Toy qualification inspection method, product, equipment and medium

Abstract

The invention relates to the technical field of product quality detection, in particular to a toy qualification inspection method, a product, equipment and a medium. The method comprises the following steps: acquiring a first image of a toy shot by a camera device and the weight of the toy, wherein the first image comprises a plurality of toy images at different angles; judging whether the appearance of the toy is qualified according to the first image; if the appearance of the toy is qualified, acquiring a second image of the toy irradiated by the X-ray; extracting brightness information in the second image, and judging whether the cotton filling amount of the toy is uniform or not according to the brightness information and the weight; and if the cotton filling amount of the toy is uniform, judging the toy as a qualified product. According to the invention, unqualified products can be effectively screened out, and the accuracy of toy quality detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of product quality inspection, and in particular to a toy quality inspection method, product, equipment and medium. Background Art

[0002] With the continuous expansion of the toy market and the increasing demand for product quality from consumers, how to ensure the safety and compliance of toy products has become a common focus for manufacturers and regulators. Traditional toy inspection methods often rely on manual visual inspection and simple physical testing, which are not only inefficient but also easily affected by human factors, making it difficult to ensure the accuracy and reliability of inspection results. Summary of the invention

[0003] In order to improve the accuracy of toy quality inspection, the present application provides a toy qualification inspection method, product, equipment and medium.

[0004] In the first aspect, the present application provides a toy qualification inspection method, which adopts the following technical solution: A toy qualification inspection method, comprising: Acquire a first image of a toy captured by a camera device and the weight of the toy, wherein the first image includes multiple images of the toy at different angles; judging whether the appearance of the toy is qualified according to the first image; If the appearance of the toy is qualified, obtaining a second image of the toy after being irradiated with X-rays; Extracting brightness information from the second image, and judging whether the filling amount of the toy is uniform according to the brightness information and the weight; If the filling amount of the toy is uniform, the toy is judged to be a qualified product.

[0005] By adopting the above technical solution, the camera device captures toy images from multiple different angles, which can fully capture the appearance information of the toy, including shape, color, texture, etc., and obtain the weight information of the toy at the same time, providing the necessary physical parameters for the subsequent judgment of the uniformity of the filling amount. The image processing technology is used to automatically judge whether the toy appearance is qualified, which can quickly identify appearance defects and reduce the subjectivity and time cost of manual judgment. The brightness information of the X-ray image is used to indirectly reflect the distribution of the filling amount inside the toy. By combining the brightness information and weight data, the uniformity of the filling amount can be more accurately evaluated. The comprehensive judgment combined with the appearance and internal structure (filling amount) ensures the comprehensiveness and reliability of the toy quality, can effectively screen out unqualified products, and improve the overall quality level of the product.

[0006] In a preferred example, the present application can be further configured as follows: judging whether the filling amount of the toy is uniform according to the brightness information and the weight includes: Get the component type of the toy; If the toy is composed of multiple independent parts, obtaining a preset standard filling amount corresponding to each part; Calculating the standard weight of the toy based on the preset standard filling amounts corresponding to the multiple parts; The weight is compared with the standard weight. If the weight meets the standard weight, whether the filling amount of the toy is uniform is determined based on the brightness information.

[0007] By adopting the above technical solution, the composition type of the toy (a single entity or multiple independent parts) is identified. Understanding the specific structure of the toy helps to more accurately evaluate the uniformity of its filling amount. Because the filling requirements of different parts may be different, a preset standard filling amount is set for each independent part, and the preset standard filling amount of each part is accumulated to calculate the standard weight of the toy. First, the weight comparison is used to preliminarily judge whether the overall filling amount of the toy meets expectations, and then the brightness information is used to further judge the uniformity of the filling amount. The brightness information can reflect the subtle differences in the filling density inside the toy. Even if the overall weight meets the standard, there may be local uneven filling. This double verification mechanism improves the accuracy and reliability of the judgment.

[0008] In a preferred example, the present application may be further configured as follows: judging whether the filling amount of the toy is uniform according to the brightness information includes: Acquire a three-dimensional model of the toy constructed based on the first image, and align the second image and the three-dimensional model in a virtual environment; Simulating a propagation path of X-rays in the virtual environment, and mapping the X-rays penetrating the toy on a second image in the virtual environment aligned with the three-dimensional model; Dividing the second image into a mapping area and a non-mapping area, wherein the mapping area is an area irradiated by X-rays penetrating the toy, and the non-mapping area is an area directly irradiated by X-rays; Selecting a plurality of mapping points from the mapping area, calculating the length of a line segment where the X-ray at each mapping point intersects with the three-dimensional model as the toy thickness, and obtaining the toy thickness corresponding to each of the plurality of mapping points; Whether the filling amount of the toy is uniform is determined according to the brightness information and the toy thicknesses corresponding to the plurality of mapping points.

