Image processing methods, image processing apparatus, computer equipment and storage media

Abstract

This invention discloses an image processing method, an image processing apparatus, a computer device, and a computer-readable storage medium. The image processing method includes: acquiring a product image of a die-cut printed material; dividing the product image into multiple product image units, each product image unit corresponding to a printed material; locating the die-cutting points of each product image unit, the die-cutting points being used to characterize the die-cutting position; and determining defects in each product image unit based on the die-cutting points. The technical solution of this invention determines the die-cutting points of each product image unit through the product image of the printed material, thereby enabling the determination of defects in each product image unit based on the die-cutting points.

Description

Technical Field

[0001] This invention relates to image processing technology, and more specifically, to an image processing method, an image processing apparatus, a computer device, and a computer-readable storage medium. Background Technology

[0002] Die-cutting is an important process in the production of printed materials such as labels and color boxes. Its function is to cut the product into the pattern model required by the customer under pressure. During the production process, problems such as die-cutting misalignment or poor die-cutting waste removal often occur due to die-cutting blade wear, insufficient die-cutting precision, etc. In order to provide customers with high-quality qualified products, printing manufacturers should avoid delivering products with die-cutting defects. Summary of the Invention

[0003] The present invention provides an image processing method, an image processing apparatus, a computer device, and a computer-readable storage medium.

[0004] This invention provides an image processing method, comprising: acquiring a product image of a die-cut printed material; dividing the product image into multiple product image units, each product image unit corresponding to a printed material; locating the die-cutting points of each product image unit, the die-cutting points being used to characterize the die-cutting position; and determining defects in each product image unit based on the die-cutting points.

[0005] In some embodiments, acquiring the product image of the die-cut printed material includes: acquiring the product image using the identifier of the printed material as a positioning reference point.

[0006] In some embodiments, the image processing method further includes: locating the die-cutting area of ​​each of the product image units, the die-cutting area being used to characterize the die-cutting position; locating the die-cutting point of each of the product image units includes: locating the die-cutting point according to the die-cutting area.

[0007] In some embodiments, the product image unit includes a backing paper area, and locating the die-cutting area of ​​each of the product image units includes: extracting pixel values ​​of the outer ring area of ​​the product image unit; determining the average value and standard deviation of the pixel values; determining a first connected region based on the average value and the standard deviation; determining the first connected region with the largest area and located on the outermost side of the product image unit as the backing paper area; and locating the die-cutting area based on the backing paper area.

[0008] In some embodiments, positioning the die-cutting area based on the base paper area includes: determining a target indentation amount based on the size of the printed matter; and indenting the base paper area inward by the target indentation amount to form the die-cutting area.

[0009] In some embodiments, locating the die-cutting point based on the die-cutting region includes: dividing the preset search range of the product image unit into multiple die-cutting blocks, each die-cutting block including one die-cutting point; determining the die-cutting direction of the die-cutting point in each die-cutting block based on the die-cutting region; and determining the point with the largest pixel value change in the die-cutting direction as the die-cutting point.

[0010] In some embodiments, the image processing method further includes: determining a preset point as the die-cutting point if locating the die-cutting point based on the die-cutting area fails.

[0011] In some embodiments, determining the defects of each of the product image units based on the die-cutting points includes: comparing the template of the printed material with the die-cutting points of each of the product image units to determine the defects.

[0012] In some embodiments, the step of comparing the template of the printed matter with the die-cutting point of each product image unit to determine the defect includes: comparing the position information of the die-cutting point of each product image unit with the template of the printed matter to calculate the offset information; and determining the corresponding die-cutting point as the defect if the offset information exceeds a preset offset range.

[0013] In some embodiments, the step of comparing the template of the printed matter with the die-cutting point of each product image unit to determine the defect includes: comparing the die-cutting point with the adjacent points of the die-cutting point; determining a second connected region based on the die-cutting point and adjacent points whose difference from the die-cutting point is greater than a preset difference; and determining the second connected region as the defect if the area of ​​the second connected region is greater than a preset area and the gray value is greater than a preset gray value.

