Paper tape carrier measurement method, apparatus and device

Abstract

The application is suitable for the technical field of carrier tape measurement, and particularly relates to a paper carrier tape measurement method, device and equipment. The method comprises the following steps: obtaining image data of a paper carrier tape to be measured, and dividing each continuous area of the carrier tape into image groups to be measured, each image group containing sub-images to be measured in different measurement dimensions and completely covering various measurement parameters of the carrier tape; calculating measurement values of each sub-image to be measured based on the image data; comparing the measurement values of each sub-image to be measured with a corresponding dimension standard value set, and obtaining a qualified domain for domain integration in the case of matching a target standard value, so that unified determination of measurement results in different dimensions can be realized; and through integration of image groups recorded by the qualified domain and in combination with error elimination operation, systematic deviation caused by the action between the material flexibility of the paper carrier tape itself and the mechanical tension of a production line is eliminated, so that the accuracy and comparability of measurement are improved.

Description

Technical Field

[0001] This application belongs to the field of carrier tape measurement technology, and in particular relates to a method, apparatus and equipment for measuring paper carrier tape. Background Technology

[0002] In modern electronic component and semiconductor packaging and automated production processes, paper carrier tape serves as a crucial medium for carrying and transporting small components, playing a critical role in transportation and protection from the production line to the assembly stage. The dimensional accuracy, hole arrangement, pitch consistency, and width stability of the paper carrier tape directly affect the automated picking, soldering accuracy, and overall assembly quality of subsequent components. Therefore, high-precision measurement and quality control of paper carrier tape are essential for ensuring the stability of the production process and the reliability of the end product.

[0003] Currently, the measurement methods for paper carrier tapes mainly rely on manual inspection or traditional optical testing methods. Technicians typically perform sampling measurements of the tape's hole positions, pitch, and width using visual inspection or simple measuring tools, and then make judgments based on standard values. These methods can, to some extent, detect obvious defects and ensure the basic qualification of the carrier tape. However, existing measurement methods have significant limitations. Manual measurement is inefficient, has limited accuracy, and is difficult to perform comprehensive measurements over continuous areas, easily leading to missed detections or misjudgments. Although optical testing improves measurement accuracy, it still has limitations in image acquisition, measurement value processing, and standard value matching in practical applications. For example, factors such as changes in ambient light, camera position offset, and minor deformation of the carrier tape can introduce systematic errors, making it difficult to guarantee the consistency of measurement results on a global scale. Unlike rigid substrates (such as PCBs and glass substrates), paper carrier tapes undergo nonlinear periodic elastic deformation and irreversible plastic tensile deformation during transport due to the interaction between the material's flexibility and the mechanical tension of the production line. At the same time, the moisture absorption and expansion of paper fibers and the drying and shrinkage further exacerbate the local dimensional drift of the carrier tape along the transport direction. These combined factors lead to random, systematic deviations in the actual physical values ​​of the same dimensional parameter on paper carriers at different pitch segments. These deviations exhibit pitch correlation rather than pure randomness, posing a unique technical challenge to traditional visual measurement methods based on global calibration. Summary of the Invention

[0004] This application provides a paper carrier tape measurement method, apparatus, and equipment, which can solve the problem of dimensional drift caused by the interaction between the flexibility of the paper carrier tape material itself and the mechanical tension of the production line.

[0005] In a first aspect, embodiments of this application provide a paper carrier tape measurement method, including: Acquire image data of a paper carrier tape to be measured; wherein, the image data includes at least one group of images to be measured; the group of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous region of the paper carrier tape is a group of images to be measured, and the group of images to be measured includes sub-images to be measured corresponding to different parameters or different positions; Based on the image data of the paper carrier tape to be measured, the measurement value of the sub-image to be measured in each group of images to be measured is calculated; Based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set, a recording operation is performed on the group of images to be measured. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, at least one qualified domain pointed to by the target standard value is obtained and the domain is integrated, and the group of images to be measured is recorded into the integrated qualified domain. Error elimination is performed on all the image groups to be measured recorded in the integrated qualified field, and the measurement of the paper carrier tape to be measured is completed.

[0006] The technical solutions described in this application embodiment have at least the following technical effects: The paper carrier tape measurement method provided in this application acquires image data of the paper carrier tape to be measured and divides each continuous area of ​​the carrier tape into a group of images to be measured. Each image group contains sub-images to be measured in different measurement dimensions, which can completely cover various measurement parameters of the carrier tape, ensuring the comprehensiveness and continuity of the measurement. The measurement value of each sub-image to be measured is calculated based on the image data, eliminating the need for manual intervention in the measurement process, significantly improving measurement efficiency, and avoiding subjective errors that may be caused by manual measurement. The measurement value of each sub-image to be measured is compared with the corresponding set of standard values ​​for each dimension, and qualified regions are obtained and integrated when matching the target standard values. This enables unified judgment of measurement results in different dimensions, avoiding the classification confusion and information redundancy problems caused by the dispersion of multi-dimensional data in traditional methods. By integrating the image groups recorded in the qualified regions and combining them with error elimination operations, the systematic deviation caused by the interaction between the flexibility of the paper carrier tape material itself and the mechanical tension of the production line is eliminated, ensuring that the measurement values ​​of each object to be measured are consistent on a global scale, improving the accuracy and comparability of paper carrier tape measurement.

[0007] Secondly, embodiments of this application provide a paper carrier tape measuring device, comprising: An acquisition unit is used to acquire image data of a paper carrier tape to be measured; wherein, the image data includes at least one group of images to be measured; the group of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous area of ​​the paper carrier tape is a group of images to be measured, and the group of images to be measured includes sub-images to be measured corresponding to different parameters or different positions; A measurement unit is used to calculate the measurement value of the sub-image to be measured in each group of images to be measured based on the image data of the paper carrier tape to be measured; The integration unit is used to perform a recording operation on the image group to be measured based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, the unit obtains at least one qualified domain pointed to by the target standard value and performs domain integration, and records the image group to be measured into the integrated qualified domain. The result unit is used to perform error elimination on all the image groups to be measured recorded in the integrated qualified field and to complete the measurement of the paper carrier tape to be measured.

[0008] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any of the foregoing aspects.

[0009] Fourthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any of the above aspects.

[0010] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the above aspects, and will not be repeated here. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a paper carrier tape measurement method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the operation of a paper carrier tape measurement method provided in an embodiment of this application; Figure 3This is a schematic diagram of the paper carrier tape to be measured in a paper carrier tape measurement method provided in an embodiment of this application; Figure 4 This is a graph showing the measurement data after measurement of a paper carrier tape measurement method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a paper carrier tape measuring device provided in one embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0013] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0014] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0015] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0016] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determination" or "if the described condition or event is detected" may be interpreted, depending on the context, as "once determination," "in response to determination," "once the described condition or event is detected," or "in response to the detection of the described condition or event."