[0009] By adopting the above technical solution, the second image and the three-dimensional model are aligned in the virtual environment to ensure the consistency of the spatial position of the two. Through simulation, the attenuation and scattering of X-rays when penetrating the toy can be predicted, and multiple mapping points are selected from the mapping area. These points can represent the filling conditions at different positions inside the toy. Combined with the brightness information and the toy thickness corresponding to the multiple mapping points, the attenuation of X-rays when penetrating fillings of different thicknesses and densities is comprehensively considered, so that areas with uneven filling, such as local over-thickness or over-thinness, can be identified more accurately, thereby improving the accuracy and reliability of the judgment.

[0010] In a preferred example, the present application may be further configured as follows: judging whether the filling amount of the toy is uniform according to the brightness information and the toy thicknesses corresponding to the plurality of mapping points, including: Calculating a brightness loss value corresponding to a target mapping point according to a toy thickness of the target mapping point, and determining a brightness loss range based on the brightness loss value, wherein the target mapping point is any one of the plurality of mapping points; Acquire the average brightness value of the non-mapped area from the brightness information as an initial brightness value; Determine the brightness value of the target mapping point from the brightness information, and calculate the brightness difference between the initial brightness value and the brightness value; determining whether the brightness difference is within the brightness loss range, and if so, determining the cotton filling amount determination result of the target mapping point as uniform cotton filling amount; The filling amount determination results corresponding to the plurality of mapping points are obtained. If the filling amount determination results of the plurality of mapping points are all uniform filling amounts, it is determined that the filling amount of the toy is uniform.

[0011] By adopting the above technical solution, the brightness loss value is calculated according to the toy thickness at the target mapping point, and the attenuation law of X-rays in materials of different thicknesses is taken into account, so that the subsequent judgment is more scientific and reliable, and the average brightness value is obtained from the non-mapping area as the initial brightness value. The brightness of the non-mapping area is not affected by the internal structure of the toy, so its brightness value can represent the brightness level of the X-ray source itself. By calculating the difference between the initial brightness value and the brightness value of the mapping point, a quantitative description of the brightness change is achieved. By comparing the brightness difference with the brightness loss range, it is possible to accurately judge whether the filling amount at the mapping point meets the uniformity requirement. By combining the judgment results of multiple mapping points, the uniformity of the filling amount of the entire toy can be comprehensively evaluated.

[0012] In a preferred example, the present application may be further configured as follows: the step of calculating the brightness loss value corresponding to the target mapping point according to the toy thickness of the target mapping point includes: The part of the toy corresponding to the target mapping point is used as the target part, and the preset standard filling amount and fabric type of the target part are obtained; determining the volume of the target part according to the three-dimensional model of the toy; Calculating the cotton filling density of the target part according to the volume of the target part and the corresponding preset standard cotton filling amount; Determine a first brightness loss value corresponding to the cotton filling density according to a first preset corresponding relationship, wherein the first preset corresponding relationship is a corresponding relationship between the cotton filling density and the brightness loss value caused by X-rays passing through cotton of unit thickness on the image; Determine a second brightness loss value corresponding to the cloth type according to a second preset corresponding relationship, where the second preset corresponding relationship is a corresponding relationship between the cloth type and the brightness loss value caused by X-rays passing through the cloth of the cloth type on the image; The brightness loss value corresponding to the target mapping point is calculated according to the first brightness loss value and the second brightness loss value.

[0013] By adopting the above technical solution, the preset standard filling amount and fabric type of the target part are obtained, which can more accurately reflect the actual physical properties of the part. The calculation of the filling density is based on physical principles, that is, the ratio of mass to volume. This calculation method is scientific and reasonable. Through the preset corresponding relationship (the first preset corresponding relationship and the second preset corresponding relationship), the filling density and fabric type can be quickly converted into corresponding brightness loss values, thereby improving the calculation efficiency.

[0014] In a preferred example, the present application may be further configured as follows: judging whether the appearance of the toy is qualified according to the first image includes: constructing a three-dimensional model of the toy according to the first image, and comparing the three-dimensional model with a preset standard model to obtain a first comparison result; Extracting features from the first image, and comparing the features with preset standard features to obtain a second comparison result; If the first comparison result is that the three-dimensional model conforms to the preset standard model and the second comparison result is that the feature conforms to the preset standard feature, the appearance of the toy is determined to be qualified.

