Intelligent heat press transfer method, device, equipment and storage medium

Abstract

The application discloses an intelligent pressing and transferring method, device and equipment and a storage medium, and relates to the technical field of pressing and transferring. The method comprises the following steps: an image acquisition device is arranged above a transferring material feeding station of a pressing and transferring equipment, and after the image acquisition device acquires a transferring pattern on the surface of the transferring material to obtain an acquired image, the acquired image is analyzed and an image processing decision is output; when the image processing decision is to execute pressing and transferring, the pressing and transferring equipment is controlled to perform pressing and transferring processing, so that the transferring pattern is transferred to a printing substrate. Through the arrangement of the image acquisition device and the analysis and decision of the acquired image in the image acquisition device, whether the pressing and transferring equipment executes the pressing and transferring operation is controlled, so that efficient, automatic and intelligent image transferring is realized. The analysis of the acquired image in the image acquisition device also helps to reduce data transmission delay, improve detection efficiency, enable the pressing and transferring equipment to quickly respond to the detection result, and improve production efficiency and the yield of finished products.

Description

Technical Field

[0001] This invention relates to the field of heat transfer technology, and in particular to an intelligent heat transfer method, apparatus, equipment and storage medium. Background Technology

[0002] Heat transfer printing is a garment printing technique that uses heat transfer methods such as pressing to transfer patterns onto clothing. It is suitable for customized applications such as T-shirts, promotional shirts, advertising shirts, jackets, jeans, children's wear, plush toys, and sportswear. The quality of the transferred pattern directly affects the appearance and market competitiveness of the finished garment. Currently, the quality inspection of transferred patterns mainly relies on manual visual inspection. Workers need to check the transferred pattern on the transfer material (such as transfer paper) before the pressing process to ensure its integrity, color accuracy, and consistency with the design. However, manual inspection has many drawbacks, especially in mass production scenarios. Prolonged visual inspection can easily lead to eye fatigue, resulting in missed or incorrect inspections, thus affecting product quality. Furthermore, manual inspection has limited efficiency and cannot meet the demands of the modern garment industry for efficient and accurate inspection, easily causing unnecessary material waste and increased rework costs. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide an intelligent heat transfer method, apparatus, equipment, and storage medium to solve the problem of low efficiency and poor accuracy in inspecting the transfer pattern before the heat transfer process in the prior art.

[0004] In a first aspect, embodiments of the present invention provide an intelligent heat transfer method applied to a heat press device. An image acquisition device is installed above the material loading station of the heat press device. The material loading station is used to place transfer material with a transfer pattern. The method includes:

[0005] Perform parameter calibration on the image acquisition device;

[0006] The image acquisition device is controlled to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image;

[0007] The image acquisition device analyzes the acquired image and outputs an image processing decision, wherein the image processing decision includes performing heat pressing or not performing heat pressing;

[0008] When the image processing decision is to perform heat pressing, the heat pressing equipment is controlled to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate.

[0009] Preferably, the method further includes, before calibrating the parameters of the image acquisition device:

[0010] Multiple standard transfer patterns are imported into the storage unit of the image acquisition device to establish a standard image database;

[0011] Based on the standard image database, a deep learning algorithm is run in the computing unit of the image acquisition device to perform feature extraction and analysis training on the standard images;

[0012] The trained deep learning model is integrated into the image acquisition device to directly perform image comparison and analysis processing after image acquisition.

[0013] Preferably, the parameter calibration of the image acquisition device includes:

[0014] Obtain initial parameters of the image acquisition device, the initial parameters including one or more of focal length, exposure time, white balance, and color gain;

[0015] Under preset lighting conditions, test images are acquired, and one or more of the image's sharpness, color reproduction, and contrast are analyzed to determine whether they meet the preset acquisition accuracy requirements.

[0016] Otherwise, adjust the parameters of the image acquisition device until it meets the preset acquisition accuracy requirements.

[0017] Preferably, the step of analyzing the acquired image and outputting an image processing decision within the image acquisition device includes:

[0018] After feature extraction and pattern recognition of the acquired image by the deep learning model in the image acquisition device, completeness analysis, color deviation analysis and missing color analysis are performed based on the corresponding standard image, and the corresponding first analysis result, second analysis result and third analysis result are output respectively.

[0019] When the first analysis result, the second analysis result, and the third analysis result all indicate that heat pressing should be performed, the output image processing decision is to perform heat pressing.

[0020] If any one of the first analysis result, the second analysis result, or the third analysis result indicates that pressing is not performed, then the output image processing decision is to not perform pressing.

[0021] Preferably, the integrity analysis includes:

[0022] The contour features of the acquired image are obtained and compared with the contour features of the corresponding standard image to calculate the proportion of the missing pattern area.

[0023] When the proportion of the missing area is less than or equal to a preset proportion threshold, the transfer pattern is considered complete, and the first analysis result of heat pressing is output.

[0024] When the proportion of the missing area is greater than the preset proportion threshold, the transfer pattern is considered incomplete, and the first analysis result of not performing heat pressing is output.

