Printed product quality detection method, device and storage medium

Abstract

The present application relates to a method, device, and storage medium for testing the quality of printed products, and relates to the technical field of printed product quality testing, including obtaining material data of the printed product to be tested; obtaining image data of the printed product to be tested acquired by an image acquisition device and environmental data acquired by an environmental acquisition device; preprocessing the image data based on the material data and environmental data; obtaining visual feature data of the preprocessed image data, the visual feature data including at least print clarity features, color consistency features, and contrast features; obtaining content feature data of the preprocessed image data, the content feature data including one or more of printed text data features, pattern data features, and barcode data features; and obtaining a quality test result of the printed product to be tested based on the visual feature data and content feature data of the image data. The present application has the effect of improving the accuracy and stability of printed product quality testing.

Description

Technical Field

[0001] The present application relates to the technical field of printed matter quality detection, and in particular to a printed matter quality detection method, device and storage medium. Background Art

[0002] Labels are used to identify items and typically require printing with text and images. During the printing process, quality inspection is essential to improving product quality. With growing market demand and technological advancements, automated inspection systems are becoming a key tool for improving print quality and production efficiency. These systems not only increase inspection speed and accuracy, but also reduce human error and production costs, thereby delivering significant economic and social benefits to businesses.

[0003] Among existing technologies for inspecting printed product quality, common methods include manual visual inspection, traditional optical inspection, and machine vision inspection. While manual visual inspection is intuitive and reliable, it is subject to eye fatigue and subjective judgment errors, making it difficult to ensure consistency and efficiency. Traditional optical inspection relies on specific light sources and sensors. While it can be partially automated, it has limitations when inspecting complex patterns and multiple colors. Machine vision inspection, on the other hand, utilizes cameras and image processing technology to achieve high-precision automated inspection and is widely used in various fields of the printing industry. However, existing machine vision inspection systems still face challenges in practical application, particularly in improving detection accuracy and stability. For example, existing inspection systems often struggle to accurately identify subtle color differences, blur, and misalignment, resulting in inaccurate inspection results. Furthermore, the robustness and adaptability of the system need to be improved, especially when faced with varying materials and environmental changes, where existing systems can exhibit unstable performance. Summary of the Invention

[0004] The purpose of this application is to provide a printed matter quality detection method, device and storage medium for improving the accuracy and stability of printed matter quality detection.

[0005] In the first aspect, the present application provides a method for detecting the quality of printed matter using the following technical solutions:

[0006] A method for detecting the quality of printed matter, comprising:

[0007] Obtain material data of the printed product to be tested;

[0008] Acquiring image data of the printed product to be tested acquired by an image acquisition device and environmental data acquired by an environmental acquisition device;

[0009] Preprocess the image data according to material data and environment data;

[0010] Acquiring visual feature data of the preprocessed image data, wherein the visual feature data includes at least a print clarity feature, a color consistency feature, and a contrast feature;

[0011] Acquiring content feature data of the pre-processed image data, wherein the content feature data includes one or more of printed text data features, pattern data features, and barcode data features;

[0012] The quality inspection result of the printed product to be tested is obtained according to the visual feature data and the content feature data of the image data.

[0013] By adopting the above technical solution, this application obtains the material data of the printed product to be tested and the current environmental data to pre-process and calibrate the collected image data, and then performs print quality analysis. This can effectively reduce the impact of the material and environment on the quality detection of printed products. In addition, by combining visual feature data with content feature data for print quality detection, compared with traditional single detection methods, this method can more accurately and quickly identify various quality issues of printed products, improving the reliability and efficiency of detection. In particular, the detection capability in complex backgrounds is significantly improved, effectively avoiding misjudgments and missed detections, and can effectively improve the accuracy and stability of printed product quality detection.

[0014] Furthermore, the acquisition of visual feature data of the pre-processed image data includes clarity feature extraction, specifically comprising:

[0015] Identify the edge clarity of image data using edge detection algorithms;

[0016] Comparing the image data with the standard image data to obtain a structural similarity index;

[0017] The edge clarity and structural similarity index are input into a pre-built clarity assessment model to obtain the clarity features of the image data.

[0018] By adopting the above technical solution, the present application performs print quality detection by extracting the clarity features of image data, thereby ensuring the accuracy of print quality detection.

[0019] Furthermore, the acquisition of visual feature data of the pre-processed image data further includes color consistency feature extraction, specifically including:

[0020] Acquiring color spectrum data of the image data by a color measurement device;

[0021] Convert color spectrum data to a standard color space;

[0022] Calculate the color difference between the color spectrum data and the standard color spectrum data using the color difference formula;

[0023] The color difference values ​​are input into a pre-built color consistency evaluation model to obtain the color consistency features of the image data.

[0024] By adopting the above technical solution, the present application performs print quality detection by extracting the color consistency features of image data, thereby ensuring the accuracy of print quality detection.