[0015] By adopting the above technical solution, a three-dimensional model of the toy is constructed and compared with a preset standard model, so that the three-dimensional spatial information such as the shape and size of the toy can be accurately captured, thereby ensuring that the appearance of the toy meets the design requirements. Feature extraction can capture key detail information in the first image, such as color, texture, pattern, etc., and by comparing with preset standard features, the eligibility of the toy's appearance can be further verified. By combining the two methods of three-dimensional model comparison and feature extraction comparison, double verification of the toy's appearance is achieved, thereby improving the reliability of the judgment.

[0016] In a preferred example, the present application can be further configured as follows: the method further includes: Acquire a first brightness value of an image formed by direct X-ray irradiation of a preset intensity; Respectively obtain second brightness values ​​of images formed by X-rays of the preset intensity penetrating toy filling cotton of different densities per unit thickness; For any density, calculating the difference between the first brightness value and the second brightness value corresponding to the thickness as the brightness loss value corresponding to the density; Each density and the corresponding brightness loss value are stored in a preset database as a first preset correspondence relationship.

[0017] By adopting the above technical solution, for each density, the difference between the first brightness value and the second brightness value of the corresponding thickness, that is, the brightness loss value, is calculated, and each density and the corresponding brightness loss value is stored in a preset database as a first preset correspondence, thereby realizing data standardization and unified management. This preset correspondence provides a convenient query and reference method for subsequent inspections and evaluations, without the need to recalculate the brightness loss value for each inspection, thereby improving inspection efficiency.

[0018] In a second aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program. When the computer program is executed by a processor, the toy qualification inspection method as described in any one of the first aspects is implemented.

[0019] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the toy qualification inspection method as described in any one of the first aspects.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the toy qualification inspection method as described in any one of the first aspects.

[0021] In summary, this application includes the following beneficial technical effects: The present application uses a camera to capture toy images from multiple different angles, which can comprehensively capture the appearance information of the toy, including shape, color, texture, etc., and obtain the weight information of the toy at the same time, providing the necessary physical parameters for the subsequent judgment of the uniformity of the filling amount. The image processing technology is used to automatically judge whether the toy appearance is qualified, which can quickly identify appearance defects and reduce the subjectivity and time cost of manual judgment. The brightness information of the X-ray image is used to indirectly reflect the distribution of the filling amount inside the toy. By combining the brightness information and weight data, the uniformity of the filling amount can be more accurately evaluated. The comprehensive judgment combined with the appearance and internal structure (filling amount) ensures the comprehensiveness and reliability of the toy quality, can effectively screen out unqualified products, and improves the overall quality level of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of a toy qualification inspection method provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figure 1 -Attached Figure 2 This application is described in further detail.

[0024] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0027] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0028] The present application embodiment provides a toy qualification inspection method, such as Figure 1 As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S105, wherein: S101, obtaining a first image of a toy and a weight of the toy taken by a camera device, wherein the first image includes multiple images of the toy taken at different angles.

[0029] Specifically, multiple camera devices (such as high-definition cameras) are set up in the production line or inspection area to take pictures of the toy from different angles (such as the front, side, and top), and the electronic device controls the camera devices to take pictures at the same time to obtain a first image of the toy. Furthermore, an electronic scale or weight sensor can be set up to measure the weight of the toy and transmit the obtained weight data to the electronic device.

[0030] S102: Determine whether the appearance of the toy is qualified based on the first image.

[0031] Specifically, each toy image in the first image is preprocessed, including denoising, contrast enhancement, etc., to improve image quality for subsequent analysis. The key features in the preprocessed first image are extracted using an image processing algorithm, and the extracted features are compared with preset standard features that characterize qualification. If the features meet the preset standard features, the appearance of the toy is determined to be qualified.

[0032] There may be multiple types of features extracted from the first image. If any type of feature does not meet the corresponding preset standard feature, the appearance of the toy is judged to be unqualified, and the toy is directly judged to be a defective product.

[0033] S103: If the appearance of the toy is qualified, obtain a second image of the toy after being irradiated with X-rays.

[0034] Specifically, an X-ray detection device is provided, which can emit X-rays and capture images of the internal structure of a toy. A toy with a qualified appearance is placed on a detection table of the X-ray detection device, and the device is started to obtain a second image of the toy after being irradiated with X-rays.

[0035] S104: extracting brightness information from the second image, and judging whether the filling amount of the toy is uniform according to the brightness information and the weight.

[0036] Specifically, the composition types of different toys can be divided into two types, one is a toy that is directly connected internally, and the other is a toy composed of multiple independent parts.

