Anti-counterfeiting packaging box printing image defect detection system and method
By introducing synchronous control and multi-dimensional detection modules into the anti-counterfeiting packaging box printing image defect detection system, the problem of incomplete detection in the existing technology is solved, high-precision and accurate detection results are achieved, and the anti-counterfeiting effect and production quality management are improved.
Patent Information
- Application Number
- CN202510971310.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-15
- Publication Date
- 2025-09-12
AI Technical Summary
The existing anti-counterfeiting packaging box printing image defect detection system has difficulty in achieving synchronous high-precision detection of the pattern areas on the front and back surfaces of the anti-counterfeiting packaging box. It is unable to comprehensively consider the offset, color deviation, surface flatness and laser pattern integrity of the printed pattern, resulting in inaccurate and incomplete detection results, and is prone to defect omission or misjudgment.
The data processing and collaborative control module is adopted to coordinate the working timing of multiple detection modules through the synchronous control unit. Combined with high-precision clock synchronization technology, a trigger signal is generated to achieve synchronous detection of the pattern areas on the front and back surfaces of the anti-counterfeiting packaging box. The multi-dimensional detection module is used to identify the offset of the printed pattern, evaluate the surface flatness and the integrity of the laser pattern, and use the data processing unit to perform data preprocessing and quantitative analysis, and establish a comprehensive evaluation model for final judgment.
It realizes multi-dimensional detection of anti-counterfeiting packaging boxes, significantly improves the accuracy of detection, reduces missed defects and misjudgments, ensures the anti-counterfeiting effect, provides accurate quality feedback, and helps enterprises optimize production processes and quality control.
Smart Images
Figure CN120629175A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of printed image defect detection, and more particularly to a system and method for detecting printed image defects in an anti-counterfeiting packaging box. Background Art
[0002] In the field of commodity anti-counterfeiting, the printing quality of anti-counterfeiting packaging boxes is of vital importance. The integrity and accuracy of the printed image on its surface directly affect the anti-counterfeiting effect and product image. However, existing anti-counterfeiting packaging box printing image defect detection systems have significant shortcomings. Most traditional detection systems have difficulty in achieving simultaneous high-precision detection of the pattern areas on the front and back surfaces of anti-counterfeiting packaging boxes. In addition, during the detection process, they are unable to comprehensively consider multi-dimensional information such as the offset, color deviation, surface flatness, and laser pattern integrity of the printed pattern, resulting in inaccurate and incomplete detection results. Defects are easily missed or misjudged, making it difficult to meet the increasingly stringent quality inspection requirements for anti-counterfeiting packaging boxes. In view of this, we propose a system and method for detecting printed image defects on anti-counterfeiting packaging boxes. Summary of the Invention
[0003] The purpose of the present invention is to provide a system and method for detecting defects in printed images of anti-counterfeiting packaging boxes, so as to solve the technical problem that the existing system for detecting defects in printed images of anti-counterfeiting packaging boxes does not fully detect defects and affects the anti-counterfeiting effect.
[0004] To solve the above technical problems, the present invention provides the following technical solutions: a system for detecting printed image defects on anti-counterfeiting packaging boxes, comprising a first detection module, a second detection module, a third detection module, and a data processing and collaborative control module; The data processing and collaborative control module has a built-in synchronization control unit and a data processing unit. The synchronization control unit is used to coordinate the working sequence of the first, second, and third detection modules to achieve synchronous detection of the pattern areas on the front and back surfaces of the anti-counterfeiting packaging box. The data processing unit is used to receive the data collected by each detection module, and after pre-processing and quantitative analysis, provide data support for defect judgment; The first detection module includes an image acquisition unit and a scratch detection unit. The image acquisition unit captures images of both the front and back of the anti-counterfeiting packaging box. The scratch detection unit identifies the offset value of the actual contour information of the printed pattern through image feature matching and determines the surface scratch condition based on the image texture change. The second detection module consists of a surface image acquisition unit and a color detection unit. The surface image acquisition unit collects the surface image of the packaging box in real time to evaluate the surface flatness. The color detection unit collects the color data of the printed pattern and compares and analyzes it to obtain the color deviation value. The third detection module uses multi-angle optical acquisition equipment to collect the reflection and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtains the integrity of the laser pattern by comparing and analyzing it with the standard information.