[0025] Furthermore, the acquisition of visual feature data of the pre-processed image data further includes contrast feature extraction, specifically including:

[0026] Obtaining a grayscale histogram of the image data to obtain the grayscale distribution of the image data;

[0027] The maximum contrast of the image data is obtained according to the grayscale difference between the brightest and darkest pixels in the grayscale distribution of the image data;

[0028] The contrast ratio of the image data is obtained according to the ratio of the maximum grayscale value to the minimum grayscale value in the grayscale distribution of the image data;

[0029] According to the grayscale difference between adjacent areas in the grayscale distribution of the image data, a local contrast enhancement algorithm is used to obtain the enhanced local contrast of the image data;

[0030] The maximum contrast, contrast ratio and local contrast are input into a pre-built color contrast evaluation model to obtain the contrast characteristics of the image data.

[0031] By adopting the above technical solution, the present application performs print quality detection by extracting contrast features of image data, thereby ensuring the accuracy of print quality detection.

[0032] Furthermore, the obtaining of content feature data of the pre-processed image data specifically includes:

[0033] Determine whether there is text data, pattern data or barcode data through image recognition algorithm;

[0034] When text data exists, the integrity, clarity and accuracy of the text data are automatically identified through an optical character recognition algorithm to obtain text data features;

[0035] When pattern data exists, identifying and verifying the integrity, clarity and accuracy of the pattern to obtain pattern data features;

[0036] When barcode data exists, the readability of the barcode data is identified by barcode recognition software to obtain barcode data features.

[0037] By adopting the above technical solution, the present application can calibrate the text, patterns and barcodes of printed materials through image recognition, ensure the accuracy of the printed content, and thus improve the comprehensiveness of printed material quality inspection.

[0038] Furthermore, the obtaining of content feature data of the pre-processed image data further includes:

[0039] The image data is compared with the standard template through template matching technology to determine whether the printed content on the image data is located in the correct position and obtain position feature data.

[0040] By adopting the above technical solution, this application further improves the comprehensiveness of printed product quality inspection by extracting position feature data to determine whether the position of printed content such as text, patterns and barcodes printed on the printed product is accurate.

[0041] Furthermore, obtaining the quality inspection result of the printed product to be tested based on the visual feature data and content feature data of the image data includes:

[0042] Construct an initial quality inspection model and configure model parameters of the initial quality inspection model;

[0043] Obtain visual feature samples, content feature samples, and corresponding quality inspection result samples of different printed products to be tested in a quality inspection database, wherein the quality inspection result samples include normal quality inspection samples and abnormal quality inspection samples;

[0044] Constructing visual feature samples, content feature samples and corresponding quality inspection result samples of different printed products to be tested into a quality inspection sample set;

[0045] The initial quality detection model is trained according to the quality detection sample set to obtain a trained quality detection model;

[0046] The visual feature data and content feature data of the image data are input into the trained quality detection model to obtain the quality detection results of the image data.

[0047] By adopting the above technical solution, this application improves the intelligence and accuracy of printed product quality detection by constructing a quality detection model and predicting the quality detection results through the quality detection model.

[0048] Furthermore, the initial quality detection model is trained based on the quality detection sample set to obtain a trained quality detection model, specifically including:

[0049] The quality inspection sample set is divided into a quality inspection training set and a quality inspection test set, and the number of training rounds is preset;

[0050] Input the quality inspection training set into the quality inspection initial model and train it according to the preset number of training rounds;

[0051] When the initial quality inspection model reaches the preset number of training rounds, the trained quality inspection model is obtained;

[0052] Input the visual feature samples and content feature samples in the quality detection test set into the trained quality detection model to obtain the quality detection result prediction samples;

[0053] The model parameters of the quality detection model are adjusted according to the quality detection result samples in the test set and the corresponding quality detection result prediction samples, and the trained quality detection model is obtained according to the adjusted model parameters.

[0054] By adopting the above-mentioned technical solution, this application trains the model through a quality inspection sample set, so that the quality inspection model can use deep learning to obtain the feature relationship between visual feature data, content feature data and quality inspection results, thereby improving the intelligence and accuracy of printed product quality inspection.

[0055] In a second aspect, the present application provides a printed matter quality inspection device that adopts the following technical solution:

[0056] A printed matter quality detection device comprises a processor, wherein the processor is configured to execute the printed matter quality detection method according to the first aspect;

[0057] It also includes an image acquisition device and an environment acquisition device. The image acquisition device is used to acquire image data of the printed product to be tested and upload it to the processor, and the environment acquisition device is used to acquire environmental data and upload it to the processor.

[0058] By adopting the above technical solution, the present application collects image data of the printed product to be tested through an image acquisition device, collects environmental data of the current environment through environmental acquisition data, obtains material data of the printed product to be tested and current environmental data, pre-processes and calibrates the collected image data, and then performs print quality analysis. This can effectively reduce the impact of the material and environment on the quality detection of printed products, and by combining visual feature data with content feature data for print quality detection, compared with traditional single detection methods, this method can more accurately and quickly identify various quality problems of printed products, thereby improving the reliability and efficiency of detection. In particular, the detection capability in complex backgrounds is significantly improved, effectively avoiding misjudgments and missed detections, and can effectively improve the accuracy and stability of printed product quality detection.

