number of elements and the difference value of adjacent elements in the thermal deformation degree sequence, the detection necessary value corresponding to the continuous frame first image is determined.
7. The method of claim 6, wherein the image quality monitoring method of the wood grain transfer process of the heat-protective aluminum veneer is characterized by, The specific steps of obtaining the texture color difference blur value of the second image corresponding to the continuous frame first image in the case that the detection necessary value corresponding to the continuous frame first image is in the preset detection necessary value threshold range include the following: The detection necessary value corresponding to the continuous frame first image is judged: in the case that the detection necessary value corresponding to the continuous frame first image is in the preset first detection necessary value threshold range, the wood grain transfer process of the thermal insulation aluminum single board is prewarned; The specific steps of prewarning the wood grain transfer process of the thermal insulation aluminum single board in the case that the detection necessary value corresponding to the continuous frame first image is in the preset first detection necessary value threshold range include the following: In the case that the detection necessary value corresponding to the continuous frame first image is greater than or equal to the preset first detection necessary value threshold and less than or equal to the preset second detection necessary value threshold, the wood grain transfer process of the thermal insulation aluminum single board is prewarned; In the case that the detection necessary value corresponding to the continuous frame first image is in the preset second detection necessary value threshold range, the second image corresponding to the continuous frame first image is obtained; The specific steps of obtaining the second image corresponding to the continuous frame first image in the case that the detection necessary value corresponding to the continuous frame first image is in the preset second detection necessary value threshold range include the following: In the case that the detection necessary value corresponding to the continuous frame first image is greater than the preset second detection necessary value threshold and less than or equal to the preset third detection necessary value threshold, the second image corresponding to the continuous frame first image is obtained; The second image is segmented and clustered to obtain all cluster clusters in the second image; Based on the gray value of the pixel points in each cluster cluster, the gray entropy of each cluster cluster is obtained; The contrast of the second image is obtained, and the texture color difference blur value of the second image corresponding to the continuous frame first image is obtained by using the contrast of the second image, the gray entropy of each cluster cluster and the number of cluster clusters.
8. The image quality monitoring method for the wood grain transfer process of thermal insulation aluminum veneer according to claim 1, characterized in that, The specific steps of adjusting the wood grain transfer process of the thermal insulation aluminum single board by using the wood grain transfer quality detection value of the thermal insulation aluminum single board include the following: In the case that the wood grain transfer quality detection value of the thermal insulation aluminum single board is greater than or equal to the preset quality detection value threshold, the wood grain transfer of the thermal insulation aluminum single board is stopped. In the case that the wood grain transfer quality detection value of the heat preservation aluminum veneer is less than the preset quality detection value threshold, the wood grain transfer process parameter of the heat preservation aluminum veneer is adjusted.
Citation Information
Patent Citations
Product defect detection method, device and equipment and readable storage medium
CN114937037A
Packaging printed matter printing quality detection method
CN115272343A