[0025] Preferably, the color deviation analysis includes:

[0026] Based on the color distribution histogram of the standard image and the color distribution histogram of the acquired image, the color difference value ΔE of each color channel is calculated;

[0027] When the color difference value ΔE is less than or equal to the preset color difference threshold, it is considered that the transfer pattern has no color deviation, and the second analysis result of heat pressing is output.

[0028] When the color difference value ΔE is greater than the preset color difference threshold, it is considered that the transfer pattern has a color deviation, and the second analysis result of not performing heat pressing is output.

[0029] Preferably, the color deficiency analysis includes:

[0030] The acquired image is subjected to color channel separation, and the deviation between the mean of each color channel and the mean of the corresponding color channel of the standard image is calculated and denoted as the first deviation value.

[0031] When the first deviation value of all color channels is less than or equal to the preset deviation threshold, it is considered that there is no color missing phenomenon in the transfer pattern, and the third analysis result of heat pressing is output.

[0032] When the first deviation value of any color channel exceeds the preset deviation threshold, it is considered that the transfer pattern has a color deficiency phenomenon, and the third analysis result of not performing heat pressing is output.

[0033] Secondly, embodiments of the present invention provide an intelligent heat transfer device applied to heat pressing equipment. An image acquisition device is provided above the transfer material feeding station of the heat pressing equipment. The transfer material feeding station is used to place transfer material with a transfer pattern. The device includes:

[0034] A calibration module is used to calibrate the parameters of the image acquisition device;

[0035] The acquisition module is used to control the image acquisition device to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image;

[0036] An analysis module is used to analyze the acquired image within the image acquisition device and output an image processing decision, wherein the image processing decision includes performing heat pressing or not performing heat pressing;

[0037] The heat pressing module is used to control the heat pressing equipment to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate when the image processing decision is to perform heat pressing.

[0038] Thirdly, embodiments of the present invention provide a heat pressing device, comprising:

[0039] The substrate transport mechanism is used to transport the substrate to the heat pressing station;

[0040] A transfer conveyor is used to transfer transfer material.

[0041] A heat pressing mechanism is used to heat and transfer the transfer pattern from the surface of the transfer material to the substrate.

[0042] Image acquisition device, used to acquire transfer patterns;

[0043] The main control module includes at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method as described in any one of the first aspects.

[0044] Fourthly, embodiments of the present invention provide a storage medium storing computer program instructions, which, when executed by a processor, implement the method of the first aspect described above.

[0045] In summary, the beneficial effects of the present invention are as follows:

[0046] The intelligent heat transfer method, apparatus, equipment, and storage medium provided in this invention include setting up an image acquisition device above the loading station of the heat transfer equipment, controlling the image acquisition device to acquire the transfer pattern on the surface of the transfer material, obtaining the acquired image, analyzing the acquired image, and outputting an image processing decision; when the image processing decision is to perform heat transfer, controlling the heat transfer equipment to perform heat transfer processing to transfer the transfer pattern onto the substrate. This invention achieves efficient, automated, and intelligent image quality detection by setting up an image acquisition device and analyzing and making decisions within it, thereby controlling whether the heat transfer equipment performs the heat transfer operation. Directly analyzing the acquired image in the image acquisition device also helps reduce data transmission delay, improve detection efficiency, enable the heat transfer equipment to quickly respond to detection results, optimize the heat transfer process, reduce unnecessary processing, and improve production efficiency and yield. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, and these are all within the protection scope of the present invention.

[0048] Figure 1 This is a schematic diagram of the heat pressing device according to an embodiment of the present invention.

[0049] Figure 2 This is a flowchart illustrating the intelligent heat transfer method according to an embodiment of the present invention.

[0050] Figure 3 This is a schematic diagram illustrating the process of integrating a deep learning model into an image acquisition device in an embodiment of the present invention.

[0051] Figure 4 This is a schematic diagram of the process of analyzing the acquired images and outputting image processing decisions in an embodiment of the present invention.

[0052] Figure 5 This is a schematic diagram of the intelligent heat transfer device according to an embodiment of the present invention.

[0053] Figure 6 This is a schematic diagram of the main control module of the heat pressing device according to an embodiment of the present invention. Detailed Implementation

[0054] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the invention.

[0055] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0056] Example 1

[0057] This invention provides an intelligent hot stamping transfer method, applied in hot stamping equipment. In one example, such as... Figure 1 As shown, the heat transfer equipment includes a substrate transport mechanism 1 for transporting substrates (such as T-shirts, jackets, jeans, etc.) to the heat transfer station; a transfer conveying device 2, including a feeding mechanism 21 and a receiving mechanism 22, which are located on opposite sides of the heat transfer station; a heat transfer mechanism 3, including a lifting device 31 and a heat transfer head 32, which is located above the heat transfer station, and the lifting device 31 is connected to the heat transfer head 32; preferably, it also includes a film-tearing mechanism, including a translation device and a film-tearing component, which are connected to the film-tearing component and used to remove the transferred material from the substrate. To facilitate the implementation of the heat transfer process, the heat transfer equipment in this embodiment is equipped with multiple stations, such as a substrate loading station (for loading substrates such as clothing), a transfer material loading station (for loading transfer material), and a heat transfer station. In this embodiment, the substrate transport mechanism 1 transports the substrate to the heat pressing station, while the transfer conveying device 2 transports the transfer material to the heat pressing station. To achieve intelligent and automated pattern quality inspection, the heat pressing equipment in this embodiment also includes an image acquisition device 5, which is installed at the transfer material loading station of the heat pressing equipment. The image acquisition device 5 acquires the transfer pattern on the surface of the transfer material, inspects the acquired image, and determines whether the transfer pattern meets the requirements.

