Method, device, equipment and storage medium for defect detection of die-cut products

Abstract

The present invention discloses a method, apparatus, device, and storage medium for defect detection of die-cut products. The method comprises acquiring a first die-cut material image and a second die-cut material image; comparing the first die-cut material image and the second die-cut material image to obtain defect information; extracting features from the defect information to obtain defect characteristics, and determining whether the defect characteristics are stored in a memory; if it is determined that the defect characteristics are stored in the memory, calling a first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device produces the target die-cut material; if it is determined that the defect characteristics are not stored in the memory, generating a second correction instruction based on the defect information, storing the second correction instruction and the defect information in the memory, and calling the second correction instruction to perform a correction operation so that the die-cutting device produces the target die-cut material. The method can improve the speed and smoothness of the production line, thereby improving production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of die-cut products, and in particular to a method, device, electronic equipment and storage medium for defect detection of die-cut products. Background Art

[0002] Die-cutting is a material processing technology primarily used to cut various materials (such as paper, cardboard, rubber, plastic, metal foil, cloth, leather, etc.) into predetermined shapes and sizes. Die-cutting is widely used in a variety of fields, including packaging and printing, electronics, medical devices, automotive manufacturing, apparel, and printed circuit boards (PCBs). However, during the die-cutting process, the die-cut products may develop defects such as dimensional deviations, shape and surface defects in specific locations, scratches, dents, impurities, and color unevenness. Due to the large number of die-cut products to be produced, the number of errors in the die-cutting process increases. Therefore, specific defect detection technologies are needed to monitor and optimize the entire die-cutting process to improve production efficiency.

[0003] Existing die-cutting defect detection technologies generally employ an approach that involves performing defect detection during the die-cutting process and automatically correcting any defects detected. However, as people's material needs continue to grow, the volume of die-cut products being produced is also increasing, leading to an increasing number of errors in the die-cutting process. This poses a challenge to the speed and fluidity of die-cutting production lines.

[0004] During the die-cutting production process, once an error occurs, the die-cutting production line needs to stop working immediately and perform automatic system correction. If the number of errors increases, it will seriously affect the speed and smoothness of the die-cutting production line, and thus affect production efficiency. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for defect detection of die-cut products, which can efficiently utilize historical defects for rapid correction, so as to achieve smooth and rapid operation of the die-cutting production line and improve production efficiency.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a defect detection method for die-cut products, comprising:

[0007] Acquire a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects;

[0008] Comparing the first die-cut material image with the second die-cut material image to obtain defect information;

[0009] Extracting features from the defect information to obtain defect features, and determining whether the defect features are stored in the memory;

[0010] When it is determined that the defect feature is stored in the memory, a first correction instruction corresponding to the defect information is called to perform a correction operation so that the die-cutting device produces the target die-cutting material;

[0011] When it is determined that the defect feature is not stored in the memory, a second correction instruction is generated based on the defect information, the second correction instruction and the defect information are stored in the memory, and the second correction instruction is called to perform a correction operation so that the die-cutting equipment produces the target die-cutting material.

[0012] The first correction instruction is an instruction pre-generated based on historical defect information and stored in the memory.

[0013] Preferably, the comparing the first die-cut material image and the second die-cut material image to obtain defect information includes:

[0014] performing image comparison based on the first die-cut material image and the second die-cut material image to obtain image difference information;

[0015] Analyze the image difference information to obtain defect information.

[0016] Preferably, extracting features from the defect information to obtain defect features includes:

[0017] From the time the die-cutting material is loaded, the timer starts timing and generates the die-cutting start time; when it is determined that the die-cutting material has defects, the timer stops timing and generates the die-cutting error time;

[0018] Obtaining die-cutting duration according to the die-cutting start time and die-cutting error time;

[0019] generating a time defect feature according to the die-cutting duration;

[0020] Wherein, the defect characteristics include time defect characteristics.

[0021] Preferably, extracting features from the defect information to obtain defect features includes:

[0022] generating position comparison information based on the first die-cut material image and the second die-cut material image;

[0023] generating position defect features according to the position comparison information;

[0024] Wherein, the defect characteristics include position defect characteristics.

[0025] Preferably, it is determined whether the die-cutting duration has been recorded in the memory; if so, it is determined that the defect feature has been stored in the memory; if not, it is determined that the defect feature has not been stored in the memory.