[0017] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0018] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0019] Currently, the measurement methods for paper carrier tapes mainly rely on manual inspection or traditional optical testing methods. Technicians typically use visual inspection or simple measuring tools to sample and measure the hole positions, pitch, and width of the carrier tape, and then make judgments based on standard values. These methods can detect obvious defects to a certain extent and ensure the basic qualification of the carrier tape. However, existing measurement methods have significant limitations. Manual measurement is inefficient, has limited accuracy, and is difficult to measure continuously over a wide area, easily leading to missed detections or misjudgments. Although optical testing improves measurement accuracy, it still has limitations in image acquisition, measurement value processing, and standard value matching in practical applications. For example, factors such as changes in ambient light, camera position offset, and slight deformation of the carrier tape can introduce systematic errors, making it difficult to ensure the consistency of measurement results on a global scale. Unlike rigid substrates (such as PCBs and glass substrates), paper carrier tapes undergo nonlinear periodic elastic deformation and irreversible plastic tensile deformation during transport due to the interaction between the material's flexibility and the mechanical tension of the production line. At the same time, the moisture absorption and expansion of paper fibers and the drying and shrinkage further exacerbate the local dimensional drift of the carrier tape along the transport direction. These combined factors lead to random, systematic deviations in the actual physical values ​​of the same dimensional parameter on paper carriers at different pitch segments. These deviations exhibit pitch correlation rather than pure randomness, posing a unique technical challenge to traditional visual measurement methods based on global calibration.

[0020] To address the aforementioned issues, this application provides a method, apparatus, and device for measuring paper carrier tape. In this method, image data of the paper carrier tape to be measured is acquired, and each continuous segment of the tape is divided into a group of images to be measured. Each image group contains sub-images to be measured in different measurement dimensions, comprehensively covering various measurement parameters of the carrier tape and ensuring the comprehensiveness and continuity of the measurement. The measurement value of each sub-image to be measured is calculated based on the image data, eliminating the need for manual intervention and significantly improving measurement efficiency while avoiding subjective errors that may arise from manual measurement. The measurement value of each sub-image to be measured is compared with the corresponding set of standard values ​​for each dimension. When matching the target standard value, a qualified domain is obtained and integrated, enabling unified judgment of measurement results across different dimensions. This avoids the classification confusion and information redundancy problems caused by the dispersion of multi-dimensional data in traditional methods. By integrating the image groups recording the qualified domains and combining them with error elimination operations, systematic deviations caused by the interaction between the flexibility of the paper carrier tape material and the mechanical tension of the production line are eliminated, ensuring that the measurement values ​​of each object to be measured remain consistent on a global scale, thus improving the accuracy and comparability of the measurement.

[0021] For example, electronic devices can be ultra-mobile personal computers (UMPCs), netbooks, desktop computers, computers, laptops, communication equipment, computing devices, satellite wireless equipment, etc.

[0022] To better understand the paper carrier tape measurement method provided in the embodiments of this application, the specific implementation process of the paper carrier tape measurement method provided in the embodiments of this application will be described by way of example below.

[0023] Figure 1 A schematic flowchart of the paper carrier tape measurement method provided in an embodiment of this application is shown. Figure 2 This paper application provides a flowchart illustrating the operation of a paper carrier tape measurement method. The paper carrier tape measurement method includes: S100, acquire image data of the paper carrier tape to be measured; wherein, the image data includes at least one set of images to be measured; the set of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous area of ​​the paper carrier tape is a set of images to be measured, and the set of images to be measured includes sub-images to be measured corresponding to different parameters or different positions.

[0024] Image data, as we understand it, refers to the digital information obtained through optical acquisition of a paper carrier tape to be measured using imaging equipment (such as industrial cameras, line scan scanners, or high-precision CCD cameras). Image data can include not only a two-dimensional pixel matrix but also parameters related to imaging conditions, such as resolution, grayscale level, exposure time, and the intensity and angle of the light source during acquisition. A set of images to be measured refers to a collection of image data acquired synchronously or asynchronously to comprehensively characterize different physical dimensions of the paper carrier tape. Each set of images covers a continuous area of ​​the paper carrier tape and is segmented according to different measurement dimensions (such as width, aperture, spacing, printed markings, etc.), with each dimension corresponding to at least one sub-image to be measured. These sub-images to be measured can be obtained by cropping the ROI (Region of Interest) from the overall image or by multi-camera collaborative acquisition, with the aim of achieving targeted and detailed analysis.

[0025] The reason for defining each continuous segment of the paper carrier tape as a group of images to be measured is that the carrier tape often exhibits periodic or segmental characteristics during production and use, such as perforation pitch and indentation cycle. These characteristics require the detection system to analyze each segment individually to achieve higher-precision positioning and comparison. By grouping images by region, overall errors caused by distortion, uneven lighting, or local defects in a single global image can be avoided, thus making subsequent measurements more stable. The carrier tape can be controlled to pass through the imaging area at a constant speed by controlling the conveyor mechanism, and the imaging device will take pictures according to preset time intervals or displacement triggers, ensuring that each segment of the carrier tape generates corresponding image group data. This not only facilitates subsequent multi-dimensional comprehensive measurements but also provides a complete data foundation for error elimination and standard value comparison. Its core function is to establish a digital characterization library of the paper carrier tape, converting the physical entity into calculable image information, thereby laying the foundation for subsequent steps of the entire measurement method.

[0026] S200, based on the image data of the paper carrier tape to be measured, calculates the measurement value of the sub-image to be measured in each group of images to be measured.

[0027] It can be understood that the measured value refers to the numerical result of converting the identified geometric or physical objects (such as positioning holes, edges, spacing marks, notches, indentations, characters / codes, etc.) in the sub-image into engineering dimensions (millimeters, degrees, pixels / millimeters, contrast index, etc.) after spatial calibration. The extrinsic / intrinsic parameter calibration matrix and pixel physical dimensions of the camera-lens-carrier plane are loaded, and grayscale homogenization and denoising filtering (Gaussian / bilateral / guided filtering) are applied to stabilize the texture. Subsequently, based on the ROI (Region of Interest) division, sub-pixel edge extraction (such as Canny + non-maximum suppression + sub-pixel interpolation), morphological cleansing (opening / closing / thinning / skeletonization), and geometric fitting (least square lines / circles / ellipses, RANSAC noise-resistant fitting) are performed on each sub-image to be measured. Distances, angles, diameters, etc., obtained in the pixel domain are converted into physical quantities using calibration coefficients and distortion correction models (radial / tangential), forming a structured record containing measured values, confidence levels, residuals, and ROI metadata. The reason for calculating each image separately rather than making a one-time global estimate is that the paper carrier has local curvature along the belt direction, differences in paper fiber texture, and gradual changes in illumination. Different parameters have different requirements for resolution and field of view. Calculating them separately can significantly reduce false detections / false negatives and quantization bias, and facilitate independent judgment and backtracking according to dimensional standards.

[0028] In one possible implementation, S200, based on the image data of the paper carrier tape to be measured, calculates the measurement value of the sub-image to be measured in each group of images to be measured, including: S210, based on the image data of the paper carrier tape to be measured, perform feature recognition on the sub-images to be measured in each group of images to be measured, and determine the multi-class measurement objects corresponding to each sub-image to be measured.

[0029] Feature recognition, as we understand it, refers to the use of image processing and pattern recognition methods to distinguish and classify different categories of measurement objects within a sub-image to be measured. Please refer to [link / reference]. Figure 3 The measurement objects here can be different types of holes in paper carriers (labeled 1 in the figure are circular holes in paper carriers, and labeled 2 are square holes in paper carriers), printed markings, edge contours, positioning points, indentations, and other structural or functional elements. Multiple measurement objects refer to the possibility that a single sub-image may contain multiple different types of detection targets. These targets differ significantly in morphological features and geometric parameters, thus requiring differentiation through feature extraction and classification algorithms.

