Wire harness laser marking and automatic identification method and system

Abstract

The invention relates to a wire harness laser marking and automatic identification method and system, and the method comprises the following steps: carrying out the parameterization definition of target wire harness identification information, generating a wire harness identification parameter table, converting the wire harness identification parameter table into a laser marking instruction, and carrying out the laser marking, and obtaining a laser marking image. An identification positioning frame is determined through an identification area positioning technology, and identification character features are extracted according to the identification positioning frame. And comparing the feature map with an original wire harness identification parameter table, and executing consistency verification to obtain a verification result. If the deviation exists, the laser marking instruction is adjusted according to the verification result feedback, dynamic compensation is achieved, it is ensured that the actual marking content is completely consistent with the expected identification information, and the technical problems that a traditional marking method is prone to abrasion and fuzziness and low in production efficiency are solved.

Description

Technical Field

[0001] This invention relates to the field of wire harness technology, and in particular to a method and system for laser marking and automatic identification of wire harnesses. Background Technology

[0002] With the rapid development of industrial automation and intelligent manufacturing, wire harnesses, as indispensable connecting components in electronic devices and electrical systems, face increasingly stringent requirements for precision and traceability in their production processes. Wire harness products typically require clear and durable marking during the production process, including key data such as model number, specifications, batch number, and distribution information. Traditionally, inkjet printing or mechanical embossing methods are used for marking. However, these traditional marking methods suffer from problems such as easy wear and tear, easy blurring, poor environmental performance, and low production efficiency, making it difficult to meet the demands of modern high-precision, high-speed, and high-reliability production. Therefore, utilizing laser marking technology to achieve permanent, high-contrast marking on wire harness surfaces has become an important development direction in the wire harness manufacturing field. Summary of the Invention

[0003] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a method for laser marking and automatic identification of wire harnesses, comprising the following steps: The identification information of the target wire harness is parameterized to obtain a wire harness identification parameter table, and the marking format of the wire harness identification parameter table is converted to obtain a laser marking instruction; The target line bundle is laser-marked based on the laser marking command to obtain a laser-marked image, and the marked area is located in the laser-marked image to obtain a marked positioning box. Based on the identification positioning box, character features are extracted from the laser marking image to obtain the identification character features; The consistency of the identified character features with the wire harness identification parameter table is verified to obtain the verification result. When the verification result shows a character recognition deviation, the laser marking instruction is dynamically compensated and adjusted based on the verification result so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

[0004] Furthermore, the identification information of the target wire harness is parameterized to obtain a wire harness identification parameter table, including: The identification information of the target wire harness is classified and organized to obtain a wire harness information classification table. The mandatory fields of the wire harness information classification table are then checked to obtain a qualified information table. Based on the verification pass information table, the parameter format is defined to obtain the information format template, and the information format template is filled and matched with the verification pass information to obtain the harness identification parameter table.

[0005] Furthermore, the step of converting the marking format of the wire harness identification parameter table to obtain laser marking instructions includes: The character parameters in the wire harness identification parameter table are matched and converted with the preset marking device vector library to obtain vector characters, and the marking parameters of the vector characters are configured to obtain device parameters; The device parameters are compiled with the preset control protocol of the laser marking device to obtain the initial instruction code, and the device response is tested on the initial instruction code to obtain the laser marking instruction.

[0006] Furthermore, the step of performing laser marking processing on the target line bundle based on the laser marking command to obtain a laser-marked image includes: The target wire bundle is clamped and positioned to obtain wire bundle positioning information. The marking area of ​​the wire bundle positioning information is calibrated based on the marking position parameters in the laser marking command to obtain calibration positioning parameters. The focal length of the lens of the laser marking equipment is adjusted based on the calibration and positioning parameters, and the laser energy of the adjusted laser marking equipment is pre-tested to obtain an energy test diagram. Based on the optimal energy parameters determined by the energy test diagram, the target line bundle is laser-marked in combination with the optimal energy parameters and the laser marking command to generate an initial marked line bundle. The marking area of ​​the initial marked line bundle is then imaged to obtain an initial marked image. The initial marking image is subjected to a sharpness test to obtain a sharpness score, and the initial marking image is then color-corrected based on the sharpness score to obtain a laser marking image.

[0007] Furthermore, the step of locating the marked area in the laser-marked image to obtain the marked positioning box includes: The laser marking image is subjected to background grayscale suppression processing to obtain a background suppressed image, and the background suppressed image is subjected to marking feature enhancement to obtain a feature enhanced image; Based on the feature-enhanced image, character connected component detection is performed to obtain a character connected component map, and candidate regions are filtered from the character connected component map to obtain candidate bounding boxes. The pixels within the candidate frame are verified for character arrangement to obtain an arrangement verification image. When the arrangement verification image shows that the characters within the candidate frame have uneven spacing, offset direction, or overall arrangement that does not conform to the expected rules, the candidate frame boundary is dynamically stretched and adjusted based on the arrangement verification image to obtain the identifier positioning frame.

[0008] Furthermore, the step of extracting character features from the laser marking image based on the marker positioning box to obtain marker character features includes: The image within the positioning box is binarized to obtain a binary image within the box, and noise pixels are removed from the binary image within the box to obtain a clean character image. The net character image is segmented to obtain a set of single character images, and the size of the single character image set is normalized to obtain standard characters; Extract the stroke features of the characters from the standard characters, and mark the stroke features with structural features to obtain structural features; The structural features are combined to obtain character composite features, and the character composite features are superimposed pixel by pixel to obtain identifier character features.

[0009] Furthermore, the step of performing consistency verification between the identified character features and the harness identification parameter table to obtain the verification result includes: Based on the harness identification parameter table, the expected character features are extracted to obtain the expected features. The expected features are then aligned with the identification character features in terms of feature dimensions to obtain an aligned feature map. The alignment feature map is compared character by character to obtain a character comparison map, and the feature matching rate is calculated based on the character comparison map to obtain a matching rate statistics table; Characters with matching rates below a preset threshold in the matching rate statistics table are marked with differences to obtain a difference marker map. The difference marker map is then superimposed and integrated with the character comparison map to obtain the verification result.