[0058] Please see Figure 2 The method specifically includes the following steps:

[0059] S1: Perform parameter calibration on the image acquisition device;

[0060] S2: Control the image acquisition device to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image;

[0061] S3: Analyze the acquired image within the image acquisition device and output an image processing decision, wherein the image processing decision includes performing heat pressing or not performing heat pressing;

[0062] S4: When the image processing decision is to perform heat pressing, control the heat pressing equipment to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate.

[0063] Specifically, this invention utilizes an image acquisition device (such as an industrial camera) to capture the transfer pattern on the surface of the transfer material and analyzes the captured images to determine whether a heat pressing process should be performed. First, before performing the inspection, the image acquisition device needs to be calibrated to ensure the stability and accuracy of image acquisition. This image acquisition device can be a CCD camera, a CMOS camera, or a depth camera, etc., and its acquisition range can completely cover the transfer material at the material loading station. In one example, parameter calibration includes adjusting parameters such as focal length, exposure time, white balance, and color gain, and acquiring test images under preset lighting conditions. Sharpness, color reproduction, and contrast are adjusted to meet preset acquisition accuracy requirements, ensuring that the camera can accurately capture the details of the transfer pattern. After parameter calibration, the image acquisition device captures images of the transfer pattern on the transfer material at the feeding station, and performs image analysis directly on these images to determine if the transfer pattern meets preset quality standards. Based on the analysis results, an image processing decision is output: if the results meet the requirements, a "perform heat pressing" command is generated and sent to the main control module of the heat pressing equipment. The main control module then controls the corresponding mechanism to transfer the transfer material from the feeding station to the heat pressing station for heat pressing, transferring the pattern to the substrate (such as the surface of clothing). If the results do not meet the requirements, a "do not perform heat pressing" command is generated to prevent defective products from entering subsequent processes and reduce material waste. This method automatically screens for unqualified transfer patterns before transfer, effectively reducing the workload of manual inspection and the risk of misjudgment, improving the level of intelligence, and ensuring stable transfer quality.

[0064] Please see Figure 3 In one embodiment, the method further includes, before calibrating the parameters of the image acquisition device:

[0065] S31: Import multiple standard transfer patterns into the storage unit of the image acquisition device to establish a standard image database;

[0066] S32: Based on the standard image database, a deep learning algorithm is run in the computing unit of the image acquisition device to perform feature extraction and analysis training on the standard image;

[0067] S33: Integrate the trained deep learning model into the image acquisition device to directly perform image comparison analysis processing after image acquisition.

[0068] Specifically, to ensure accurate analysis and detection of acquired images within the image acquisition device, a standard image database is established and a deep learning algorithm is used for model training before formal image acquisition and detection. Specifically, multiple standard transfer patterns are imported into the storage unit of the image acquisition device. These standard images can be high-quality transfer patterns that have been manually selected and verified, or pattern data files from the production process design stage. This database provides the foundational data for subsequent deep learning model training, enabling the model to learn and compare based on the standard images, thus improving detection accuracy. After the standard image database is established, the computing unit of the image acquisition device begins running deep learning algorithms to extract features and analyze and train these standard images. The main goal of deep learning is to automatically identify key features of the transfer patterns, such as contour completeness, color distribution, and detailed texture. During training, key features of the standard images are extracted, and neural networks are used for pattern recognition learning to form a deep learning model suitable for transfer detection. For example, in color feature training, the RGB color distribution of the standard images can be analyzed, and a baseline color model can be established so that color deviations and missing colors can be detected during subsequent comparisons. Once the deep learning model is trained, it is integrated into the image acquisition device, enabling it to directly perform image comparison and analysis after image acquisition. In other words, the image acquisition device is not merely for simply capturing images; it also possesses intelligent analysis capabilities, performing image feature matching locally without relying on external servers for computation, thereby improving detection efficiency and reducing data transmission latency. Furthermore, by continuously updating the standard image database and optimizing the deep learning model, it can adapt to different transfer materials and production batches, exhibiting strong versatility and adaptability, thus further enhancing the level of intelligence in the garment heat transfer printing industry.

[0069] Please see Figure 4 In one embodiment, the step of analyzing the acquired image and outputting an image processing decision within the image acquisition device includes:

[0070] S41: After extracting features and recognizing patterns from the acquired images using the deep learning model in the image acquisition device, completeness analysis, color deviation analysis, and color missing analysis are performed based on the corresponding standard images, and the corresponding first analysis result, second analysis result, and third analysis result are output respectively.