[0037] When the toy being tested is of the type with internal direct connections, the preset standard cotton filling amount (filling weight) inside the toy and the preset standard fabric weight of the fabric required for the toy (which can be obtained by calculating the product of the fabric weight and the required fabric area, where the weight is the fabric weight per unit area) can be obtained by referring to the design documents, rule books or production standards of the toy. The sum of the preset standard cotton filling amount and the preset standard fabric weight shall be used as the standard weight of the toy.

[0038] When the toy being tested consists of multiple independent parts, the preset standard cotton filling amount of each part and the preset standard fabric weight of the fabric required for the toy can be obtained by referring to the design documents, rule books or production standards of the toy, and the sum of the preset standard cotton filling amount and the preset standard fabric weight of each part can be calculated as the standard weight of the toy.

[0039] After obtaining the weight and standard weight of the toy, the difference between the measured weight and the standard weight is calculated, and the allowable weight error range of the toy is checked from the design document, rule book or production standard of the toy. The obtained difference is compared with the weight error range. If the difference exceeds the weight error range, the toy is directly judged as a defective product; if the difference does not exceed the weight error range, the weight is judged to meet the standard weight, and then, the brightness information is used to determine whether the filling amount of the toy is uniform.

[0040] The brightness information can be obtained by graying the second image and then extracting the brightness value at each point in the second image.

[0041] S105. If the filling amount of the toy is uniform, the toy is determined to be a qualified product.

[0042] Furthermore, if it is determined based on the brightness information that the filling amount of the toy is uneven, the toy is determined to be a defective product.

[0043] The embodiment of the present application uses a camera to capture toy images from multiple different angles, which can comprehensively capture the appearance information of the toy, including shape, color, texture, etc., and obtain the weight information of the toy at the same time, providing necessary physical parameters for subsequent judgment of the uniformity of the filling amount. Image processing technology is used to automatically judge whether the toy appearance is qualified, and appearance defects can be quickly identified, reducing the subjectivity and time cost of manual judgment. The brightness information of the X-ray image is used to indirectly reflect the distribution of the filling amount inside the toy. By combining the brightness information and weight data, the uniformity of the filling amount can be more accurately evaluated. The comprehensive judgment combined with the appearance and internal structure (filling amount) ensures the comprehensiveness and reliability of the toy quality, can effectively screen out unqualified products, and improves the overall quality level of the product.

[0044] A possible implementation of the embodiment of the present application is to determine whether the filling amount of the toy is uniform according to the brightness information and the weight, including: Get the component type of the toy; If the toy is composed of multiple independent parts, obtain the preset standard filling amount corresponding to each part; Calculate the standard weight of the toy based on the preset standard filling amounts corresponding to multiple parts; The weight is compared with the standard weight. If the weight meets the standard weight, the brightness information is used to determine whether the filling amount of the toy is uniform.

[0045] The embodiment of the present application identifies the component type of the toy (a single entity or multiple independent parts) and understands the specific structure of the toy, which helps to more accurately evaluate the uniformity of its filling amount. Because the filling requirements of different parts may be different, a preset standard filling amount is set for each independent part, and the preset standard filling amount of each part is accumulated to calculate the standard weight of the toy. First, a weight comparison is used to preliminarily determine whether the overall filling amount of the toy meets expectations, and then the uniformity of the filling amount is further determined through brightness information. The brightness information can reflect subtle differences in the filling density inside the toy. Even if the overall weight meets the standard, there may be local uneven filling. This double verification mechanism improves the accuracy and reliability of the judgment.

[0046] A possible implementation of the embodiment of the present application is to determine whether the filling amount of the toy is uniform according to the brightness information, including: Acquire a three-dimensional model of the toy constructed based on the first image, and align the second image and the three-dimensional model in the virtual environment; Simulating the propagation path of the X-rays in the virtual environment, and mapping the X-rays penetrating the toy on a second image aligned with the three-dimensional model in the virtual environment; Dividing the second image into a mapping area and a non-mapping area, the mapping area is an area irradiated by the X-rays that penetrate the toy, and the non-mapping area is an area directly irradiated by the X-rays; Select multiple mapping points from the mapping area, calculate the length of the line segment where the X-ray at each mapping point intersects the three-dimensional model as the toy thickness, and obtain the toy thickness corresponding to each of the multiple mapping points; Whether the filling amount of the toy is uniform is determined based on the brightness information and the toy thickness corresponding to each of the multiple mapping points.