[0010] The present invention also provides a wire beam laser marking and automatic identification system, comprising: The conversion module is used to parameterize the identification information of the target wire harness to obtain a wire harness identification parameter table, and to convert the marking format of the wire harness identification parameter table to obtain laser marking instructions; The positioning module is used to perform laser marking processing on the target line bundle based on the laser marking command to obtain a laser marking image, and to locate the marked area of ​​the laser marking image to obtain a mark positioning frame; The extraction module is used to extract character features from the laser marking image based on the identification positioning frame, obtain identification character features, and perform consistency recognition and verification between the identification character features and the wire harness identification parameter table to obtain the verification result. The adjustment module is used to dynamically compensate and adjust the laser marking command based on the verification result when there is a character recognition deviation in the verification result, so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

[0011] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0012] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods described above.

[0013] This invention provides a method for laser marking and automatic identification of wire harnesses, comprising the following steps: parameterizing the identification information of the target wire harness to obtain a wire harness identification parameter table, and converting the marking format of the wire harness identification parameter table to obtain laser marking instructions; performing laser marking processing on the target wire harness based on the laser marking instructions to obtain a laser marking image, and locating the marking area of ​​the laser marking image to obtain a marking positioning box; extracting character features from the laser marking image based on the marking positioning box to obtain marking character features; performing consistency recognition and verification between the marking character features and the wire harness identification parameter table to obtain a verification result; when there is a character recognition deviation in the verification result, dynamically compensating and adjusting the laser marking instructions based on the verification result to ensure that the actual marking content of the target wire harness is completely consistent with the expected identification information in the wire harness identification parameter table. This solves the technical problems of easy wear, easy blurring, and low production efficiency in traditional marking methods, and realizes character feature extraction based on the marking positioning box to obtain marking character features, and performs consistency comparison with the original wire harness identification parameter table, achieving closed-loop information verification from image to semantics. This technology can not only detect the presence of characters, but also determine whether their content is accurate, significantly improving the depth and reliability of the identification quality detection. Attached Figure Description

[0014] 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: Figure 1 This is a flowchart illustrating the steps of the laser marking and automatic identification method for wire beams in an embodiment of the present invention. Figure 2 This is a structural block diagram of the wire beam laser marking and automatic identification system in an embodiment of the present invention; Figure 3 This is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0015] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0016] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein 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.

[0017] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0018] In the description of this invention, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0019] In the description of this invention, unless otherwise explicitly defined, terms such as "set up," "install," and "connect" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.

[0020] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0021] Reference Figure 1 This invention provides a method for laser marking and automatic identification of wire harnesses, comprising the following steps: Step S1: Define the identification information of the target wire harness in a parameterized manner to obtain a wire harness identification parameter table, and convert the marking format of the wire harness identification parameter table to obtain a laser marking instruction.

[0022] Specifically, the parameterization of the identification information of the target wiring harness involves organizing the key data that needs to be marked on the wiring harness, such as model, specifications, batch number, production date, and distribution code, according to a preset data structure and encoding rules. This results in a wiring harness identification parameter table that includes field names, character types, length limits, arrangement order, and special symbol requirements. For example, in automotive wiring harness production, the identification information of a certain model of wiring harness can be defined as "JY-H12345-20251027-BATCH01", and its fields can be mapped to entries such as "prefix=JY", "type=H", "number=12345", "date=20251027", and "batch=BATCH01" in the parameter table. Then, the wiring harness identification parameter table is converted into a labeling format, that is, the structured data in the parameter table is transformed. Based on the instruction protocols supported by the laser marking equipment (such as LST, G-code, or dedicated SDK interface), mapping is performed, and combined with process parameters such as font type, character height, spacing, direction, marking speed, and power template, laser marking instructions that can be directly parsed and executed by the laser controller are generated. For example, the above parameter table is converted into an instruction string containing "TEXT10,50,JY-H12345-20251027-BATCH01,FONT=Arial,HEIGHT=3.0,POWER=60%,SPEED=200mm / s", thereby ensuring that subsequent laser marking processing can accurately reproduce the expected marking content. The entire process is completed automatically by the industrial control system reading order data to build the parameter table and convert the format, without manual intervention, achieving seamless connection from information definition to equipment instructions.

[0023] Step S2: Perform laser marking processing on the target line bundle based on the laser marking command to obtain a laser marking image, and locate the marked area in the laser marking image to obtain a mark positioning frame.

[0024] Specifically, laser marking of the target wire bundle based on the laser marking command involves transmitting the previously generated laser marking command to the control unit of the laser marking equipment. This triggers the laser head to ablate or color-change marks on the outer surface of the target wire bundle according to the position, font, size, and energy parameters set in the command, completing the physical marking process. Subsequently, an industrial camera installed on the production line captures an image containing the marked area in real time after marking, forming a laser marking image. This image includes the wire bundle body and the marked character information, and may contain interference factors such as background noise, uneven lighting, or angle tilt. Next, the marked area is located in the laser marking image, and image preprocessing techniques such as grayscale conversion, binarization, and filtering denoising are used to enhance image quality. Then, the marked area is further processed. Edge detection or template matching algorithms are used to search for regions in an image that match the expected character arrangement features, identify the rectangular range of continuous character distribution, and thus determine and extract the coordinate boundaries of the region, ultimately obtaining the identification positioning box. For example, in the automotive wiring harness production scenario, after the wiring harness is conveyed to the marking station, the system executes the laser marking command to engrave the information "JY-H12345-20251027-BATCH01". The camera then captures an image, and the algorithm locates the character region with a size of approximately 40mm × 5mm above the wiring harness insulation layer in the image, generating an identification positioning box represented by the upper left corner coordinates (x1, y1) and the lower right corner coordinates (x2, y2), providing a spatial reference for subsequent accurate extraction of character features within this region.