[0005] Preferably, the synchronization control unit adopts high-precision clock synchronization technology to generate trigger signals for each module based on a preset detection beat; After receiving the data collected by the three detection modules, the data processing unit uses normalization processing to clean and standardize the original data, and then performs unified data quantification processing and analysis on the data through a customized quantitative analysis model.
[0006] Preferably, the image acquisition unit of the first detection module uses an industrial camera array to capture images of both the front and back sides of the anti-counterfeiting packaging box to obtain comprehensive image data; The scratch detection unit rotates the anti-counterfeiting package box 90 degrees and collects the surface pattern again. It then uses an image feature matching algorithm to identify the offset value of the printed pattern on the surface of the anti-counterfeiting package box. At the same time, by analyzing the texture changes of the two collected images, a texture change threshold is set. When the change exceeds the threshold, it is determined that the surface of the anti-counterfeiting package box is scratched. The offset value acquisition process of the printed pattern on the surface of the anti-counterfeiting packaging box is as follows: the data processing unit of the data processing and coordinated control module obtains the surface image contour of the anti-counterfeiting packaging box, first uses the edge detection algorithm to extract the contour features, and then uses the contour matching algorithm to match the surface image contour of the anti-counterfeiting packaging box with the pre-stored actual contour of the anti-counterfeiting packaging box; Assume that the coordinates of the key points of the actual contour of the anti-counterfeiting packaging box are , the coordinates of the key points corresponding to the surface image contour are , , then the contour information of each surface printed pattern is offset from the actual contour information of the anti-counterfeiting packaging box The calculation formula is: .
[0007] Preferably, the surface image acquisition unit of the second detection module acquires real-time images of the surface of the anti-counterfeiting packaging box through a high-resolution image acquisition device equipped with a megapixel lens; The color detection unit uses a spectrum acquisition technology with a spectral resolution of 1nm to collect color data of the printed pattern image of the anti-counterfeiting packaging box, achieving high-precision color information acquisition; The data processing and collaborative control module performs image feature recognition and matching on the image transmitted by the surface image acquisition unit and the qualified packaging box image template stored in the system, obtains the image feature matching value, and outputs the flatness value of the anti-counterfeiting packaging box surface through the pre-established flatness evaluation model based on the image feature matching value. .
[0008] Preferably, the image color data collected by the color detection unit is compared with the color information in the qualified anti-counterfeiting packaging box image template, and a color deviation analysis algorithm based on the CIE color space is used to output the color deviation value of the anti-counterfeiting packaging box printing pattern, wherein the data processing and collaborative control module collects the color information of the pattern image printed on the surface of the anti-counterfeiting packaging box, and converts the collected color information from the RGB color space to the CIELab color space; Then, according to the importance of each area of the image, different weight coefficients are set , perform weighted average of the information deviation values of each area of the image to obtain the color deviation value of the pattern image printed on the surface of the anti-counterfeiting packaging box .
[0009] Preferably, the multi-angle optical acquisition device of the third detection module includes at least three optical acquisition lenses at different angles, which are used to collect the reflection surface information and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtain complete information of the laser pattern from multiple angles; The data processing and collaborative control module compares the collected information with the laser pattern information collected from the qualified anti-counterfeiting packaging box pre-stored in the system under the same detection position and conditions, obtains the laser pattern information deviation distance value, and obtains the laser pattern integrity evaluation model based on the laser pattern information deviation distance value. .
[0010] Preferably, the method for detecting defects in the laser pattern of the pattern printed on the surface of the anti-counterfeiting packaging box is specifically as follows: the data processing unit of the data processing and collaborative control module collects the reflective surface information of the laser pattern printed on the surface of the anti-counterfeiting packaging box and the refractive surface information of the laser pattern printed on the surface of the anti-counterfeiting packaging box, and uses the formula according to the reflective surface information of the laser pattern printed on the surface of the anti-counterfeiting packaging box and the refractive surface information of the laser pattern printed on the surface of the anti-counterfeiting packaging box. Get the laser pattern refraction effect difference parameters ,in, It is the average brightness difference of the reflective surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box, calculated by statistical analysis of the grayscale value of the reflective surface image. It is the average brightness difference of the refractive surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box, calculated by statistical analysis of the grayscale values of the refractive surface image.
