Smart checkout counter quality detection method, device and electronic equipment

Abstract

The present invention provides a method, device, and electronic device for quality inspection of smart settlement counters, which obtain a first quantity of standard dimensional data of smart settlement counters and standardize the quality inspection measurement standard through the standard dimensional data of smart settlement counters. An image of the table surface to be tested of the smart settlement counter to be tested is obtained, and data processing is performed based on the table surface image to be tested to obtain a first quantity of dimensional data to be tested. The dimensional data to be tested represents the features of multiple dimensions of the table surface image to be tested, so that subsequent quality inspection results are more accurate. The quality inspection results of the smart settlement counter to be tested are determined based on the first quantity of standard dimensional data of smart settlement counters and the first quantity of dimensional data to be tested. Factory quality inspection of the table surface image of the smart settlement counter based on computer vision is implemented.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a checkout counter quality detection method, device and electronic equipment. Background Art

[0002] The smart checkout counter is an integrated device that uses computer vision to identify goods. Unlike traditional commodity settlement equipment, the smart checkout counter based on computer vision has the advantages of low cost, high robustness and high speed.

[0003] However, intelligent checkout counters based on visual algorithms rely on the accuracy of their recognition algorithms. Therefore, external factors that influence visual recognition accuracy, such as device lighting, countertop color, and camera clarity, are critical. These factors affect the final countertop image captured by the intelligent checkout counter. Conversely, these images can be used to perform quality inspections on the intelligent checkout counters. Therefore, providing a computer vision-based intelligent checkout counter for factory quality inspection of countertop images is a pressing issue. Summary of the Invention

[0004] The present invention provides a method, device and electronic equipment for quality inspection of intelligent settlement counters, which are used to solve the problem in the prior art that it is impossible to conduct factory quality inspection of intelligent settlement counters based on computer vision.

[0005] The present invention provides a method for detecting quality of an intelligent checkout counter, comprising:

[0006] Obtaining a first quantity of standard dimension data for smart checkout platforms;

[0007] Acquire an image of the test surface of the intelligent checkout counter to be tested;

[0008] Performing data processing according to the image of the table surface to be measured to obtain a first quantity of dimension data to be measured;

[0009] The quality inspection result of the smart settlement station to be tested is determined based on the first number of smart settlement station standard dimension data and the first number of dimension data to be tested.

[0010] According to a method for detecting quality of an intelligent checkout counter provided by the present invention, the standard dimension data of the intelligent checkout counter is obtained by the following steps, including:

[0011] For each of the plurality of smart checkout counter samples, obtaining a plurality of counter surface image samples;

[0012] Performing data processing on a plurality of countertop image samples of a plurality of smart checkout counter samples to obtain dimension data to be verified corresponding to the plurality of smart checkout counter samples;

[0013] Perform differentiated comparison on the dimension data to be verified corresponding to multiple smart checkout counter samples;

[0014] When the differentiated comparison passes, the first number of smart settlement station standard dimensional data is determined based on the to-be-verified dimensional data corresponding to the multiple smart settlement station samples.

[0015] According to a smart checkout counter quality inspection method provided by the present invention, data processing is performed based on multiple countertop image samples of multiple smart checkout counter samples to obtain dimensional data to be verified corresponding to the multiple smart checkout counter samples, including:

[0016] Perform image positioning on multiple table surface image samples of each intelligent checkout counter sample to obtain corresponding positioning image samples;

[0017] Perform feature extraction and averaging of a first number of dimensions on the positioning image samples to obtain a first number of dimension data to be verified for each smart checkout counter sample.

[0018] According to a smart checkout counter quality inspection method provided by the present invention, the differentiated comparison of the to-be-verified dimensional data corresponding to multiple smart checkout counter samples includes:

[0019] Constructing a first number of relationship matrices based on a first number of to-be-verified dimension data corresponding to each of the plurality of smart checkout station samples;

[0020] Normalizing the first number of relationship matrices to obtain the first number of fuzzy similarity matrices;

[0021] generating a merge matrix according to a first number of fuzzy similarity matrices, and determining a fuzzy equivalent matrix based on a transitive closure theorem and the merge matrix;

[0022] When the fuzzy equivalence matrix meets a preset condition, it is determined that the differential comparison is passed.