[0030] Feature point extraction and edge analysis can be performed on the sub-image to be measured. For example, edge contours can be obtained using the Canny operator, circular or linear structures can be detected using the Hough transform, or standardized positioning holes can be identified using template matching methods. For complex textures or printed marks, grayscale histogram features, Fourier transform features, or Local Binary Patterns (LBP) can also be used for identification. After identification, different objects in the image are classified and stored according to feature labels, and an object index is built for subsequent use in the corresponding measurement algorithm.

[0031] The reason for this is that paper carrier tapes typically contain multiple functional areas, such as punched areas for component positioning and printed marking areas for mechanical identification. Without distinguishing these objects, performing a uniform measurement directly would lead to data confusion and even erroneous results. Identifying multiple measurement objects in each sub-image through feature recognition not only improves the targeting and accuracy of subsequent measurements but also provides flexibility in complex scenarios, ensuring that measurement results cover all key indicators of the paper carrier tape.

[0032] S220: Match the measurement algorithm corresponding to each type of measurement object according to the measurement object, and calculate the object measurement value of each type of measurement object in each sub-image to be measured according to the measurement algorithm.

[0033] As can be understood, a measurement algorithm refers to the mathematical calculation methods and image processing procedures designed for different types of measurement objects. Examples include geometric fitting algorithms for diameter calculation, pixel distance calculation algorithms for spacing measurement, and contour filling algorithms for area estimation. Each type of measurement object has its unique geometric features and functional attributes, thus requiring different measurement algorithms to obtain accurate measurement values. An object measurement value refers to the quantitative result obtained after processing a certain type of object using a specific measurement algorithm, such as the millimeter value of an aperture or the square pixel value of a surface defect area.

[0034] Based on the object classification results established in the previous step, a preset measurement algorithm can be selected for each object category. For example, a least-squares circle fitting algorithm can be used for circular positioning holes to extract boundary points and fit a circular outline to obtain the precise diameter; a boundary projection algorithm can be used to measure the width and height of rectangular windows or strips; and OCR recognition can be used to verify the integrity of printed markings. During the calculation process, the measurement results can be converted from pixel units to physical units by combining the calibration ratio between pixels and actual physical dimensions.

[0035] The reason for employing an object matching algorithm is the complexity of the paper carrier tape structure and the significant differences in geometric features between different objects. Using a single algorithm would lead to measurement distortion or omissions. For example, aperture and strip width have completely different characteristics; one is suitable for edge fitting, while the other is suitable for line segment detection. By establishing an object-algorithm correspondence, targeted measurements can be performed, ensuring high accuracy and consistency of results. This not only improves detection efficiency but also avoids systematic errors caused by algorithm mismatch, providing a reliable data foundation for subsequent measurement value integration and standard value comparison. S230, based on the integration of all object measurements, determine the measurement values ​​of the sub-images to be measured in each group of images to be measured.

[0036] It can be understood that integrating measurements based on all objects refers to the orderly summarization, weighting, or fusion of independent measurements from multiple objects to obtain a comprehensive measurement value that reflects the overall characteristics of the entire sub-image being measured. Object measurements refer to quantitative results obtained using specialized algorithms for different objects, such as aperture diameter, aperture spacing, carrier tape width, or edge straightness. Since each sub-image may contain multiple types of objects, it is necessary to uniformly integrate the measurements of these objects to avoid the inability of a single parameter to fully reflect the actual situation of the paper carrier tape.

[0037] A data matrix can be built for the measurements of each type of object, and weighted according to the object's importance and location. For example, the diameter and spacing of positioning holes may have higher weights because they directly determine whether the carrier tape can be accurately identified and conveyed in the production line; while the weight of the integrity of printed marks may be relatively lower. The integration can be achieved using mathematical methods such as weighted averaging, principal component analysis, or fuzzy comprehensive evaluation, so that the final generated sub-image measurements contain multi-dimensional information while being represented in a single numerical form.

[0038] The reason for this integration is that the quality of paper carrier tapes is often influenced by multiple parameters. Relying solely on the measurement value of a single object can easily lead to bias or inaccuracies. For example, if the aperture diameter is acceptable but the aperture spacing is not, the carrier tape will still experience positioning errors on the pick-and-place machine. Integration creates comprehensive and unified measurement indicators, providing consistent data for subsequent comparisons with a set of standard values, thereby improving the stability and scientific rigor of the judgment.

[0039] S300: Based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set, a recording operation is performed on the image group to be measured. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, at least one qualified domain pointed to by the target standard value is obtained for domain integration, and the image group to be measured is recorded to the integrated qualified domain.

[0040] It can be understood that the set of standard dimensional values ​​refers to the pre-defined range of standard parameters for different measurement dimensions of paper carrier tape, such as the standard value range for aperture, the allowable error range for pitch, and the upper and lower limits for width. The measured values ​​of the sub-image to be measured obtained in the previous step can be matched and verified one by one with the corresponding dimensional values ​​in the set of standard values ​​to determine whether they fall within the specified acceptable range. The recording operation refers to storing the comparison results, whether they are acceptable or not, into the system database or logical area for subsequent analysis and statistics.

[0041] The system can sequentially iterate through all sub-image measurements within the image group to be measured and match them against the corresponding set of standard values. If a measurement falls within the standard interval of the set, it is considered compliant. If a measurement corresponds exactly to at least one standard value, the qualified region pointed to by that standard value can be further obtained. The qualified region is a logical storage area used to aggregate all measurement results that conform to the standard. Region integration can be performed, merging qualified regions pointed to by different standard values ​​to form the final integrated qualified region. After this process is completed, the image group to be measured is officially recorded in the qualified region.

[0042] The reason for this design is that paper-based carrier tapes often involve multi-dimensional detection indicators, and the measurement values ​​of a single image set may simultaneously correspond to multiple different acceptable ranges. Without integration, this would lead to data fragmentation and redundant results. Domain integration effectively reduces redundant storage and classification confusion, while ensuring that each set of detection results can be accurately categorized into a unified acceptable range. This not only improves data management efficiency but also allows subsequent error elimination and correction processes to be based on a unified acceptable range, thereby guaranteeing the integrity and traceability of the entire measurement process.

[0043] In one possible implementation, S300, based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set, a recording operation is performed on the group of images to be measured. When there is a target standard value in the corresponding dimension standard value set corresponding to at least one measured value of the sub-image to be measured, at least one qualified domain pointed to by the target standard value is obtained for domain integration, and the group of images to be measured is recorded into the integrated qualified domain, including: S310, compare the measured value of each sub-image to be measured with the standard value in the corresponding dimension standard value set one by one, filter out the target standard value that matches at least one measured value, and obtain the qualified domain pointed to by each target standard value.

[0044] As can be understood, a one-to-one comparison refers to matching the measured value of each sub-image to be measured with each standard value in the set of dimensional standard values ​​one by one until the target standard value that is closest to or completely consistent with it is found. The target standard value refers to a numerical value or range in the set of standard values ​​that can represent the acceptable range, reflecting the process requirements of the paper carrier tape in a specific dimension. For example, the aperture must be within the range of 1.50mm ± 0.05mm, or the pitch must be 4.00mm ± 0.02mm. The acceptable domain is a logical partition that points to the set of results corresponding to the target standard value. All measurement data that conform to this standard can be centrally stored in the same acceptable domain.