[0014] This invention provides an image processing apparatus, comprising: an acquisition module, a first processing module, a second processing module, and a third processing module. The acquisition module acquires a product image of a die-cut printed material. The first processing module divides the product image into multiple product image units, each product image unit corresponding to one printed material. The second processing module locates the die-cutting points of each product image unit, the die-cutting points characterizing the die-cutting position. The third processing module determines defects in each product image unit based on the die-cutting points.

[0015] The present invention provides a computer device, which includes one or more processors and a memory. The memory stores a computer program, which, when executed by the processor, implements the steps of the image processing method of any of the above embodiments.

[0016] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the image processing method of any of the above embodiments.

[0017] In the image processing method, image processing apparatus, computer equipment, and computer-readable storage medium of the present invention, the die-cutting points of each product image unit are determined by the product image of the printed matter, thereby determining the defects of each product image unit based on the die-cutting points.

[0018] Additional aspects and advantages of embodiments of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of the invention. Attached Figure Description

[0019] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0020] Figure 1 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0021] Figure 2 This is a schematic diagram of an image processing apparatus according to certain embodiments of the present invention;

[0022] Figure 3 This is a schematic diagram of a computer device according to certain embodiments of the present invention;

[0023] Figure 4 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0024] Figure 5 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0025] Figure 6 This is a schematic diagram of an image processing apparatus according to certain embodiments of the present invention;

[0026] Figure 7 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0027] Figure 8 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0028] Figure 9 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0029] Figure 10 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0030] Figure 11 This is a schematic diagram of an image processing apparatus according to certain embodiments of the present invention;

[0031] Figure 12 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0032] Figure 13 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0033] Figure 14 This is a flowchart illustrating an image processing method according to certain embodiments of the present invention;

[0034] Figure 15 This is a schematic diagram illustrating the poor waste discharge defects in certain embodiments of the present invention. Detailed Implementation

[0035] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings. The same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0036] The following disclosure provides many different embodiments or examples of different structures for implementing embodiments of the present invention. To simplify the disclosure of embodiments of the present invention, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of the invention.

[0037] Die-cutting is an important process in the production of printed materials such as labels and color boxes. Its function is to cut the product into the pattern model required by the customer under pressure. During the production process, problems such as die-cutting misalignment or poor die-cutting waste removal often occur due to die-cutting blade wear, insufficient die-cutting precision, etc. In order to provide customers with high-quality qualified products, printing manufacturers should avoid delivering products with die-cutting defects.

[0038] In related technologies, die-cutting defects are addressed through manual re-inspection and manual correction. Manual re-inspection involves rapidly feeding the die-cut products through the machine, where quality inspectors visually check for quality issues. Manual correction involves installing imaging equipment on the die-cutting machine, allowing printing machine operators to judge whether the die-cutting is misaligned and whether the die-cutting blade is in the correct position by observing the static image.

[0039] In practical applications, die-cut products require further processing. For example, after die-cutting, cardboard is glued together to make color boxes. If die-cut cardboard with defects is not removed in time, the pattern on the box will be misaligned with the box, affecting the quality of the product. If the die-cutting of labels is misaligned, the graphics on the die-cut edge will be missing. Poorly removed labels, especially electronic labels, are prone to not being able to fully adhere to the groove during labeling. Therefore, the release of poorly die-cut printed products will affect or even cause losses to downstream users.

[0040] Manual defect detection methods are slow, the quality of detection is affected by human intuition, and relying on human eyes to inspect printed materials is a challenging task.

[0041] Please see Figure 1 The present invention provides an image processing method, which includes:

[0042] 01: Obtain product images of the die-cut printed materials;

[0043] 02: Divide the product image into multiple product image units, with each product image unit corresponding to a printed material;

[0044] 03: Locate the die-cutting points of each product image unit. The die-cutting points are used to characterize the die-cutting position.

[0045] 04: Determine the defects of each product image unit based on the die-cutting points.

[0046] Please see Figure 2 The present invention provides an image processing device 100, which includes: an acquisition module 11, a first processing module 12, a second processing module 13 and a third processing module 14.