[0025] Step S3: Based on the identification positioning frame, extract character features from the laser marking image to obtain identification character features, and perform consistency recognition and verification between the identification character features and the wire harness identification parameter table to obtain the verification result.

[0026] Specifically, character feature extraction from the laser-marked image based on the marker positioning box involves using the spatial coordinate range provided by the marker positioning box to crop out an effective region containing the marked characters from the laser-marked image. This region is then thinned, denoised, and its contour enhanced to highlight the character stroke structure. Subsequently, an image segmentation algorithm is used to separate individual characters from the continuous string. Then, feature extraction algorithms such as Histogram of Oriented Gradients (HOG) or shallow convolutional neural networks (CNN) are used to extract visual features such as the shape, stroke direction, and topological structure of each character, forming a set of digitized feature vectors. Finally, these feature vectors are reassembled in their original order to form the marker character features. These marker character features represent the identifiable features of the actual marked characters in matrix form. Finally, the marker character features are aligned with the wire harness marking parameter table. Character recognition verification involves inputting the extracted character features into a pre-trained character recognition model, which then identifies them as corresponding character sequences. For example, the feature map is parsed as "JY-H12345-20251027-BATCH01". The recognition result is then compared character by character with the expected content defined in the wire harness identification parameter table to determine whether there are deviations such as missing, misaligned, connected, or multiple strokes. The location and type of the difference are recorded, and a visual output containing matching and non-matching regions is generated by image overlay or matrix labeling. Finally, the verification result is obtained. For example, if the recognition result is found to be "JY-H12345-20251027-BATCHOI" during the verification process, where "0" is misidentified as "O", then the position of this character is marked in red in the verification result and labeled "character deviation", thus completing the closed-loop verification process from image features to parameter table content.

[0027] Step S4: When the verification result has a character recognition deviation, the laser marking instruction is dynamically compensated and adjusted based on the verification result so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

[0028] Specifically, when the verification result shows character recognition deviation, the first step is to analyze the mismatched areas and their types identified in the verification result. For example, if the character "0" is found to be misidentified as "O", then the deviation information is used to trace back to the parameter settings that may lead to such errors during the laser marking process, such as laser intensity, scanning speed, or focusing accuracy. Next, the laser marking command is dynamically compensated and adjusted based on the verification result. This includes using machine learning algorithms to analyze similar deviation cases in historical data and the corresponding optimal parameter correction schemes. Then, the current deviation is input into the algorithm model to obtain the best adjustment strategy for this deviation. For example, the model might suggest appropriately reducing the laser intensity and slightly slowing down the scanning speed to improve character edge clarity, thereby avoiding confusion between the number "0" and the letter "O". Subsequently, Based on the parameter adjustment suggestions given by the model, the working parameters of the laser marking equipment are automatically updated, and small-scale test marking is conducted in a non-production environment. The newly generated laser marking image is then verified again using the aforementioned character feature extraction and consistency recognition verification process to ensure that all characters can be accurately recognized. For example, the new test marking result correctly displays "JY-H12345-20251027-BATCH01", and no character deviation is detected in the verification result. This achieves dynamic feedback control from the verification result to the laser marking command, ensuring that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table. By continuously iterating this process, the marking quality can be continuously optimized, ensuring that each wire harness product meets the strict marking specifications.

[0029] In a specific embodiment, the parameterization of the identification information of the target wire harness to obtain a wire harness identification parameter table includes: The identification information of the target wire harness is classified and organized to obtain a wire harness information classification table. The mandatory fields of the wire harness information classification table are then checked to obtain a qualified information table. Based on the verification pass information table, the parameter format is defined to obtain the information format template, and the information format template is filled and matched with the verification pass information to obtain the harness identification parameter table.

[0030] Specifically, the process of parameterizing the identification information of the target wire harness to obtain the wire harness identification parameter table first requires a comprehensive and detailed classification and organization of the identification information of the target wire harness, thereby forming a wire harness information classification table. In this process, all relevant information such as production date, batch number, model and specifications need to be classified according to certain logic and standards. For example, for the identification content JY-H12345-20251027-BATCH01, it is divided into three parts: product model (JY-H12345), production date (20251027), and batch number (BATCH01), and it is ensured that each part accurately reflects the characteristics and status of the wire harness. Next, the required fields in the harness information classification table are validated. Data integrity is ensured by checking whether each category contains the necessary information. For example, in the above example, if the production date or batch number is missing, the qualified information table cannot be constructed. Therefore, it is necessary to confirm that all key fields are filled in to generate a qualified information table. Subsequently, the parameter format is defined based on the qualified information table. This step aims to set specific format rules for various types of information. For example, the production date should follow the format YYYYMMDD, and the batch number should be represented by "BATCH" followed by a numerical sequence. This forms an information format template to ensure that there is a unified standard to follow in subsequent operations. Next, the information format template is filled and matched with the qualified information. That is, each specific identification information item is adjusted or reorganized according to the determined format specifications to make them conform to the requirements of the established template. For example, the original non-standard production date expression such as "October 27, 2025" needs to be converted into the form of "20251027" to match the template. At the same time, any information that does not conform to the expected format needs to be corrected or supplemented to ensure that all data can be seamlessly connected to the corresponding fields, so as to finally obtain a wire harness identification parameter table with a complete structure and uniform format. Based on this, assuming a new wire harness product needs to be identified, with initial information as "Product Model: JY-H12346 Production Date: November 1, 2025 Batch: 02", it is first broken down and standardized according to the classification and standardization principle into "Product Model: JY-H12346 Production Date: 20251101 Batch Number: BATCH02". Then, all necessary elements are verified to be complete according to the required fields. Next, each item is formatted according to the predefined parameter format. Finally, these processed data are filled into the corresponding format template to form a complete wire harness identification parameter table. This allows both manual review and automated system processing to quickly and accurately obtain the required information, thereby ensuring the efficient operation of the entire wire harness production and management process.This approach not only improves data consistency and accuracy but also provides strong support for subsequent tasks such as quality tracking, inventory management, and logistics scheduling, ensuring that every record is accurate and easy to parse.