[0059] In a second aspect, the present application provides a computer-readable storage medium that employs the following technical solutions:

[0060] A computer-readable storage medium stores a computer program that can be loaded by a processor and executes a printed product quality detection method as described in the first aspect.

[0061] In summary, this application includes at least one of the following beneficial technical effects:

[0062] 1. This application obtains material data and current environmental data of the printed product to be tested, pre-processes and calibrates the collected image data, and then performs print quality analysis. This effectively reduces the impact of material and environment on print quality testing. Furthermore, by combining visual feature data with content feature data for print quality testing, this method can more accurately and quickly identify various quality issues in printed products compared to traditional single-detection methods, improving the reliability and efficiency of testing. In particular, the detection capability is significantly improved in complex backgrounds, effectively avoiding misjudgments and missed detections, and effectively improving the accuracy and stability of print quality testing.

[0063] 2. This application uses image recognition to calibrate text, patterns, and barcodes on printed materials to ensure the accuracy of printed content. By extracting positional feature data, the accuracy of the position of printed content such as text, patterns, and barcodes on printed materials can be determined, thereby improving the comprehensiveness of printed material quality inspection.

[0064] 3. This application improves the intelligence and accuracy of printed product quality inspection by constructing a quality inspection model and predicting the quality inspection results through the quality inspection model. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 Schematic diagram of a printed matter quality detection method according to an embodiment of the present application;

[0066] Figure 2 This is a flowchart of the specific method of step S6 in the embodiment of the present application;

[0067] Figure 3 This is a connection diagram of a printed matter quality inspection device according to an embodiment of the present application;

[0068] In the figure, 1. Processor; 2. Image acquisition device; 3. Environment acquisition device. DETAILED DESCRIPTION

[0069] The following is combined with Figure 1 -Attached Figure 3 , further details of this application are given.

[0070] Among existing technologies for inspecting printed product quality, common methods include manual visual inspection, traditional optical inspection, and machine vision inspection. While manual visual inspection is intuitive and reliable, it is subject to eye fatigue and subjective judgment errors, making it difficult to ensure consistency and efficiency. Traditional optical inspection relies on specific light sources and sensors. While it can be partially automated, it has limitations when inspecting complex patterns and multiple colors. Machine vision inspection, on the other hand, utilizes cameras and image processing technology to achieve high-precision automated inspection and is widely used in various fields of the printing industry. However, existing machine vision inspection systems still face challenges in practical application, particularly in improving detection accuracy and stability. For example, existing inspection systems often struggle to accurately identify subtle color differences, blur, and misalignment, resulting in inaccurate inspection results. Furthermore, the robustness and adaptability of the system need to be improved, especially when faced with varying materials and environmental changes, where existing systems can exhibit unstable performance.

[0071] Therefore, the present invention provides a method for detecting the quality of printed matter. Figure 1 ,include:

[0072] S1. Obtain material data of the printed product to be tested.

[0073] Specifically, because different printed materials can affect printing quality, different quality inspection standards are applied to printed products of different materials. In practice, obtaining material data for the printed product under test can be accomplished through a variety of methods, such as manual input, scanning QR codes, or RFID tags. Material data can include paper type, coating information, thickness, and more.

[0074] S2. Acquire image data of the printed product to be tested acquired by the image acquisition device and environmental data acquired by the environment acquisition device.

[0075] Specifically, because different testing environments can affect detection results, it's important to consider current environmental data, primarily brightness data, when capturing image data. In practice, the image acquisition device can be a high-resolution camera, such as a CCD or CMOS camera, for capturing high-definition images of printed materials. Environmental data acquisition devices can include temperature and humidity sensors, light intensity sensors, and other sensors to record test environment conditions. This data helps eliminate external interference and improve detection accuracy.

[0076] S3. Preprocess the image data according to the material data and the environment data.

[0077] Specifically, considering the influence of different material and environmental data, image data is preprocessed through denoising, correction, and enhancement. Denoising can use methods such as median filtering and Gaussian filtering to remove noise from the image. Correction can use methods such as geometric correction and color correction to make the image more realistic. Enhancement can use methods such as histogram equalization and Laplace transform to improve image contrast and detail.

[0078] S4. Obtain visual feature data of the preprocessed image data.

[0079] Specifically, the visual feature data includes at least printing clarity features, color consistency features, and contrast features.

[0080] S5. Obtain content feature data of the pre-processed image data.

[0081] Specifically, the content feature data includes one or more of printed text data features, pattern data features, and barcode data features.

[0082] S6. Obtaining a quality inspection result of the printed product to be inspected based on the visual feature data and the content feature data of the image data.