[0011] Preferably, the laser pattern information of the anti-counterfeiting packaging box surface printing pattern collected in the laser pattern defect detection method is the refractive surface and reflective surface information of the laser pattern, and the laser pattern information of the anti-counterfeiting packaging box surface printing pattern is positively correlated with the reflective surface and refractive surface information in the laser pattern information of the anti-counterfeiting packaging box surface printing pattern, respectively. The data processing unit of the data processing and collaborative control module processes the laser pattern refraction effect difference parameter according to the laser pattern refraction effect difference parameter. Combined with the completeness of laser pattern information ,Use the comprehensive defect evaluation algorithm to comprehensively evaluate the defect degree of the laser pattern.
[0012] Preferably, the image defect detection result of the anti-counterfeiting packaging box printing is obtained by the actual contour information offset value of the pattern printed on the surface of the anti-counterfeiting packaging box. , Color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box The integrity of the laser pattern information printed on the surface of the anti-counterfeiting packaging box together constitute; The data processing unit of the data processing and collaborative control module establishes a comprehensive evaluation model based on the hierarchical analysis method. According to the degree of influence of each parameter on product quality, different weight coefficients are determined. The weight coefficients of the actual contour information offset value of the pattern printed on the surface of the anti-counterfeiting packaging box, the color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box, and the laser pattern information completeness of the laser pattern information printed on the surface of the anti-counterfeiting packaging box are respectively 、 、 ,and , then the final image defect detection result .
[0013] A method for detecting printing image defects on an anti-counterfeiting packaging box uses a printing image defect detection system for an anti-counterfeiting packaging box. The system is used for detecting printing image defects on an anti-counterfeiting packaging box.
[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention adopts high-precision clock synchronization technology through the synchronization control unit in the data processing and collaborative control module to coordinate the working timing of the first detection module, the second detection module and the third detection module, and generates a trigger signal for each module based on a preset detection rhythm, so that the three detection modules can synchronously detect the front surface pattern area and the back surface pattern area of the anti-counterfeiting packaging box. At the same time, the data processing unit uses a variety of data preprocessing algorithms and customized quantitative analysis models to uniformly process and analyze the collected data, effectively solving the problem that traditional systems cannot synchronize high-precision detection, significantly improving the accuracy of detection, and reducing the cases of missed defect detection and misjudgment.
[0015] 2. The present invention includes multiple detection modules with different functions. The first detection module can identify the offset value of the printed pattern and determine the surface scratch condition. The second detection module can evaluate the surface flatness and obtain the color deviation value. The third detection module can analyze the integrity of the laser pattern. By performing multi-dimensional detection and analysis on the printed image on the surface of the anti-counterfeiting packaging box, the key factors affecting the anti-counterfeiting effect are comprehensively covered, ensuring that the various quality indicators of the anti-counterfeiting packaging box meet the requirements, effectively guaranteeing the anti-counterfeiting effect, and further solving the problem that the traditional system detection is not comprehensive and affects the anti-counterfeiting effect.
[0016] 3. The data processing and collaborative control module of the present invention establishes a comprehensive evaluation model based on the hierarchical analysis method, determines different weight coefficients according to the degree of influence of each detection parameter on product quality, performs weighted calculations on parameters such as pattern information offset value, color deviation information and laser pattern integrity, and outputs the final image defect detection results. This scientific evaluation method can provide accurate and quantitative quality feedback for production companies, help companies adjust production processes in a timely manner, optimize production quality control processes, and further improve production efficiency and product quality on the basis of ensuring anti-counterfeiting effects, thereby realizing refined management of the production process. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION
[0018] To facilitate those skilled in the art to understand the technical solution of the present invention, the technical solution of the present invention is further described with reference to the accompanying drawings.