[0026] Preferably, it is determined whether the position comparison information has been recorded in the memory; if so, it is determined that the defect feature has been stored in the memory; if not, it is determined that the defect feature has not been stored in the memory.

[0027] Preferably, after storing the second correction instruction and the defect information in the memory, the method further includes:

[0028] When the next defect information determination is made, the defect information and the second correction instruction stored in the memory are used as the stored defect information and the corresponding first correction instruction.

[0029] In a second aspect, the present invention provides a defect detection device for die-cut products, comprising:

[0030] An image acquisition module is configured to acquire a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects;

[0031] A defect detection module, configured to compare the first die-cut material image with the second die-cut material image to obtain defect information;

[0032] A feature extraction module is used to extract features from defect information, obtain defect features, and determine whether the defect features are stored in the memory;

[0033] A first correction module is configured to, when determining that the defect feature is stored in the memory, call a first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device can produce a target die-cutting material;

[0034] a second correction module, configured to, when it is determined that the defect feature is not stored in the memory, generate a second correction instruction based on the defect information, store the second correction instruction and the defect information in the memory, and call the second correction instruction to perform a correction operation so that the die-cutting device produces the target die-cutting material;

[0035] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the defect detection method for die-cut products described in any one of the above is implemented.

[0036] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned die-cut product defect detection methods.

[0037] Compared with the prior art, the present invention has the following beneficial effects: an embodiment of the present invention provides a method, apparatus, device and storage medium for defect detection of die-cut products, the method comprising acquiring a first die-cutting material image and a second die-cutting material image; performing comparison based on the first die-cutting material image and the second die-cutting material image to obtain defect information; performing feature extraction on the defect information to obtain defect features, and determining whether the defect features are stored in a memory; when it is determined that the defect features are stored in the memory, the first correction instruction corresponding to the defect information is called to perform a correction operation so that the die-cutting device produces the target die-cutting material; when it is determined that the defect features are not stored in the memory, a second correction instruction is generated based on the defect information, the second correction instruction and the defect information are stored in the memory, and the second correction instruction is called to perform a correction operation so that the die-cutting device produces the target die-cutting material.

[0038] In the present invention, the method extracts features from defect information to obtain defect features. If the obtained defect features have been stored in a storage device, then the next time a defect of the same type occurs, the system can immediately retrieve the previously generated correction measures to perform correction operations, without the need to generate the corresponding correction measures again. This is especially true in the context of an increasing number of die-cut products to be produced leading to an increasing number of die-cut defects, which can greatly improve the speed and smoothness of the production line and thus improve production efficiency. In addition, since the number of defects that appear will increase with the increase in the number of die-cut products to be produced, the system will store too much defect information, which is not conducive to calling the corresponding correction instructions. The present invention also filters and saves the repeated defect occurrence time and repeated defect location, solving the problem of storing too many repeated defects, thereby improving the efficiency of the correction operation and production efficiency. In addition, the defect features stored in the memory can also help technicians further improve and optimize the parameters of the die-cutting equipment to avoid waste of materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 1 is a flow chart of a defect detection method for die-cut products provided by the first embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a defect detection device for die-cut products provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] Reference Figure 1 A first embodiment of the present invention provides a method for detecting defects in die-cut products, comprising the following steps:

[0043] S11, acquiring a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects;

[0044] S12, comparing the first die-cut material image with the second die-cut material image to obtain defect information;

[0045] S13, extracting features from the defect information to obtain defect features, and determining whether the defect features are stored in the memory;

[0046] S14, when it is determined that the defect feature is stored in the memory, calling the first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device can produce the target die-cutting material;

[0047] S15, when it is determined that the defect feature is not stored in the memory, a second correction instruction is generated according to the defect information, the second correction instruction and the defect information are stored in the memory, and the second correction instruction is called to perform a correction operation so that the die-cutting equipment produces the target die-cutting material.

[0048] It should be noted that die-cutting is a material processing technology primarily used to cut various materials (such as paper, cardboard, rubber, plastic, metal foil, cloth, leather, etc.) into predetermined shapes and sizes. Die-cutting is widely used in a variety of fields, including packaging and printing, electronics, medical devices, automotive manufacturing, apparel, and printed circuit boards (PCBs). However, during the die-cutting process, the die-cut products may develop defects such as dimensional deviations, shape and surface defects in specific locations, scratches, dents, impurities, and color unevenness. In such cases, specialized defect detection technologies are required to monitor and optimize the entire die-cutting process to improve production efficiency.