[0031] In a specific embodiment, the step of converting the marking format of the wire harness identification parameter table to obtain laser marking instructions includes: The character parameters in the wire harness identification parameter table are matched and converted with the preset marking device vector library to obtain vector characters, and the marking parameters of the vector characters are configured to obtain device parameters; The device parameters are compiled with the preset control protocol of the laser marking device to obtain the initial instruction code, and the device response is tested on the initial instruction code to obtain the laser marking instruction.

[0032] Specifically, the character parameters in the wire harness identification parameter table are matched and converted with the preset marking equipment vector library. This involves searching for the corresponding vector path data in the built-in or external vector font library of the laser marking equipment for each character defined in the wire harness identification parameter table, including letters, numbers, and special symbols. This vector library stores the geometric contour information of each character under each supported font (such as Arial, Times New Roman, or a dedicated industrial font), describing its stroke direction using coordinate point sequences and Bézier curves. For example, if the wire harness identification parameter table contains the character sequence "JY-H12345-20251027-BATCH01", the system will retrieve the vector definitions of characters such as "J", "Y", "-", and "H" under the specified font and concatenate them sequentially into a complete graphic path structure, thereby generating a vector character that completely corresponds to the identification content. This vector character not only retains the shape characteristics of the character but also has the advantages of being scalable and non-deformable, making it suitable for marking tasks with different size requirements. Then, the vector character is marked with parameters... The configuration process involves assigning specific equipment execution parameters to the graphic path based on the vector characters and the actual marking process requirements. These parameters include setting the percentage of laser output power, scanning speed (mm / s), acceleration, focal length position, character height to width ratio, character spacing compensation value, and whether to enable rotation or mirroring functions. These parameters are pre-configured into templates based on the wire harness material type (such as PVC or XLPE insulation layer) and past process experience, and dynamically adapted to the current vector characters to form a complete set of equipment parameters. For example, for PVC materials that are more easily ablated, the system automatically selects the combination of "low power 60% + high speed 200mm / s" to avoid edge carbonization.The device parameters are then compiled with the preset control protocol of the laser marking equipment. This involves encoding and encapsulating the configured device parameters and path data in the vector characters according to the communication protocol format supported by the target laser controller. Common protocols include LaserStation Script (LST), SCPI instruction sets, or manufacturer-specific SDK instruction formats. The compilation process converts the vector path into motion control commands that the device can parse (such as X / Y axis galvanometer deflection angle sequences) and embeds parameters such as power and speed into the corresponding instruction segments. Finally, an initial instruction code containing a complete marking action sequence is generated, for example, in the form of "@LASER ON, POWER=60%, SPEED=200, FONT=VECTOR, The initial instruction code is either a textual or binary command stream named "TEXTJY-H12345-20251027-BATCH01". Then, a device response test is performed on the initial instruction code. This involves sending the initial instruction code to the control unit of the laser marking equipment via an industrial communication interface (such as RS-485, Ethernet, or EtherCAT). The entire instruction flow is simulated without actual light output, detecting for syntax errors, path out-of-bounds errors, parameter exceeding limits, or communication timeouts. The status feedback information returned by the equipment is recorded. If an anomaly is detected, the process is paused and a correction is prompted. If the equipment successfully parses the code and returns a "Ready" status, the initial instruction code is confirmed to be valid. Finally, it is solidified into a laser marking instruction that can be put into actual production. For example, on an automotive wiring harness production line, the laser marking instruction generated after the system completes the above process can be called to drive the laser head to accurately mark clear and legible markings that meet the parameter table requirements on the moving wiring harness surface.

[0033] In a specific embodiment, the step of performing laser marking processing on the target line bundle based on the laser marking command to obtain a laser-marked image includes: The target wire bundle is clamped and positioned to obtain wire bundle positioning information. The marking area of ​​the wire bundle positioning information is calibrated based on the marking position parameters in the laser marking command to obtain calibration positioning parameters. The focal length of the lens of the laser marking equipment is adjusted based on the calibration and positioning parameters, and the laser energy of the adjusted laser marking equipment is pre-tested to obtain an energy test diagram. Based on the optimal energy parameters determined by the energy test diagram, the target line bundle is laser-marked in combination with the optimal energy parameters and the laser marking command to generate an initial marked line bundle. The marking area of ​​the initial marked line bundle is then imaged to obtain an initial marked image. The initial marking image is subjected to a sharpness test to obtain a sharpness score, and the initial marking image is then color-corrected based on the sharpness score to obtain a laser marking image.