[0045] The measured values ​​of the sub-image to be measured can be standardized, for example, through unit conversion, rounding, or deviation normalization, so that the measured values ​​can be directly compared with values ​​in the standard set. The difference between each measured value and the standard value in the set can be calculated one by one. When the difference is less than or equal to a preset threshold, the measured value is determined to match the target standard value. After matching, the corresponding qualified domain can be indexed according to the target standard value, and the measurement result of the sub-image can be marked as qualified, ready for subsequent domain merging.

[0046] The reason for requiring individual comparisons rather than batch judgment is that the precision requirements for different dimensions of paper carrier tape vary, and the standard value set often contains multiple candidate values ​​or ranges. Failure to compare them individually could lead to misjudgments or omissions. For example, the precision levels of the allowable aperture range and the allowable pitch range are different, requiring separate and precise comparisons. By comparing and filtering the target standard values ​​one by one, the accuracy and controllability of the comparison can be ensured, while providing a clear basis for subsequent merging of qualified regions.

[0047] S320: Perform an interval merging operation on each target standard value, which points to at least one qualified field, to generate an integrated qualified field.

[0048] Interval merging can be understood as logically integrating and merging at least one qualified region pointed to by different target standard values ​​to generate a unified integrated qualified region. A qualified region is a logical area that records measurement results that conform to a certain target standard value. However, since multiple measurements in an image group may correspond to different standard values, a single image group may fall into multiple qualified regions simultaneously during recording. Interval merging can unify these scattered qualified regions into a single integrated qualified region, simplifying the storage structure and facilitating subsequent processing.

[0049] The system can statistically analyze the acceptable regions pointed to by all target standard values ​​in the current image group to be measured, and merge their boundary ranges. For example, if the acceptable region corresponding to the aperture measurement value is [1.45mm, 1.55mm], and the acceptable region corresponding to the pitch is [3.98mm, 4.02mm], these independent intervals can be integrated into a multi-dimensional interval space in the form of a logical union, thereby generating a new integrated acceptable region. During the merging process, if an intersection is found between different acceptable regions, the intersection can be preferentially retained; if there is no intersection at all, they can be merged into a unified index by expanding the range or logical labels.

[0050] The reason for this approach is that maintaining multiple scattered qualified fields not only complicates data management but also leads to redundant calculations and wasted resources in subsequent error elimination and correction steps. By merging intervals, the previously scattered qualified fields can be unified into a single integrated qualified field, resulting in simpler data recording and facilitating global analysis of the entire carrier tape. This method significantly improves detection efficiency, reduces computational overhead, and ensures logical consistency and traceability of the results.

[0051] S330 records the association information of the image group to be measured into the integrated qualified field.

[0052] As can be understood, associated information refers to the identifiers, location information, and indexes of the measurement results related to the image group to be measured. Examples include the image group's location number on the conveyor belt, the shooting timestamp, conveyor belt operating parameters, and the corresponding sub-image index. This information is crucial metadata that ensures the measurement results are traceable and verifiable in subsequent stages. Recording to the integrated qualification domain means writing the image group to be measured and its associated information into the logical area corresponding to the integrated qualification domain in the system database, thus formally classifying the image group as qualified and including it in the statistical analysis.

[0053] After merging intervals to generate an integrated qualified domain, the measurement values ​​of the current image group to be measured and its associated information can be bound and stored together. For example, if the aperture, pitch, and width measurement results of a certain image group have been judged to be qualified through comparison, these values ​​and their corresponding location information can be uniformly stored in the integrated qualified domain database, and a unique index can be generated for subsequent fast retrieval.

[0054] The reason for this approach is that paper-based carrier tape measurement not only needs to determine whether a particular image set is acceptable, but also needs to establish a complete traceability chain in production quality management. By recording the associated information along with the measured values ​​into an integrated acceptance domain, specific carrier tape areas and testing conditions can be quickly located in subsequent error analysis, statistical report generation, and anomaly backtracking, thereby achieving end-to-end traceable quality control. This design ensures the practicality and standardization of the measurement method, while also meeting the needs of batch management of acceptable products in industrial production. In one possible implementation, the method also includes: S500: When there is no target standard value in the corresponding dimension standard value set that corresponds to the measured value of the sub-image to be measured, the measured value of the sub-image to be measured is recorded in the non-conforming field.

[0055] As can be understood, the non-conforming region refers to a logical area used to store all measurement results that fail to meet standard requirements. When the measured value of a sub-image fails to match the target standard value in any dimension's standard value set, the measurement result is considered non-compliant with process or quality requirements and needs to be individually marked and recorded. Classifying it into the non-conforming region facilitates subsequent analysis, anomaly detection, and quality improvement.

[0056] Each measurement value of the sub-image to be measured can be compared with the set of standard values ​​for the corresponding dimension. If all standard values ​​do not match, the measurement value is determined to be unqualified. Subsequently, the measurement value and its associated information (such as image group number, sub-image index, measurement timestamp, carrier location, etc.) are uniformly recorded in the unqualified field for centralized management and statistics of unqualified cases. The recording method can employ database storage, logical index, or file system archiving to ensure that each unqualified record can be traced back to the specific measurement object and acquisition conditions.

[0057] The reason for this is that localized process anomalies, image acquisition interference, or measurement errors may occur during paper carrier tape production, causing some measurements to deviate from the standard range. If these abnormal measurements are not centrally categorized and marked, they may mask the actual problems in subsequent statistical analysis, affecting quality assessment and improvement strategies. By establishing non-conforming domains, independent management of abnormal measurement results can be achieved, facilitating real-time monitoring of the production process, analysis of the causes of anomalies, and process optimization. Simultaneously, the recording of non-conforming domains provides a reliable data foundation for production quality traceability, batch analysis, and process adjustments, ensuring the integrity and controllability of the entire measurement system.

[0058] S400 performs error elimination on all groups of images to be measured that are integrated into the qualified field records, and completes the measurement of the paper carrier tape to be measured.

[0059] Error elimination, as understood, refers to the process of uniformly correcting and calibrating the measured values ​​of all image groups within the acceptable range after completing the recording of the acceptable range, ensuring the accuracy and consistency of the final measurement results. Paper carrier tapes are susceptible to various errors during imaging and measurement, such as optical distortion, uneven illumination, camera sensor noise, and mechanical vibration of the conveyor, which can introduce systematic errors. Without correction, even if a single image group is deemed acceptable, the overall measurement results may still contain deviations. Completing the measurement means that after eliminating systematic errors, the corrected measurement results are used as the final inspection conclusion for the paper carrier tape, forming a complete quality data output.

[0060] It can iterate through and integrate all recorded groups of images to be measured within the qualified domain, and perform uniform error correction on the sub-image measurements of each group. Specific methods may include using multi-image statistical modeling to identify global bias trends, or eliminating fixed systematic errors through correction curves based on standard samples. The corrected data is then rewritten into the database, replacing the original values, and serves as the basis for subsequent analysis.

[0061] The reason for this design is that while judging a single set of images can screen out qualified products, industrial inspection requires extremely high overall stability, especially in batch production scenarios. Even small systematic deviations can accumulate into large errors, leading to unstable product quality. By eliminating errors in the integrated qualified domain, it can be ensured that the final measurement results not only meet the requirements for single-point qualification but also maintain consistency and reliability in the overall trend, thereby improving the scientific nature and application value of the paper carrier tape inspection method.

