Printing content inspection method and system

Abstract

The embodiment of the invention provides a printing content inspection method and system, and the method comprises the steps: determining a standard feature based on a general feature and a special feature; the general feature is related to general printing content of the to-be-checked object, and the special feature is related to special printing content of the to-be-checked object; acquiring actual characteristics of the to-be-checked object, wherein the actual characteristics are related to actual printing contents of the to-be-checked object; and determining an inspection result of the printing content of the to-be-inspected object based on the actual features and the standard features.

Description

Technical Field

[0001] The present invention relates to the field of printing, and in particular to a printing content inspection method and system. Background Art

[0002] During the production process, many structural parts of audio or other products, especially key parts such as back panels and bases, often need to be printed with a variety of information related to product specifications and technical parameters. When the amount of information is dense and screen printing technology is used, the quality of printing often faces multiple challenges, such as missing content, insufficient font clarity, color deviation, and position offset.

[0003] At present, the main means of detecting printed content relies on manual labor, for example, by comparing the sealed sample with the printed drawing for verification, but the efficiency and accuracy of manual inspection are unstable.

[0004] Therefore, it is necessary to provide a printed content inspection method and system to better ensure the efficiency and accuracy of printed content inspection and reduce misjudgment. Summary of the invention

[0005] One or more embodiments of the present specification provide a printed content inspection method, which includes: determining standard features based on common features and special features; the common features are related to the common printed content of the object to be inspected, and the special features are related to the special printed content of the object to be inspected; obtaining actual features of the object to be inspected, and the actual features are related to the actual printed content of the object to be inspected; and determining the inspection results of the printed content of the object to be inspected based on the actual features and the standard features.

[0006] One or more embodiments of the present specification provide a printed content inspection system, which includes a first acquisition module, a second acquisition module and a determination module; wherein the first acquisition module is configured to determine standard features based on general features and special features; the general features are related to the general printed content of the object to be inspected, and the special features are related to the special printed content of the object to be inspected; the second acquisition module is configured to acquire actual features of the object to be inspected, and the actual features are related to the actual printed content of the object to be inspected; and the result determination module is configured to determine the inspection result of the printed content of the object to be inspected based on the actual features and the standard features.

[0007] One or more embodiments of the present specification provide a printed content inspection device, including a processor, wherein the processor is used to execute the printed content inspection method.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aforementioned printed content inspection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is a schematic diagram of an application scenario of a printed content inspection system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary module diagram of a printed content inspection system according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of a printed content inspection method according to some embodiments of this specification;

[0013] Figure 4 is a schematic diagram of a method for determining actual characteristics according to some embodiments of this specification;

[0014] Figure 5 It is a schematic diagram of a method for determining inspection results according to some embodiments of this specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 1 is a schematic diagram of an application scenario of a printed content inspection system according to some embodiments of this specification. The application scenario 100 of the printed content inspection system involved in the embodiments of this specification will be described in detail below. It should be noted that the following embodiments are only used to explain this application and do not constitute a limitation on this application.

[0020] like Figure 1 As shown, the application scenario 100 of the printed content inspection system may include an object to be inspected 110 , an acquisition device 120 , a processor 130 , and a user terminal 140 .

[0021] The object to be inspected 110 is an entity whose printed content needs to be inspected to see whether it meets the requirements.

[0022] In some embodiments, the object to be inspected may be a structural member corresponding to a certain batch of printing tasks. The structural member may be a product back panel and / or base, or other components that require printed content. Interface information, safety specification certification information, and other content may be printed on these structural members. When there is a lot of content, problems such as missing printing, misprinting, blurred fonts, printing color deviation, and printing content deviation may easily occur. The printed content inspection system may inspect the printed content of the batch of structural members to determine whether the printed content of the batch of structural members has the aforementioned problems.

[0023] The acquisition device 120 is a device for acquiring printed content. The printed content may include general printed content, dedicated printed content, and actual printed content. For detailed descriptions of general printed content, dedicated printed content, and actual printed content, please refer to this specification. Figure 3 Related description in .

[0024] In some embodiments, the acquisition device 120 may include but is not limited to an image acquisition device, a user input acquisition device, and the like.

[0025] The processor 130 can process data and / or information in the printed content inspection system 200. In some embodiments, the processor 130 can be a computer, a user console, a single processor or a processor group, etc. The processor group can be centralized or distributed. In some embodiments, the processor 120 can be implemented on a cloud platform.

[0026] In some embodiments, the processor 130 may include a memory. The memory is used to store data information during the operation of the printed content inspection system 200. For example, the stored data may include but is not limited to general features, special features, and actual features.

[0027] The user terminal 140 may refer to one or more terminal devices or software used by the user. In some embodiments, the user terminal 140 may be a mobile device such as a mobile phone, a tablet computer, a laptop computer, or any combination thereof. In some embodiments, the user terminal 140 may interact with other components of the printed content inspection system via a network. For example, the user terminal 140 may present data generated by the processor 130 to the user.

[0028] In some embodiments, the user terminal 140 may include a device for data collection. As an example only, the data collection device may include an image collection device, a file transmission device, etc. These devices may be independent devices or integrated into the aforementioned mobile devices such as mobile phones, tablet computers, and laptop computers. The user of the printed content inspection system may obtain an image of the object to be inspected 110 through the aforementioned data collection device, or upload files and / or data to the printed content inspection system.