[0034] Specifically, the target wire harness is clamped and positioned by using mechanical fixtures or vacuum adsorption devices on an automated production line to fix the wire harness to be marked at a preset processing station, preventing the marking from shifting due to vibration or movement during the marking process. After clamping, an industrial camera installed in a fixed position photographs the entire wire harness, acquiring a visual image containing the wire harness's shape, relative position, and approximate coordinates of the marking area, forming wire harness positioning information. This positioning information serves as the basis for subsequent spatial coordinate mapping. Then, based on the marking position parameters in the laser marking command, the marking area is calibrated using the wire harness positioning information. This involves aligning the preset marking start coordinates (e.g., 30mm from the end of the wire harness) in the laser marking command with the wire harness's position. The physical position in the harness positioning information is aligned with coordinates. An image registration algorithm is used to identify fixed feature points on the harness (such as connector positions, color mark rings, or bending inflection points). The affine transformation matrix between the actual image coordinate system and the equipment motion coordinate system is calculated to correct positioning errors caused by clamping deviations or viewing angle tilts. Finally, after processing by the calibration algorithm, calibration positioning parameters containing the precise marking start point and character arrangement direction are generated. For example, in the automotive harness production scenario, when the system identifies that the actual position of the connector of a JY-H12345 model harness is offset by 2.3mm from the standard, the marking area is automatically compensated forward by 2.3mm in the calibration positioning parameters to ensure that the marking is engraved within the specified range of the insulation layer. Adjusting the lens focal length of the laser marking equipment based on the calibration and positioning parameters involves automatically adjusting the Z-axis of the laser galvanometer or the focal length of the motorized zoom lens, based on the spatial distance between the marking area and the laser head as indicated in the calibration and positioning parameters, combined with the lens's depth-of-field parameters and focusing curve model. This ensures that the laser spot achieves the minimum diameter and maximum energy density on the target marking surface, guaranteeing marking clarity. For example, when the outer diameter of the wire bundle fluctuates by ±0.5mm due to different batches, the system dynamically adjusts the focal length using a ranging sensor or a pre-calibrated 3D model to ensure focusing accuracy. Subsequently, a laser energy pre-test is performed on the adjusted laser marking equipment. This involves performing low-power pulse marking on non-critical areas of the wire bundle (such as the end section) or on a dedicated test substrate without formal marking, forming a set of tiny marker dots under different energy gradients. The camera captures and records the ablation effect, generating an energy test map. This energy test map contains visual information such as the contrast, edge sharpness, and material damage degree of the markings at different powers (e.g., 50%, 60%, 70%).The optimal energy parameters determined based on the energy test map are obtained by using image analysis algorithms to perform grayscale statistics, edge gradient calculation, and regional uniformity evaluation on each test point in the energy test map. The energy value with the highest contrast and sharpest edges, without causing burn-through or carbonization, is selected as the optimal energy parameter. For example, if analysis shows that character edges are clear and without overflow at 65% power, while slight burrs appear at 70%, then 65% is selected as the optimal value. Then, the target line bundle is laser-marked using the optimal energy parameters and the laser marking command. This involves embedding the optimal energy parameters into the power field of the original laser marking command and calling... After calibrating the device coordinates and focusing parameters, the laser head is driven to perform a complete character sequence engraving action on the clamped and positioned wire bundle surface, generating a preliminary marked wire bundle with the information "JY-H12345-20251027-BATCH01". Next, the marking area of ​​the preliminary marked wire bundle is imaged. This is done by using a high-resolution industrial camera to vertically photograph the marking area of ​​the preliminary marked wire bundle under standard lighting conditions, capturing the original image containing character color, background texture, light distribution, and possible defects (such as broken strokes or adhesion), forming the preliminary marked image. This image serves as a direct basis for quality assessment. The initial marking image undergoes sharpness detection by using Sobel or Laplacian operators to analyze edge sharpness and calculate the average gradient magnitude of character stroke regions as a sharpness score. A heatmap is generated to display the sharpness scores of locally blurred or out-of-focus areas. For example, if the score of a character on the right side of the image is below a threshold, it indicates potential under-focusing in that area. Finally, color correction is performed on the initial marking image based on the sharpness score. This involves applying adaptive histogram equalization, contrast stretching, or gamma correction algorithms, based on the distribution characteristics of low-scoring areas in the sharpness score, to enhance the grayscale difference between characters and the background and suppress the effects of uneven illumination. This makes characters with insufficient contrast clearly distinguishable, ultimately outputting an optimized laser marking image suitable for subsequent character feature extraction, ensuring sufficient image quality for subsequent recognition and verification.

[0035] In a specific embodiment, the step of locating the marked area in the laser-marked image to obtain the marked positioning box includes: The laser marking image is subjected to background grayscale suppression processing to obtain a background suppressed image, and the background suppressed image is subjected to marking feature enhancement to obtain a feature enhanced image; Based on the feature-enhanced image, character connected component detection is performed to obtain a character connected component map, and candidate regions are filtered from the character connected component map to obtain candidate bounding boxes. The pixels within the candidate frame are verified for character arrangement to obtain an arrangement verification image. When the arrangement verification image shows that the characters within the candidate frame have uneven spacing, offset direction, or overall arrangement that does not conform to the expected rules, the candidate frame boundary is dynamically stretched and adjusted based on the arrangement verification image to obtain the identifier positioning frame.