[0083] Specifically, by constructing a quality inspection model and inputting the visual feature data and content feature data of the image data into the quality inspection model, the quality inspection result of the printed product to be tested can be obtained.

[0084] The implementation principle of the embodiment of this application is as follows: by obtaining material data of the printed product to be tested and current environmental data, pre-processing and calibrating the collected image data, and then performing print quality analysis, it can effectively reduce the impact of the material and environment on print quality detection. In addition, by combining visual feature data with content feature data for print quality detection, compared with traditional single detection methods, this method can more accurately and quickly identify various quality issues of printed products, improving the reliability and efficiency of detection. In particular, the detection capability in complex backgrounds is significantly improved, effectively avoiding misjudgments and missed detections, and can effectively improve the accuracy and stability of print quality detection.

[0085] In the embodiment of the present application, step S4 includes clarity feature extraction S41 , color consistency feature extraction S42 , and contrast feature extraction S43 .

[0086] The clarity feature extraction S41 specifically includes:

[0087] S411 , identifying edge clarity of image data using an edge detection algorithm.

[0088] Specifically, edge detection algorithms such as Canny edge detection, Sobel operator, and Laplacian operator can be used to identify edges in an image. Edge clarity reflects the clarity of a printed product; the sharper the edge, the higher the clarity.

[0089] S412: Compare the image data with the standard image data to obtain a structural similarity index.

[0090] Specifically, the Structural Similarity Index (SSIM) is used to assess the similarity between images. SSIM takes into account brightness, contrast, and structural information. This can be achieved using the SSIM algorithm, which compares the image data of a printed product with standard image data of standard definition. The closer the SSIM value is to 1, the higher the definition.

[0091] S413 , inputting the edge clarity and the structural similarity index into a pre-built clarity evaluation model to obtain clarity features of the image data.

[0092] Specifically, by extracting the clarity features of image data to detect the quality of printed matter, the accuracy of the printed matter quality detection can be ensured.

[0093] Color consistency feature extraction S42 specifically includes:

[0094] S421. Obtain color spectrum data of the image data through a color measurement device.

[0095] Specifically, use a color measurement instrument, such as a spectrophotometer, to measure the color on the printed product and obtain color spectral data. Ensure that the measurement is performed under a standard light source to eliminate the influence of ambient light on color perception.

[0096] S422: Convert the color spectrum data into a standard color space.

[0097] Specifically, the measured spectral data is converted to a standard color space, such as CIELAB, CIELUV, or CMYK, to facilitate comparison and analysis. The CIELAB color space is based on human perception and can more accurately represent color differences.

[0098] S423: Calculate the color difference value between the color spectrum data and the standard color spectrum data using a color difference formula.

[0099] Specifically, a color difference formula, such as CIEDE2000 or CIE76, is used to calculate the color difference (ΔE) between the printed color and the standard color. The smaller the color difference, the better the color consistency.

[0100] S424: Input the color difference value into a pre-built color consistency evaluation model to obtain a color consistency feature of the image data.

[0101] Specifically, by extracting the color consistency feature of image data to detect the quality of printed products, the accuracy of the printed product quality detection can be ensured.

[0102] Contrast feature extraction S43 specifically includes:

[0103] S431. Obtain a grayscale histogram of the image data to obtain a grayscale distribution of the image data.

[0104] Specifically, the grayscale histogram of the image data is analyzed. The grayscale histogram shows the number of pixels with different grayscale levels in the image. Contrast can be assessed by the width and distribution of the grayscale histogram. The wider the grayscale distribution, the higher the contrast.

[0105] S432 : Obtain the maximum contrast of the image data according to the grayscale difference between the brightest and darkest pixels in the grayscale distribution of the image data.

[0106] S433. Obtain a contrast ratio of the image data according to a ratio of a maximum grayscale value to a minimum grayscale value in a grayscale distribution of the image data.

[0107] Specifically, contrast metrics such as Max Contrast, Mean Contrast, or Contrast Ratio are used to quantify the contrast of an image. Max Contrast is the grayscale difference between the brightest and darkest pixels in an image, and Contrast Ratio is the ratio of the maximum grayscale value to the minimum grayscale value.

[0108] S434 , using a local contrast enhancement algorithm according to the grayscale difference between adjacent regions in the grayscale distribution of the image data to obtain enhanced local contrast of the image data.

[0109] Specifically, the local contrast of the image is analyzed, that is, the grayscale difference between adjacent regions in the image. Local contrast enhancement algorithms such as color adaptive histogram equalization (CLAHE) can be used to improve the local contrast of the image.

[0110] S435 , inputting the maximum contrast, contrast ratio, and local contrast into a pre-built color contrast evaluation model to obtain contrast features of the image data.

[0111] Specifically, by extracting contrast features of image data to detect printed matter quality, the accuracy of printed matter quality detection can be ensured.