[0047] In this embodiment, the second image and the three-dimensional model of the toy are loaded into a computer or an image processing system, and the second image is preprocessed, including denoising and contrast enhancement, etc., to improve the image quality. In the second image, a feature point detection algorithm (such as SIFT, SURF, ORB, etc.) is used to identify key feature points in the image. For the three-dimensional model, feature points or feature surfaces are extracted from the three-dimensional model, which can be the edge, corner point or special texture area of ​​the model. The feature points extracted from the second image are matched with the features extracted from the three-dimensional model. The matching algorithm can be brute force matching or FLANN (fast nearest neighbor search library) to find multiple matching pairs. Furthermore, the optimal transformation matrix from the image space to the model space is calculated based on multiple matching pairs through a random sampling consistency algorithm. The transformation matrix includes rotation, translation and possible scaling parameters, which are used to set the points in the second image to the corresponding positions of the three-dimensional model, thereby completing the alignment. After the alignment is completed, quantitative indicators such as the root mean square error and the average error can be calculated to measure the distance deviation between the points in the second image and the corresponding points on the three-dimensional model to ensure the accuracy of the alignment.

[0048] For the second image, an automatic threshold selection algorithm (such as Otsu method, adaptive threshold, etc.) can be used to determine the optimal segmentation threshold. These algorithms can automatically calculate the optimal threshold based on the statistical characteristics of the second image to distinguish between the mapping area and the non-mapping area. After dividing the mapping area and the non-mapping area, multiple mapping points are evenly selected in the mapping area, and the selected mapping points exist in the area corresponding to each part. For each mapping point, the length of the line segment where the X set point intersects with the three-dimensional model at this point is calculated by ray tracing technology, that is, the thickness of the toy at this point, and the thickness of the toy corresponding to each mapping point is recorded to form a thickness data set.

[0049] The embodiment of the present application ensures the consistency of the spatial position of the second image and the three-dimensional model by aligning the second image with the three-dimensional model in a virtual environment. Through simulation, the attenuation and scattering of X-rays when penetrating the toy can be predicted, and multiple mapping points are selected from the mapping area. These points can represent the filling conditions at different positions inside the toy. Combined with the brightness information and the toy thickness corresponding to the multiple mapping points, the attenuation of X-rays when penetrating fillings of different thicknesses and densities is comprehensively considered, so that areas with uneven filling, such as local over-thickness or over-thinness, can be more accurately identified, thereby improving the accuracy and reliability of the judgment.

[0050] A possible implementation of the embodiment of the present application is to determine whether the filling amount of the toy is uniform according to the brightness information and the toy thickness corresponding to each of the multiple mapping points, including: Calculating a brightness loss value corresponding to the target mapping point according to the toy thickness of the target mapping point, and determining a brightness loss range based on the brightness loss value, wherein the target mapping point is any one of the multiple mapping points; Obtain the average brightness value of the non-mapped area from the brightness information as the initial brightness value; Determine the brightness value of the target mapping point from the brightness information, and calculate the brightness difference between the initial brightness value and the brightness value; It is determined whether the brightness difference is within the brightness loss range. If so, the filling amount determination result of the target mapping point is determined as uniform filling amount. The filling amount determination results corresponding to the plurality of mapping points are obtained. If the filling amount determination results of the plurality of mapping points are all uniform, it is determined that the filling amount of the toy is uniform.

[0051] In this embodiment, for the target mapping point, the attenuation degree of the X-ray caused by the cotton filling material at the target mapping point can be calculated according to the thickness of the toy at the target mapping point. The attenuation degree can be represented by a brightness loss value, which represents the difference between the brightness of the image formed by direct X-ray irradiation without passing through the toy and the brightness of the image formed by passing through a toy of a certain thickness. The brightness loss range can be flexibly set according to actual experience. Optionally, the product of the brightness loss value corresponding to the target mapping point and 90% can be used as the minimum value of the brightness loss range, and the product of the brightness loss value corresponding to the target mapping point and 110% can be used as the maximum value of the brightness loss range. The brightness loss range is used to determine whether the actual brightness difference is within an acceptable range.

[0052] The initial brightness value represents the X-ray brightness without attenuation caused by the filling inside the toy. For the target mapping point, the brightness value at that point is read from the brightness information. This brightness value indicates that it has been affected by the X-ray attenuation caused by the filling inside the toy. The difference between the initial brightness value and the brightness value of the target mapping point is calculated, that is, the brightness difference. This difference reflects the brightness loss of the X-ray due to the filling material when penetrating the inside of the toy. Compare the calculated brightness difference with the determined brightness loss range. If the brightness difference is within this range, it means that the attenuation of the X-ray by the filling at the target mapping point is consistent with expectations, so it can be preliminarily determined that the filling at the target mapping point is uniform.