[0029] The printed content inspection system involved in some embodiments of this specification can be applied to other scenarios that require printed content inspection, in addition to the above-mentioned scenario of structural component printed content inspection. For example, the printed content of objects including but not limited to packaging materials, labels, bills, certificates, etc. can be inspected. This specification takes structural component content inspection as an example to illustrate the application of the printed content inspection system.

[0030] It should be noted that the application scenario is provided only for the purpose of illustration and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or changes can be made according to the description of this specification. For example, the application scenario may also include a database. For another example, the application scenario may be implemented on other devices to achieve similar or different functions. However, changes and modifications will not deviate from the scope of this specification.

[0031] Figure 2 is an exemplary module diagram of a printed content inspection system according to some embodiments of the present specification.

[0032] In some embodiments, the printed content inspection system 200 may include a first acquisition module 210 , a second acquisition module 220 , and a result determination module 230 .

[0033] The first acquisition module 210 is configured to determine the standard features based on the general features and the special features; the general features are related to the general printed content of the object to be inspected, and the special features are related to the special printed content of the object to be inspected.

[0034] In some embodiments, the first acquisition module is further configured to determine the dedicated printed content of the object to be inspected based on the target printed content and the universal printed content of the object to be inspected; and determine the dedicated feature based on the dedicated printed content.

[0035] The second acquisition module 220 is configured to acquire actual features of the object to be inspected, where the actual features are related to actual printed content of the object to be inspected.

[0036] In some embodiments, the second acquisition module is further configured to determine the actual printed content and center point position of the object to be inspected based on scanning the object to be inspected; and determine the actual features based on the actual printed content and center point position.

[0037] The result determination module 230 is configured to determine the inspection result of the printed content of the object to be inspected based on the actual features and the standard features.

[0038] In some embodiments, the result determination module is further configured to determine difference information based on the actual features and the standard features; determine the inspection result based on the difference information and the qualified condition; wherein the qualified condition is related to the printing tolerance of the difference information.

[0039] In some embodiments, the printed content inspection system 200 may further include a storage module for storing various data during the operation of the printed content inspection system 200, including but not limited to general features, special features, standard features, inspection results, and data input and / or uploaded by users.

[0040] In some embodiments, some or all modules of the printed content inspection system 200 may be integrated into a processor. Figure 3-Figure 5 Related description in .

[0041] It should be noted that the above description of the printed content inspection system and its modules is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 1 The modules disclosed in the specification may be different modules in a system, or one module may realize the functions of two or more modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0042] Figure 3 FIG. 1 is an exemplary flow chart of a printed content inspection method according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 may be executed by a processor.

[0043] Step 310, determining standard features based on the common features and the special features.

[0044] Common features refer to features corresponding to common printing content, which refers to common printing content shared by multiple batches of printing tasks, including but not limited to common characters, interface information, safety specification information, certification symbol information, and customer logo information.

[0045] Exemplarily, the common features may include, but are not limited to, at least one of the font, size, color, shape, and position of the common printed content.

[0046] The universal printing content maintains consistency and universality in multiple batches of printing tasks. In some embodiments, the processor can identify and integrate common and reusable printing content in multiple batches of historical printing contents as universal printing content based on historical printing content of at least one batch in the historical printing tasks.

[0047] In some embodiments, the processor may also obtain universal printed content input by the user through the user terminal.

[0048] In some embodiments, the processor may perform modular processing on the universal printed content, dividing the universal printed content into at least one universal content module, each universal content module corresponding to a portion of the indivisible universal printed content. As an example only, the processor may divide the interface information into a universal content module, divide the security specification information into a universal content module, divide the authentication symbol information into a universal content module, divide the customer logo into a universal content module, etc. In some embodiments, the division of the universal content modules may also be based on other criteria, which may be determined based on prior experience or actual needs.

[0049] In some embodiments, the processor may process the aforementioned at least one universal content module through a text recognition or image processing algorithm, extract universal module features of each universal content module, and determine universal features based on the universal module features. The aforementioned universal module features may include at least one of the font, size, color, shape of the universal printed content in the universal content module, and the position of the universal module, and may also include other features, which may be determined according to actual conditions.

[0050] Among them, the position of the universal content module refers to the coordinate position of the center point of the universal content module. In some embodiments, the processor can identify the contour of the historical object to be inspected through image processing algorithms, such as Hough transform, contour detection, etc., and determine the center point of the historical object to be inspected by calculating the centroid or geometric center of the contour. The historical object to be inspected refers to the historical object to be inspected where the universal content module is located, and identify the contour of the universal content module through a similar method to further determine the center point of the universal content module; take the center point of the historical object to be inspected as the origin of the coordinate system, and select two mutually perpendicular directions as the X-axis and the Y-axis; starting from the coordinate origin, calculate the distance from the center point of the universal content module to the origin of the coordinate system through the distance measurement technology in the image processing algorithm, such as the Euclidean distance, and determine the projection of the aforementioned distance to the X-axis and the Y-axis, so as to obtain the coordinate value of the center point of the universal content module, and use the coordinate value as the position of the universal content module.

[0051] In some embodiments, the processor may number at least one universal content module based on a preset coding rule. As an example only, the preset coding rule may include a numbering component corresponding to the content module. For example, the numbering corresponding to the content module may include but is not limited to the following parts: the code of the object to be inspected where the content module is located, the location of the content module, the subject code of the content module, the format code of the content module, etc., and each part may be distinguished by a separator or other means. Among them, the aforementioned content module may be at least one of a universal content module, a dedicated content module, and an actual content module.