[0112] In another embodiment, the contrast feature can also be used in advance to evaluate the contrast of the image structure using a structural contrast evaluation method, such as the contrast component of the Structural Similarity Index (SSIM). Structural contrast considers the contrast relationship between different regions in the image, rather than just the grayscale differences.

[0113] Step S5 of the embodiment of the present application specifically includes:

[0114] S51. Determine whether text data, pattern data or barcode data exists through an image recognition algorithm.

[0115] S52. When text data exists, the integrity, clarity, and accuracy of the text data are automatically identified by an optical character recognition algorithm to obtain text data features.

[0116] Specifically, the text in the image is analyzed to ensure that it is legible and free of blur, offset, missing or misprinted text. Optical character recognition (OCR) technology can be used to automatically identify and verify the correctness of the text.

[0117] S53: When pattern data exists, identify and verify the integrity, clarity and accuracy of the pattern to obtain pattern data features.

[0118] Specifically, identify and verify the integrity of the pattern, without blurring, offset, missing or misprinted issues, to ensure the clarity of the pattern.

[0119] S54: When barcode data exists, the readability of the barcode data is identified by barcode recognition software to obtain barcode data features.

[0120] Specifically, use barcode recognition software to check the readability and accuracy of the barcode.

[0121] In order to improve the comprehensiveness of printed product quality inspection, step S5 of the embodiment of the present application also includes comparing the image data with the standard template through template matching technology to determine whether the printed content on the image data is in the correct position and obtain position feature data. Use position feature data to check whether the text, pattern, barcode and other elements on the printed product are in the correct position. In the specific implementation process, template matching technology can be used to compare the actual image with the standard template to ensure accurate positioning. Template matching technology can also be used to check all necessary information on the label, such as product name, net content, production date, shelf life, manufacturer, etc. Ensure that all information is complete and complies with relevant laws and regulations and standards.

[0122] like Figure 2 As shown, step S6 of the embodiment of the present application specifically includes:

[0123] S61. Construct an initial quality inspection model and configure model parameters of the initial quality inspection model.

[0124] Specifically, an optimization scheme is constructed based on LSTM to detect an initial model, and model parameters of the optimization scheme are configured to detect the initial model. The model parameters include but are not limited to the number of LSTM units, activation function, and input sequence length.

[0125] S62: Obtain visual feature samples, content feature samples, and corresponding quality inspection result samples of different printed products to be tested in the quality inspection database.

[0126] Specifically, the quality inspection database includes quality inspection data stored in previous quality inspection processes, and the quality inspection result samples include normal quality inspection samples and abnormal quality inspection samples.

[0127] S63: Constructing visual feature samples, content feature samples, and corresponding quality inspection result samples of different printed products to be tested into a quality inspection sample set.

[0128] Specifically, visual feature samples and content feature samples are used as input features, and quality detection result samples are used as output features to construct a quality detection sample set to train and test the constructed initial quality detection model.

[0129] S64. Train the initial quality detection model according to the quality detection sample set to obtain a trained quality detection model.

[0130] Specifically, the quality detection initial model is trained using a quality detection sample set, where visual feature samples and content feature samples are used as input data and quality detection result samples are used as output data, so that the model can learn the feature relationship between visual feature samples, content feature samples and corresponding quality detection result samples.

[0131] S65 , inputting the visual feature data and content feature data of the image data into the trained quality detection model to obtain a quality detection result of the image data.

[0132] Specifically, the quality detection model predicts the corresponding quality detection results based on the learned feature relationship and the input visual feature data and content feature data, and outputs the quality detection results.

[0133] Step S64 of the embodiment of the present application specifically includes:

[0134] S641. Divide the quality inspection sample set into a quality inspection training set and a quality inspection test set, and preset the number of training rounds.

[0135] Specifically, 70% of the data in the sample set is usually used as the training set, and 30% of the data is used as the test set. The number of training rounds is determined according to actual needs.

[0136] S642: Input the quality inspection training set into the quality inspection initial model, and perform training according to a preset number of training rounds.

[0137] Specifically, the visual feature samples and content feature samples of the quality detection training set are used as input features, and the quantity detection result samples are used as output features, and are all input into the quality detection initial model for training.

[0138] S643: When the initial quality detection model reaches a preset number of training rounds, a trained quality detection model is obtained.

[0139] Specifically, the quality detection initial model autonomously learns the feature relationship between visual feature samples, content feature samples and corresponding quality detection result samples during the training process.

[0140] S644: Input the visual feature samples and content feature samples in the quality detection test set into the trained quality detection model to obtain quality detection result prediction samples.

[0141] Specifically, the quality inspection result prediction samples are predicted by the quality inspection model after preliminary training.

[0142] S645. Adjust the model parameters of the quality detection model according to the quality detection result samples and the corresponding quality detection result prediction samples in the test set, and obtain the trained quality detection model according to the adjusted model parameters.