[0047] The image processing method of this invention can be implemented by the image processing apparatus 100 of this invention. Step 01 can be implemented by the acquisition module 11, step 02 by the first processing module 12, step 03 by the second processing module 13, and step 04 by the third processing module 14. That is, the acquisition module 11 can be used to acquire product images of the die-cut printed material. The first processing module 12 can be used to divide the product image into multiple product image units, each product image unit corresponding to a printed material. The second processing module 13 can be used to locate the die-cutting points of each product image unit, whereby the die-cutting points characterize the die-cutting position. The third processing module 14 can be used to determine the defects of each product image unit based on the die-cutting points.

[0048] In the image processing method and image processing apparatus 100 of the present invention, the die-cutting points of each product image unit are determined by the product image of the printed matter, thereby determining the defects of each product image unit based on the die-cutting points.

[0049] The technical solution of this invention adds a quality inspection process after the die-cutting process, using machine vision for die-cutting defect detection, which can achieve high-precision and efficient surface defect detection. This application can detect defects such as die-cutting misalignment and poor die-cutting waste removal in the printed matter within the product image unit. High-efficiency defect detection can free quality inspectors from their work, reducing unnecessary labor costs. In this application's technical solution, if the number of defects is greater than or equal to 1, the corresponding die-cut printed matter can be rejected, thereby ensuring the timely removal of defective products and reducing material waste and machine wear. If the number of defects is 0, i.e., there are no defects, the die-cut printed matter can be determined to be qualified.

[0050] Please see Figure 3 The image processing device 100 can be applied to the computer device 1000.

[0051] In some embodiments, printed materials include labels, color boxes, etc., which are not specifically limited here. The product images of this application can be captured by a high-resolution camera, and defects can be detected through a fast and efficient detection algorithm, thereby improving the accuracy of rejecting defective products and ensuring the delivery of high-quality products.

[0052] Please see Figure 4 In some implementations, step 01 (obtaining a product image of the die-cut printed material) includes:

[0053] 011: Collect product images using the printed markings as the positioning reference point.

[0054] Please see Figure 2In some implementations, step 011 can be implemented by the acquisition module 11, that is, the acquisition module 11 can be used to acquire product images with the markings of the printed matter as the positioning reference point.

[0055] In this way, product images of printed materials can be captured. Specifically, the text, patterns, colors, and other markings on the printed materials can be used as positioning reference points to capture product images. In this case, multiple printed materials can be captured consecutively using the markings as positioning reference points to obtain product images.

[0056] Step 02 divides the product image into multiple product image units, each corresponding to a printed material, thereby dividing the product image into the smallest version.

[0057] Please see Figure 5 In some embodiments, the image processing method further includes:

[0058] 05: Locate the die-cutting area of ​​each product image unit. The die-cutting area is used to characterize the die-cutting position.

[0059] Step 03 (Locating the die-cutting points of each product image unit) includes:

[0060] 031: Locate the die-cutting point based on the die-cutting area.

[0061] Please see Figure 6 In some embodiments, the image processing apparatus 100 further includes a fifth processing module 15. Step 05 can be implemented by the fourth processing module 15, and step 031 can be implemented by the second processing module 13. That is, the fourth processing module 15 can be used to locate the die-cutting area of ​​each product image unit, and the die-cutting area is used to characterize the die-cutting position. The second processing module 13 can be used to locate the die-cutting point according to the die-cutting area.

[0062] In this way, the die-cutting point can be located in the die-cutting area of ​​each product image unit. The die-cutting area is used to represent the rough position of the die-cutting, and the die-cutting point is used to represent the precise position of the die-cutting.

[0063] Please see Figure 7 In some embodiments, the product image unit includes a backing paper area. Step 05 (positioning the die-cutting area of ​​each product image unit) includes:

[0064] 051: Extract the pixel values ​​of the outer ring region of the product image unit;

[0065] 052: Determine the mean and standard deviation of pixel values;

[0066] 053: Determine the first connected region based on the mean and standard deviation;

[0067] 054: Determine the first connected region with the largest area and located on the outermost side of the product image unit as the base paper region;

[0068] 055: Locate the die-cutting area based on the base paper area.