[0019] Example 1, as Figure 1 As shown, the present invention provides an anti-counterfeiting packaging box printing image defect detection system, including a first detection module, a second detection module, a third detection module and a data processing and collaborative control module; The data processing and collaborative control module has a built-in synchronization control unit and a data processing unit. The synchronization control unit is used to coordinate the working sequence of the first, second, and third detection modules to achieve synchronous detection of the pattern areas on the front and back surfaces of the anti-counterfeiting packaging box. The data processing unit is used to receive the data collected by each detection module, and after pre-processing and quantitative analysis, provide data support for defect judgment; The first detection module includes an image acquisition unit and a scratch detection unit. The image acquisition unit captures images of both the front and back of the anti-counterfeiting packaging box. The scratch detection unit identifies the offset value of the actual contour information of the printed pattern through image feature matching and determines the surface scratch condition based on the image texture change. The second detection module consists of a surface image acquisition unit and a color detection unit. The surface image acquisition unit collects the surface image of the packaging box in real time to evaluate the surface flatness. The color detection unit collects the color data of the printed pattern and compares and analyzes it to obtain the color deviation value. The third detection module uses multi-angle optical acquisition equipment to collect the reflection and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtains the integrity of the laser pattern by comparing and analyzing it with the standard information.
[0020] In an embodiment of the present invention, the synchronization control unit uses high-precision clock synchronization technology to generate trigger signals for each module based on a preset detection beat. In this way, the three detection modules can synchronously detect the patterned areas on the front and back surfaces of the anti-counterfeiting packaging box, ensuring efficient coordination of the detection work. After receiving the data collected by the three detection modules, the data processing unit uses normalization processing to clean and standardize the original data. Then, it uses the customized quantitative analysis model to perform unified data quantification processing and analysis on the data. In the specific quantification process, the collected data is assumed to be , the data after normalization The calculation formula is: ; in, and The original data The minimum and maximum values in the data are processed by the above formula, and then subsequent filtering, noise reduction and other quantitative analysis are performed to provide an accurate data basis for subsequent defect judgment.
[0021] In an embodiment of the present invention, the image acquisition unit of the first detection module uses an industrial camera array to capture images of both the front and back sides of the anti-counterfeiting packaging box to obtain comprehensive image data; The scratch detection unit rotates the anti-counterfeiting package box 90 degrees and collects the surface pattern again. It then uses an image feature matching algorithm to identify the offset value of the printed pattern on the surface of the anti-counterfeiting package box. At the same time, by analyzing the texture changes of the two collected images, a texture change threshold is set. When the change exceeds the threshold, it is determined that the surface of the anti-counterfeiting package box is scratched. The offset value acquisition process of the printed pattern on the surface of the anti-counterfeiting packaging box is as follows: the data processing unit of the data processing and coordinated control module obtains the surface image contour of the anti-counterfeiting packaging box, first uses the edge detection algorithm to extract the contour features, and then uses the contour matching algorithm to match the surface image contour of the anti-counterfeiting packaging box with the pre-stored actual contour of the anti-counterfeiting packaging box; Assume that the coordinates of the key points of the actual contour of the anti-counterfeiting packaging box are , the coordinates of the key points corresponding to the surface image contour are , , then the contour information of each surface printed pattern is offset from the actual contour information of the anti-counterfeiting packaging box The calculation formula is: .
[0022] In an embodiment of the present invention, the surface image acquisition unit of the second detection module performs real-time image acquisition of the surface of the anti-counterfeiting packaging box through a high-resolution image acquisition device equipped with a megapixel lens, with an acquisition frequency of not less than 20 frames per second to ensure the real-time and accuracy of the image; The color detection unit uses a spectrum acquisition technology with a spectral resolution of 1nm to collect color data of the printed pattern image of the anti-counterfeiting packaging box, achieving high-precision color information acquisition; The data processing and collaborative control module performs image feature recognition and matching on the image transmitted by the surface image acquisition unit and the qualified packaging box image template stored in the system, obtains the image feature matching value, and outputs the flatness value of the anti-counterfeiting packaging box surface through the pre-established flatness evaluation model based on the image feature matching value. ; Assume that the feature point set in the qualified packaging box image template is , the corresponding feature point set in the collected image is The coordinates of the feature points are and , first calculate the distance deviation of each feature point pair : ; Then calculate the surface flatness value by the distance deviation of all feature point pairs , using the weighted average method, the weight of each feature point is set to ,and , then the calculation formula of the leveling value is: ; At the same time, the image color data collected by the color detection unit is compared with the color information in the qualified anti-counterfeiting packaging box image template, and the color deviation analysis algorithm based on the CIE color space is used to output the color deviation value of the anti-counterfeiting packaging box printing pattern. Among them, the data processing and collaborative control module collects the color information of the pattern image printed on the surface of the anti-counterfeiting packaging box and converts the collected color information from the RGB color space to the CIELab color space; Assume that the standard color information in the CIELab color space coordinates is , the color information coordinates are collected as , then the information deviation value of the image The calculation formula is: ; in, , , ; Then, according to the importance of each area of the image, different weight coefficients are set , perform weighted average of the information deviation values of each area of the image to obtain the color deviation value of the pattern image printed on the surface of the anti-counterfeiting packaging box , and its calculation formula is: , and the color deviation value of the pattern image printed on the surface of the anti-counterfeiting packaging box is proportional to the information deviation value of the pattern image printed on the surface of the anti-counterfeiting packaging box.