[0143] Specifically, by comparing the quality inspection result prediction samples and quality inspection result samples obtained by the quality inspection model after preliminary training, the accuracy of the current model after preliminary training can be obtained, and the model can be adjusted according to the comparison results to further improve the model accuracy.

[0144] The implementation principle of the embodiment of the present application is: by constructing a quality detection model and training the model through a quality detection sample set, the quality detection model can use deep learning to obtain the feature relationship between visual feature data, content feature data and quality detection results, thereby improving the intelligence and accuracy of printed product quality detection.

[0145] In another embodiment, in order to adapt to the detection requirements under different environmental conditions, the embodiment of the present application can also add a dynamic adjustment mechanism for environmental data. Specifically including: dynamically adjusting the environmental data acquisition frequency, adjusting the acquisition frequency in real time according to changes in the detection environment, such as increasing the acquisition frequency in an environment with large changes in light to ensure the accuracy of the data. In the preprocessing process, an adaptive filter is introduced to dynamically adjust the filter parameters according to the environmental data to adapt to different detection environments. For example, a stronger denoising filter is used in a high-brightness environment, and a weaker denoising filter is used in a low-brightness environment. In the clarity feature extraction, a dynamic threshold adjustment mechanism is introduced to dynamically adjust the threshold of the edge detection algorithm according to the environmental data to adapt to different lighting conditions. In the color consistency feature extraction, an adaptive color correction algorithm is introduced to dynamically adjust the color conversion parameters according to the environmental data to eliminate the influence of ambient light on color. In the contrast feature extraction, an adaptive contrast enhancement algorithm is introduced to dynamically adjust the local contrast enhancement parameters according to the environmental data to adapt to different contrast requirements.

[0146] By introducing a dynamic adjustment mechanism for environmental data and an adaptive algorithm, the embodiments of the present application can better adapt to detection requirements under different environmental conditions, improving the flexibility and reliability of detection. Particularly in complex production environments, this dynamic adjustment mechanism can effectively reduce external interference and ensure the accuracy of detection results. Furthermore, the application of the adaptive algorithm enables the detection system to automatically adjust parameters based on actual conditions, simplifying system maintenance and management and improving work efficiency.

[0147] In another embodiment, in order to improve the comprehensive performance of detection, the embodiment of the present application can also introduce multimodal data fusion technology to comprehensively utilize multiple types of detection data. Specifically, when obtaining the material data of the printed matter, in addition to the basic material data, the physical property data of the printed matter can also be obtained, such as surface roughness, thickness uniformity, etc. These data can be collected by tactile sensors, laser rangefinders and other devices. When obtaining image data and environmental data, in addition to image data and environmental data, sound data, temperature data, etc. can also be obtained. These data can be collected by microphones, thermal imagers and other devices. In the preprocessing process, a multimodal data fusion algorithm is introduced to fuse different types of detection data to generate comprehensive feature data. For example, image data and temperature data are fused to generate thermal image data for detecting the temperature distribution of printed matter. In the clarity feature extraction, a multimodal feature extraction algorithm is introduced to comprehensively utilize image data and other types of data to extract richer feature information. For example, the vibration characteristics of the printed matter are extracted in combination with image data and sound data to detect the stability of the printed matter. In the feature extraction of text data, a multimodal feature extraction algorithm is introduced to comprehensively utilize image data and other types of data to extract more accurate text features. For example, by combining image data and sound data, the sound features of printed products are extracted to detect the integrity of printed products. In the training process of the quality detection model, a multimodal data fusion strategy is introduced to take different types of detection data as input to generate a more comprehensive feature vector. For example, image data, temperature data, sound data, etc. are used as input to train a multimodal quality detection model. By introducing multimodal data fusion technology, the embodiment of the present application can make full use of various types of detection data and improve the comprehensive performance of detection. Compared with the detection method of a single data source, multimodal data fusion can provide richer and more comprehensive information, which helps to more accurately identify quality problems of printed products. Especially in complex and changeable production environments, multimodal data fusion technology can effectively improve the reliability and accuracy of detection, reduce the error rate, and improve production efficiency.

[0148] In another embodiment, to enable remote management and maintenance of the printed product quality inspection system, the present embodiment may also incorporate remote monitoring and fault diagnosis capabilities. Specifically, these capabilities include: receiving material data from users via a cloud platform, enabling users to upload material data via mobile apps, web pages, and other methods. Using wireless transmission technology, image data and environmental data are transmitted to a cloud server in real time, enabling remote monitoring and data analysis. Image data is preprocessed on the cloud server, leveraging powerful computing resources to improve preprocessing speed and accuracy. Using the cloud computing platform, distributed computing technology is utilized to accelerate the extraction of visual feature data, improving inspection efficiency. Using the cloud computing platform, distributed computing technology is utilized to accelerate the extraction of content feature data, improving inspection efficiency. Using the cloud computing platform, distributed computing technology is utilized to accelerate the training and inference of quality inspection models, improving inspection accuracy. Users are supported to view inspection results in real time via mobile apps, web pages, and other methods, supporting historical data query and statistical analysis. The cloud platform monitors the operating status of the inspection system in real time, enabling remote fault diagnosis and repair guidance. A fault warning function is provided to promptly notify users of any anomalies in the inspection system and provide solutions. By introducing remote monitoring and fault diagnosis capabilities, the embodiments of this application enable remote management and maintenance of the printed product quality inspection system, improving system availability and reliability. Especially on large-scale production lines, remote monitoring and fault diagnosis capabilities can promptly identify and resolve problems, reducing downtime and improving production efficiency. Furthermore, through the support of a cloud computing platform, this embodiment can fully utilize powerful computing resources, improving the speed and accuracy of inspections and meeting the needs of large-scale production.