[0053] Summarize the filling amount determination results of all mapping points. If all mapping points are determined to be uniformly filled, then the filling amount of the entire toy can be considered uniform. If any mapping point is determined to be unevenly filled, the toy can be judged as unqualified, and the staff can further analyze the reasons for the uneven filling amount and conduct further inspections or adjustments.

[0054] The embodiment of the present application calculates the brightness loss value according to the toy thickness at the target mapping point, taking into account the attenuation law of X-rays in materials of different thicknesses, making subsequent judgments more scientific and reliable, and obtaining the average brightness value from the non-mapping area as the initial brightness value. The brightness of the non-mapping area is not affected by the internal structure of the toy, so its brightness value can represent the brightness level of the X-ray source itself. By calculating the difference between the initial brightness value and the brightness value of the mapping point, a quantitative description of the brightness change is achieved. By comparing the brightness difference with the brightness loss range, it is possible to accurately determine whether the filling amount at the mapping point meets the uniformity requirements. By combining the judgment results of multiple mapping points, the uniformity of the filling amount of the entire toy can be comprehensively evaluated.

[0055] A possible implementation of the embodiment of the present application is to calculate the brightness loss value corresponding to the target mapping point according to the toy thickness of the target mapping point, including: The part of the toy corresponding to the target mapping point is used as the target part, and the preset standard filling amount and fabric type of the target part are obtained; Determine the volume of the target part according to the three-dimensional model of the toy; Calculate the cotton filling density of the target part according to the volume of the target part and the corresponding preset standard cotton filling amount; Determine a first brightness loss value corresponding to the cotton filling density according to a first preset corresponding relationship, where the first preset corresponding relationship is a corresponding relationship between the cotton filling density and the brightness loss value caused by X-rays passing through cotton of unit thickness on the image; Determine a second brightness loss value corresponding to the cloth type according to a second preset corresponding relationship, where the second preset corresponding relationship is a corresponding relationship between the cloth type and the brightness loss value caused by the X-ray passing through the cloth of the cloth type on the image; A brightness loss value corresponding to the target mapping point is calculated according to the first brightness loss value and the second brightness loss value.

[0056] In this embodiment, the density of the filling material inside different parts of the toy may be different. For example, for toys with limbs, the density of the filling material in the limbs is often higher than that in the body parts, and the different densities of the toy filling material cause different degrees of attenuation of X-rays. The three-dimensional model of the toy is loaded, and the target part of the target mapping point mapped on the three-dimensional model can be determined according to the position of the target mapping point on the second image and the propagation path of the simulated X-ray. The preset standard filling amount and fabric type of the target part can be determined from the production standard of the toy. Using the three-dimensional model data, the volume of the target part can be calculated through three-dimensional geometric calculations such as volume integral or approximate methods based on the model grid. Filling density = preset standard filling amount / volume.

[0057] The preset database of the electronic device pre-stores a first preset correspondence and a second preset correspondence, and the first preset correspondence and the second preset correspondence can be obtained based on experiments. The first preset correspondence is a correspondence between brightness loss values ​​of different cotton filling densities and unit thicknesses. After determining the cotton filling density of the target part, find out from the first preset correspondence whether there is a cotton filling density that is the same as the cotton filling density of the target part. If so, use the corresponding brightness loss value as the first brightness loss value. If not, interpolate the first preset correspondence to calculate the first brightness loss value corresponding to the cotton filling density of the target part. The second preset correspondence can be a correspondence between brightness loss values ​​caused by different fabric types and two layers of fabric of the same fabric type when X-rays pass through.

[0058] Furthermore, the brightness loss value corresponding to the target mapping point=the first brightness loss value+the second brightness loss value.

[0059] The embodiment of the present application can more accurately reflect the actual physical properties of the target part by obtaining the preset standard filling amount and fabric type of the target part. The calculation of the filling density is based on physical principles, that is, the ratio of mass to volume. This calculation method is scientific and reasonable. Through the preset corresponding relationship (the first preset corresponding relationship and the second preset corresponding relationship), the filling density and fabric type can be quickly converted into corresponding brightness loss values, thereby improving the calculation efficiency.

[0060] A possible implementation of the embodiment of the present application is to determine whether the appearance of the toy is qualified according to the first image, including: constructing a three-dimensional model of the toy according to the first image, and comparing the three-dimensional model with a preset standard model to obtain a first comparison result; Extracting features from the first image, comparing the features with preset standard features, and obtaining a second comparison result; If the first comparison result is that the three-dimensional model conforms to the preset standard model and the second comparison result is that the feature conforms to the preset standard feature, the appearance of the toy is determined to be qualified.