[0023] According to a smart settlement station quality inspection method provided by the present invention, determining a quality inspection result of the smart settlement station to be tested based on the first number of smart settlement station standard dimension data and the first number of dimension data to be tested includes:

[0024] When the first number of dimension data to be tested all fall within the range of the first number of standard dimension data of the smart settlement platform of the corresponding dimension, the quality inspection result of the smart settlement platform to be tested is determined to be passed.

[0025] The present invention also provides a smart checkout counter quality detection device, comprising:

[0026] A standard module, configured to obtain a first quantity of standard dimension data of smart checkout platforms;

[0027] The testing module is used to obtain an image of the test table surface of the smart settlement table to be tested, perform data processing based on the test table surface image to obtain a first number of test dimension data, and determine the quality inspection result of the smart settlement table to be tested based on the first number of smart settlement table standard dimension data and the first number of test dimension data.

[0028] According to the intelligent checkout counter quality inspection device provided by the present invention, the standard module is specifically used for:

[0029] For each of the plurality of smart checkout counter samples, obtaining a plurality of counter surface image samples;

[0030] Performing data processing on a plurality of countertop image samples of a plurality of smart checkout counter samples to obtain dimension data to be verified corresponding to the plurality of smart checkout counter samples;

[0031] Perform differentiated comparison on the dimension data to be verified corresponding to multiple smart checkout counter samples;

[0032] When the differentiated comparison passes, the first number of smart settlement station standard dimensional data is determined based on the to-be-verified dimensional data corresponding to the multiple smart settlement station samples.

[0033] According to the intelligent checkout counter quality inspection device provided by the present invention, the standard module is specifically used for:

[0034] Perform image positioning on multiple table surface image samples of each intelligent checkout counter sample to obtain corresponding positioning image samples;

[0035] Perform feature extraction and averaging of a first number of dimensions on the positioning image samples to obtain a first number of dimension data to be verified for each smart checkout counter sample.

[0036] The present invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described smart checkout counter quality inspection methods are implemented.

[0037] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described intelligent checkout counter quality detection methods.

[0038] The smart settlement counter quality inspection method, device, and electronic device provided by the present invention obtain a first quantity of standard dimensional data for smart settlement counters, and standardize the quality inspection measurement standard through the standard dimensional data for smart settlement counters. An image of the table surface to be tested of the smart settlement counter to be tested is obtained, and data processing is performed based on the table surface image to be tested to obtain a first quantity of dimensional data to be tested. The dimensional data to be tested represents the features of multiple dimensions of the table surface image to be tested, so that subsequent quality inspection results are more accurate. The quality inspection results of the smart settlement counter to be tested are determined based on the first quantity of standard dimensional data for smart settlement counters and the first quantity of dimensional data to be tested. Factory quality inspection of the table surface image of the smart settlement counter based on computer vision is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 It is a flow chart of the quality inspection method of the intelligent checkout counter provided by the present invention;

[0041] Figure 2 It is a structural diagram of the intelligent checkout counter quality inspection device provided by the present invention;

[0042] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The present invention provides a method for detecting the quality of an intelligent settlement platform. Figure 1 As shown, the following steps are included:

[0045] S11. Obtain a first amount of standard dimension data of smart checkout counters.

[0046] Specifically, a pre-set first quantity of standard dimension data for smart checkout counters can be obtained. In one example, data of six dimensions, including color deviation, brightness, mean, variance, blurriness, and number of feature points, can be pre-set as standard dimension data for smart checkout counters. Color deviation can be extracted by decomposing the LAB color gamut, brightness, mean, and variance can be calculated by converting the image from RGB to GRY format, blurriness can be obtained by performing second-order difference calculation on gradient differences, and feature points can be obtained based on preset focus calibration. The detailed process can refer to the existing technology and is not limited to this.

[0047] S12. Obtain an image of the test table surface of the smart checkout counter to be tested.

[0048] Specifically, the image of the countertop to be tested corresponding to the smart checkout counter to be tested can be obtained. There can be multiple images of the countertop to be tested. In one example, 100 images of the countertop to be tested can be taken using the smart checkout counter to be tested, and quality inspection can be performed based on the 100 images of the countertop to be tested, thereby making the inspection result more accurate.

[0049] S13: Perform data processing according to the image of the table surface to be measured to obtain a first quantity of dimensional data to be measured.