[0052] The type code of the object to be inspected is used to characterize the object to be inspected where the universal content module is located. A content module may appear on different objects to be inspected, or appear in different positions of the same object to be inspected. For example, customer 1's products include two types, A and B. The customer logo of product A is printed on the back panel of the product, while the customer logo of product B is printed on the bottom panel of the product. Therefore, when encoding the universal content module, it is necessary to consider the type of the object to be inspected, that is, to clarify the structural component where the universal content module is located. In some embodiments, the processor can set the type code of the object to be inspected based on user input or preset rules. For example, A1 represents the first structural component of product A, etc.

[0053] The subject code of the content module is used to characterize the content type in the general content module and can be determined based on the content in the content module. In some embodiments, the processor can set the codes corresponding to different themes based on user input or preset rules. For example, the code corresponding to the customer logo is set to 1. If the content in the content module is the customer logo, the subject code corresponding to the content module is 1.

[0054] The format code of the content module can represent the font, size, color, shape and other features in the content module, and can be determined based on the format design scheme in the content module. In some embodiments, the processor can determine the codes corresponding to different format design schemes based on user input.

[0055] Exemplarily, the number corresponding to the content module can be expressed as A1-XY-1, indicating that the content module is a module on the first structural component of product A, located at (X, Y), and containing the customer's logo.

[0056] In some embodiments, the processor may further encode the universal content module in other ways to distinguish at least one universal content module.

[0057] Special features refer to features corresponding to the special printed content of the object to be inspected, where the special printed content refers to the special printed content on a batch of objects to be inspected. For example, the special printed content may include but is not limited to the text content, font design, color design, pattern or unique typesetting style unique to the batch of objects to be inspected.

[0058] Exemplarily, the special features may include, but are not limited to, at least one of the font, size, color, shape, and position of the special printed content.

[0059] In some embodiments, the processor may determine the dedicated signature in a variety of ways.

[0060] In some embodiments, the processor may obtain a dedicated feature based on the user input content. For example, the processor may obtain the dedicated feature input by the user through the user terminal.

[0061] In some embodiments, the processor may determine the dedicated printed content of the object to be inspected based on the target printed content and the universal printed content of the object to be inspected; and determine the dedicated features based on the dedicated printed content.

[0062] The target printing content refers to the content planned to be printed on the object to be inspected. For example, the target printing content may include general information planned to be printed on the object to be inspected, such as common characters, interface information, safety specification information, certification symbol information, and customer logo information, etc. It may also include special printing content planned to be printed on the object to be inspected, such as text content, font design, color design, pattern, or unique typesetting style unique to the object to be inspected.

[0063] In some embodiments, the processor can divide the target printed content into at least one target content module, each target content module includes a portion of the indivisible target printed content. The division method of the target content module is similar to the division method of the general content module, and the above description can be referred to.

[0064] In some embodiments, the processor may determine the target printing content in a variety of ways. For example, the processor may obtain the target printing content input by the user through the user terminal. For another example, the processor may call the target printing data preset in the storage device to determine the target printing content.

[0065] In some embodiments, the processor may determine the special printed content based on the general printed content and the target printed content of the object to be inspected. For example, the processor may compare at least one target content module in the target printed content with at least one general content module in the general printed content through character recognition (OCR) technology or image processing algorithm; the processor may determine the target content module that cannot be matched with the aforementioned at least one general content module as the special printed content. Wherein, the inability to match may mean that the similarity between the target content module and the general content module is lower than a similarity threshold, and the similarity threshold may be set based on prior experience.

[0066] In some embodiments, the processor can divide the dedicated printed content into at least one dedicated content module, each dedicated content module includes a portion of indivisible dedicated printed content. The division method of the dedicated content module is similar to the division method of the general content module, and the above-mentioned related description can be referred to.

[0067] In some embodiments, the processor may process the aforementioned at least one dedicated content module through a text recognition or image processing algorithm, extract the dedicated module features of each dedicated content module, and determine the dedicated features based on the dedicated module features. The aforementioned dedicated module features may include at least one of the color and shape of the dedicated printed content in the dedicated content module and the position of the dedicated content module, and may also include other features, such as font, size, etc., which may be determined according to actual conditions.

[0068] The position of the dedicated content module refers to the coordinate position of the center of the dedicated content module, and the determination method thereof is similar to the determination method of the position of the general content module. For more detailed descriptions, please refer to the relevant description above.

[0069] In some embodiments, the processor may number at least one dedicated content module based on a preset coding rule. For a detailed description of the preset coding rule, please refer to the above description.

[0070] In some embodiments, the processor may further encode the dedicated content modules based on other methods to distinguish at least one dedicated content module.

[0071] The standard feature is a feature used to determine whether the actual printed content of the object to be inspected is qualified. In some embodiments, the standard feature may include common features and special features of the current batch of objects to be inspected.

[0072] In some embodiments, the processor may determine the universal printed content of the current batch of objects to be inspected based on the universal printed content and the target printed content of the objects to be inspected. For example, the processor may compare at least one target content module in the target printed content with at least one universal content module of the universal printed content through character recognition (OCR) technology or image processing algorithm; the processor may determine the universal content module that can match the target content module in the target printed content as the universal printed content of the current batch of objects to be inspected. Among them, being able to match may mean that the similarity between the universal content module and a certain target content module is not less than a similarity threshold, and the similarity threshold may be set based on prior experience.