[0071] S42: When the first analysis result, the second analysis result, and the third analysis result are all to perform heat pressing, the output image processing decision is to perform heat pressing.

[0072] S43: When any one of the first analysis result, the second analysis result, or the third analysis result is "do not perform heat pressing", the output image processing decision is "do not perform heat pressing".

[0073] Specifically, the process begins by acquiring an image of the transfer material to be tested using an image acquisition device, and then performing feature extraction and pattern recognition using its internal deep learning model. This deep learning model has been pre-trained on a standard image database and is capable of accurately identifying various features of the pattern. Preferably, the acquired image is then compared and analyzed with a standard image to assess its integrity, color deviation, and color defects, thereby outputting analysis results: a first analysis result (integrity analysis), a second analysis result (color deviation analysis), and a third analysis result (color defect analysis). Integrity analysis primarily detects whether there are any defects in the transfer pattern; color deviation analysis detects whether the color of the transfer pattern is consistent with the standard image, ensuring that the color quality of the finished product is not distorted; and color defect analysis checks whether specific colors in the pattern are missing. After all analysis results are generated, a final image processing decision is made based on these results. If the first, second, and third analysis results all meet the requirements—that is, the detected pattern is complete, the color deviation is within an acceptable range, and there are no color defects—then the image processing decision to "perform heat pressing" is output, meaning that the transfer material meets the quality standards and can proceed to the heat pressing process to complete the transfer operation. However, if any of the above analysis results fail to meet the standards, such as pattern defects, excessive color deviation, or missing colors, a "Do not perform heat pressing" decision will be output, meaning that the transfer material has quality problems and should not proceed to the subsequent heat pressing process. In this case, an alarm can be triggered or the operator can be prompted to perform manual verification, controlling the receiving mechanism to recycle the unqualified transfer material.

[0074] In one embodiment, the completeness analysis includes:

[0075] The contour features of the acquired image are obtained and compared with the contour features of the corresponding standard image to calculate the proportion of the missing pattern area.

[0076] When the proportion of the missing area is less than or equal to the preset proportion threshold, the transfer pattern on the transfer material is considered complete, and the first analysis result of heat pressing is output.

[0077] When the proportion of the missing area is greater than the preset proportion threshold, the transfer pattern on the transfer material is considered incomplete, and the first analysis result of not performing heat pressing is output.

[0078] Specifically, the integrity analysis first acquires the outer contour features of the acquired image, i.e., the boundary shape of the entire transfer pattern, and matches it with the outer contour of the standard image. If the contour shape deviation between the two is large or there are obvious missing areas, it indicates that the transfer pattern may be incomplete due to cutting deviation, printing problems, or other factors. Then, the contour overlap between the acquired image and the standard image can be calculated, and the proportion of the missing area can be further calculated. When the proportion of the missing area exceeds a preset proportion threshold, the transfer pattern is determined to be incomplete, and the first analysis result of "do not perform heat pressing" is output. If the proportion of the missing area is within the threshold range, the pattern is determined to be complete overall, and the next step of analysis is performed. Based on the outer contour detection, the internal contour feature analysis is further performed. The internal contour refers to the contour of key elements in the transfer pattern, such as color blocks, lines, and pattern details. This analysis step identifies the shape, position, and integrity of the internal pattern by performing edge detection and feature extraction on the acquired image, and compares it with the corresponding part of the standard image. If some internal contours are broken, missing, or significantly offset, the proportion of the internal missing area is calculated and compared with a preset proportion threshold. If the percentage of internal defects exceeds a threshold, the transfer pattern is determined to be incomplete, and the first analysis result of "Do not perform heat pressing" is output. Conversely, if the percentage is less than a threshold, the internal outline is considered complete, and the first analysis result of "Perform heat pressing" is output.

[0079] To improve comparison accuracy, a combination of contour matching methods can be used for integrity analysis. For example, morphological analysis methods can improve contour detection accuracy through techniques such as dilation, erosion, and edge detection. Deep learning models can be used to perform pattern recognition on contour features through pre-trained neural networks, improving anti-interference capabilities. Furthermore, adjustable comparison parameters can be set, such as contour matching threshold, shape similarity, and preset proportion threshold, to adapt to different types of transfer materials and application requirements. The contour matching threshold measures the degree of matching between the outer contour of the acquired image and the standard image. A higher matching degree ensures that the edges of the transferred pattern accurately conform to the standard pattern, while a lower matching degree threshold is suitable for situations where slight deformation or error is permissible. Shape similarity is mainly used for internal contour comparison to ensure that key elements of the pattern have not undergone significant deformation or loss. This parameter can be calculated based on feature point matching, edge detection, or deep learning models to adjust the tolerance for detail variations. The preset proportion threshold defines the allowable proportion of missing area. When the proportion of the missing part is below this threshold, the pattern is considered complete; if it exceeds this threshold, it is considered severely missing, and heat pressing is not performed. By flexibly adjusting these comparison parameters, different printing accuracy requirements can be met, improving detection stability and thus enhancing overall production efficiency.