[0049] To facilitate understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0050] In step S11, the first die-cut material image, i.e., the target die-cut material image, is the desired image of the perfect die-cut product. This image can be obtained from the original design file pre-stored in the system, or by photographing a perfect die-cut sample using a high-precision camera or scanning device. The second die-cut material image, i.e., the image of the die-cut material on the production line awaiting defect detection, can be obtained by installing an image acquisition module on the die-cutting production line to photograph the die-cut product in production in real time. The image acquisition module can include a high-resolution industrial camera, an optical lens system, and machine vision technology.

[0051] In step S12, defect information is obtained by comparing the first die-cut material image and the second die-cut material image, including:

[0052] performing image comparison based on the first die-cut material image and the second die-cut material image to obtain image difference information;

[0053] Analyze the image difference information to obtain defect information.

[0054] Specifically, defect information can be obtained through image comparison technology, which involves image matching algorithms, such as feature matching algorithms, including scale-invariant feature transform (Scale-Invariant Feature Transform) and SURF algorithm (Speeded-Up Robust Features); template matching algorithms, including standard template matching; and edge detection and matching, including Canny edge detection and Sobel operator.

[0055] Specifically, features such as shape features, texture features, and color features can be extracted from image differences through feature extraction technology. The algorithms involved include: edge detection, such as Canny edge detection and Sobel operator; corner detection, such as Harris corner detection and Shi-Tomasi corner detection.

[0056] Among them, the defects that may appear in the second die-cut material image include: size deviation of the die-cut material, shape defects, surface defects, color defects, impurity defects, position defects, and edge defects.

[0057] After image comparison, if no defect information is obtained, it means that the die-cut product produced has no defects, the product is qualified, and the die-cutting work can continue.

[0058] In step S13, feature extraction is performed on the defect information to obtain defect features, and it is determined whether the defect features are stored in the memory. The defect features include time defect features and position defect features;

[0059] In one embodiment, the extracted defect features include time defect features. The steps for extracting the time defect features are as follows: starting a timer from the start of die-cutting material loading to generate a die-cutting start time; stopping the timer when it is determined that the die-cutting material has a defect to generate a die-cutting error time; obtaining a die-cutting duration based on the die-cutting start time and the die-cutting error time; and generating a time defect feature based on the die-cutting duration.

[0060] In order to achieve the effect of timing from the time the die-cutting material is loaded, a proximity sensor or position sensor can be installed on the die-cutting equipment. When the die-cutting material reaches the specified position, the sensor is triggered and sends a signal to the system to start the timer. In order to achieve the effect of stopping the timer when it is determined that the die-cutting material has a defect, the timer can be stopped by sending a timer stop timing instruction to the timer when the defect information is generated. Based on the generated die-cutting start time and die-cutting error time, the duration of the die-cutting process is calculated to generate a time defect feature. It is worth noting that the time defect feature is generated based on the die-cutting start time and die-cutting error time. It represents the duration of the die-cutting process and is a time interval from the start of die-cutting to the detection of the defect.

[0061] In this embodiment, it is determined whether the die-cutting duration has been recorded in the memory; if so, it is determined that the defect feature has been stored in the memory; if not, it is determined that the defect feature has not been stored in the memory.

[0062] Specifically, to determine whether the generated time defect signature is stored in memory, the newly generated time defect signature must be matched with the historical time defect signatures stored in memory to determine whether the same type of defect has occurred before. A successful match with the historical time defect signature indicates that the same defect has occurred historically. During the die-cutting process, die-cutting often makes mistakes at specific times. The system can immediately correct these mistakes based on historically generated correction instructions to ensure the orderly progress of the die-cutting process. Saved time defect signatures can also help technicians further improve and optimize the parameters of the die-cutting equipment to avoid material waste.

[0063] In another embodiment, the step of extracting the position defect feature is specifically as follows: generating position comparison information based on the first die-cut material image and the second die-cut material image; generating the position defect feature based on the position comparison information;

[0064] It is worth noting that the position defect characteristics obtained in this step can also be directly obtained from step S12. When the defect information is generated in step S12, the position defect characteristics of the specific defect location are generated at the same time, which is used to determine whether to repeat the storage in step S13. It is worth noting that the position defect characteristics include dimensional deviations of the die-cut material, shape defects, surface defects, color defects, impurity defects, position defects, and edge defects.