[0073] In some embodiments, the processor may determine the standard features based on the general features and the special features. For example, the processor may combine the general features and the special features of the current batch of objects to be inspected to construct a standard feature database, and the general features and / or special features of the current batch of objects to be inspected may be used as standard features in the standard feature database to determine whether the actual printed content is qualified.

[0074] In some embodiments, the processor may use the general content modules corresponding to the general features of the current batch of objects to be inspected as standard content modules in the standard feature database, and mark the module types of these standard content modules as general classes; and / or use the special content modules corresponding to the special features as standard content modules in the standard feature database, and mark the module types of these standard content modules as special classes. For more detailed descriptions on module types, please refer to this specification. Figure 5 Description in .

[0075] In some embodiments, the processor may use the code corresponding to the common content module of the current batch of objects to be inspected as the code of the corresponding standard content module in the standard feature database, and / or use the code corresponding to the special content module as the code of the corresponding special content module in the standard feature database.

[0076] Step 320: Acquire actual features of the object to be inspected.

[0077] Actual features refer to features corresponding to the actual printed content of the object to be inspected. For example, the target printed content may include general information that has been printed on the object to be inspected, such as common characters, interface information, safety specification information, certification symbol information, and customer logo information, etc. It may also include unique printed content that has been printed on the object to be inspected, such as text content, font design, color design, pattern, or unique typesetting style that is unique to the object to be inspected.

[0078] In some embodiments, the actual features may include, but are not limited to, the shape, color, and position of the actual printed content, and may also include features such as font and size.

[0079] In some embodiments, the processor may obtain the actual features of the object to be inspected in a variety of ways. For example, the processor may obtain image data of the object to be inspected, identify the actual printed content of the object to be inspected through text recognition or image processing algorithms, and perform image analysis on the actual printed content to determine the actual features corresponding to the actual printed content.

[0080] In some embodiments, the processor may determine the actual printed content and the center point position of the object to be inspected based on the scanning of the object to be inspected; and determine the actual features based on the actual printed content and the center point position.

[0081] Detailed instructions for determining the actual characteristics can be found in this manual Figure 4 Related content in .

[0082] Step 330: Determine the inspection result of the printed content of the object to be inspected based on the actual features and the standard features.

[0083] The inspection result refers to the judgment result on whether the printed content of the content to be inspected meets the requirements. For example, the inspection result may include but is not limited to qualified, unqualified, etc.

[0084] The processor may determine the inspection result in a variety of ways based on the actual features and the standard features.

[0085] In some embodiments, the processor can determine whether the actual features are consistent with the standard features. If they are consistent, the inspection result of the printed content of the object to be inspected is determined to be qualified. If they are inconsistent, the inspection result of the printed content of the object to be inspected is determined to be unqualified.

[0086] In some embodiments, the processor may determine difference information based on the actual features and the standard features; and determine the inspection result based on the difference information and the qualified condition. Figure 5 Related content in .

[0087] In some embodiments of the present specification, standard features are determined through common features and special features, which can comprehensively cover the requirements for printed content of the object to be inspected, greatly improving the accuracy of the inspection; based on the scanning results of the object to be inspected, the printed content is inspected by the processor, which can effectively avoid omissions or misjudgments, thereby improving the efficiency and accuracy of the inspection.

[0088] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0089] Figure 4 It is a schematic diagram of determining actual features according to some embodiments of this specification.

[0090] In some embodiments, the processor may determine the actual printed content 420 and the center point position 430 of the object to be inspected based on the scanning of the object to be inspected.

[0091] In some embodiments, by scanning the object to be inspected, the processor can obtain an image 410 of the object to be inspected, where the image includes the object to be inspected and its actual printed content.

[0092] In some embodiments, the processor may acquire an image of the object to be inspected through a preset acquisition device, wherein the acquisition device may include but is not limited to at least one of a 3D scanner, a laser scanner, a digital camera, and an infrared imager.

[0093] For details on the actual printed content, see this manual. Figure 3 The relevant description in step 320.

[0094] The processor may determine the actual printed content of the object to be inspected in a variety of ways based on the image of the object to be inspected.

[0095] In some embodiments, the processor may identify the image of the object to be inspected and determine the actual printed content through an image recognition method and an image feature extraction method.

[0096] The image recognition method may include, but is not limited to, one or more of a computer image recognition method, a structural image recognition method, a fuzzy image recognition method, and the like.

[0097] The image feature extraction method may include but is not limited to one or more of an edge detection method, a corner detection method, a texture detection method, and the like.

[0098] The center point position refers to the position of the center point of the object to be detected. The center point position can be used as a coordinate origin, and the processor can determine the position of each module in the object to be detected based on the coordinate origin.

[0099] In some embodiments, the processor can identify the contour of the object to be inspected through image processing algorithms, such as Hough transform, contour detection, etc., and determine the center point position of the object to be inspected by calculating the centroid or geometric center of the contour.

[0100] In some embodiments, the processor can determine the actual feature 440 based on the actual printed content 420 and the center point position 430. For detailed description of the actual feature, please refer to the specification Figure 3 The relevant description in step 320.