[0050] Specifically, data processing may be performed on the image of the table to be tested, including but not limited to operations such as positioning, cutting, scaling, feature extraction, and fusion of the image.

[0051] Continuing with the previous example, a deep learning algorithm model can be used to locate 100 images of the countertop to be tested, remove excess background from the images, and capture images of a specified area. Feature extraction is then performed on the captured images to obtain a first amount of dimensional data to be tested.

[0052] In one example, the Yolov5s target detection algorithm model can be used to locate the image of a tabletop to be tested. The target area is captured and uniformly sliced ​​into 244*224 resolution images. Feature extraction is performed on the captured image from six (i.e., a first number) dimensions: color cast, brightness, mean, variance, blur, and number of feature points. This yields six (i.e., a first number) of target dimensional data. The structure of the Yolov5s target detection algorithm model can refer to existing technologies and is not limited here.

[0053] S14. Determine the quality inspection result of the smart settlement station to be tested based on the first number of smart settlement station standard dimension data and the first number of dimension data to be tested.

[0054] Specifically, continuing with the above example, the six (i.e. the first number) dimensions of data to be tested and the six (i.e. the first number) standard dimensions of smart settlement stations can be compared from six (i.e. the first number) dimensions, such as color deviation, brightness, mean, variance, blurriness, and number of feature points, and the quality inspection results of the smart settlement station to be tested can be determined based on the comparison results.

[0055] Optionally, step S14 may specifically include:

[0056] When the first number of dimensional data to be tested all fall within the range of the first number of standard dimensional data of the smart settlement station of the corresponding dimension, the quality inspection result of the smart settlement station to be tested is determined to be passed.

[0057] In an example, the ranges of the standard dimensional data of the smart settlement station in six (i.e., the first quantity) dimensions of color deviation, brightness, mean, variance, blurriness, and number of feature points are [1,5], [1,5], [1,5], [2,7], [4,8], and [5,10] respectively; the dimensional data to be tested in six (i.e., the first quantity) dimensions of color deviation, brightness, mean, variance, blurriness, and number of feature points are 2.4, 3.6, 1.6, 6.2, 5.2, and 7.9 respectively, that is, under each of the same dimensions, the dimensional data to be tested falls within the range of the standard dimensional data of the smart settlement station, and the quality inspection result of the smart settlement station to be tested is determined to be passed.

[0058] In an embodiment of the present invention, a first quantity of standard dimensional data for smart checkout counters is obtained, and the quality inspection measurement standard is standardized using the standard dimensional data for smart checkout counters. An image of the countertop of the smart checkout counter to be tested is obtained, and data processing is performed based on the image to be tested to obtain a first quantity of dimensional data to be tested. The dimensional data to be tested represents the characteristics of multiple dimensions of the image to be tested, thereby making subsequent quality inspection results more accurate. The quality inspection results of the smart checkout counter to be tested are determined based on the first quantity of standard dimensional data for smart checkout counters and the first quantity of dimensional data to be tested. This implements factory quality inspection of the countertop image of the smart checkout counter using computer vision.

[0059] According to a method for detecting quality of an intelligent checkout counter provided by the present invention, the standard dimension data of the intelligent checkout counter is obtained by the following steps, including:

[0060] S21. For each smart checkout counter sample of the multiple smart checkout counter samples, obtain multiple counter surface image samples.

[0061] Specifically, for each of the multiple smart checkout counter samples, multiple countertop image samples are obtained for each smart checkout counter sample. In one example, for 10 smart checkout counter samples, 100 countertop image samples are obtained for each smart checkout counter sample as one group, i.e., a total of 10 groups of countertop image samples are obtained for the multiple smart checkout counter samples.

[0062] S22. Perform data processing based on multiple countertop image samples of multiple smart checkout counter samples to obtain dimension data to be verified corresponding to the multiple smart checkout counter samples.

[0063] Furthermore, step S22 may be specifically as follows:

[0064] S221. Perform image positioning on multiple table image samples of each smart checkout counter sample to obtain corresponding positioning image samples.

[0065] S222. Perform feature extraction and averaging of a first number of dimensions on the positioning image samples to obtain a first number of dimension data to be verified for each smart checkout counter sample.