[0069] Please see Figure 6 In some embodiments, the product image unit includes a backing paper area. Steps 051, 052, 053, 054, and 055 can all be implemented by the fourth processing module 15. That is, the fourth processing module 15 can be used to: extract the pixel values ​​of the outer ring area of ​​the product image unit; determine the average value and standard deviation of the pixel values; determine the first connected region based on the average value and standard deviation; determine the first connected region with the largest area and located on the outermost side of the product image unit as the backing paper area; and locate the die-cutting area based on the backing paper area.

[0070] In this way, the die-cutting area can be accurately located through the base paper area (a unique feature of the die-cutting position), which facilitates the accurate determination of the die-cutting points in the subsequent process. Multiple die-cutting points constitute the die-cutting edge.

[0071] The most distinctive feature of die-cut edges is that they are located on the outermost layer of the printed material, and the outer side of the die-cut edge is the backing paper to which the printed material is attached. Since the backing paper is often a single color, the pixel values ​​of the backing paper are extracted from the outermost (a certain width outer ring area) within the cut small sheets (product image units). The average value and standard deviation of the backing paper in the outer ring area for each channel are also determined. According to the three-standard-deviation principle, 99.7% of the pixels fall within three standard deviations. Therefore, the data of the outer ring area is used to represent the entire backing paper area. Based on the average value and standard deviation, the area that meets the requirements for all three channels is extracted as the first connected region. There may be multiple first connected regions extracted, but the backing paper area has the largest area and is distributed on the outermost edge of the entire printing plate. Therefore, the first connected region that is closest to the die-cutting edge is extracted as the backing paper area. Thus, the die-cutting area can be located based on the backing paper area, completing the coarse positioning of the die-cut edge.

[0072] The parameters used to determine the base paper area are the average and standard deviation of the pixel values ​​in the outer ring area. In this way, the average and standard deviation can be adaptively changed, which is convenient for production personnel to use, reduces the difficulty of use, and can detect die-cutting defects of most printed materials on the market. To a certain extent, it reduces the decline in detection capability caused by improper use.

[0073] Among them, the average value Standard deviation p represents a pixel in the outer ring region R, g(p) is the pixel value of pixel p, and F is the number of pixels in the outer ring region R. The upper and lower limits of the threshold for the first connected region, Mean-3*Deviation and Mean+3*Deviation, are determined based on the mean and standard deviation. This threshold does not need to be manually set.

[0074] Please see Figure 8 In some implementations, step 055 (locating the die-cutting area based on the base paper area) includes:

[0075] 0551: Determine the target indentation amount based on the dimensions of the printed material;

[0076] 0552: The base paper area is recessed inward by the target indentation amount to serve as the die-cutting area.

[0077] Please see Figure 6 In some implementations, steps 0551 and 0552 can be implemented by the fourth processing module 15. That is, the fourth processing module 15 can be used to: determine the target indentation amount according to the size of the printed matter; and indent the base paper area inward by the target indentation amount to serve as the die-cutting area.

[0078] In this way, the target indentation can be adaptively determined according to the size of the printed material, thereby indenting the target indentation from the base paper area to determine the die-cutting area.

[0079] Specifically, after extracting the base paper area, a certain inward indentation is required to accommodate die-cutting misalignment. For example, taking printed materials as labels, statistical analysis shows that the target indentation amount is proportional to the label size; larger labels allow for greater indentation. A suitable effect is achieved when the target indentation amount is 2 / 100 of the width of the label area or the minimum of the high and low center values. The horizontal and vertical indentation amounts are proportional to the horizontal and vertical resolution, ensuring that the horizontal and vertical indentation amounts display the same width on the interface during extraction. The target indentation amount can be determined based on the dimensions of the printed material, and the die-cutting area is determined by indenting the base paper area inwards based on this target indentation amount. The target indentation amount can adaptively change, facilitating use by production personnel, reducing the difficulty of use, and enabling the detection of die-cutting defects in most printed materials on the market, thus mitigating the decline in detection capability caused by improper use.