[0080] In one embodiment, the color deviation analysis includes:

[0081] Based on the color distribution histogram of the standard image and the color distribution histogram of the acquired image, the color difference value ΔE of each color channel is calculated;

[0082] When the color difference value ΔE is less than or equal to the preset color difference threshold, it is considered that the transfer pattern has no color deviation, and the second analysis result of heat pressing is output.

[0083] When the color difference value ΔE is greater than the preset color difference threshold, it is considered that the transfer pattern has a color deviation, and the second analysis result of not performing heat pressing is output.

[0084] Specifically, in the color deviation analysis process, this embodiment uses a color distribution histogram method to compare the standard image and the acquired image to detect whether there is a color deviation in the transferred pattern. First, the color information of the standard image and the acquired image are extracted separately, and corresponding color distribution histograms are generated for them. Color histograms can be calculated based on different color spaces, such as RGB, Lab, or CMYK, to adapt to different application needs. The data for each channel reflects the distribution of that color component, allowing for comparative analysis of image colors through mathematical calculations. After obtaining the color distribution histogram, the color difference value ΔE between the acquired image and the standard image is calculated. The color difference value ΔE is a numerical value that measures the degree of difference between two colors in visual perception. Its calculation method is usually based on the Lab color space because the Lab color space better conforms to the color perception rules of the human eye and can more accurately describe color deviation. There are several methods for calculating ΔE, including ΔE76, ΔE94, and ΔE2000. Different calculation methods vary in accuracy and computational complexity, and the specific method should be chosen according to the actual application. The calculated color difference value ΔE is compared with a preset color difference threshold. When ΔE is less than or equal to the threshold, it indicates that the color deviation of the acquired image is within an acceptable range, and the color of the transferred pattern is considered to meet the standard. The second analysis result for performing heat pressing is then output. However, when ΔE is greater than the preset color difference threshold, it indicates a significant color deviation between the acquired image and the standard image, which may lead to color distortion in the final product, affecting the overall appearance and quality. In this case, the second analysis result for not performing heat pressing is output to prevent patterns with color differences from entering subsequent processing stages. This color deviation analysis method can effectively detect the color consistency of the transferred pattern, ensuring that the color effect of the final product meets design requirements and avoiding product scrapping or quality problems caused by color distortion. Furthermore, the preset color difference threshold can be flexibly adjusted according to different materials and production process requirements to adapt to different types of transfer materials, ink types, and customer color accuracy requirements, thereby improving the adaptability and robustness of the heat pressing equipment.

[0085] In one embodiment, the color loss analysis includes:

[0086] The acquired image is subjected to color channel separation, and the deviation between the mean of each color channel and the mean of the corresponding color channel of the standard image is calculated and denoted as the first deviation value.

[0087] When the first deviation value of all color channels is less than or equal to the preset deviation threshold, it is considered that there is no color missing phenomenon in the transfer pattern, and the third analysis result of heat pressing is output.

[0088] When the first deviation value of any color channel exceeds the preset deviation threshold, it is considered that the transfer pattern has a color deficiency phenomenon, and the third analysis result of not performing heat pressing is output.

[0089] Specifically, the color loss analysis method is mainly based on color channel separation and mean calculation. It determines the presence of color loss by analyzing the mean deviation between the acquired image and the standard image across each color channel. Specifically, the acquired image is first separated into color channels, extracting data for each channel (e.g., RGB or CMYK), and the mean value for each channel is calculated. These mean values ​​are then compared with the mean values ​​of the corresponding color channels in the standard image to calculate the first deviation value. Color loss typically manifests as the absence or weakening of a certain color component. For example, in the RGB color space, the red (R), green (G), and blue (B) channels represent the intensity of red, green, and blue colors in an image, respectively. During the preparation of the transfer pattern for the transfer material, if a certain color is not fully coated onto the material, the overall pixel value of that color channel will be low, leading to a decrease in its mean value. For example, if insufficient blue ink is sprayed, the pixel value of the B channel will decrease overall, making the mean value of the B channel significantly lower than the corresponding value in the standard image, indicating a possible absence of the blue component.

[0090] In the color defect analysis process, a preset deviation threshold is set to improve the accuracy and robustness of the detection. When the mean deviation of all color channels, i.e., the first deviation value, is less than or equal to this threshold, it indicates that the overall color distribution of the transfer image is normal and there is no obvious color defect. Therefore, the third analysis result of performing heat pressing is output. Conversely, if the first deviation value of any color channel exceeds the preset threshold, it indicates that there is a significant lack of that color component, which may affect the color presentation of the final product. Therefore, the third analysis result of not performing heat pressing is output to prevent defective products from entering the next process.