[0036] Specifically, background grayscale suppression processing of the laser marking image addresses the background brightness fluctuations caused by uneven wire sheath material, differences in light reflection, or ambient light interference. An adaptive local grayscale correction algorithm is used to preprocess the entire image. By constructing a background brightness estimation model, morphological opening operations or Gaussian low-pass filtering are used to extract low-frequency background components from the image, and these components are subtracted from the original laser marking image. This reduces grayscale variations in non-character areas, highlights the contrast difference between the characters and the substrate, and generates a more uniform background-suppressed image. Next, the background-suppressed image undergoes feature enhancement, which is based on the background-suppressed image... The process involves applying a sharpening filter (such as an unsharpened mask) and contrast-limited adaptive histogram equalization (CLAHE) to enhance the gradient intensity of character edges and the clarity of texture within strokes. This makes shallowly engraved characters, which were originally caused by insufficient laser energy or uneven material absorption, more prominent, ultimately resulting in a feature-enhanced image with more prominent features and easier-to-identify structure. For example, in the automotive wiring harness production scenario, when the character color of a JY-H12345 model wiring harness is lighter after marking due to batch differences in PVC material, the outline of the character "JY-H12345-20251027-BATCH01" is significantly enhanced after the above processing, providing a reliable basis for subsequent positioning. Character connected component detection based on the enhanced image involves converting the enhanced image into a binary image. Typically, the Otsu's method or adaptive thresholding is used to determine the optimal segmentation threshold, making the character region appear as a white foreground pixel and a black background. Then, 8-neighborhood connectivity analysis is used to identify all interconnected white pixel regions. Each independent connected region is a candidate character block, and its geometric attributes such as the coordinates of its minimum bounding rectangle, area, and aspect ratio are recorded to form a character connected component map containing all potential character regions. Subsequently, candidate region filtering is performed on the character connected component map, based on a preset character size range, shape proportion, and spatial distribution pattern, eliminating regions with excessively small areas. Connected regions that are too large (e.g., noisy points), too large (e.g., connected characters), or have abnormal shapes (e.g., non-rectangular) are identified. Clustering algorithms (e.g., DBSCAN or K-means) are used to group the remaining valid character blocks according to their positional clustering in the horizontal or vertical direction. The system then determines which group of connected regions is most likely to form a continuous sequence of identifier strings. For example, when identifying “JY-H12345-20251027-BATCH01”, the system will select 16 character block combinations that are located on the same horizontal line, have similar spacing, and match in number, while excluding other isolated or scattered areas. Finally, this group is retained as the main candidate area, and its bounding rectangles are merged to generate preliminary identifier candidate boxes.Verifying the character arrangement of pixels within the candidate identification box involves in-depth analysis of the spatial distribution characteristics of each character's connected components. This includes calculating the center distance, relative angle, and overall linearity of the arrangement between adjacent characters, generating an arrangement verification image that reflects the consistency of character spacing, direction, and arrangement regularity. For example, if the distance between the 8th and 9th characters is significantly greater than the spacing between other characters, or if the overall character line exhibits a slight arc rather than the expected straight line arrangement, this abnormal area is marked in the arrangement verification image. When the arrangement verification image shows uneven character spacing, directional deviation, or overall arrangement not conforming to expected rules within the candidate box, it indicates that the initial candidate box may be truncated or contain redundancy. To address the issue of redundant areas, the candidate box boundaries need to be dynamically scaled and adjusted based on the arrangement verification image. Specific operations include: if the edges of the first and last characters are not fully contained, the candidate box boundaries are expanded outwards along the arrangement direction; if a break occurs in the middle, it is checked whether the characters are not correctly segmented due to adhesion, and morphological closing operations are attempted to connect the breakpoints before re-detection; if the overall arrangement is tilted, the linear equation of the line connecting the character centers is fitted, the coordinate system is rotated, and the enclosing rectangle is recalculated; finally, through multiple iterative adjustments, the candidate box accurately encloses all valid characters without any redundant blank areas, resulting in an accurate and appropriate labeling location box that adapts to the actual labeling shape, ensuring that subsequent character feature extraction can be performed within the correct area.

[0037] In a specific embodiment, the step of extracting character features from the laser marking image based on the marker positioning box to obtain marker character features includes: The image within the positioning box is binarized to obtain a binary image within the box, and noise pixels are removed from the binary image within the box to obtain a clean character image. The net character image is segmented to obtain a set of single character images, and the size of the single character image set is normalized to obtain standard characters; Extract the stroke features of the characters from the standard characters, and mark the stroke features with structural features to obtain structural features; The structural features are combined to obtain character composite features, and the character composite features are superimposed pixel by pixel to obtain identifier character features.

[0038] Specifically, in processing the image within the marker positioning box, the laser marking image within the box is first binarized. This process involves converting the grayscale image within the box to a black-and-white image, maximizing the contrast between the character and the background, thus obtaining the binary image within the box. Next, to improve the accuracy of character recognition, noise pixel removal is performed on the binary image within the box. This step is mainly achieved by filtering out discontinuous small-area pixels, which usually represent noise in the image rather than actual character parts. After processing, a clean character image is obtained. Next, character segmentation is performed on the clean character image to separate individual characters from the overall image, forming a set of individual character images. This is achieved by calculating the spacing between characters and the character outlines. Then, the size of each character in the single-character image set is normalized to ensure that all character images have the same size, facilitating subsequent feature extraction and comparison, thus obtaining standard characters. For each character in the standard character set, its stroke features need to be extracted, including the direction, length, and intersections of the lines within the character. These stroke features are then labeled with structural features to highlight the character's unique structural characteristics, such as the connection point between the vertical line and the horizontal line in the shape of an "H". This step helps to more accurately describe the character's shape, thus obtaining structural features. After obtaining the structural features, the next step is feature combination. Different structural features are combined according to certain logic or algorithms to form a comprehensive feature that fully reflects the character's characteristics—the character comprehensive feature. This step may involve integrating information about the character's shape, proportions, and spatial layout to achieve the most accurate character representation. Finally, the character comprehensive feature is converted into a computer-recognizable digital form. The final identifier character feature is generated through pixel overlay. This image is an abstract representation of the character content in the original laser-marked image and can be used in subsequent consistency verification processes. For example, on a target wire harness production line, suppose there is a batch of wire harnesses that need to be marked with a specific model code. Using the above method, laser marking technology is first used to mark the surface of the wire harnesses with a mark containing the model code. Subsequently, the system automatically scans the marked wire bundles, uses the marker positioning box to accurately locate the marked area, and performs a series of operations such as binarization, noise removal, character segmentation, and size normalization until the features of the marked characters are obtained. If the actual marking is found to be inconsistent with the expectation during the verification process, such as a missing horizontal line of a character, the system will dynamically adjust the laser marking parameters according to the deviation and re-compensate and correct the marking to ensure that the final marking result fully meets the preset requirements.The entire process not only ensures the accuracy of the marking but also greatly improves the automation level and efficiency of the production line. Furthermore, the specific steps for overlaying the character composite features to obtain the identifying character features are as follows: After obtaining the character composite features, the process of converting these features into pixel information and overlaying them is a crucial step in constructing the identifying character feature map. First, based on the character stroke features and structural feature markings contained in the character composite features, the pixel position and color value corresponding to each feature element are determined. This step requires precise calculation to ensure the accuracy of the character shape. Then, based on the combination method of the character composite features, different structural features are sequentially mapped onto a blank image according to their relative positional relationships. In this process, each structural feature is converted into a specific set of pixels, and the color and brightness of the corresponding pixels are adjusted according to details such as the thickness, length, and intersections of the character strokes. For example, after laser marking a specific model code on a wire harness production line, the character composite features obtained through the above method contain all the necessary information to reconstruct the identifying character feature map. When performing pixel overlay, the specific pixel coordinates of the connection point between the vertical line representing the character "H" and the horizontal line in the middle are first identified. Then, based on these coordinates and preset pixel rules, the pixels representing each part are drawn one by one on the image, ultimately forming a clearly recognizable "H" character pattern. In this way, by progressively overlaying the pixel representation of each character, the entire logo character feature map is completely reconstructed, thus realizing the conversion process from comprehensive character features to a visualized logo character feature map. This ensures accurate character reproduction and facilitates subsequent quality inspection and verification. Throughout the entire process, consistency with the original application scenario is maintained, ensuring high-precision reproduction of laser-marked characters.