[0080] Please see Figure 9 In some implementations, step 031 (locating the die-cutting point based on the die-cutting area) includes:

[0081] 0311: Divide the preset search range of the product image unit into multiple die-cutting blocks, each die-cutting block including a die-cutting point;

[0082] 0312: Determine the die-cutting direction of the die-cutting points in each die-cutting block based on the die-cutting area;

[0083] 0313: Determine the point with the largest change in pixel value along the die-cutting direction as the die-cutting point.

[0084] Please see Figure 6 In some implementations, steps 0311, 0312 and 0313 can be implemented by the second processing module 13. That is, the second processing module 13 can be used to: divide the preset search range of the product image unit into multiple die-cutting blocks, each die-cutting block including a die-cutting point; determine the die-cutting direction of the die-cutting point in each die-cutting block according to the die-cutting area; and determine the point with the largest change in pixel value in the die-cutting direction as the die-cutting point.

[0085] In this way, the die-cutting point can be accurately determined.

[0086] Specifically, a preset search range for the product image unit can be determined first. The purpose of the preset search range is to define an area and find the die-cutting point within that area. If the preset search range is too small, it cannot accommodate die-cutting misalignment; if the misalignment slightly exceeds the preset search range, false alarms will be severe. If the preset search range is too large, it is easy to move the positioning point to an adjacent product image unit, and the larger the search range, the longer the time required. Production personnel can adjust the preset search range based on the actual results. In one embodiment, the preset search range can be 20*20, but no specific limitation is made here.

[0087] After obtaining the approximate die-cutting area, the die-cutting points (which constitute the die-cutting edge) can be calculated more accurately based on this area. To save time in locating the die-cutting points, while maintaining the accuracy of the positioning, the die-cutting points are extracted at equal intervals. The preset search range is divided into multiple die-cutting blocks, and only one die-cutting point is extracted from each block to represent the position of the die-cutting within the entire perimeter of the printing plate. This step simplifies the extraction of die-cutting points throughout the preset search range. Due to the inherent characteristics of the die-cutting edge, this operation does not affect the accuracy of the die-cutting point positioning. The vertical direction of the die-cutting area is extracted from each die-cutting block, which can be used as the normal direction (i.e., the die-cutting direction) of the die-cutting point in that block. The die-cutting point represents the precise position of the die-cutting. The accumulated die-cutting points approximate the actual situation of the die-cutting edge. The die-cutting edge, viewed from the cross-section, is the point of greatest abrupt change inward from the base paper. Therefore, the point with the largest pixel value change in the die-cutting direction is the most representative die-cutting point in the die-cutting block.

[0088] In some implementations, the die-cutting point of the template can be accurately located based on the template of the printed matter. For the detection process of the product image unit, since the printed matter corresponding to the product image unit is the same as the template of the printed matter, in order to reduce the time consumption, the detection information of the template of the printed matter can be inherited. Therefore, it is not necessary to extract the backing paper information again, because the backing paper used is consistent. Similarly, the preset search range and the relative direction of the die-cutting direction are also the same. Since the shape of the die-cutting will not change, the product image unit can directly use the detection information of the template of the printed matter.

[0089] Please see Figure 10 In some embodiments, the image processing method further includes:

[0090] 06: If it fails to locate the die-cutting point based on the die-cutting area, determine the preset point as the die-cutting point.

[0091] Please see Figure 11 In some embodiments, the image processing apparatus 100 further includes a fifth processing module 16. Step 06 can be implemented by the fifth processing module 16, that is, the fifth processing module 16 can be used to determine a preset point as the die-cutting point when the die-cutting point cannot be located according to the die-cutting area.

[0092] In this way, even if it fails to locate the die-cutting point based on the die-cutting area, the die-cutting point can still be determined.

[0093] Specifically, when the die-cutting offset exceeds the die-cutting search range, some die-cutting points will not obtain effective positioning information. Therefore, the die-cutting area is divided into blocks and they are bound together. Because of the characteristics of the process, even if the die-cutting is offset, the overall size of the die-cutting will not change. Based on this characteristic, the die-cutting points that do not obtain effective information (die-cutting point positioning based on the die-cutting area fails) can be replaced by preset points (determined based on empirical values).