[0091] Color channel mean analysis effectively reflects the overall color distribution of an image and can be used for automated detection of color defects. Unlike direct pixel-based color difference calculations, color channel mean calculations smooth out fluctuations in individual pixels by statistically analyzing the color components of the entire image, improving the stability and reliability of the overall analysis. For example, in some cases, slight color fluctuations may exist in local areas, but if the overall color channel mean remains within the normal range, these minor differences can be tolerated, reducing the false positive rate. However, if the overall color channel mean deviates significantly, it indicates that the color defect is not merely a local problem but a global color deficiency, requiring corrective measures. Furthermore, different preset deviation thresholds can be set to adapt to different application requirements. For example, for products with high precision requirements, a lower preset deviation threshold can be set to ensure higher color accuracy in the transferred image. For products that allow for a certain range of color differences, the preset deviation threshold can be appropriately relaxed to reduce false positives and improve production efficiency. Simultaneously, combining deep learning models to optimize color channel feature analysis makes color defect detection more intelligent, further improving detection accuracy and stability.

[0092] In other embodiments, analyzing the acquired images may further include color uniformity analysis, wherein the color uniformity analysis includes:

[0093] The color distribution of the acquired image is obtained, and the acquired image is divided into grids. The average color value of each grid region is calculated.

[0094] Based on the color uniformity model of the standard image, the deviation between the color mean of each grid region of the acquired image and the color mean of the corresponding standard image is calculated, and denoted as the second deviation value;

[0095] When the second deviation value of each grid area is less than or equal to the preset uniformity threshold, it is considered that there is no color unevenness in the transfer pattern, and the fourth analysis result of heat pressing is output.

[0096] When the second deviation value of any grid area is greater than the preset uniformity threshold, it is considered that the transfer pattern has uneven color, and the fourth analysis result of not performing heat pressing is output.

[0097] Specifically, color uniformity analysis is mainly used to detect whether the color distribution of the transferred pattern is uniform in different areas, avoiding transfer quality problems caused by uneven color distribution. Specifically, firstly, the color distribution information of the acquired image is obtained, such as dividing the acquired image into multiple grid regions, the size of which can be adjusted according to different application requirements. After division, the color mean of each grid region is calculated, that is, the color information of all pixels in that region is statistically analyzed and the average value is calculated, thus obtaining the overall color performance of that region. To evaluate color uniformity, a color uniformity model of a standard image needs to be established. This model is usually obtained by dividing a pre-stored standard image into grid regions and calculating the mean value in the same way. Then, the color mean of each grid region of the acquired image is compared with the color mean of the corresponding standard image, and the deviation value between the two is calculated, denoted as the second deviation value. This deviation value reflects the color consistency between the acquired image and the standard image in each region. If the second deviation value is small, it indicates that the color distribution in that region is relatively uniform and basically consistent with the standard image; if the second deviation value is large, it indicates that there may be color unevenness in that region, such as inconsistent color depth or local color shift. Regarding the judgment criteria, if the second deviation value of all grid areas is less than or equal to the preset uniformity threshold, the overall color distribution of the transfer pattern is considered uniform, with no obvious color unevenness, thus outputting the fourth analysis result of performing heat pressing. Conversely, if the second deviation value of any grid area exceeds the preset uniformity threshold, it indicates that the color in that area has significant unevenness, which may affect the visual quality of the final product. Therefore, the fourth analysis result of not performing heat pressing is output to prevent transfer material with quality defects from entering subsequent processes. In addition, by reasonably setting the grid size and preset uniformity threshold, different material and application requirements can be adapted. For example, in high-precision printing, a smaller grid area can be used to improve the sensitivity and accuracy of detection; while in batch production where a certain color difference is allowed, the uniformity threshold can be appropriately relaxed to reduce false judgments and improve production efficiency. At the same time, by combining a deep learning model and learning the data features of a large number of standard images, the accuracy of color uniformity detection is optimized, making it more adaptable and robust in different application scenarios.

[0098] In other embodiments, one or more of the following can be performed: edge sharpness analysis, pattern deformation analysis, impurity or stain detection, layering analysis (gradient transition detection), positioning error analysis, etc. For example, edge sharpness analysis involves extracting edge features from the acquired image using edge detection algorithms (such as Sobel and Canny algorithms) and comparing them with the edge distribution of a standard image. If blurred or severely jagged edges are detected, the pattern outline may be unclear after transfer, thus determining whether heat pressing should be performed. Pattern deformation analysis calculates the degree of deformation between the acquired image and the standard image, including scaling, distortion, and stretching, and uses shape matching algorithms (such as morphological transformation and SIFT feature matching) to determine whether the pattern has undergone significant deformation. If the deformation exceeds the allowable range, it may affect the transfer quality, thus determining whether heat pressing should be performed. Impurity or stain detection uses image filtering and threshold segmentation methods to detect abnormal spots, scratches, or stains in the acquired image and assesses their impact range. If the area or number of impurities exceeds a set threshold, it may affect the aesthetics or adhesion after heat pressing, thus determining whether heat pressing should be performed. Layering analysis (gradient transition detection) analyzes the smoothness of color changes in patterns containing gradients or complex color transitions. If color banding, streaks, or color lines appear in the acquired image, it may affect the final transfer effect, thus determining whether heat pressing should be performed. Positioning error analysis uses image registration technology to detect the alignment between the acquired image and a standard image, determining whether the transferred pattern has shifted position. If the offset exceeds a set threshold, it may cause misalignment or inaccurate overprinting during final heat pressing, affecting product quality; therefore, it can also determine whether heat pressing should be performed.