[0101] In some embodiments, the processor may divide the actual printed content into at least one actual content module, each actual content module including a portion of the indivisible actual printed content. The division method of the actual content module is similar to the division method of the general content module, which can be found in this specification. Figure 3 Relevant description of step 310.

[0102] In some embodiments, each actual content module may be used as an area to be scanned; the processor may scan the actual content module multiple times, and perform image processing on the results of the multiple scans to determine the image of the actual content module.

[0103] The aforementioned image processing process includes image alignment and image fusion. Image alignment refers to aligning images obtained by multiple scans to make them in the same coordinate system; image fusion refers to fusing the aligned images by averaging pixel values ​​or other possible methods to obtain a clearer image.

[0104] In some embodiments, the processor may process the at least one actual content module through a text recognition or image processing algorithm, extract the actual module features of each actual content module, and determine the actual features based on the actual module features. The actual module features may include at least one of the color and shape of the actual printed content in the actual content module and the position of the actual content module, and may also include other features, such as font, size, etc., which may be determined according to actual conditions.

[0105] The position of the actual content module refers to the coordinate position of the center point of the actual content module, and its determination method is similar to the determination method of the position of the general module. For more detailed descriptions, please refer to this manual. Figure 3 The relevant description in step 310.

[0106] In some embodiments, the processor may number at least one actual content module based on a preset coding rule. For detailed description of the preset coding rule, please refer to the specification Figure 3 The relevant description in step 310.

[0107] In some embodiments, the processor may further encode the actual content modules based on other methods to distinguish at least one actual content module.

[0108] In some embodiments of the present specification, actual features can be determined more accurately by identifying actual printed content and center point positions, thereby reducing errors in subsequent inspections of whether the printed content is qualified and improving inspection accuracy and efficiency.

[0109] When scanning the actual content module of the object to be inspected, if only one scan is performed, it may be affected by chance and inaccurate scanning results may not be obtained. However, if too many scans are performed, the scanning time will be increased and the scanning efficiency will be reduced. Therefore, it is necessary to determine a reasonable number of scans to ensure the accuracy of the scanning results while avoiding unnecessary scans and improving scanning efficiency.

[0110] In some embodiments, the processor may further determine the module type of the actual content module in the object to be inspected based on the standard features, and determine the initial scanning times for the actual content module based on the module type.

[0111] The module type refers to the type of content corresponding to the actual content module. For example, the module type may include a general class and a special class. Among them, the general class means that the module content corresponding to the actual content module is general content, and the special class means that the module content corresponding to the actual content module is special content.

[0112] In some embodiments, the processor may determine the module type of the actual content module in the object to be checked based on the standard feature. For example, the processor may compare the actual content corresponding to the actual content module with the standard content corresponding to the standard feature, determine the reference standard content whose similarity with the actual content is greater than a preset threshold, determine the type of the actual content based on the type of the reference standard content, and determine the type as the module type of the actual content module.

[0113] For example, if the reference standard content is universal content, the actual content module may be determined to be universal. For another example, the processor may compare the actual content module with the standard content module based on the number of the actual content module and the number of the standard content module, determine the standard content module with the same number as the actual content module, and determine the module type of the actual content module based on the type of content in the standard content module.

[0114] The initial scanning number refers to the predetermined number of times the actual content module is scanned.

[0115] In some embodiments, the processor may determine the initial scan times based on the module type of the actual content module. For example, if the actual content module is a general type, the initial scan times of the actual content module may be determined to be a first preset value; if the actual content module is a special type, the initial scan times of the actual content module may be determined to be a second preset value. The first preset value and the second preset value may be set based on prior experience and / or actual needs, and the second preset value is not less than the first preset value.

[0116] In some embodiments, the processor may scan the actual content module multiple times based on the initial scanning number to obtain images of multiple actual content modules.

[0117] In some embodiments of the present specification, the processor can determine the initial scanning times for different actual content modules based on the module type of the actual content module, which can reduce the initial scanning times for easily identifiable general type modules and improve scanning efficiency and resource utilization.

[0118] Due to the limitation of the number of scans that can be performed at a time by the scanning device, objects to be inspected in the same batch need to be placed in the scanning device for scanning multiple times.

[0119] In some embodiments, the processor may further determine the initial number of scans based on the number of objects to be inspected that are placed at a single time.

[0120] In some embodiments, the number of initial scans is proportional to the number of objects to be inspected placed at a time, that is, the more objects to be inspected placed at a time, the more initial scans are required.

[0121] In some embodiments, the processor may also determine the initial scan times based on the module type of the actual content module and the number of inspection objects placed at a time. As an example only, the order quantity of the current batch of objects to be inspected is 1,000 pieces. When it is planned to place 10 objects to be inspected at a time for scanning and inspection, and the actual content module types of the objects to be inspected are all general types, the initial scan times may be determined as the first preset value; when it is planned to place 10 objects to be inspected at a time for scanning and inspection, and the actual content module types of the objects to be inspected are special types, the initial scan times may be determined as the second preset value; when it is planned to place 20 objects to be inspected at a time for scanning and inspection, and the actual content module types of the objects to be inspected are all general types, the initial scan times may be determined as the second preset value.

[0122] In some embodiments of the present specification, the processor determines the initial number of scans based on the number of inspection objects placed at a single time, which can reduce repeated scans of the same object to be inspected, thereby improving scanning efficiency while ensuring scanning accuracy.