[0094] Please see Figure 12 In some implementations, step 04 (determining defects in each product image unit based on the die-cutting point) includes:

[0095] 041: Defects are identified by comparing the template of the printed material with the die-cut points of each product image unit.

[0096] Please see Figure 2 In some implementations, step 041 can be implemented by a third processing module 14, that is, the third processing module 14 can be used to compare the template of the printed matter with the die-cutting point of each product image unit to determine defects.

[0097] In this way, defects can be identified by template comparison.

[0098] Specifically, the template of the printed material is compared with the die-cutting point of each product image unit to detect defects larger than the benchmark, thereby facilitating the rejection of defective printed materials.

[0099] Please see Figure 13 In some embodiments, step 041 (comparing the template of the printed material with the die-cutting points of each product image unit to determine defects) includes:

[0100] 0411: Compare the position information of the die-cutting point of each product image unit with the template of the printed material to calculate the offset information;

[0101] 0412: If the offset information exceeds the preset offset range, the corresponding die-cutting point is determined to be a defect.

[0102] Please see Figure 2 In some embodiments, steps 0411 and 0412 can be implemented by the third processing module 14. That is, the third processing module 14 can be used to: compare the position information of the die-cutting point of each product image unit with the template of the printed matter to calculate the offset information; and determine the corresponding die-cutting point as a defect when the offset information exceeds the preset offset range.

[0103] Thus, the misalignment defect can be identified.

[0104] Specifically, after determining the position information of the die-cutting point of each product image unit, the position information can be compared with the template to calculate the offset information. If the offset information exceeds the preset offset range, the corresponding die-cutting point can be identified as a defect, which facilitates the subsequent removal of defective printed materials.

[0105] Please see Figure 14 In some embodiments, step 041 (comparing the template of the printed material with the die-cutting points of each product image unit to determine defects) includes:

[0106] 0413: Compare the die-cutting point with its adjacent points;

[0107] 0414: Determine the second connected region based on the die-cutting point and its adjacent points whose difference from the die-cutting point is greater than a preset difference;

[0108] 0415: If the area of ​​the second connected region is greater than the preset area and the gray value is greater than the preset gray value, the second connected region is determined to be a defect.

[0109] Please see Figure 2In some implementations, steps 0413, 0414 and 0415 can be implemented by the third processing module 14. That is, the third processing module 14 can be used to: compare the die-cutting point with its adjacent points; determine the second connected region based on the die-cutting point and its adjacent points whose difference from the die-cutting point is greater than a preset difference; and determine the second connected region as a defect if the area of ​​the second connected region is greater than a preset area and the gray value is greater than a preset gray value.

[0110] In this way, the defects in waste discharge can be identified.

[0111] Specifically, besides the misalignment defect, the waste removal situation of the die-cut edges is also a key piece of information that needs to be paid attention to (for example, please refer to...). Figure 15 (The label in the image has redundant edges, indicating a defect in waste removal.) After determining the location information of the die-cutting point of each product image unit, the die-cutting point is compared with its adjacent points. The adjacent points with differences greater than a preset difference are recorded. The die-cutting point and its adjacent points with differences greater than the preset difference constitute a second connected region. If the area of ​​the second connected region is greater than a preset area and the gray value is greater than a preset gray value, the second connected region is determined to be a defect in waste removal, which facilitates the subsequent removal of defective printed materials.

[0112] Please see Figure 3 The image processing method of this invention can be implemented by the computer device 1000 of this invention. Specifically, the computer device 1000 includes one or more processors 200 and a memory 300. The memory 300 stores a computer program. When the computer program is executed by the processor 200, the steps of the image processing method of any of the above embodiments are implemented.

[0113] For example, when a computer program is executed by processor 200, the following steps are implemented for image processing:

[0114] 01: Obtain product images of the die-cut printed materials;

[0115] 02: Divide the product image into multiple product image units, with each product image unit corresponding to a printed material;

[0116] 03: Locate the die-cutting points of each product image unit. The die-cutting points are used to characterize the die-cutting position.

[0117] 04: Determine the defects of each product image unit based on the die-cutting points.

[0118] The present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the image processing method of any of the above embodiments.