[0023] In an embodiment of the present invention, the multi-angle optical acquisition device of the third detection module includes at least three optical acquisition lenses at different angles, which are used to collect the reflection surface information and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtain complete information of the laser pattern from multiple angles; The data processing and collaborative control module compares the collected information with the laser pattern information collected from the qualified anti-counterfeiting packaging box pre-stored in the system under the same detection position and conditions, obtains the laser pattern information deviation distance value, and obtains the laser pattern integrity evaluation model based on the laser pattern information deviation distance value. ; Assume that the coordinates of the key points of the standard laser pattern information are , the key point coordinates corresponding to the collected laser pattern information are , then the laser pattern information deviation distance value The calculation formula is: ; Laser pattern information completeness Apply the completeness assessment formula Calculated, where is the maximum allowable deviation distance value, and outputs the integrity of the laser pattern information printed on the surface of the anti-counterfeiting packaging box according to the integrity of the laser pattern information; The method for detecting defects in laser patterns of patterns printed on the surface of anti-counterfeiting packaging boxes is specifically as follows: a data processing unit of a data processing and collaborative control module collects information on the reflective surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box, and information on the refractive surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box; and a formula is used based on the information on the reflective surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box and the refractive surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box. Get the laser pattern refraction effect difference parameters ,in, It is the average brightness difference of the reflective surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box, calculated by statistical analysis of the grayscale value of the reflective surface image. The average brightness difference of the refraction surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box is calculated by statistical analysis of the grayscale value of the refraction surface image; Assume that the grayscale value of the reflection surface image pixel is , its average gray value The calculation formula is ; The grayscale value of the refraction surface image pixel is , its average gray value The calculation formula is ; but , ,in, and are the average grayscale reference values of the standard reflective surface and refractive surface respectively; The laser pattern information of the anti-counterfeiting packaging box surface printing pattern collected in the laser pattern defect detection method is the refraction surface and reflection surface information of the laser pattern, and the laser pattern information of the anti-counterfeiting packaging box surface printing pattern is positively correlated with the reflection surface and refraction surface information in the laser pattern information of the anti-counterfeiting packaging box surface printing pattern, respectively. The data processing unit of the data processing and collaborative control module is based on the laser pattern refraction effect difference parameter. Combined with the completeness of laser pattern information ,Use the comprehensive defect evaluation algorithm to comprehensively evaluate the defect degree of the laser pattern.
[0024] In an embodiment of the present invention, the image defect detection result of the anti-counterfeiting packaging box printing is obtained by offsetting the actual contour information of the pattern printed on the surface of the anti-counterfeiting packaging box. , Color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box The integrity of the laser pattern information printed on the surface of the anti-counterfeiting packaging box together constitute; The data processing unit of the data processing and collaborative control module establishes a comprehensive evaluation model based on the hierarchical analysis method. According to the degree of influence of each parameter on product quality, different weight coefficients are determined. The weight coefficients of the actual contour information offset value of the pattern printed on the surface of the anti-counterfeiting packaging box, the color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box, and the laser pattern information completeness of the laser pattern information printed on the surface of the anti-counterfeiting packaging box are respectively 、 、 ,and , then the final image defect detection result .