[0149] In another embodiment, to achieve seamless integration between printed product quality inspection and production, the present application may also incorporate automated production line integration technology. Specifically, this includes: Automatically acquiring printed product material data through sensors on the production line, eliminating the need for manual intervention and improving data acquisition efficiency. Automatically acquiring image and environmental data through image acquisition and environmental acquisition devices on the production line, supporting high-speed, continuous acquisition. Preprocessing image data within the production line's embedded system, utilizing high-performance hardware accelerators, improves preprocessing speed and accuracy. Accelerating the extraction of visual feature data through the production line's embedded system, utilizing high-performance hardware accelerators, improves inspection efficiency. Accelerating the extraction of content feature data through the production line's embedded system, utilizing high-performance hardware accelerators, improves inspection efficiency. Accelerating the training and inference of quality inspection models through the production line's embedded system, utilizing high-performance hardware accelerators, improves inspection accuracy. Real-time feedback of inspection results to the production line control system supports automated decision-making and control, such as automatic rejection of defective products and automatic adjustment of the production line. Standardized interfaces and protocols enable seamless integration of the quality inspection system and the production line, supporting plug-and-play. Supporting modular design of the production line allows for flexible configuration and expansion according to actual needs, improving the system's adaptability and flexibility. By introducing automated production line integration technology, the embodiments of this application enable seamless integration of printed product quality testing and production, improving testing efficiency and accuracy. Especially on large-scale production lines, automated production line integration technology enables automated management of the entire process, reducing manual intervention and improving production efficiency. Furthermore, through the support of standardized interfaces and protocols, this embodiment can be easily integrated with other production equipment and systems to form a complete production chain, enhancing the intelligence level of the entire production system.

[0150] The present application also provides a printed matter quality detection device, referring to Figure 1 , comprising a processor 1, the processor 1 being configured to execute a printed matter quality detection method:

[0151] S1. Obtain material data of the printed product to be tested.

[0152] S2. Acquire image data of the printed product to be tested acquired by the image acquisition device and environmental data acquired by the environment acquisition device.

[0153] S3. Preprocess the image data according to the material data and the environment data.

[0154] S4. Obtain visual feature data of the preprocessed image data.

[0155] S5, obtaining content feature data of the pre-processed image data,

[0156] S6. Obtaining a quality inspection result of the printed product to be inspected based on the visual feature data and the content feature data of the image data.

[0157] The printed product quality inspection device of the embodiment of the present application further includes an image acquisition device 2 and an environment acquisition device 3. The image acquisition device 2 is used to capture image data of the printed product to be tested and upload it to the processor 1, while the environment acquisition device 3 is used to capture environmental data and upload it to the processor 1. In a specific implementation, the image acquisition device 2 can be a high-resolution camera, such as a CCD or CMOS camera, for capturing high-definition images of the printed product. The environment acquisition device 3 can be a sensor such as a temperature and humidity sensor or a light intensity sensor, which is used to record the conditions of the testing environment. This data helps eliminate external interference and improves detection accuracy.

[0158] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by the processor 1, the following steps are implemented:

[0159] S1. Obtain material data of the printed product to be tested.

[0160] S2. Acquire image data of the printed product to be tested acquired by the image acquisition device and environmental data acquired by the environment acquisition device.

[0161] S3. Preprocess the image data according to the material data and the environment data.

[0162] S4. Obtain visual feature data of the preprocessed image data.

[0163] S5, obtaining content feature data of the pre-processed image data,

[0164] S6. Obtaining a quality inspection result of the printed product to be inspected based on the visual feature data and the content feature data of the image data.

[0165] When executing the computer program, the processor can also execute the steps of the printed product quality detection method in any of the above embodiments.

[0166] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0167] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0168] The examples of this specific embodiment are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Identical components are represented by the same reference numerals. Therefore, any equivalent changes made based on the structure, shape, and principle of this application should be included in the scope of protection of this application.