[0039] In a specific embodiment, the step of performing consistency verification between the identifier character features and the wire harness identifier parameter table to obtain the verification result includes: Based on the harness identification parameter table, the expected character features are extracted to obtain the expected features. The expected features are then aligned with the identification character features in terms of feature dimensions to obtain an aligned feature map. The alignment feature map is compared character by character to obtain a character comparison map, and the feature matching rate is calculated based on the character comparison map to obtain a matching rate statistics table; Characters with matching rates below a preset threshold in the matching rate statistics table are marked with differences to obtain a difference marker map. The difference marker map is then superimposed and integrated with the character comparison map to obtain the verification result.

[0040] Specifically, the process of extracting expected character features based on the harness identification parameter table to obtain expected features, and aligning the expected features with the identification character features to obtain an aligned feature map, firstly requires reading the idealized feature template corresponding to each character from the predefined harness identification parameter table. These templates typically contain the best visual representation of a specific character under conditions without any physical or optical interference, including information such as stroke thickness, proportional relationships, and topological structure. Then, these idealized character images are processed using the same algorithm (e.g., edge detection, histogram of oriented gradients calculation) to generate a feature map that matches the identification character features. The expected features are of the same format and resolution. Next, to ensure accurate comparison between the two feature maps, a feature dimension alignment step must be performed. This involves adjusting the coordinate system, scaling ratio, and rotation angle in the expected features to be completely consistent with the identifier character features. For example, if the original size of the character "B" in the wire harness identifier parameter table is 100×100 pixels, while the actual size of the corresponding character in the identifier character features is 80×80 pixels, then the expected features need to be scaled to 80×80 pixels using bilinear interpolation, while ensuring that its internal structural features are not distorted, thereby obtaining an accurately matched aligned feature map. In the process of performing character-by-character feature comparison on the aligned feature map to obtain a character comparison map, and calculating the feature matching rate based on the character comparison map to obtain a matching rate statistics table, the aligned expected features and the identifier character features are first segmented according to the character bounding boxes to ensure that each individual character has an independent feature region for comparison. Then, for each character, a similarity measurement algorithm such as Normalized Cross-Relation Coefficient (NCC) or Structural Similarity Index (SSIM) is used to compare the differences between the expected features and the identifier character features pixel by pixel. For characters with obvious unique structures (such as the letter "G" and the number "9"), even slight deformations can be identified with high accuracy, thus generating a character comparison map that reflects the degree of similarity between the two. Based on this, the feature matching rate of each character is calculated based on the data in the character comparison map, that is, the proportion of the overlapping part of the effective feature region in the expected features and the corresponding position in the actual identifier character features to the total area. The results of all characters are summarized to form a matching rate statistics table. This table not only records the specific matching score of each character, but also provides a basis for overall consistency evaluation.The process involves marking the differences in characters with matching rates below a preset threshold in the matching rate statistics table to obtain a difference marker map. This difference marker map is then overlaid and integrated with the character comparison map to obtain the verification result. First, a reasonable matching rate threshold is set, such as 90%. Characters with matching rates below this value are considered to have significant differences. Then, the matching rate statistics table is traversed to find all characters with matching rates below this threshold, and the specific locations and discrepancies of these characters are marked in the difference marker map. For example, if the upper part of the character "5" is missing or its curvature angle is incorrect, this area is marked with a red box in the difference marker map. Finally, the difference marker map is overlaid and integrated with the previously generated character comparison map, essentially adding the difference markers as a transparent overlay layer on top of the character comparison map. This allows users to visually see where the problems occur. The final verification result not only shows the overall matching status of the entire identified character sequence but also clearly indicates which characters have problems and their specific defect types and locations, facilitating subsequent correction work. For example, in an automated quality control system on an automotive production line, when inspecting wiring harness markings on a vehicle, if a small section of the bottom of the "T" in the marking character "20251027-BATCH01" on a certain wiring harness is missing, resulting in a matching rate of only 85%, the verification results will clearly show the location of the character and the specific details of the difference, thereby helping engineers quickly locate and fix this error.

[0041] The above describes the method for laser marking and automatic identification of the wire beam in the embodiments of the present invention. The following describes the system for laser marking and automatic identification of the wire beam in the embodiments of the present invention. Please refer to [link / reference]. Figure 2 One embodiment of the wire beam laser marking and automatic identification system of the present invention includes: The conversion module 21 is used to parameterize the identification information of the target wire harness to obtain a wire harness identification parameter table, and to convert the marking format of the wire harness identification parameter table to obtain a laser marking instruction; The positioning module 22 is used to perform laser marking processing on the target line bundle based on the laser marking command to obtain a laser marking image, and to locate the marked area of ​​the laser marking image to obtain a mark positioning frame; Extraction module 23 is used to extract character features from the laser marking image based on the marking positioning frame, obtain marking character features, and perform consistency recognition and verification between the marking character features and the wire harness marking parameter table to obtain the verification result; The adjustment module 24 is used to dynamically compensate and adjust the laser marking command based on the verification result when there is a character recognition deviation in the verification result, so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

[0042] In this embodiment, the specific implementation of each unit in the above system embodiment is described in the above method embodiment, and will not be repeated here.