[0123] In some embodiments, the processor may also determine an adjustment amount for the initial scan times based on the proportion of common features in the initial scan results and the error results of feature recognition.

[0124] The initial scan result refers to the actual printed content obtained by the first scan. For example, for the same batch of 1,000 objects to be inspected, 10 objects are put in for scanning for the first time, and 20 objects are put in for scanning for the second time. The actual printed content of the 10 objects to be inspected put in for the first time is the initial scan result.

[0125] In some embodiments, the processor can determine the actual printed content corresponding to the initial scan result based on the image acquired by the acquisition device through an image recognition method. For a detailed description of acquiring the actual printed content, please refer to the above related description.

[0126] The general feature ratio refers to the ratio of the number of actual content modules of the general type to the total number of actual content modules in the actual printed content corresponding to the initial scan result. For example, the processor can divide the actual printed content corresponding to the initial scan result into content modules to obtain 50 actual content modules, of which 30 are of the general type, and the general feature ratio is 30÷50×100%=60%.

[0127] The error result of feature recognition refers to the error of the processor in recognizing the aforementioned actual content module. As an example only, the error result may include at least one of type recognition error, shape deviation, color deviation, and position deviation, and may also include other types of deviations that can be set according to prior experience and / or actual needs.

[0128] The type recognition error refers to the error in the processor's recognition of the actual content module type. For example, among the module type recognition results of the processor for 50 actual content modules, 40 are accurately recognized and 10 are inaccurately recognized, then the type recognition error is 20%. Among them, accurate recognition means that the processor's recognition result of the module type is consistent with the actual type of the module.

[0129] Shape deviation refers to the deviation of the processor from the actual content module shape recognition, which can be expressed as a value between 0 and 1, with the larger the value, the more accurate the recognition. Accurate recognition means that the processor's recognition result of the module shape is consistent with the actual shape of the module.

[0130] Color deviation refers to the deviation of the processor's recognition of the color of the actual content module, which can be expressed by the difference between the recognized color value and the color value of the actual content.

[0131] The deviation of the position deviation value processor in identifying the actual content module position can be represented by the difference between the identified coordinate information and the coordinate information of the actual content.

[0132] In some embodiments, the processor may determine the error result of feature recognition based on a sampling check of feature recognition results of multiple actual content modules. Taking type recognition error as an example, the processor may determine the type recognition error based on a sampling check of type recognition results of multiple actual content modules.

[0133] For example, the processor can randomly select several actual content modules and their type recognition results and send them to the user terminal, and obtain the module type input by the user through the user terminal; if the type recognition result is consistent with the module type input by the user, the processor can determine whether the recognition result is accurate; the processor can determine the type recognition error based on the number of accurate recognition results and the total number of samples. The determination of shape deviation, color deviation, and position deviation is similar to the determination of type recognition error. The processor can obtain manually input data, such as the shape outline of the actual content module, the manually input color value, or the manually input position, and compare the aforementioned manually input data with the feature recognition result to determine the error result of feature recognition.

[0134] In some embodiments, the processor may perform weighted summation on at least one of the type recognition error, shape deviation, color deviation, and position deviation to determine the error result of feature recognition, wherein the weight of the weighted summation may be determined based on prior experience and / or actual needs.

[0135] In some embodiments, the processor may determine the adjustment amount of the initial scan times based on preset rules according to the proportion of common features in the initial scan results and the error results of feature recognition.

[0136] In some embodiments, the preset rules may include: when the proportion of common features is greater than the proportion threshold and the error result is less than the error threshold, the processor reduces or does not adjust the initial scan number; when the proportion of common features is not greater than the proportion threshold and the error result is less than the error threshold, the processor needs to increase the initial scan number, and the increase is not greater than the first adjustment value; when the proportion of common features is greater than the proportion threshold and the error result is not less than the error threshold, the processor needs to increase the initial scan number, and the increase must be greater than the first adjustment value and not greater than the second adjustment value; when the common proportion feature is not greater than the proportion threshold and the error result is not less than the error threshold, the processor needs to increase the initial scan number, and the increase must be greater than the second adjustment value and less than the third adjustment value.

[0137] The proportion threshold, error threshold, first adjustment value, second adjustment value and third adjustment value can be set based on prior experience and / or actual needs. The first adjustment value is not less than 1, the second adjustment value is not less than the first adjustment value, and the third adjustment value is not less than the second adjustment value.

[0138] In some embodiments, the processor may scan the object to be inspected multiple times based on the adjusted initial scanning number to obtain multiple images, and determine the actual printed content of the object to be inspected based on the multiple images.

[0139] In some embodiments of the present specification, the processor determines the adjustment amount of the number of scans based on the proportion of common features and the error results in the initial scan results. This can reduce the number of scans and improve the scanning efficiency when the error remains basically unchanged. It can also adjust the number of scans in a timely manner to improve the scanning accuracy when the error is large.

[0140] Figure 5 It is a schematic diagram of determining inspection results according to some embodiments of this specification.

[0141] In some embodiments, the processor may determine difference information 520 based on the actual features 440 and the standard features 510 .

[0142] The difference information 520 is information for characterizing the difference between the actual feature and the standard feature. In some embodiments, the difference information may include at least one of shape deviation, color deviation, and position deviation.