[0065] In this embodiment, the determination of whether the defect feature is stored in the memory is specifically as follows: determining whether the position comparison information has been recorded in the memory; if so, determining that the defect feature has been stored in the memory; if not, determining that the defect feature has not been stored in the memory.

[0066] Specifically, to determine whether the generated position defect feature is stored in the memory, the newly generated position defect feature needs to be matched with the historical position defect features stored in the memory to determine whether the same type of defect has occurred before. If the historical position defect feature successfully matches, it means that the same defect has occurred in the past. During the die-cutting process, die-cutting work often makes mistakes at a specific location on the die-cutting material. The system can immediately correct the errors based on the historical correction instructions to ensure the orderly progress of the die-cutting work. The saved position defect features can also help technicians further improve and optimize the parameters of the die-cutting equipment to avoid material waste.

[0067] In another optional embodiment, it is also possible to determine whether the defect feature is stored in the memory based on both the generated time defect feature and the position defect feature. Specifically, it is determined whether the die-cutting duration is stored in the memory. If so, it is further determined whether the position comparison information is stored in the memory; if not, it is determined that the defect information is not stored in the memory. Next, it is determined whether the position comparison information is stored in the memory. If so, it is determined that the defect feature is stored in the memory; if not, it is determined that the defect feature is not stored in the memory.

[0068] Specifically, the newly generated time defect feature is first matched with the historical time defect feature stored in the memory to determine whether the same type of defect has occurred before. If the match with the historical time defect feature is successful, it means that the same error may have occurred when the die-cutting work reached a certain specific position. At this time, the final judgment is further made through position comparison information. The newly generated position defect feature is matched with the historical time defect feature stored in the memory to determine whether the same type of defect has occurred before. If the match with the historical position defect feature is successful, it means that the same defect has occurred in the past. At this time, the system can make immediate corrections based on the correction instructions generated historically to ensure the orderly progress of the die-cutting work.

[0069] After step S13 , when it is determined that the defect feature is stored in the memory, step S14 is executed.

[0070] In step S14, the first correction instruction is pre-generated based on historical defect information and stored in memory. The system can then execute correction operations based on the first correction instruction, including automatically adjusting relevant parameters of the die-cutting equipment, such as pressure, speed, die position, material tension, and equipment temperature. This process saves time generating correction instructions based on defect information and ensures smooth production line operation.

[0071] After step S13 , when it is determined that the defect feature is not stored in the memory, step S15 is executed.

[0072] In step S15, if the defect characteristics are not stored in the memory, it indicates that a new defect has occurred. At this point, the system needs to accurately identify the defect characteristics and generate corresponding correction instructions. Defect information includes dimensional deviations, shape defects, and surface defects. Correction instructions generated based on the defect information include adjusting the pressure and speed of the die-cutting equipment, adjusting the mold position, adjusting the material tension, and adjusting the equipment temperature.

[0073] In one embodiment, after storing the second correction instruction and the defect information in the memory, the method further includes:

[0074] When the next defect information determination is made, the defect information and the second correction instruction stored in the memory are used as the stored defect information and the corresponding first correction instruction.

[0075] In this embodiment, after the second correction instruction is generated, the second correction instruction and the defect information are stored in the memory together. When the next defect feature determination is made, the defect information and the corresponding second correction instruction stored in the memory are used as the stored defect information and the corresponding first correction instruction. This step forms a closed loop with step S14. The newly obtained defect feature is used as the defect feature stored in the memory when the same defect reappears in the subsequent die-cutting operation; the newly generated second correction instruction can be used as the first correction instruction when the same defect reappears in the subsequent die-cutting operation; the first correction instruction, as a previously generated correction instruction, can be immediately called and executed, saving the time of regenerating the correction instruction.

[0076] The following describes the working process of the present invention using a relatively common scenario as an example. The working process is as follows:

[0077] The die-cutting production line is equipped with an image acquisition module equipped with a high-resolution industrial camera. This camera captures the die-cut material in real time after die-cutting, known as the second die-cut material image. Simultaneously, the system stores the target die-cut material image, known as the first die-cut material image, obtained from the design file.