[0066] Specifically, continuing with the above example, image positioning is performed on the 100 table surface image samples of each smart checkout counter sample (the description of image positioning can refer to the description of step S13, which will not be repeated here), and the corresponding 100 positioning image samples are obtained. Afterwards, feature extraction is performed on the 100 image positioning samples (the description of feature extraction can refer to the description of step S13 and will not be repeated here), and data of 6 (i.e. the first number) different dimensions corresponding to the color deviation, brightness, mean, variance, blurriness, and feature point number dimensions of each positioning image sample are obtained. For 100 positioning image samples, 600 data are obtained, which are divided into 6*100=600 data according to the above 6 (i.e. the first number) different dimensions. The 100 data under each dimension are averaged, and the calculated mean is used as the dimension data to be verified for that dimension. For the 6*100 data of the 6 (i.e. the first number) different dimensions of the smart checkout counter sample, a total of 6 (i.e. the first number) different dimensions of dimension data to be verified are obtained. For the 10 smart checkout counter samples, a total of 10*6=60 dimension data to be verified are obtained, and the 60 dimension data to be verified belong to the above 6 (i.e. the first number) different dimensions.

[0067] S23. Perform differentiated comparison on the dimension data to be verified corresponding to multiple smart checkout counter samples.

[0068] S24. When the differentiated comparison passes, the first number of smart settlement station standard dimensional data is determined based on the to-be-verified dimensional data corresponding to the multiple smart settlement station samples.

[0069] Specifically, as a comparison basis for subsequent quality inspection of the smart settlement counters to be tested, it is necessary to perform differentiated comparison of the dimensional data to be verified, which can also be called similarity comparison, to determine whether the quality differences between multiple smart settlement counter samples are within an acceptable range.

[0070] When the differential comparison passes, the first number of smart settlement station standard dimensional data is determined based on the to-be-verified dimensional data corresponding to the multiple smart settlement station samples. Continuing with the above example, optionally, the mean and variance can be calculated based on the to-be-verified dimensional data corresponding to the multiple smart settlement station samples to obtain the mean of the dimensional data and the variance of the dimensional data. The standard dimensional data of the smart settlement station is obtained through the mean of the dimensional data and the variance of the dimensional data. For example, for 10 smart settlement station samples, a total of 10*6=60 to-be-verified dimensional data are obtained, and the 60 to-be-verified dimensional data belong to the above 6 (i.e., the first number) different dimensions. For the 10 to-be-verified dimensional data under one dimension, the mean and variance are calculated, and an interval is determined based on the sum of the mean and 2 times the variance, and the difference between the mean and 2 times the variance. The interval is used as the standard dimensional data of the smart settlement station corresponding to the dimension, and a total of 6 (i.e., the first number) different dimensions of the standard dimensional data of the smart settlement station are obtained.

[0071] In this embodiment of the present invention, data processing is performed on tabletop image samples from multiple smart checkout counter samples to obtain dimensional data to be verified. A differential comparison is then performed on the dimensional data corresponding to the multiple smart checkout counter samples, ensuring minimal data variability in the dimensional data to be verified. If conditions are met, a first quantity of standard dimensional data for smart checkout counters is further determined based on the dimensional data to be verified. This data provides a reference that complies with regulatory standards, facilitating subsequent quality testing based on the dimensional data of the smart checkout counters to be tested, using the standard dimensional data as a standard, thereby obtaining accurate quality test results.

[0072] According to a quality inspection method for an intelligent checkout counter provided by the present invention, step S23 includes:

[0073] S231. Construct a first number of relationship matrices based on a first number of dimensional data to be verified corresponding to each of the plurality of smart checkout counter samples.

[0074] Specifically, continuing with the above example, since the data importance of the above six dimensions (i.e., the first number) is different, the distance function is expressed using a segmented expression, in which the important indicators are amplified. Since the value of the dimension data to be verified in a certain dimension is larger than the value of the dimension data to be verified in other dimensions, the square root of this dimension data to be verified is performed to reduce the weight. Let R p =μ m×m , where m is the number of samples of the smart settlement station, μ is a real number matrix, R pis the relationship matrix of m smart checkout counter samples in the pth dimension. Each element in the relationship matrix is ​​expressed as follows:

[0075]

[0076] Among them, i and j represent the i-th smart settlement station sample and the j-th smart settlement station sample respectively, p represents the dimension, m is the preset value, indicating the specified dimension, d i is the dimension data to be verified for the i-th smart settlement station sample in this dimension, d j is the dimension data to be verified for the j-th smart settlement station sample in this dimension, r ij It is an element that constitutes the relationship matrix, representing the Euclidean distance between the i-th smart checkout counter sample and the j-th smart checkout counter sample in the relationship matrix under this dimension.