[0062] In one possible implementation, S400 performs error elimination on all groups of images to be measured, integrating qualified field records, and completes the measurement of the paper carrier tape to be measured, including: S410, traverse all groups of images to be measured that are integrated into the qualified field records, and extract the object measurement values ​​of each type of measurement object in each sub-image to be measured.

[0063] It's understandable that traversal refers to sequentially accessing all groups of images to be measured recorded in the integrated qualified domain, ensuring that no data set is missed. Object measurements refer to the raw numerical results obtained for each type of measured object, such as an aperture of 1.51 mm or a pitch of 3.99 mm. Since the integrated qualified domain stores results that have passed standard value comparison, all object measurements need to be extracted uniformly before error elimination to ensure complete data input for systematic error analysis.

[0064] The data interface can be called to retrieve records for each image group from the integrated qualified domain database, including sub-image indexes, measurement object types, and their values. These values ​​are then categorized and summarized according to object type to form a complete set of object measurements. Taking aperture as an example, aperture measurements are extracted from all sub-images to form a complete aperture data sequence; the same applies to pitch, width, and other objects.

[0065] The reason for this is that error analysis must be based on global data, not local or fragmented data. Relying solely on partial data for correction may lead to biased results or even amplify errors. By traversing and integrating the qualified domain, we ensure that every object measurement is incorporated into the error model, making subsequent systematic error elimination more representative and accurate. This step is essentially a preparatory stage for global error correction, laying the foundation for establishing a complete input dataset.

[0066] S420, based on all object measurements, perform systematic error elimination on the object measurements of each type of object in each sub-image to be measured, and determine the object correction value for each type of object in each sub-image to be measured.

[0067] Systematic error elimination, as we understand it, refers to identifying and removing non-random biases introduced by equipment, optical systems, or environmental conditions through a holistic analysis of all object measurements. The object correction value refers to the new measurement result obtained after error elimination, which is closer to the true physical size or parameters of the object than the original object measurement. Unlike random errors, systematic errors are directional and regular; for example, all aperture measurements may be generally overestimated by 0.02 mm. This bias needs to be corrected through model calculations.

[0068] It can statistically analyze all object measurements, calculate the overall deviation distribution from the standard value, and then construct a systematic error model. Common methods include least squares fitting, regression analysis, or offset correction based on statistical averages. For example, if all aperture values ​​are larger than the standard by a fixed amount, a correction coefficient will be automatically generated, and the original values ​​will be adjusted. The adjusted value is defined as the object correction value and is stored instead of the original object measurement value.

[0069] The reason for this design is that batch measurements of paper carrier tapes inevitably introduce overall deviations from the measurement system. Without eliminating these deviations, even if each image group is within the standard range, it may still differ from the true value, leading to distorted process control. By eliminating systematic errors, the accuracy of measurements can be improved on a global scale, making the output results more consistent with reality and providing a reliable basis for subsequent corrections and final measurements.

[0070] Optionally, S420, systematic error elimination is performed on the object measurement values ​​of each class of measured objects in each sub-image to be measured based on all object measurement values, and an object correction value for each class of measured objects in each sub-image to be measured is determined, including: S421, determine the first systematic error coefficient for each class of measured objects in each sub-image to be measured based on all object measurements.

[0071] The first systematic error coefficient can be understood as a numerical deviation factor obtained by statistically analyzing the difference between the measured object and the standard value for each type of measurement object in each sub-image. Systematic error refers to a fixed, directional deviation caused by factors such as defects in the imaging equipment, optical system, transmission device, or algorithm model itself during the measurement process. For example, if the measurement results for all apertures are 0.01 mm larger than the standard, then a constant positive deviation coefficient can be considered to exist. By calculating the first systematic error coefficient, the manifestation of this deviation in a single sub-image and a single type of object can be quantitatively described.

[0072] The measured values ​​of each type of object can be compared with the corresponding target standard values ​​in the standard value set, and the difference can be calculated. This difference is used as the initial systematic error. Subsequently, statistical methods (such as mean difference, residual regression, or normalized difference) are used to obtain the first systematic error coefficient for that type of object in the sub-image. For example, for aperture objects, if the measured aperture value of a sub-image is 1.52 mm, while the standard value is 1.50 mm, then the error coefficient is +0.02 mm. This coefficient will be stored for subsequent global error analysis.

[0073] The reason for this design is that individual sub-images are often affected by local lighting, focusing, or mechanical errors, causing measurements to deviate from the standard. Therefore, it is necessary to establish separate error coefficients for each sub-image and each object class so that common patterns can be discovered through overall induction in subsequent steps. If this step is skipped and global correction is performed directly, local differences may be ignored, thereby reducing the accuracy of the correction. By calculating the first systematic error coefficients, basic data can be provided for error modeling, making subsequent corrections more scientific and targeted.

[0074] S422, Based on the first systematic error coefficient of each type of measurement object in all the sub-images to be measured, determine the first systematic error average coefficient of each type of measurement object.

[0075] It can be understood that the average coefficient of the first systematic error refers to the average value obtained by statistically calculating the first systematic error coefficients of the same type of measurement object in all the sub-images to be measured. This parameter is used to reflect the overall deviation level of a certain type of object in the entire image data. For example, if the average deviation of aperture objects in all sub-images is +0.015mm, then this average value can be regarded as the average coefficient of the first systematic error of aperture objects.

[0076] The first systematic error coefficients of similar objects in each sub-image can be summarized, and their arithmetic mean or weighted average can be calculated. The weighted average is usually determined based on image sharpness, regional importance, or acquisition stability. For example, for aperture objects, assuming the error coefficients of ten sub-images are between +0.01mm and +0.02mm, the overall average (e.g., +0.015mm) can be calculated and used as the first systematic error average coefficient for this type of object.

[0077] The reason for this is that the error coefficient of a single sub-image may fluctuate significantly due to local environmental influences. However, by statistically analyzing the errors of all sub-images, the randomness of local fluctuations can be eliminated, resulting in a more stable global deviation trend. This average coefficient not only reveals the common errors of a certain type of object across the entire carrier, but also serves as the basis for subsequent calculations of global correction parameters. In other words, this step is a crucial link in the transition from local errors to global errors, ensuring the stability and reliability of the correction model.

[0078] S423, based on the first systematic error average coefficient for each type of measurement object, determine the second systematic error coefficient corresponding to the image data.

[0079] It can be understood that the second systematic error coefficient refers to the correction factor that reflects the overall common deviation of the entire carrier image data after the first systematic error average coefficient for each type of measurement object is obtained and further integrated on a global scale. Here, "image data correspondence" means that this coefficient is not for a single object or a single image, but for the comprehensive correction amount of the entire carrier data, used to uniformly adjust the measurement values ​​of all objects.

[0080] The average coefficients of the first systematic error for each type of object can be categorized and integrated according to object category. For example, the average coefficient for aperture is +0.015 mm, the average coefficient for pitch is -0.01 mm, and the average coefficient for width is +0.005 mm. Based on the correlation and weights among these average coefficients, a global correction parameter, namely the second systematic error coefficient, is calculated. This coefficient can be obtained through methods such as multidimensional weighted fusion, principal component analysis, or cooperative fluctuation analysis, and its value reflects the overall deviation of the batch of carrier tapes under production and testing conditions.