Claims

1. A method for detecting the quality of printed matter, characterized in that: include: Obtain material data of the printed product to be tested; The material data includes paper type, coating information and thickness; Acquiring image data of the printed product to be tested acquired by an image acquisition device and environmental data acquired by an environmental acquisition device; Preprocess the image data according to material data and environment data; Acquiring visual feature data of the preprocessed image data, wherein the visual feature data includes at least a print clarity feature, a color consistency feature, and a contrast feature; Acquiring content feature data of the pre-processed image data, wherein the content feature data includes one or more of printed text data features, pattern data features, and barcode data features; Obtaining a quality inspection result of the printed product to be tested based on the visual feature data and content feature data of the image data; The acquisition of visual feature data of the pre-processed image data further includes contrast feature extraction, specifically including: Obtaining a grayscale histogram of the image data to obtain the grayscale distribution of the image data; The maximum contrast of the image data is obtained according to the grayscale difference between the brightest and darkest pixels in the grayscale distribution of the image data; The contrast ratio of the image data is obtained according to the ratio of the maximum grayscale value to the minimum grayscale value in the grayscale distribution of the image data; According to the grayscale difference between adjacent areas in the grayscale distribution of the image data, a local contrast enhancement algorithm is used to obtain the enhanced local contrast of the image data; The maximum contrast, contrast ratio and local contrast are input into a pre-built color contrast evaluation model to obtain the contrast characteristics of the image data.

2. A printed matter quality detection method according to claim 1, characterized in that: The obtaining of visual feature data of the pre-processed image data includes extracting clarity features, specifically comprising: Identify the edge clarity of image data using edge detection algorithms; Comparing the image data with the standard image data to obtain a structural similarity index; The edge clarity and structural similarity index are input into a pre-built clarity assessment model to obtain the clarity features of the image data.

3. A printed matter quality detection method according to claim 2, characterized in that: The acquisition of visual feature data of the pre-processed image data further includes color consistency feature extraction, specifically including: Acquiring color spectrum data of the image data by a color measurement device; Convert color spectrum data to a standard color space; Calculate the color difference between the color spectrum data and the standard color spectrum data using the color difference formula; The color difference values ​​are input into a pre-built color consistency evaluation model to obtain the color consistency features of the image data.

4. A printed matter quality inspection method according to claim 1, characterized in that: The obtaining of content feature data of the pre-processed image data specifically includes: Determine whether there is text data, pattern data or barcode data through image recognition algorithm; When text data exists, the integrity, clarity and accuracy of the text data are automatically identified through an optical character recognition algorithm to obtain text data features; When pattern data exists, identifying and verifying the integrity, clarity and accuracy of the pattern to obtain pattern data features; When barcode data exists, the readability of the barcode data is identified by barcode recognition software to obtain barcode data features.

5. A printed matter quality inspection method according to claim 4, characterized in that: The obtaining of content feature data of the pre-processed image data further includes: The image data is compared with the standard template through template matching technology to determine whether the printed content on the image data is located in the correct position and obtain position feature data.

6. A printed matter quality detection method according to any one of claims 1 to 5, characterized in that: Obtaining a quality inspection result of the printed product to be tested based on the visual feature data and the content feature data of the image data includes: Construct an initial quality inspection model and configure model parameters of the initial quality inspection model; Obtain visual feature samples, content feature samples, and corresponding quality inspection result samples of different printed products to be tested in a quality inspection database, wherein the quality inspection result samples include normal quality inspection samples and abnormal quality inspection samples; Constructing visual feature samples, content feature samples and corresponding quality inspection result samples of different printed products to be tested into a quality inspection sample set; The initial quality detection model is trained according to the quality detection sample set to obtain a trained quality detection model; The visual feature data and content feature data of the image data are input into the trained quality detection model to obtain the quality detection results of the image data.

7. A printed matter quality inspection method according to claim 6, characterized in that: The training of the initial quality detection model according to the quality detection sample set to obtain the trained quality detection model specifically includes: The quality inspection sample set is divided into a quality inspection training set and a quality inspection test set, and the number of training rounds is preset; Input the quality inspection training set into the quality inspection initial model and train it according to the preset number of training rounds; When the initial quality inspection model reaches the preset number of training rounds, the trained quality inspection model is obtained; Input the visual feature samples and content feature samples in the quality detection test set into the trained quality detection model to obtain the quality detection result prediction samples; The model parameters of the quality detection model are adjusted according to the quality detection result samples in the test set and the corresponding quality detection result prediction samples, and the trained quality detection model is obtained according to the adjusted model parameters.

8. A printed matter quality inspection device, characterized in that: comprising a processor, the processor being configured to execute a printed matter quality detection method according to any one of claims 1 to 7; It also includes an image acquisition device and an environment acquisition device. The image acquisition device is used to acquire image data of the printed product to be tested and upload it to the processor, and the environment acquisition device is used to acquire environmental data and upload it to the processor.

9. A computer-readable storage medium, characterized in that A computer program is stored which can be loaded by a processor and executes a printed product quality detection method according to any one of claims 1 to 7.

Images