[0078] The system uses image comparison technology to compare the first die-cut material image with the second die-cut material image and identify any differences. After analyzing the image differences, the system obtains defect information.

[0079] The system extracts features from defect information to obtain defect features.

[0080] In order to obtain defect characteristics, two implementation methods are provided below:

[0081] In one embodiment, a timer starts counting from the moment the die-cutting material is loaded, generating a die-cutting start time. When the die-cutting material is determined to have a defect, the timer stops counting, generating a die-cutting error time. Based on the die-cutting start time and the die-cutting error time, a die-cutting duration is obtained. Based on the die-cutting duration, a time defect feature is generated.

[0082] In another embodiment, the system generates position comparison information through image comparison technology, obtains position defects of the die-cut material based on the position comparison information, and generates position defect features.

[0083] After obtaining the time defect feature and the position defect feature, the system queries whether the same defect feature has been stored in the memory.

[0084] If the defect feature is already stored in the memory, the system will call the first correction instruction related to the defect feature to adjust the parameters of the die-cutting device, such as pressure and speed, so that the die-cutting device can produce the target die-cutting material.

[0085] If it is a new defect feature, the system will generate a new second correction instruction accordingly, store it together with the defect information in the memory, and execute the second correction instruction to enable the die-cutting equipment to produce the target die-cutting material.

[0086] In summary, the defect detection method for die-cut products provided by the embodiment of the present invention includes obtaining a first die-cut material image and a second die-cut material image; comparing the first die-cut material image and the second die-cut material image to obtain defect information; extracting features from the defect information to obtain defect features, and determining whether the defect features are stored in a memory; when it is determined that the defect features are stored in the memory, the defect information is then calling a first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device produces the target die-cut material; when it is determined that the defect features are not stored in the memory, a second correction instruction is generated according to the defect information, the second correction instruction and the defect information are stored in the memory, and the second correction instruction is called to perform a correction operation so that the die-cutting device produces the target die-cut material. The method stores the defect information and the corresponding correction instructions that have appeared so that they can be quickly retrieved and used when the same defect features are brought next time, eliminating the process of repeatedly generating correction instructions, improving the speed and fluency of the production line, and thereby improving production efficiency. Furthermore, since defects increase with the number of die-cut products to be produced, the system will store too much defect information, making it difficult to call corresponding correction instructions. The present invention also filters and saves repeated defect occurrence times and locations, solving the problem of excessive storage of repeated defects and thereby improving production efficiency. Furthermore, the defect characteristics stored in memory can also help technicians further improve and optimize die-cutting equipment parameters, avoiding material waste.

[0087] Reference Figure 2 A second embodiment of the present invention provides a defect detection device for die-cut products, wherein the device is configured in a mobile terminal and includes:

[0088] An image acquisition module is configured to acquire a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects;

[0089] A defect detection module, configured to compare the first die-cut material image with the second die-cut material image to obtain defect information;

[0090] A feature extraction module is used to extract features from defect information, obtain defect features, and determine whether the defect features are stored in the memory;

[0091] A first correction module is configured to, when determining that the defect feature is stored in the memory, call a first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device can produce a target die-cutting material;

[0092] The second correction module is used to generate a second correction instruction based on the defect information when it is determined that the defect feature is not stored in the memory, store the second correction instruction and the defect information in the memory, and call the second correction instruction to perform a correction operation so that the die-cutting equipment can produce the target die-cutting material.

[0093] In an optional implementation, the defect detection module is specifically configured to:

[0094] performing image comparison based on the first die-cut material image and the second die-cut material image to obtain image difference information;

[0095] Analyze the image difference information to obtain defect information.

[0096] In an optional implementation, the feature extraction module is specifically configured to:

[0097] From the time the die-cutting material is loaded, the timer starts timing and generates the die-cutting start time; when it is determined that the die-cutting material has defects, the timer stops timing and generates the die-cutting error time;

[0098] Obtaining die-cutting duration according to the die-cutting start time and die-cutting error time;

[0099] generating a time defect feature according to the die-cutting duration;

[0100] In another optional embodiment, the feature extraction module is specifically configured to:

[0101] generating position comparison information based on the first die-cut material image and the second die-cut material image;

[0102] generating position defect features according to the position comparison information;

[0103] In an optional implementation, the feature extraction module is specifically configured to:

[0104] Determine whether the die-cutting duration has been recorded in the memory; if so, determine that the defect feature has been stored in the memory; if not, determine that the defect feature has not been stored in the memory.