[0081] The reason for this is that even if each type of object has an average coefficient, there may still be related error sources between different objects. For example, the global scaling effect caused by camera imaging can simultaneously affect aperture, pitch, and width. If only corrections are made for a single type of object, this common deviation cannot be completely eliminated. By generating a second systematic error coefficient, a unified correction can be performed at the global level, ensuring that the measurement results of different objects are more consistent overall, thereby improving the accuracy of the measurement.

[0082] For example, S423, determining the second systematic error coefficient corresponding to the image data based on the first systematic error average coefficient for each type of measurement object includes: S4231 identifies the error sensitivity factors of each type of measurement object based on the first systematic error average coefficient of each type of measurement object, and divides the measurement objects into several error association groups according to the strain response and error sensitivity factors of each measurement object relative to the transport direction.

[0083] It can be understood that the strain response of each measured object relative to the conveying direction refers to whether the measured dimension of the object elongates or contracts when the carrier belt is stretched under tension. The direction of the strain response is directly determined by the geometric orientation of the measured object: objects measured along the conveying direction (MD direction) elongate when tension increases, while objects measured laterally (CD direction) contract due to the Poisson effect; the error directions of the two are exactly opposite when tension fluctuates. The orientation information is determined when the image processing system identifies the measured object. Objects measured with the conveying direction as the baseline, such as pitch and longitudinal spacing between holes, are labeled as MD orientation; objects measured with the perpendicular to the conveying direction as the baseline, such as paper tape width and cavity lateral width, are labeled as CD orientation; and objects obtained by bidirectional profile fitting, such as positioning hole diameter and fillet contour, are labeled as biaxial orientation. The above labels are configured once by the operator during the first inspection or automatically imported from the CAD design file, and are directly used in subsequent measurements without needing to be recalculated for each group.

[0084] For example, the errors are divided into three error correlation groups. Group 1 is the MD tensile response group, including pitch, longitudinal spacing between holes, and longitudinal length of the cavity labeled as MD orientation. The measured values ​​of objects in this group increase synchronously with increasing tension, and the average coefficient of the first systematic error shows a positive deviation. Group 2 is the CD Poisson shrinkage group, including tape width and transverse width of the cavity labeled as CD orientation. The measured values ​​of objects in this group decrease synchronously with increasing tension, and the average coefficient of the first systematic error shows a negative deviation. Group 3 is the biaxial coupling deformation group, including positioning hole diameter and fillet contour labeled as biaxial orientation. The error direction of this group changes with the relative weights of MD and CD. During the grouping process, all pitch objects and all width objects on the same carrier tape, with consistent orientation labels, are directly assigned to the corresponding group.

[0085] It's important to note that this approach is necessary because the tension fluctuations experienced by the paper carrier tape during transport generate opposite errors for measurement objects with different orientations: MD objects tend to be overestimated, while CD objects tend to be underestimated. If all objects are calculated together, the positive and negative deviations cancel each other out, and the average coefficient of the first systematic error approaches zero. Subsequent co-fluctuation analysis will fail to detect common error sources, and the tension deviation of the entire carrier tape will be missed. By grouping according to the strain response direction, all objects within the same group exhibit the same error direction during tension fluctuations, and the average coefficient of the first systematic error within the group shows the same sign. Only then can the co-fluctuation value accurately reflect whether a common error source exists within the group. Simultaneously, since the coefficients of the MD and CD groups are in opposite directions, their fusion forms a difference signal. This difference directly encodes the real-time tension state of the current production line; the greater the tension, the larger the difference. This makes the second systematic error coefficient no longer a statistical correction quantity without physical meaning, but directly corresponds to the actual stress deformation of the carrier tape. This allows for differentiated compensation with opposite directions and matched amplitudes for MD and CD objects, effectively eliminating orientation-related systematic deviations that traditional unified correction methods cannot address. This application groups the components according to the direction of strain response, so that the first group and the second group produce first systematic error average coefficients with opposite directions when tension fluctuates. The difference between the two directly reflects the real-time tension state of the current production line, thereby realizing differentiated strain compensation for the entire carrier belt and effectively eliminating the directional correlation systematic deviation caused by the flexibility of the carrier belt material under the action of conveying tension.

[0086] S4232, calculate the co-variance value of the average coefficient of the first systematic error within each error association group.

[0087] The co-variance value refers to the statistical consistency or fluctuation of the average coefficient of the first systematic error among objects within an error correlation group, used to quantify the strength of common bias within the group. It can be integrated into a single numerical index by calculating the variance or covariance matrix of the errors within the group, or by using methods such as principal component analysis. For example, if the errors of both aperture and pitch objects within a group are close to the group's average, the co-variance value is low, indicating the existence of a significant common error source in the group. This is because the co-variance value can determine the consistency within the error correlation group, providing a basis for determining the existence of global common bias, thus ensuring that the second systematic error coefficient accurately reflects the global characteristics of the entire carrier image data segment.

[0088] S4233, based on the coordinated fluctuation value of each error association group, obtains the second systematic error coefficient that reflects the global common deviation of the entire carrier image data.

[0089] It can be understood that the second systematic error coefficient refers to the global correction parameter obtained by further integrating the deviation information of each group after analyzing the coordinated fluctuation values ​​of each error correlation group. It is used to uniformly correct the systematic deviation of all measured objects in the entire carrier image data. The global common deviation here means that the coefficient reflects the overall offset or scaling trend that may exist in the entire carrier image under production and inspection conditions, and is not limited to a single object or a single sub-image.

[0090] Based on the co-variance values ​​of each error association group, it can be determined which groups share significant common error sources. For groups with common error sources, the weighted average of the first systematic error average coefficients within the group can be used as the error representation value for that group. The weighting coefficients can be set according to the importance of objects within the group, image sharpness, or measurement stability, so that objects with a greater impact on global bias have a higher proportion in the calculation. Subsequently, the error representation values ​​of all error association groups are fused, and a single second systematic error coefficient is obtained through methods such as weighted averaging, multidimensional weighted fusion, or principal component analysis.

[0091] The reason for this approach is that even if various measurement objects have a first systematic error average coefficient, common error sources may still exist between different objects, such as camera image scaling, optical distortion, or carrier tape position shift. Correcting only a single type of object cannot completely eliminate the overall deviation. By synthesizing the coordinated fluctuation values ​​of various error correlation groups and generating a second systematic error coefficient, the entire carrier tape image data can be uniformly corrected on a global scale. This ensures that the measurement results for different objects are more consistent overall, thereby improving measurement accuracy and data comparability, and providing a stable and reliable foundation for subsequent object correction and quality control.

[0092] For example, in S4233, a second systematic error coefficient reflecting the global common deviation of the entire carrier image data is obtained based on the cooperative fluctuation value of each error association group, including: S42331, compare the co-fluctuation value of each error association group with a preset threshold, and determine that there is a common error source in the error association group when the co-fluctuation value is lower than the preset threshold.