[0143] In some embodiments, the processor may determine the difference information in a variety of ways based on the actual features and the standard features.

[0144] For example, the processor can calculate the position deviation between the actual feature and the standard feature through a position deviation calculation method (such as Euclidean distance calculation, Manhattan distance calculation, Chebyshev distance calculation, etc.), calculate the shape deviation between the actual feature and the standard feature through a shape deviation calculation method (such as Fourier frequency domain analysis, deep learning, Hough transform method, etc.), and calculate the color deviation between the actual feature and the standard feature through a color deviation calculation method (such as cluster analysis, image segmentation, calculation of Euclidean / Manhattan / Chebyshev distance in color space, etc.); the processor can determine the difference information by weighted summation based on at least one of the shape deviation, color deviation and position deviation, and the weight of the weighted summation can be set based on prior experience and / or actual needs.

[0145] In some embodiments, the processor may determine an inspection result 540 based on the difference information 520 and the qualified condition 530 .

[0146] The qualified condition 530 refers to the condition for judging whether the actual printed content is qualified. In some embodiments, the qualified condition is related to the printing tolerance of the difference information. For example, the qualified condition can be that when the difference information falls within the range of the printing tolerance, the inspection result can be determined to be qualified; when the difference information falls outside the range of the printing tolerance, the inspection result can be determined to be unqualified.

[0147] Printing tolerance refers to the range of deviation between actual features and standard features.

[0148] The processor may determine printing tolerances based on the difference information in a variety of ways.

[0149] In some embodiments, when the total number of objects to be inspected is not greater than the quantity threshold, the processor may determine the printing tolerance through statistical analysis based on the difference information. For example, the processor performs statistical analysis on the difference information between the standard features and the actual features of the current batch of objects to be inspected to determine the printing tolerance. The quantity threshold may be determined based on prior experience and / or actual needs.

[0150] The statistical analysis may include, but is not limited to, one or more of methods such as calculating the mean value, calculating the median, and determining the upper and lower error limits based on a normal distribution.

[0151] As an example only, if the quantity threshold is set to 50 pieces and the number of objects to be inspected is 40 pieces, the processor can compare the actual features of the 40 objects to be inspected with the standard features to determine the average deviation value and the normal distribution value; if all 40 pieces conform to the normal distribution law and 38 of them fall within the range of ±2 standard deviations of the mean, then 38 pieces are qualified and 2 pieces are unqualified. The aforementioned standard deviation refers to the standard deviation of the difference information between the standard features and the actual features.

[0152] In some embodiments of the present specification, when the total number of objects to be inspected is not greater than a quantity threshold, the number of objects to be inspected that the processor needs to process is relatively small. At this time, the inspection result is determined based on the difference information between the actual features and the standard features and the printing tolerance. By adopting a unified printing tolerance, the efficiency of the printed content inspection system is better guaranteed without adjusting the determined printing tolerance.

[0153] In some embodiments, when the total number of objects to be inspected is greater than the quantity threshold, the processor may determine the initial printing tolerance by matching in the tolerance database based on the standard features, actual features, and current number of objects to be inspected.

[0154] Initial printing tolerances are printing tolerances that are predetermined before inspection.

[0155] The current number of objects to be inspected refers to the number of objects to be inspected in the current batch. In some embodiments, the processor may determine the current number of objects to be inspected based on user input.

[0156] The tolerance database stores at least one reference inspection feature vector and its corresponding reference printing tolerance, wherein the elements in the reference inspection feature vector may include reference actual features, reference standard features, and reference number of objects to be inspected.

[0157] In some embodiments, the processor may construct a tolerance database based on data of at least one historical batch of objects to be inspected in the historical data. For example, the processor may determine reference actual features, reference standard features, and reference number of objects to be inspected based on historical standard features, historical actual features, and historical number of objects to be inspected of the historical batch of objects to be inspected, and then construct a reference inspection feature vector; and determine the historical printing tolerance corresponding to the historical batch as the reference tolerance corresponding to the reference inspection feature vector.

[0158] In some embodiments, the processor can construct an inspection feature vector based on the standard features, actual features, and the current number of objects to be inspected corresponding to the current object to be inspected; perform vector matching in a tolerance database based on the inspection feature vector, and determine the reference inspection feature vector that is closest to the inspection feature vector as the target inspection feature vector; and determine the initial printing tolerance based on the reference tolerance corresponding to the target inspection feature vector.

[0159] In some embodiments, the processor may match the printing tolerances corresponding to the historical objects to be inspected with the standard features, the actual features, and the number of historical objects to be inspected through a data query method, and determine the matched printing tolerances as the initial printing tolerances.

[0160] In some embodiments, the processor may determine the inspection result based on the difference information and the initial printing tolerance. If the difference information is within the initial printing tolerance, the printing is qualified; if the difference information is not within the initial printing tolerance, the printing is unqualified.

[0161] In some embodiments of the present specification, when the total number of objects to be inspected is greater than a quantity threshold, the processor needs to process a large number of objects to be inspected. At this time, the initial printing tolerance is further determined based on the standard features, actual features, and the historical number of objects to be inspected. The qualified conditions can be reasonably adjusted according to the total number of objects to be inspected to improve the accuracy of inspecting the objects to be inspected.

[0162] In some embodiments, the processor may further modify the reference printing tolerances in the tolerance database based on the historical misjudgment data.