[0077] S232. Standardize the first number of relationship matrices to obtain a first number of fuzzy similarity matrices.

[0078] Specifically, following the above example, 6 (i.e., the first number) relationship matrices are standardized, and the elements r in the relationship matrix can be mapped from 0 to 1. ij Normalization is performed because the correlation between different elements of the fuzzy similarity matrix is ​​strong. Each time the sampling elements are different, the result of the 0-1 mapping will change, and at the same time, the original similarity index can be widened, making the detection standard inaccurate. Preferably, the 0-1 mapping is performed using an index, which has the advantage of not causing distortion of the mapping as the relationship between elements changes. The normalization expression is as follows: Formula 1:

[0079]

[0080] in, Indicates r ij The power of the base n, where n is an adjustable parameter, n>0, the size of the result is adjusted by n, norm ij For r ij The output result after standardization represents the output result after the Euclidean distance between the i-th smart settlement station sample and the j-th smart settlement station sample in the relationship matrix under this dimension is standardized, which conforms to the definition of the membership function.

[0081] Get the element norm of the corresponding fuzzy similarity matrix ij Satisfy the following formulas 2 and 3:

[0082] norm ij =norm ji (2)

[0083] norm ij =1,i=j (3)

[0084] Among them, norm ji It represents the output result of the Euclidean distance normalization between the j-th smart checkout counter sample and the i-th smart checkout counter sample in the relationship matrix under this dimension.

[0085] After the above standardization, according to the element norm ij Composition and corresponding r ij The fuzzy similarity matrix corresponding to the relationship matrix.

[0086] S233. Generate a merge matrix according to the first number of fuzzy similarity matrices, and determine a fuzzy equivalent matrix based on the transitive closure theorem and the merge matrix.

[0087] Specifically, following the above example, after obtaining 6 (i.e., the first number) fuzzy similarity matrices, the 6 (i.e., the first number) fuzzy similarity matrices can be merged to obtain a merged matrix. Alternatively, the merging can be performed using the following formula 4:

[0088] norm ij ′=∧ p norm ij (4)

[0089] Among them, ∧ p Indicates that the elements at the same position of the p fuzzy similarity matrices corresponding to p dimensions take the minimum value, norm ij ′ represents the output result, that is, the elements that make up the merge matrix.

[0090] By using Formula 4, the minimum value of the elements of the 6 (ie, the first number) fuzzy similarity matrices at the same position can be used as the elements constituting one merged matrix, thereby obtaining the merged matrix.

[0091] Furthermore, the fuzzy equivalent matrix is ​​determined based on the merged matrix and the transitive closure theorem. The transitive closure theorem is common knowledge in this field and can be referred to in the prior art, which will not be described in detail here.

[0092] S234: When the fuzzy equivalence matrix meets a preset condition, determine that the differential comparison is passed.

[0093] Specifically, the preset condition can be set according to actual needs. In one example, the value of the fuzzy equivalence matrix can be set to be compared with a preset value. For example, if the value is smaller than the preset value, it is determined that the preset condition is met.

[0094] In the embodiment of the present invention, since the similarity of the indicators used in the comparison of the differences between smart settlement stations is a fuzzy concept, there is no definite boundary to determine similarity and dissimilarity. At the same time, the use of traditional clustering methods requires the determination of the number of unsupervised categories, which greatly limits the use scenario. Therefore, the present invention uses a method based on fuzzy mathematical membership matrix clustering to compare the differences between different smart settlement station samples. By constructing a first number of relationship matrices based on a first number of dimensional data to be verified corresponding to each of the multiple smart settlement station samples; standardizing the first number of relationship matrices to obtain a first number of fuzzy similarity matrices; determining a fuzzy equivalence matrix based on the first number of fuzzy similarity matrices and the transitive closure theorem; and determining that the difference comparison is passed when the fuzzy equivalence matrix meets the preset conditions, thereby achieving a high-precision difference comparison.