[0025] Embodiment 2: A method for detecting printed image defects on an anti-counterfeiting packaging box uses a printed image defect detection system for an anti-counterfeiting packaging box. The system is used for detecting printed image defects on an anti-counterfeiting packaging box.
[0026] The embodiments disclosed in the present invention are preferred embodiments, but are not limited to them. Ordinary technicians in this field can easily understand the spirit of the present invention based on the above embodiments and make different extensions and changes. As long as they do not deviate from the spirit of the present invention, they are all within the scope of protection of the present invention.
Claims
1. A system for detecting defects in printed images of anti-counterfeiting packaging boxes, characterized in that: It includes a first detection module, a second detection module, a third detection module and a data processing and collaborative control module; The data processing and collaborative control module has a built-in synchronization control unit and a data processing unit. The synchronization control unit is used to coordinate the working sequence of the first, second, and third detection modules to achieve synchronous detection of the pattern areas on the front and back surfaces of the anti-counterfeiting packaging box. The data processing unit is used to receive the data collected by each detection module, and after pre-processing and quantitative analysis, provide data support for defect judgment; The first detection module includes an image acquisition unit and a scratch detection unit. The image acquisition unit captures images of both the front and back of the anti-counterfeiting packaging box. The scratch detection unit identifies the offset value of the actual contour information of the printed pattern through image feature matching and determines the surface scratch condition based on the image texture change. The second detection module consists of a surface image acquisition unit and a color detection unit. The surface image acquisition unit collects the surface image of the packaging box in real time to evaluate the surface flatness. The color detection unit collects the color data of the printed pattern and compares and analyzes it to obtain the color deviation value. The third detection module uses multi-angle optical acquisition equipment to collect the reflection and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtains the integrity of the laser pattern by comparing and analyzing it with the standard information.
2. The anti-counterfeiting packaging box printing image defect detection system according to claim 1, characterized in that: The synchronization control unit adopts high-precision clock synchronization technology to generate trigger signals for each module based on a preset detection beat; After receiving the data collected by the three detection modules, the data processing unit uses normalization processing to clean and standardize the original data, and then performs unified data quantification processing and analysis on the data through a customized quantitative analysis model.
3. The anti-counterfeiting packaging box printing image defect detection system according to claim 2, characterized in that: The image acquisition unit of the first detection module uses an industrial camera array to capture images of both the front and back sides of the anti-counterfeiting packaging box to obtain comprehensive image data; The scratch detection unit rotates the anti-counterfeiting package box 90 degrees and collects the surface pattern again. It then uses an image feature matching algorithm to identify the offset value of the printed pattern on the surface of the anti-counterfeiting package box. At the same time, by analyzing the texture changes of the two collected images, a texture change threshold is set. When the change exceeds the threshold, it is determined that the surface of the anti-counterfeiting package box is scratched. The offset value acquisition process of the printed pattern on the surface of the anti-counterfeiting packaging box is as follows: the data processing unit of the data processing and coordinated control module obtains the surface image contour of the anti-counterfeiting packaging box, first uses the edge detection algorithm to extract the contour features, and then uses the contour matching algorithm to match the surface image contour of the anti-counterfeiting packaging box with the pre-stored actual contour of the anti-counterfeiting packaging box; Assume that the coordinates of the key points of the actual contour of the anti-counterfeiting packaging box are , the coordinates of the key points corresponding to the surface image contour are , , then the contour information of each surface printed pattern is offset from the actual contour information of the anti-counterfeiting packaging box The calculation formula is: .
4. The anti-counterfeiting packaging box printing image defect detection system according to claim 3, characterized in that: The surface image acquisition unit of the second detection module acquires real-time images of the surface of the anti-counterfeiting packaging box through a high-resolution image acquisition device equipped with a megapixel lens; The color detection unit uses a spectrum acquisition technology with a spectral resolution of 1nm to collect color data of the printed pattern image of the anti-counterfeiting packaging box, achieving high-precision color information acquisition; The data processing and collaborative control module performs image feature recognition and matching on the image transmitted by the surface image acquisition unit and the qualified packaging box image template stored in the system, obtains the image feature matching value, and outputs the flatness value of the anti-counterfeiting packaging box surface through the pre-established flatness evaluation model based on the image feature matching value. .