[0043] like Figure 3 As shown in the diagram, this embodiment of the invention provides a structural schematic block diagram of a computer device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described method for laser marking and automatic identification of wire harnesses.

[0044] It is evident that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented in this device embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0045] Furthermore, this application also discloses a computer program product or computer program stored in a computer-readable storage medium. A processor of a computer device can read the computer program from the computer-readable storage medium and execute the computer program, causing the computer device to perform the aforementioned wire-beam laser marking and automatic identification method. Similarly, the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0046] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for laser marking and automatic identification of a wire bundle, characterized in that, Includes the following steps: The identification information of the target wire harness is parameterized to obtain a wire harness identification parameter table, and the marking format of the wire harness identification parameter table is converted to obtain a laser marking instruction; The target line bundle is laser-marked based on the laser marking command to obtain a laser-marked image, and the marked area is located in the laser-marked image to obtain a marked positioning box. Based on the identification positioning frame, character features are extracted from the laser marking image to obtain identification character features. The identification character features are then matched with the wire harness identification parameter table for consistency verification to obtain the verification result. When the verification result shows a character recognition deviation, the laser marking instruction is dynamically compensated and adjusted based on the verification result so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

2. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The parameterization of the target harness identification information to obtain a harness identification parameter table includes: The identification information of the target wire harness is classified and organized to obtain a wire harness information classification table. The mandatory fields of the wire harness information classification table are then checked to obtain a qualified information table. Based on the verification qualified information table, the parameter format is defined to obtain the information format template, and the information format template is filled and matched with the verification qualified information table to obtain the harness identification parameter table.

3. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The step of converting the marking format of the wire harness identification parameter table to obtain laser marking instructions includes: The character parameters in the wire harness identification parameter table are matched and converted with the preset marking device vector library to obtain vector characters, and the marking parameters of the vector characters are configured to obtain device parameters; The device parameters are compiled with the preset control protocol of the laser marking device to obtain the initial instruction code, and the device response is tested on the initial instruction code to obtain the laser marking instruction.

4. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The step of performing laser marking processing on the target line bundle based on the laser marking command to obtain a laser-marked image includes: The target wire bundle is clamped and positioned to obtain wire bundle positioning information. The marking area of ​​the wire bundle positioning information is calibrated based on the marking position parameters in the laser marking command to obtain calibration positioning parameters. The focal length of the lens of the laser marking equipment is adjusted based on the calibration and positioning parameters, and the laser energy of the adjusted laser marking equipment is pre-tested to obtain an energy test diagram. Based on the energy test diagram, the optimal energy parameters are determined. The target line bundle is laser-marked in combination with the optimal energy parameters and the laser marking command to generate an initial marked line bundle. The marking area of ​​the initial marked line bundle is then imaged to obtain an initial marked image. The initial marking image is subjected to a sharpness test to obtain a sharpness score, and the initial marking image is then color-corrected based on the sharpness score to obtain a laser marking image.

5. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The step of locating the marked area in the laser-marked image to obtain the marked positioning box includes: The laser marking image is subjected to background grayscale suppression processing to obtain a background suppressed image, and the background suppressed image is subjected to marking feature enhancement to obtain a feature enhanced image; Based on the feature-enhanced image, character connected component detection is performed to obtain a character connected component map, and candidate regions are filtered from the character connected component map to obtain candidate bounding boxes. The pixels within the candidate identification box are verified for character arrangement to obtain an arrangement verification image. When the arrangement verification image shows that the character arrangement within the candidate identification box has uneven character spacing, offset arrangement direction, or overall arrangement does not conform to the expected rules, the candidate box boundary is dynamically stretched and adjusted based on the arrangement verification image to obtain the identification positioning box.

6. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The step of extracting character features from the laser marking image based on the marker positioning box to obtain marker character features includes: The image within the positioning box is binarized to obtain a binary image within the box, and noise pixels are removed from the binary image within the box to obtain a clean character image. The net character image is segmented to obtain a set of single character images, and the size of the single character image set is normalized to obtain standard characters; Extract the stroke features of the characters from the standard characters, and mark the stroke features with structural features to obtain structural features; The structural features are combined to obtain character composite features, and the character composite features are superimposed pixel by pixel to obtain identifier character features.

7. The method for laser marking and automatic identification of wire harnesses according to claim 1, characterized in that, The step of performing consistency verification between the identifier character features and the wire harness identifier parameter table to obtain the verification result includes: Based on the harness identification parameter table, the expected character features are extracted to obtain the expected features. The expected features are then aligned with the identification character features in terms of feature dimensions to obtain an aligned feature map. The alignment feature map is compared character by character to obtain a character comparison map, and the feature matching rate is calculated based on the character comparison map to obtain a matching rate statistics table; Characters with a match rate below a preset threshold in the matching rate statistics table are marked with differences to obtain a difference marker map. The difference marker map is then overlaid and integrated with the character comparison map to obtain the verification result.

8. A laser marking and automatic identification system for wire harnesses, characterized in that, include: The conversion module is used to parameterize the identification information of the target wire harness to obtain a wire harness identification parameter table, and to convert the marking format of the wire harness identification parameter table to obtain laser marking instructions; The positioning module is used to perform laser marking processing on the target line bundle based on the laser marking command to obtain a laser marking image, and to locate the marked area of ​​the laser marking image to obtain a mark positioning frame; The extraction module is used to extract character features from the laser marking image based on the identification positioning frame, obtain identification character features, and perform consistency recognition and verification between the identification character features and the wire harness identification parameter table to obtain the verification result. The adjustment module is used to dynamically compensate and adjust the laser marking command based on the verification result when there is a character recognition deviation in the verification result, so that the actual marking content of the target wire harness is completely consistent with the expected marking information in the wire harness marking parameter table.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images