[0099] Finally, after analyzing the acquired images in the image acquisition device, the corresponding image processing decisions are output to the control system of the heat press equipment based on the analysis results. When heat pressing is required, the feeding mechanism of the heat press equipment is controlled to drive normally, conveying the transfer material from the loading station to the heat press station, and the heat press head is controlled to descend to perform the transfer operation on the substrate. When "heat pressing is not performed," the heat press head is kept in place and does not descend, while the receiving mechanism is controlled to recycle the transfer material that does not meet the requirements, thereby preventing unqualified patterns from being transferred incorrectly. Through this linkage control, the scrap rate can be effectively reduced, material use optimized, production efficiency improved, unnecessary heat pressing operations reduced, energy consumption and mechanical wear reduced, and the overall intelligence level and reliability of the heat press equipment improved.

[0100] The method of this invention automatically detects the transfer pattern of the transfer material using an image acquisition device. Compared with the traditional method relying on manual visual inspection, it can effectively improve the detection accuracy and consistency, avoid misjudgment and omission due to human factors, and thus improve the stability of product quality. Secondly, by combining deep learning algorithms and image analysis technology to perform multiple detections on the acquired images, such as integrity analysis, color deviation analysis, missing color analysis, and color uniformity analysis, it can comprehensively determine whether the transfer pattern meets the heat pressing requirements, ensuring that only qualified transfer materials enter the heat pressing process, thereby reducing waste caused by heat pressing of unqualified materials, reducing material waste and production costs. Furthermore, the image acquisition device's built-in computing unit directly processes and makes decisions, reducing data transmission delays, improving detection efficiency, and enabling the heat pressing equipment to quickly respond to detection results, achieving automated production and improving production efficiency. In summary, this invention, by integrating image acquisition and analysis functions, achieves intelligent screening and precise control of the transfer material quality, optimizes the heat pressing process, reduces unnecessary processing, and improves production efficiency and yield.

[0101] Example 2

[0102] Please see Figure 5 This invention provides an intelligent heat press transfer device 200, applied to heat press equipment. An image acquisition device is installed above the transfer material feeding station of the heat press equipment. The transfer material feeding station is used to place transfer material with a transfer pattern. The device includes:

[0103] Calibration module 201 is used to calibrate the parameters of the image acquisition device;

[0104] The acquisition module 202 is used to control the image acquisition device to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image;

[0105] Analysis module 203 is used to analyze the acquired image within the image acquisition device and output an image processing decision, wherein the image processing decision includes performing heat pressing and not performing heat pressing;

[0106] The heat pressing module 204 is used to control the heat pressing equipment to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate when the image processing decision is to perform heat pressing.

[0107] In summary, the intelligent heat transfer device provided in this invention automatically detects the transfer pattern of the transfer material through an image acquisition device. Compared with the traditional method relying on manual visual inspection, it can effectively improve the detection accuracy and consistency, avoid misjudgment and omission caused by human factors, and thus improve the stability of product quality. Secondly, by combining deep learning algorithms and image analysis technology to perform multiple detections on the acquired images, such as integrity analysis, color deviation analysis, missing color analysis, and color uniformity analysis, it can comprehensively determine whether the transfer pattern meets the heat transfer requirements, ensuring that only qualified transfer materials enter the heat transfer process, thereby reducing waste caused by unqualified materials and reducing material loss and production costs. In addition, the image acquisition device's built-in computing unit directly processes and makes decisions, reducing data transmission delays and improving detection efficiency. This allows the heat transfer equipment to quickly respond to detection results, achieving automated production and improving production efficiency. In conclusion, this invention, by integrating image acquisition and analysis functions, achieves intelligent screening and precise control of the quality of transfer materials, optimizes the heat transfer process, reduces unnecessary processing, and improves production efficiency and yield.

[0108] Example 3

[0109] In addition, the intelligent heat transfer method of this invention can be implemented by heat transfer equipment. Figure 1 A structural diagram of the heat pressing device provided in an embodiment of the present invention is shown. Figure 6 A schematic diagram of the hardware structure of the main control module of the heat pressing device provided in an embodiment of the present invention is shown.

[0110] The main control module may include a processor 301 and a memory 302 storing computer program instructions.

[0111] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0112] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to a data processing device. In a particular embodiment, memory 302 is a non-volatile solid-state memory. In a particular embodiment, memory 302 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0113] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the intelligent heat transfer methods in the above embodiments.

[0114] In one example, the main control module may also include a communication interface 303 and a bus 310. For example, Figure 6 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0115] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of the present invention.

[0116] Bus 310 includes hardware, software, or both, that couples components of the main control module together. For example, and not limitingly, bus 310 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0117] Example 4

[0118] Furthermore, in conjunction with the intelligent heat transfer method in the above embodiments, this invention can be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by the processor 301, they implement any one of the intelligent heat transfer methods in the above embodiments.