5. The anti-counterfeiting packaging box printing image defect detection system according to claim 4, characterized in that: The image color data collected by the color detection unit is compared with the color information in the qualified anti-counterfeiting packaging box image template, and the color deviation value of the anti-counterfeiting packaging box printing pattern is output using the color deviation analysis algorithm based on the CIE color space. Among them, the data processing and collaborative control module collects the color information of the pattern image printed on the surface of the anti-counterfeiting packaging box and converts the collected color information from the RGB color space to the CIELab color space; Then, according to the importance of each area of the image, different weight coefficients are set , perform weighted average of the information deviation values of each area of the image to obtain the color deviation value of the pattern image printed on the surface of the anti-counterfeiting packaging box .
6. The anti-counterfeiting packaging box printing image defect detection system according to claim 5, characterized in that: The multi-angle optical acquisition device of the third detection module includes at least three optical acquisition lenses at different angles, which are used to collect the reflection surface information and refraction surface information of the laser pattern on the surface of the anti-counterfeiting packaging box, and obtain complete information of the laser pattern from multiple angles; The data processing and collaborative control module compares the collected information with the laser pattern information collected from the qualified anti-counterfeiting packaging box pre-stored in the system under the same detection position and conditions, obtains the laser pattern information deviation distance value, and obtains the laser pattern integrity evaluation model based on the laser pattern information deviation distance value. .
7. The anti-counterfeiting packaging box printing image defect detection system according to claim 6, characterized in that: The method for detecting defects in laser patterns of patterns printed on the surface of anti-counterfeiting packaging boxes is specifically as follows: a data processing unit of a data processing and collaborative control module collects information on the reflective surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box, and information on the refractive surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box; and a formula is used based on the information on the reflective surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box and the refractive surface of the laser pattern printed on the surface of the anti-counterfeiting packaging box. Get the laser pattern refraction effect difference parameters ,in, It is the average brightness difference of the reflective surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box, calculated by statistical analysis of the grayscale value of the reflective surface image. It is the average brightness difference of the refraction surface in the laser pattern printed on the surface of the anti-counterfeiting packaging box, calculated by statistical analysis of the grayscale values of the refraction surface image.
8. The anti-counterfeiting packaging box printing image defect detection system according to claim 7, characterized in that: The laser pattern information of the anti-counterfeiting packaging box surface printing pattern collected in the laser pattern defect detection method is the refraction surface and reflection surface information of the laser pattern, and the laser pattern information of the anti-counterfeiting packaging box surface printing pattern is positively correlated with the reflection surface and refraction surface information in the laser pattern information of the anti-counterfeiting packaging box surface printing pattern, respectively. The data processing unit of the data processing and collaborative control module is based on the laser pattern refraction effect difference parameter. Combined with the completeness of laser pattern information ,Use the comprehensive defect evaluation algorithm to comprehensively evaluate the defect degree of the laser pattern.
9. The anti-counterfeiting packaging box printing image defect detection system according to claim 8, characterized in that: The image defect detection result of the anti-counterfeiting packaging box printing is obtained by the actual contour information offset value of the pattern printed on the surface of the anti-counterfeiting packaging box. , Color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box The integrity of the laser pattern information printed on the surface of the anti-counterfeiting packaging box together constitute; The data processing unit of the data processing and collaborative control module establishes a comprehensive evaluation model based on the hierarchical analysis method. According to the degree of influence of each parameter on product quality, different weight coefficients are determined. The weight coefficients of the actual contour information offset value of the pattern printed on the surface of the anti-counterfeiting packaging box, the color deviation value of the pattern printed on the surface of the anti-counterfeiting packaging box, and the laser pattern information completeness of the laser pattern information printed on the surface of the anti-counterfeiting packaging box are respectively 、 、 ,and , then the final image defect detection result .
10. A method for detecting defects in printed images of anti-counterfeiting packaging boxes, using the system for detecting defects in printed images of anti-counterfeiting packaging boxes according to claim 9, characterized in that: The system is used to detect printing image defects on anti-counterfeiting packaging boxes.