[0095] The following describes the intelligent checkout counter quality inspection device provided by the present invention. The intelligent checkout counter quality inspection device described below can be used in conjunction with the intelligent checkout counter quality inspection method described above. The various modules of the intelligent checkout counter quality inspection device described below can be software modules within a computer or independent physical modules, without limitation.

[0096] The present invention also provides a smart checkout counter quality detection device, such as Figure 2 Shown, including:

[0097] A standard module 21 is used to obtain a first amount of standard dimension data of smart checkout stations;

[0098] The testing module 22 is used to obtain an image of the test table surface of the smart settlement table to be tested, perform data processing based on the test table surface image to obtain a first number of test dimension data, and determine the quality inspection result of the smart settlement table to be tested based on the first number of smart settlement table standard dimension data and the first number of test dimension data.

[0099] In an embodiment of the present invention, a first quantity of standard dimensional data for smart checkout counters is obtained, and the quality inspection measurement standard is standardized using the standard dimensional data for smart checkout counters. An image of the countertop of the smart checkout counter to be tested is obtained, and data processing is performed based on the image to be tested to obtain a first quantity of dimensional data to be tested. The dimensional data to be tested represents the characteristics of multiple dimensions of the image to be tested, thereby making subsequent quality inspection results more accurate. The quality inspection results of the smart checkout counter to be tested are determined based on the first quantity of standard dimensional data for smart checkout counters and the first quantity of dimensional data to be tested. This implements factory quality inspection of the countertop image of the smart checkout counter using computer vision.

[0100] The present invention also provides a smart checkout counter quality inspection device, wherein the standard module 21 is specifically used for:

[0101] For each smart checkout counter sample of the multiple smart checkout counter samples, multiple counter image samples are obtained; data processing is performed based on the multiple counter image samples of the multiple smart checkout counter samples to obtain the dimension data to be verified corresponding to the multiple smart checkout counter samples; a differentiated comparison is performed on the dimension data to be verified corresponding to the multiple smart checkout counter samples; when the differentiated comparison passes, the first number of smart checkout counter standard dimension data is determined based on the dimension data to be verified corresponding to the multiple smart checkout counter samples.

[0102] The present invention also provides a smart checkout counter quality inspection device, wherein the standard module 21 is specifically used for:

[0103] Perform image positioning on multiple table image samples of each smart checkout counter sample to obtain corresponding positioning image samples; perform feature extraction and averaging on the positioning image samples in a first number of dimensions to obtain a first number of dimension data to be verified for each smart checkout counter sample.

[0104] The present invention also provides a smart checkout counter quality inspection device, wherein the standard module 21 is specifically used for:

[0105] According to the first number of dimensional data to be verified corresponding to each of the multiple smart checkout counter samples, a first number of relationship matrices are constructed; the first number of relationship matrices are standardized to obtain a first number of fuzzy similarity matrices; a fuzzy equivalence matrix is ​​determined based on the first number of fuzzy similarity matrices and the transitive closure theorem; when the fuzzy equivalence matrix meets the preset conditions, it is determined that the differential comparison is passed.

[0106] The present invention also provides a smart checkout counter quality inspection device, wherein the testing module 22 is specifically used for:

[0107] When the first number of dimensional data to be tested all fall within the range of the first number of standard dimensional data of the smart settlement station of the corresponding dimension, the quality inspection result of the smart settlement station to be tested is determined to be passed.

[0108] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a smart checkout counter quality inspection method, which includes: obtaining a first quantity of smart checkout counter standard dimension data; obtaining a test table surface image of the smart checkout counter to be tested; performing data processing based on the test table surface image to obtain a first quantity of test dimension data; and determining a quality inspection result of the smart checkout counter to be tested based on the first quantity of smart checkout counter standard dimension data and the first quantity of test dimension data.

[0109] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the smart settlement table quality inspection method provided by the above methods, which includes: obtaining a first number of standard dimension data of smart settlement tables; obtaining a table surface image to be tested of the smart settlement table to be tested; performing data processing based on the table surface image to be tested to obtain a first number of dimension data to be tested; and determining the quality inspection result of the smart settlement table to be tested based on the first number of standard dimension data of smart settlement tables and the first number of dimension data to be tested.