[0105] In another optional embodiment, the feature extraction module is specifically configured to:

[0106] Determine whether the position comparison information has been recorded in the memory; if so, determine that the defect feature has been stored in the memory; if not, determine that the defect feature has not been stored in the memory.

[0107] In an optional implementation, the second correction module is specifically configured to:

[0108] When the next defect information determination is made, the defect information and the second correction instruction stored in the memory are used as the stored defect information and the corresponding first correction instruction.

[0109] It should be noted that the defect detection device for die-cut products provided in an embodiment of the present invention is used to execute all process steps of the defect detection method for die-cut products in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated.

[0110] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a die-cut product defect detection program. When the processor executes the computer program, the steps of the above-mentioned die-cut product defect detection method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the defect detection module.

[0111] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0112] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0113] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0114] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0115] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0116] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0117] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A defect detection method for die-cut products, characterized in that: include: Acquire a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects; Comparing the first die-cut material image with the second die-cut material image to obtain defect information; Extracting features from the defect information to obtain defect features and determining whether the defect features are stored in the memory includes: From the time the die-cutting material is loaded, the timer starts timing and generates the die-cutting start time; when it is determined that the die-cutting material has defects, the timer stops timing and generates the die-cutting error time; Obtaining die-cutting duration according to the die-cutting start time and the die-cutting error time; generating a time defect feature according to the die-cutting duration; Wherein, the defect characteristics include time defect characteristics; generating position comparison information based on the first die-cut material image and the second die-cut material image; generating position defect features according to the position comparison information; Wherein, the defect characteristics include position defect characteristics; Determining whether the defect feature is stored in the memory includes: Match the newly generated time defect signature with the historical time defect signature stored in the memory; if the match is successful, it is determined that the defect signature has been stored in the memory; or Match the newly generated position defect feature with the historical position defect feature stored in the memory; if the match is successful, it is determined that the defect feature has been stored in the memory; or First, the newly generated time defect feature is matched with the historical time defect feature; if the match is successful, the newly generated position defect feature is then matched with the historical position defect feature; if both are matched successfully, it is determined that the defect feature has been stored in the memory; When it is determined that the defect feature is stored in the memory, a first correction instruction corresponding to the defect information is called to perform a correction operation so that the die-cutting device produces the target die-cutting material; When it is determined that the defect feature is not stored in the memory, a second correction instruction is generated according to the defect information, the second correction instruction and the defect information are stored in the memory, and the second correction instruction is called to perform a correction operation so that the die-cutting device produces the target die-cutting material; wherein, after the second correction instruction and the defect information are stored in the memory, the defect information and the second correction instruction stored in the memory are used as the stored defect information and the corresponding first correction instruction when the next defect information determination arrives; The first correction instruction is an instruction pre-generated based on historical defect information and stored in the memory.

2. The defect detection method for die-cut products according to claim 1, characterized in that: The obtaining defect information based on the comparison between the first die-cut material image and the second die-cut material image includes: performing image comparison based on the first die-cut material image and the second die-cut material image to obtain image difference information; Analyze the image difference information to obtain defect information.

3. A defect detection device for die-cut products, characterized in that: A method for detecting defects in die-cut products according to any one of claims 1 to 2, comprising: An image acquisition module is configured to acquire a first die-cutting material image and a second die-cutting material image; wherein the first die-cutting material image is a target die-cutting material image, and the second die-cutting material image is an image of a die-cutting material to be detected for defects; A defect detection module, configured to compare the first die-cut material image with the second die-cut material image to obtain defect information; A feature extraction module is used to extract features from defect information, obtain defect features, and determine whether the defect features are stored in the memory; A first correction module is configured to, when determining that the defect feature is stored in the memory, call a first correction instruction corresponding to the defect information to perform a correction operation so that the die-cutting device can produce a target die-cutting material; The second correction module is used to generate a second correction instruction based on the defect information when it is determined that the defect feature is not stored in the memory, store the second correction instruction and the defect information in the memory, and call the second correction instruction to perform a correction operation so that the die-cutting equipment can produce the target die-cutting material.

4. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for detecting defects in die-cut products according to any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the defect detection method for die-cut products according to any one of claims 1 to 2.

Images