[0061] In this embodiment, a three-dimensional reconstruction technology (such as image-based three-dimensional reconstruction, stereoscopic vision) is used to process the first image to construct a three-dimensional model of the toy. A preset standard three-dimensional model is loaded, and the preset standard model represents the ideal appearance shape and size of the toy. A three-dimensional comparison algorithm (such as an ICP algorithm, a feature-based comparison method, etc.) is used to compare the constructed three-dimensional model with the preset standard model. The first comparison result includes a size deviation. The size deviation is compared with the size deviation threshold preset by the staff according to the production requirements. If the size deviation does not exceed the preset size deviation threshold, the first comparison result is determined to be that the three-dimensional model conforms to the preset standard three-dimensional model. If the size deviation exceeds the preset size deviation threshold, the first comparison result is determined to be that the three-dimensional model does not conform to the preset standard three-dimensional model.

[0062] Extract key features from the first image, including color, texture, and edge, load preset standard features, which may be a feature set determined based on toy production requirements and used to characterize various types of appearance characteristics that toys should have, and compare each type of extracted feature with the corresponding preset standard feature to determine whether the difference between the features exceeds a preset feature difference threshold. If each feature does not exceed the corresponding preset feature difference threshold, determine the second comparison result as a feature that meets the preset standard feature. If there is a feature that exceeds the corresponding preset feature difference threshold, determine the second comparison result as a feature that does not meet the preset standard feature.

[0063] Based on the first comparison result and the second comparison result, if the first comparison result is that the three-dimensional model does not meet the preset standard three-dimensional model or the second comparison result is that the feature does not meet the preset standard feature, the appearance of the toy is judged to be unqualified, that is, the toy is judged to be a defective product.

[0064] The embodiment of the present application constructs a three-dimensional model of the toy and compares it with a preset standard model, so as to accurately capture the three-dimensional spatial information of the toy, such as the shape and size, thereby ensuring that the appearance shape of the toy meets the design requirements. Feature extraction can capture key detail information in the first image, such as color, texture, pattern, etc., and by comparing it with preset standard features, the qualification of the toy appearance can be further verified. By combining the two methods of three-dimensional model comparison and feature extraction comparison, double verification of the toy appearance is achieved, thereby improving the reliability of the judgment.

[0065] In a possible implementation manner of the embodiment of the present application, the method further includes: Acquire a first brightness value of an image formed by direct X-ray irradiation of a preset intensity; Respectively obtain second brightness values ​​of images formed by X-rays of preset intensity penetrating toy filling cotton of different densities per unit thickness; For any density, the difference between the first brightness value and the second brightness value corresponding to the thickness is calculated as the brightness loss value corresponding to the density; Each density and the corresponding brightness loss value are stored in a preset database as a first preset correspondence relationship.

[0066] The preset intensity is the intensity of the X-ray when acquiring the second image.

[0067] For each density, the embodiment of the present application calculates the difference between the first brightness value and the second brightness value of the corresponding thickness, that is, the brightness loss value, and stores each density and the corresponding brightness loss value as a first preset correspondence in a preset database, thereby realizing data standardization and unified management. This preset correspondence provides a convenient query and reference method for subsequent detection and evaluation, without the need to recalculate the brightness loss value for each detection, thereby improving detection efficiency.

[0068] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned toy qualification inspection method embodiment are implemented.

[0069] An electronic device is provided in an embodiment of the present application, such as Figure 2 As shown, Figure 2 The electronic device 200 shown includes: a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, such as through a bus 202. Optionally, the electronic device 200 may also include a transceiver 204. It should be noted that in actual applications, the transceiver 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present application.

[0070] The processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 201 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0071] The bus 202 may include a path to transmit information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0072] The memory 203 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0073] The memory 203 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement the contents shown in the above-mentioned toy qualification inspection method embodiment.

[0074] Figure 2 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0075] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned toy qualification inspection method embodiment.

[0076] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0077] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A toy qualification inspection method, characterized in that: include: Acquire a first image of a toy captured by a camera device and the weight of the toy, wherein the first image includes multiple images of the toy at different angles; judging whether the appearance of the toy is qualified according to the first image; If the appearance of the toy is qualified, obtaining a second image of the toy after being irradiated with X-rays; Extracting brightness information from the second image, and judging whether the filling amount of the toy is uniform according to the brightness information and the weight; If the filling amount of the toy is uniform, the toy is judged to be a qualified product.