[0093] It is understandable that the preset threshold is an upper limit for the allowable co-variance set based on historical measurement experience or standard processes, used to judge the consistency of errors within a group. When the co-variance value of an error-related group is lower than this threshold, it indicates that the errors of each object within the group are highly consistent and are likely affected by the same global deviation source. Therefore, it can be determined that the group has a common error source. The co-variance value within the group can be compared with the threshold through statistical calculation or algorithm detection to automatically identify groups that need global correction. The reason for doing this is that by identifying groups with co-variance values ​​lower than the threshold, those sets of objects significantly affected by global deviations can be addressed in a targeted manner, avoiding interference from accidental or local errors on the global correction results, and improving the accuracy and stability of the second systematic error coefficient.

[0094] S42332, for error correlation groups with common error sources, the weighted average of the first systematic error average coefficients of the error correlation group is taken as the error characterization value of the error correlation group.

[0095] The error representation value is a single numerical value obtained by weighting the average coefficients of the first systematic errors of each object within an error-related group. It reflects the overall deviation level of the group. The weighted mean can be calculated by assigning weights to objects within the group based on their salience in the image, measurement accuracy, or image sharpness, thus increasing the weight of objects that have a greater impact on the global deviation. For example, aperture objects with high center sharpness can be assigned a larger weight, while edge objects can be assigned a smaller weight. The error representation value is obtained by multiplying the average coefficients of the first systematic errors of all objects within the group by their corresponding weights, summing them, and dividing by the total weight. This is done because the weighted mean can fully consider the contribution of different objects within the group to the global deviation, making the error representation of the group more accurately reflect its overall deviation characteristics, and providing a reliable basis for generating the second systematic error coefficients.

[0096] S42333, fuse the error characterization values ​​of all error association groups to obtain the second systematic error coefficient that reflects the global common deviation of the entire carrier image data.

[0097] This is understandable. Fusion refers to integrating the weighted error representation values ​​of various error association groups into a unified global correction parameter, namely the second systematic error coefficient. The error representation values ​​of all error association groups can be fused using weights and confidence levels. The weights are positively correlated with the confidence level of the error representation values ​​of each error association group, and the confidence level is determined by the sample size of the measured objects within each error association group. This positive correlation means that the larger the sample size of the measured objects within an error association group, the higher the reliability of its error representation values, and the larger its proportion in the global fusion; conversely, groups with smaller sample sizes have a lower proportion. Confidence levels are usually calculated using statistical sample size or sample distribution characteristics, such as the number of measured objects within the group. With the total number of samples The ratio of these ratios serves as the basis for weighting, ensuring that groups with sufficient data support have a greater impact on the global error coefficient.

[0098] The error characterization values ​​of each error correlation group can be used. With corresponding confidence weights The weighted average is then used to calculate the global second systematic error coefficient. : ,in, The number of error correlation groups, For the first The confidence weights of each error association group are typically proportional to the number of measured objects within that group. This formula ensures that groups with larger sample sizes and more stable errors contribute more to the global correction parameters, thereby improving the accuracy and robustness of the second systematic error coefficient. This is because the sample sizes of different error association groups may vary. Simply averaging the error representation values ​​of each group could cause a few small, highly volatile groups to excessively influence the global bias, thus reducing correction accuracy. By using confidence-weighted fusion, the reliability of large sample size groups can be effectively utilized, while reducing the interference of random fluctuations in small sample size groups on the global results. This ultimately yields a second systematic error coefficient that reflects the overall common bias of the entire carrier image data, providing a stable and reliable basis for subsequent object correction and global error elimination.

[0099] S424, based on the second systematic error coefficient, eliminate the error of the object measurement value of each type of measurement object in each sub-image to be measured, and determine the object correction value of each type of measurement object in each sub-image to be measured.

[0100] It can be understood that the object correction value refers to the final value obtained after correcting the original measurement values ​​of various measurement objects using the second systematic error coefficient. The core is to apply the global deviation factor to the measurement results of each object, so that the corrected value is closer to the actual physical size of the paper carrier.

[0101] The measurement values ​​of each type of object in each sub-image to be measured can be corrected. The correction formula can generally be expressed as: V x =V m -C, middle, V m Represents the original measured value, C represents the second systematic error coefficient, and V represents the original measured value. x This will be the final corrected value. The system can iterate through all sub-images and objects, replacing the original values ​​with the corrected results, and updating the data stored in the database.

[0102] The reason for this is that the second systematic error coefficient represents the global common deviation of the entire carrier tape data. Without its application, the final measurement results would still carry a consistent overall error, making it difficult to guarantee the true accuracy of the data. Through this step, all object measurements are uniformly corrected, ensuring that the output results are not only qualified in local dimensions but also closer to reality on an overall scale. This correction result is the core basis for subsequent quality assessment and production control; therefore, this step is of great significance for ensuring the scientific validity and industrial application value of paper carrier tape measurements.

[0103] S430, the object correction values ​​of each type of measurement object in each sub-image to be measured are re-integrated into the integration qualified domain, and the measurement of the paper carrier tape to be measured is completed.

[0104] As can be understood, re-integration refers to rewriting and replacing the original object measurement values ​​in the integrated qualified domain with the corrected object values ​​generated after error elimination, thereby forming the final, corrected qualified dataset. Completion of the measurement signifies the formal end of the entire paper carrier tape measurement process; the output measurement data is the calibrated final version and can be directly used for quality assessment, statistical analysis, or production control.

[0105] It can iterate through all object correction values ​​and, according to the index relationship between image groups and sub-images, bind the correction values ​​to the original records, replacing the corresponding measurement values ​​in the integrated qualified domain. Simultaneously, it updates the database version control information to ensure that both pre- and post-correction data are traceable, facilitating verification in case of subsequent disputes or anomalies. After the update is complete, a complete paper-based measurement report or curve visualization can be output; please refer to [link / reference]. Figure 4 This includes the final measurement value for each dimension, as well as the pass / fail result.

[0106] The reason for this re-integration is that error correction only generates new values ​​at the mathematical level. If these values ​​are not bound to the integrated pass / fail domain, the data system will still contain the original measurements, potentially leading to inconsistencies or confusion in subsequent use. Re-integration ensures that the data stored in the database is the final calibrated version, thus achieving a complete, accurate, and traceable quality control process. This step is the final stage of the entire measurement method, ensuring that the output results are scientific, reliable, and have practical application value.

[0107] Corresponding to the paper carrier tape measurement method in the above embodiments, this application also provides a paper carrier tape measurement device, the various units of which can implement the various steps of the paper carrier tape measurement method. Figure 5 A structural block diagram of the paper carrier tape measuring device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0108] Reference Figure 5 The paper carrier tape measuring device includes: An acquisition unit is used to acquire image data of a paper carrier tape to be measured; wherein, the image data includes at least one group of images to be measured; the group of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous area of ​​the paper carrier tape is a group of images to be measured, and the group of images to be measured includes sub-images to be measured corresponding to different parameters or different positions; A measurement unit is used to calculate the measurement value of the sub-image to be measured in each group of images to be measured based on the image data of the paper carrier tape to be measured; The integration unit is used to perform a recording operation on the image group to be measured based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, the unit obtains at least one qualified domain pointed to by the target standard value and performs domain integration, and records the image group to be measured into the integrated qualified domain. The result unit is used to perform error elimination on all the image groups to be measured recorded in the integrated qualified field and to complete the measurement of the paper carrier tape to be measured.