[0163] Historical misjudgment data refers to verified misjudged data. In some embodiments, the historical misjudgment data may include first misjudgment data and second misjudgment data. For example, the first misjudgment data may be data that is judged to be passed but is actually unqualified, and the second misjudgment data may be data that is judged to be unqualified but is actually qualified.

[0164] In some embodiments, historical misjudgment data may be obtained based on manual quality inspection or feedback.

[0165] In some embodiments, when the historical misjudgment data is the first misjudgment data, the processor may reduce the reference tolerance; when the historical misjudgment data is the second misjudgment data, the processor may expand the reference tolerance.

[0166] For example, when the historical misjudgment data is the second misjudgment data, the reference tolerance can be reduced from the first-level quality standard to the second-level quality standard. The first-level quality standard can be a printing tolerance of "within the range of ±1 standard deviation of the mean of the difference information", and the second-level quality standard can be a printing tolerance of "within the range of ±2 standard deviations of the mean of the difference information". The standard deviation refers to the standard deviation of the difference information between the actual features of the objects to be inspected in the current batch and the standard features.

[0167] In some embodiments of the present specification, the processor may correct the reference tolerance based on historical misjudgment data, so as to make the setting of the qualified condition more accurate and improve the inspection accuracy of the object to be inspected.

[0168] In some embodiments, the processor may further adjust the initial printing tolerance based on customer quality standards, determine the printing tolerance, and adjust the initial scan times based on the printing tolerance.

[0169] The customer quality standard refers to the printing standard required by the customer for the object to be inspected. In some embodiments, the processor can obtain the customer quality standard through user input.

[0170] In some embodiments, the initial printing tolerance is modified in a small range according to the customer quality standard. For example, if the customer quality standard is low, the processor can expand the initial printing tolerance, such as reducing the initial printing tolerance from "difference information within the mean ±1σ range" to "difference information within the mean ±2σ range", where σ refers to the standard deviation of the difference information between the actual features of the objects to be inspected in the current batch and the standard features.

[0171] In some embodiments, the processor may determine the revised initial printing tolerance as the printing tolerance.

[0172] In some embodiments, the processor may also adjust the initial scan times based on printing tolerances.

[0173] In some embodiments, the number of initial scans is negatively correlated with the range of printing tolerances. That is, the larger the range of printing tolerances, the wider the customer's quality standards are, and the number of initial scans can be reduced to ensure efficiency.

[0174] For more information on determining the initial scan number, see Figure 4 and its related description.

[0175] In some embodiments of the present specification, the processor can further adjust the printing tolerance based on the customer quality standard, can flexibly adjust the quality requirements of the inspection task, and reasonably arrange resources to better ensure the inspection efficiency.

[0176] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0177] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0178] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0179] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0180] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0181] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0182] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A printing content inspection method, characterized in that: include: Determine the standard features based on the common features and the special features; the common features are related to the common printed content of the object to be inspected, and the special features are related to the special printed content of the object to be inspected; Acquiring actual features of the object to be inspected, wherein the actual features are related to actual printed content of the object to be inspected; Based on the actual features and the standard features, an inspection result of the printed content of the object to be inspected is determined.

2. The method according to claim 1, characterized in that The method further comprises: Determining the dedicated printing content of the object to be inspected based on the target printing content of the object to be inspected and the universal printing content; Based on the dedicated printed content, the dedicated feature is determined.

3. The method according to claim 1, characterized in that The obtaining of actual features of the object to be inspected includes: Based on the scanning of the object to be inspected, determining the actual printed content and the center point position of the object to be inspected; The actual feature is determined based on the actual printed content and the center point position.

4. The method according to claim 1, characterized in that The step of determining the inspection result of the printed content of the object to be inspected based on the actual feature and the standard feature includes: Determining difference information based on the actual features and the standard features; Based on the difference information and the qualified condition, the inspection result is determined; wherein, The qualification condition is related to a printing tolerance of the difference information.

5. A printed content inspection system, characterized in that: It includes a first acquisition module, a second acquisition module and a determination module; wherein, The first acquisition module is configured to determine the standard feature based on the general feature and the special feature; the general feature is related to the general printed content of the object to be inspected, and the special feature is related to the special printed content of the object to be inspected; The second acquisition module is configured to acquire actual features of the object to be inspected, wherein the actual features are related to actual printed content of the object to be inspected; The result determination module is configured to determine the inspection result of the printed content of the object to be inspected based on the actual feature and the standard feature.

6. The system according to claim 5, characterized in that The first feature acquisition module is further configured to: Determining the dedicated printing content of the object to be inspected based on the target printing content of the object to be inspected and the universal printing content; Based on the dedicated printed content, the dedicated feature is determined.

7. The system according to claim 5, characterized in that The second acquisition module is further configured to: Based on the scanning of the object to be inspected, determining the actual printed content and the center point position of the object to be inspected; The actual feature is determined based on the actual printed content and the center point position.

8. The system according to claim 5, characterized in that The determination module is further configured to: Determining difference information based on the actual features and the standard features; Based on the difference information and the qualified condition, the inspection result is determined; wherein, The qualification condition is related to a printing tolerance of the difference information.

9. A printed content inspection device, comprising a processor, wherein the processor is configured to execute the printed content inspection method according to any one of claims 1 to 4.

10. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the printing content inspection method according to any one of claims 1 to 4.

Images