2. The toy qualification inspection method according to claim 1, characterized in that: The step of judging whether the filling amount of the toy is uniform according to the brightness information and the weight includes: Get the component type of the toy; If the toy is composed of multiple independent parts, obtaining a preset standard filling amount corresponding to each part; Calculating the standard weight of the toy based on the preset standard filling amounts corresponding to the multiple parts; The weight is compared with the standard weight. If the weight meets the standard weight, whether the filling amount of the toy is uniform is determined based on the brightness information.

3. The toy qualification inspection method according to claim 2, characterized in that: The step of judging whether the filling amount of the toy is uniform according to the brightness information includes: Acquire a three-dimensional model of the toy constructed based on the first image, and align the second image and the three-dimensional model in a virtual environment; Simulating a propagation path of X-rays in the virtual environment, and mapping the X-rays penetrating the toy on a second image in the virtual environment aligned with the three-dimensional model; Dividing the second image into a mapping area and a non-mapping area, wherein the mapping area is an area irradiated by X-rays penetrating the toy, and the non-mapping area is an area directly irradiated by X-rays; Selecting a plurality of mapping points from the mapping area, calculating the length of a line segment where the X-ray at each mapping point intersects with the three-dimensional model as the toy thickness, and obtaining the toy thickness corresponding to each of the plurality of mapping points; Whether the filling amount of the toy is uniform is determined according to the brightness information and the toy thicknesses corresponding to the plurality of mapping points.

4. The toy qualification inspection method according to claim 3 is characterized in that: The step of judging whether the filling amount of the toy is uniform according to the brightness information and the toy thicknesses corresponding to the plurality of mapping points includes: Calculating a brightness loss value corresponding to a target mapping point according to a toy thickness of the target mapping point, and determining a brightness loss range based on the brightness loss value, wherein the target mapping point is any one of the plurality of mapping points; Acquire the average brightness value of the non-mapped area from the brightness information as an initial brightness value; Determine the brightness value of the target mapping point from the brightness information, and calculate the brightness difference between the initial brightness value and the brightness value; determining whether the brightness difference is within the brightness loss range, and if so, determining the cotton filling amount determination result of the target mapping point as uniform cotton filling amount; The filling amount determination results corresponding to the plurality of mapping points are obtained. If the filling amount determination results of the plurality of mapping points are all uniform filling amounts, it is determined that the filling amount of the toy is uniform.

5. The toy qualification inspection method according to claim 4 is characterized in that: The step of calculating the brightness loss value corresponding to the target mapping point according to the toy thickness of the target mapping point includes: The part of the toy corresponding to the target mapping point is used as the target part, and the preset standard filling amount and fabric type of the target part are obtained; determining the volume of the target part according to the three-dimensional model of the toy; Calculating the cotton filling density of the target part according to the volume of the target part and the corresponding preset standard cotton filling amount; Determine a first brightness loss value corresponding to the cotton filling density according to a first preset corresponding relationship, wherein the first preset corresponding relationship is a corresponding relationship between the cotton filling density and the brightness loss value caused by X-rays passing through cotton of unit thickness on the image; Determine a second brightness loss value corresponding to the cloth type according to a second preset corresponding relationship, where the second preset corresponding relationship is a corresponding relationship between the cloth type and the brightness loss value caused by X-rays passing through the cloth of the cloth type on the image; The brightness loss value corresponding to the target mapping point is calculated according to the first brightness loss value and the second brightness loss value.

6. The toy qualification inspection method according to claim 1, characterized in that: The step of judging whether the appearance of the toy is qualified according to the first image includes: constructing a three-dimensional model of the toy according to the first image, and comparing the three-dimensional model with a preset standard model to obtain a first comparison result; Extracting features from the first image, and comparing the features with preset standard features to obtain a second comparison result; If the first comparison result is that the three-dimensional model conforms to the preset standard model and the second comparison result is that the feature conforms to the preset standard feature, the appearance of the toy is determined to be qualified.

7. The toy qualification inspection method according to claim 1, characterized in that: The method further comprises: Acquire a first brightness value of an image formed by direct X-ray irradiation of a preset intensity; Respectively obtain second brightness values ​​of images formed by X-rays of the preset intensity penetrating toy filling cotton of different densities per unit thickness; For any density, calculating the difference between the first brightness value and the second brightness value corresponding to the thickness as the brightness loss value corresponding to the density; Each density and the corresponding brightness loss value are stored in a preset database as a first preset correspondence relationship.

8. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of the toy conformity inspection method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the toy qualification inspection method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the toy qualification inspection method according to any one of claims 1 to 7.

Images