[0109] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0111] This application also provides an electronic device. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6As shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one is shown in the image), at least one memory 61 ( Figure 6 (Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60, wherein when the processor 60 executes the computer program 62, it causes the electronic device 6 to perform the steps in any of the above-described paper carrier measurement method embodiments, or causes the electronic device 6 to perform the functions of each unit in the above-described device embodiments.

[0112] Exemplarily, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the paper carrier measurement 6.

[0113] Electronic device 6 can be a computing device or terminal device such as a desktop computer, laptop, handheld computer, or cloud server. This electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0114] The processor 60 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0115] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may be an external storage device of the electronic device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 6. Furthermore, the memory 61 may include both internal and external storage units of the electronic device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0116] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0117] This application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the steps in any of the above method embodiments.

[0118] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0119] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0120] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] In the embodiments provided in this application, it should be understood that the disclosed paper carrier tape measuring device / electronic device and method can be implemented in other ways. For example, the paper carrier tape measuring device / electronic device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for measuring paper carrier tape, characterized in that, include: Acquire image data of a paper carrier tape to be measured; wherein, the image data includes at least one group of images to be measured; the group of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous region of the paper carrier tape is a group of images to be measured, and the group of images to be measured includes sub-images to be measured corresponding to different parameters or different positions; Based on the image data of the paper carrier tape to be measured, the measurement value of the sub-image to be measured in each group of images to be measured is calculated; Based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set, a recording operation is performed on the group of images to be measured. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, at least one qualified domain pointed to by the target standard value is obtained and the domain is integrated, and the group of images to be measured is recorded into the integrated qualified domain. Error elimination is performed on all the image groups to be measured recorded in the integrated qualified field, and the measurement of the paper carrier tape to be measured is completed.

2. The paper carrier tape measurement method as described in claim 1, characterized in that, The step of calculating the measurement value of the sub-image to be measured in each group of images to be measured based on the image data of the paper carrier tape to be measured includes: Based on the image data of the paper carrier tape to be measured, feature recognition is performed on the sub-images to be measured in each group of images to be measured to determine the multiple types of measurement objects corresponding to each sub-image to be measured; The measurement algorithm corresponding to each type of measurement object is matched according to the measurement object, and the measurement value of each type of measurement object in each sub-image to be measured is obtained by calculating according to the measurement algorithm. Based on the integration of all the object measurements, the measurement values ​​of the sub-images to be measured in each group of images to be measured are determined.

3. The paper carrier tape measurement method as described in claim 1, characterized in that, The step of comparing the measured value of the sub-image to be measured with the standard value in the corresponding dimension standard value set, performing a recording operation on the group of images to be measured, and when there is a target standard value in the corresponding dimension standard value set corresponding to at least one measured value of the sub-image to be measured, obtaining at least one qualified domain pointed to by the target standard value for domain integration, and recording the group of images to be measured into the integrated qualified domain, includes: The measured value of each sub-image to be measured is compared one by one with the standard value in the corresponding dimension standard value set, and the target standard value that matches at least one measured value is selected, and the qualified domain pointed to by each target standard value is obtained. Perform an interval merging operation on each of the target standard values, which points to at least one of the qualified fields, to generate an integrated qualified field; The association information of the image group to be measured is recorded in the integrated qualified domain.

4. The paper carrier tape measurement method as described in claim 1, characterized in that, The method further includes: If there is no target standard value in the corresponding dimension standard value set that corresponds to the measurement value of the sub-image to be measured, the measurement value of the sub-image to be measured is recorded in the non-compliance field.

5. The paper carrier tape measurement method as described in claim 1, characterized in that, The step of eliminating errors in all the image groups to be measured recorded in the integrated qualified field and completing the measurement of the paper carrier tape to be measured includes: The system iterates through all the image groups to be measured in the integrated qualified domain record, and extracts and determines the object measurement values ​​of each type of measurement object in each of the sub-images to be measured. Based on all the object measurements, systematic error elimination is performed on the object measurements of each type of object in each of the sub-images to be measured, and an object correction value for each type of object in each of the sub-images to be measured is determined; The object correction values ​​of each type of measurement object in each of the sub-images to be measured are reintegrated into the integrated qualified domain, and the measurement of the paper carrier tape to be measured is completed.

6. The paper carrier tape measurement method as described in claim 5, characterized in that, The step of systematically eliminating errors in the object measurement values ​​of each type of object in each of the measured sub-images based on all the object measurement values, and determining the object correction value for each type of object in each of the measured sub-images, includes: A first systematic error coefficient is determined for each class of the measured objects in each of the measured sub-images based on all the object measurements; Based on the first systematic error coefficient of each class of the measured objects in all the measured sub-images, determine the first systematic error average coefficient of each class of the measured objects; Based on the first systematic error average coefficient for each type of the measured object, the second systematic error coefficient corresponding to the image data is determined; Based on the second systematic error coefficient, the object measurement values ​​of each type of measurement object in each of the sub-images to be measured are used to eliminate errors, and an object correction value for each type of measurement object in each of the sub-images to be measured is determined.

7. The paper carrier tape measurement method as described in claim 6, characterized in that, Determining the second systematic error coefficient corresponding to the image data based on the first systematic error average coefficient for each type of the measured object includes: Based on the first systematic error average coefficient of each type of measurement object, the error sensitivity factors of each type of measurement object are identified, and the measurement objects are divided into several error association groups according to the strain response of each measurement object relative to the conveying direction and the error sensitivity factors. Calculate the co-variance value of the average coefficient of the first systematic error within each of the error association groups; Based on the cooperative fluctuation value of each of the error association groups, a second systematic error coefficient reflecting the global common deviation of the entire carrier image data is obtained.

8. The paper carrier tape measurement method as described in claim 7, characterized in that, The step of obtaining a second systematic error coefficient reflecting the global common deviation of the entire carrier image data segment based on the coordinated fluctuation value of each error association group includes: By comparing the cooperative fluctuation value of each error association group with a preset threshold, if the cooperative fluctuation value is lower than the preset threshold, it is determined that the error association group has a common error source. For the error correlation group that has a common error source, the weighted average of the first systematic error average coefficient of the error correlation group is taken as the error characterization value of the error correlation group. By fusing the error characterization values ​​of all error association groups, a second systematic error coefficient reflecting the global common deviation of the entire carrier image data is obtained.

9. A paper carrier tape measuring device, characterized in that, include: An acquisition unit is used to acquire image data of a paper carrier tape to be measured; wherein, the image data includes at least one group of images to be measured; the group of images to be measured includes sub-images to be measured corresponding to different measurement dimensions, and the image of each continuous region of the paper carrier tape is a group of images to be measured, and the group of images to be measured includes sub-images to be measured corresponding to different parameters or different positions; A measurement unit is used to calculate the measurement value of the sub-image to be measured in each group of images to be measured based on the image data of the paper carrier tape to be measured; The integration unit is used to perform a recording operation on the image group to be measured based on the comparison between the measured value of the sub-image to be measured and the standard value in the corresponding dimension standard value set. When there is a target standard value in the corresponding dimension standard value set that corresponds to the measured value of at least one sub-image to be measured, the unit obtains at least one qualified domain pointed to by the target standard value and performs domain integration, and records the image group to be measured into the integrated qualified domain. The result unit is used to perform error elimination on all the image groups to be measured recorded in the integrated qualified field and to complete the measurement of the paper carrier tape to be measured.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the paper carrier measurement method as described in any one of claims 1 to 8.

Images