[0119] For example, when the program is executed by processor 200, the following steps of image processing method are implemented:

[0120] 01: Obtain product images of the die-cut printed materials;

[0121] 02: Divide the product image into multiple product image units, with each product image unit corresponding to a printed material;

[0122] 03: Locate the die-cutting points of each product image unit. The die-cutting points are used to characterize the die-cutting position.

[0123] 04: Determine the defects of each product image unit based on the die-cutting points.

[0124] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0125] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0126] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0127] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0128] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0129] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0130] In this specification, the use of terms such as "certain embodiments" indicates that a specific feature, structure, or characteristic described in connection with the described embodiment or example is included in at least one embodiment of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment. Furthermore, the described specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0131] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An image processing method, characterized by, The image processing method comprises: acquiring a product image of a printed product after die cutting; dividing the product image into a plurality of product image units, each of which corresponds to one of the printed products; locating a die cutting point of each of the product image units, the die cutting point being used to represent a die cutting position; determining a defect of each of the product image units according to the die cutting point; The image processing method further comprises: locating a die cutting area of each of the product image units, the die cutting area being used to represent a die cutting position; The locating of the die cutting point of each of the product image units comprises: locating the die cutting point according to the die cutting area; comprising: dividing a preset search range of the product image unit into a plurality of die cutting blocks, each of which comprises one of the die cutting points; determining a die cutting direction of the die cutting point in each of the die cutting blocks according to the die cutting area; determining a point with the largest pixel value change in the die cutting direction as the die cutting point.

2. The image processing method of claim 1, wherein, The acquisition of the product image of the printed product after die cutting comprises: collecting the product image with an identification of the printed product as a positioning reference point.

3. The image processing method of claim 1, wherein, The product image unit comprises a base paper area, and the locating of the die cutting area of each of the product image units comprises: extracting a pixel value of an outer ring area of the product image unit; determining an average value and a standard deviation of the pixel value; determining a first connected area according to the average value and the standard deviation; determining a first connected area with the largest area and located at the outermost side of the product image unit as the base paper area; locating the die cutting area according to the base paper area.

4. The image processing method of claim 3, wherein, The locating of the die cutting area according to the base paper area comprises: determining a target shrinkage according to the size of the printed product; shrinking the base paper area inward by the target shrinkage to serve as the die cutting area.

5. The image processing method of claim 1, wherein, The image processing method further comprises: in the case of failure in locating the die cutting point according to the die cutting area, determining a preset point as the die cutting point.

6. The image processing method of claim 1, wherein, The determination of the defect of each of the product image units according to the die cutting point comprises: comparing a template of the printed product with the die cutting point of each of the product image units to determine the defect.

7. The image processing method of claim 6, wherein, The comparison of the template of the printed product with the die cutting point of each of the product image units to determine the defect comprises: comparing position information of the die cutting point of each of the product image units with the template of the printed product to calculate deviation information; in the case that the deviation information exceeds a preset deviation range, determining the corresponding die cutting point as the defect.

8. The image processing method of claim 6, wherein, The comparison of the template of the printed product with the die cutting point of each of the product image units to determine the defect comprises: comparing the die cutting point with adjacent points of the die cutting point; determining a second connected area according to the die cutting point and adjacent points with a difference greater than a preset difference from the die cutting point; in the case that the area of the second connected area is greater than a preset area and the gray value is greater than a preset gray value, determining the second connected area as the defect.

9. An image processing apparatus for implementing the image processing method according to any one of claims 1 to 8, characterized by The image processing device comprises: an acquisition module, configured to acquire a product image of a printed product after die cutting; a first processing module, configured to divide the product image into a plurality of product image units, each of the product image units corresponding to one of the printed products; a second processing module, configured to locate a die-cutting point of each of the product image units, the die-cutting point being used to represent a die-cutting position; a third processing module, configured to determine a defect of each of the product image units according to the die-cutting point.

10. A computer device, comprising: The computer device comprises one or more processors and a memory, and the memory stores a computer program. When the computer program is executed by the processor, the steps of the image processing method in any one of claims 1 to 8 are implemented.

11. A computer readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor, and the steps of the image processing method in any one of claims 1 to 8 are implemented.

Images