[0119] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0120] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0121] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0122] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A smart hot stamping transfer method, characterized in that, An image acquisition device is installed above the transfer material feeding station of a heat press equipment. The transfer material feeding station is used to place transfer material with a transfer pattern. The method includes: Perform parameter calibration on the image acquisition device; The image acquisition device is controlled to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image; The image acquisition device analyzes the acquired image and outputs an image processing decision, wherein the image processing decision includes performing heat pressing or not performing heat pressing; When the image processing decision is to perform heat pressing, the heat pressing equipment is controlled to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate.

2. The intelligent heat transfer method according to claim 1, characterized in that, Before calibrating the parameters of the image acquisition device, the following steps are also included: Multiple standard transfer patterns are imported into the storage unit of the image acquisition device to establish a standard image database; Based on the standard image database, a deep learning algorithm is run in the computing unit of the image acquisition device to perform feature extraction and analysis training on the standard images; The trained deep learning model is integrated into the image acquisition device to directly perform image comparison and analysis processing after image acquisition.

3. The intelligent heat transfer method according to claim 1, characterized in that, The parameter calibration of the image acquisition device includes: Obtain initial parameters of the image acquisition device, the initial parameters including one or more of focal length, exposure time, white balance, and color gain; Under preset lighting conditions, test images are acquired, and one or more of the image's sharpness, color reproduction, and contrast are analyzed to determine whether they meet the preset acquisition accuracy requirements. Otherwise, adjust the parameters of the image acquisition device until it meets the preset acquisition accuracy requirements.

4. The intelligent heat transfer method according to claim 2, characterized in that, The step of analyzing the acquired image and outputting image processing decisions within the image acquisition device includes: After feature extraction and pattern recognition of the acquired image by the deep learning model in the image acquisition device, completeness analysis, color deviation analysis and missing color analysis are performed based on the corresponding standard image, and the corresponding first analysis result, second analysis result and third analysis result are output respectively. When the first analysis result, the second analysis result, and the third analysis result all indicate that heat pressing should be performed, the output image processing decision is to perform heat pressing. If any one of the first analysis result, the second analysis result, or the third analysis result indicates that pressing is not performed, then the output image processing decision is to not perform pressing.

5. The intelligent heat transfer method according to claim 4, characterized in that, The completeness analysis includes: The contour features of the acquired image are obtained and compared with the contour features of the corresponding standard image to calculate the proportion of the missing pattern area. When the proportion of the missing area is less than or equal to a preset proportion threshold, the transfer pattern is considered complete, and the first analysis result of heat pressing is output. When the proportion of the missing area is greater than the preset proportion threshold, the transfer pattern is considered incomplete, and the first analysis result of not performing heat pressing is output.

6. The intelligent heat transfer method according to claim 4, characterized in that, The color deviation analysis includes: Based on the color distribution histogram of the standard image and the color distribution histogram of the acquired image, the color difference value ΔE of each color channel is calculated; When the color difference value ΔE is less than or equal to the preset color difference threshold, it is considered that the transfer pattern has no color deviation, and the second analysis result of heat pressing is output. When the color difference value ΔE is greater than the preset color difference threshold, it is considered that the transfer pattern has a color deviation, and the second analysis result of not performing heat pressing is output.

7. The intelligent heat transfer method according to claim 4, characterized in that, The color deficiency analysis includes: The acquired image is subjected to color channel separation, and the deviation between the mean of each color channel and the mean of the corresponding color channel of the standard image is calculated and denoted as the first deviation value. When the first deviation value of all color channels is less than or equal to the preset deviation threshold, it is considered that there is no color missing phenomenon in the transfer pattern, and the third analysis result of heat pressing is output. When the first deviation value of any color channel exceeds the preset deviation threshold, it is considered that the transfer pattern has a color deficiency phenomenon, and the third analysis result of not performing heat pressing is output.

8. An intelligent heat transfer printing device, characterized in that, An image acquisition device is installed above the transfer material feeding station of a heat press equipment. The transfer material feeding station is used to place transfer material with a transfer pattern. The device includes: A calibration module is used to calibrate the parameters of the image acquisition device; The acquisition module is used to control the image acquisition device to acquire the transfer pattern on the surface of the transfer material to obtain the acquired image; An analysis module is used to analyze the acquired image within the image acquisition device and output an image processing decision, wherein the image processing decision includes performing heat pressing or not performing heat pressing; The heat pressing module is used to control the heat pressing equipment to transfer the transfer material from the transfer material loading station to the heat pressing station for heat pressing to transfer the transfer pattern onto the substrate when the image processing decision is to perform heat pressing.

9. A heat pressing device, characterized in that, include: A substrate transport mechanism is used to transport the substrate to the heat pressing station; A transfer conveyor is used to transport transfer materials. A heat pressing mechanism is used to heat and transfer the transfer pattern from the surface of the transfer material to the substrate. Image acquisition device, used to acquire transfer patterns; The main control module includes at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method as described in any one of claims 1-7.

10. A storage medium storing computer program instructions thereon, characterized in that, The method as described in any one of claims 1-7 is implemented when the computer program instructions are executed by the processor.

Images