[0111] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the smart settlement table quality inspection method provided by the above-mentioned methods, the method including: obtaining a first number of standard dimension data of the smart settlement table; obtaining an image of the table surface to be tested of the smart settlement table to be tested; performing data processing based on the image of the table surface to be tested to obtain a first number of dimension data to be tested; and determining the quality inspection result of the smart settlement table to be tested based on the first number of standard dimension data of the smart settlement table and the first number of dimension data to be tested.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0113] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A quality inspection method for an intelligent checkout counter, characterized in that: include: Obtaining a first quantity of standard dimension data for smart checkout platforms; Acquire an image of the test surface of the intelligent checkout counter to be tested; Performing data processing according to the image of the table surface to be measured to obtain a first quantity of dimension data to be measured; determining a quality inspection result of the smart settlement station to be tested based on the first number of standard dimension data of the smart settlement stations and the first number of dimension data to be tested; The standard dimension data of the intelligent settlement platform is obtained through the following steps, including: For each of the plurality of smart checkout counter samples, obtaining a plurality of counter surface image samples; Performing data processing on a plurality of countertop image samples of a plurality of smart checkout counter samples to obtain dimension data to be verified corresponding to the plurality of smart checkout counter samples; Perform differentiated comparison on the dimension data to be verified corresponding to multiple smart checkout counter samples; If the differential comparison passes, determining the first number of smart checkout station standard dimensional data based on the to-be-verified dimensional data corresponding to the plurality of smart checkout station samples; The data processing is performed based on the multiple table image samples of the multiple smart checkout counter samples to obtain the to-be-verified dimensional data corresponding to the multiple smart checkout counter samples, including: Perform image positioning on multiple table surface image samples of each intelligent checkout counter sample to obtain corresponding positioning image samples; Perform feature extraction and averaging of a first number of dimensions on the positioning image samples to obtain a first number of dimension data to be verified for each smart checkout counter sample.

2. The quality inspection method of the intelligent checkout counter according to claim 1, characterized in that: The differentiated comparison of the to-be-verified dimension data corresponding to the multiple smart checkout station samples includes: Constructing a first number of relationship matrices based on a first number of to-be-verified dimension data corresponding to each of the plurality of smart checkout station samples; Normalizing the first number of relationship matrices to obtain the first number of fuzzy similarity matrices; generating a merge matrix according to a first number of fuzzy similarity matrices, and determining a fuzzy equivalent matrix based on a transitive closure theorem and the merge matrix; When the fuzzy equivalence matrix meets a preset condition, it is determined that the differential comparison is passed.

3. The quality inspection method of the intelligent checkout counter according to claim 1, characterized in that: The determining of the quality inspection result of the smart settlement station to be tested based on the first number of smart settlement station standard dimension data and the first number of dimension data to be tested includes: When the first number of dimensional data to be tested all fall within the range of the first number of standard dimensional data of the smart settlement station of the corresponding dimension, the quality inspection result of the smart settlement station to be tested is determined to be passed.

4. An intelligent checkout counter quality inspection device, characterized in that: include: A standard module, configured to obtain a first quantity of standard dimension data of smart checkout platforms; The testing module is configured to obtain an image of a test surface of the smart checkout counter to be tested, perform data processing based on the test surface image to obtain a first quantity of test dimensional data, and determine a quality inspection result of the smart checkout counter to be tested based on the first quantity of smart checkout counter standard dimensional data and the first quantity of test dimensional data. The standard module is specifically configured to: For each of the plurality of smart checkout counter samples, obtaining a plurality of counter surface image samples; Performing data processing on a plurality of countertop image samples of a plurality of smart checkout counter samples to obtain dimension data to be verified corresponding to the plurality of smart checkout counter samples; Perform differentiated comparison on the dimension data to be verified corresponding to multiple smart checkout counter samples; If the differential comparison passes, the first number of smart settlement station standard dimensional data is determined based on the to-be-verified dimensional data corresponding to the plurality of smart settlement station samples, wherein the standard module is specifically configured to: Perform image positioning on multiple table surface image samples of each intelligent checkout counter sample to obtain corresponding positioning image samples; Perform feature extraction and averaging of a first number of dimensions on the positioning image samples to obtain a first number of dimension data to be verified for each smart checkout counter sample.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the smart checkout station quality detection method as described in any one of claims 1 to 3 are implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart checkout station quality inspection method as described in any one of claims 1 to 3 are implemented.

Images