AI trace code recognition system and transcoding packaging method

Abstract

The application discloses an AI trace code recognition system and a transcoding packaging method. The system comprises: an acquisition module configured to acquire a to-be-recognized image of a trace code engraved in a packaging bottle; a preprocessing module configured to perform image preprocessing on the to-be-recognized image to obtain a target image; and an identification module configured to identify the target image based on an AI trace code recognition model to obtain an identification result. The trace code can be recognized conveniently, and it can be determined accurately whether the trace code is qualified, and then a two-dimensional code on a preset object can be associated according to the determined trace code, so that trace tracking of a product can be realized accurately.

Description

Technical Field

[0001] This invention relates to the field of identification technology, and in particular to an AI traceability code identification system and transcoding and packaging method. Background Technology

[0002] The traceability codes on bottle labels are easily damaged, making it impossible to trace the supply channels of the products sold. Therefore, the traceability codes are engraved inside the bottle. However, engraving them inside the bottle makes it difficult to identify the traceability codes and accurately determine whether they are qualified. Consequently, it is not easy to associate the identified traceability codes with the QR codes on the bottle caps, resulting in the inability to accurately trace the origin of the products. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in the aforementioned technologies. Therefore, the purpose of this invention is to propose an AI traceability code recognition system and transcoding / encapsulation method, which facilitates the recognition of traceability codes, accurately determines whether the traceability code is qualified, and further facilitates the accurate traceability tracking of products by associating the determined traceability code with a QR code on a preset object.

[0004] To achieve the above objectives, a first aspect of the present invention proposes an AI traceability code recognition system, comprising:

[0005] The acquisition module is used to acquire the image to be identified of the traceability code engraved inside the packaged bottle;

[0006] The preprocessing module is used to preprocess the image to be recognized to obtain the target image;

[0007] The recognition module is used to identify target images based on the AI ​​traceability code recognition model and obtain recognition results.

[0008] According to some embodiments of the present invention, the preprocessing module includes:

[0009] The evaluation module is used to evaluate the brightness features of the image to be identified and obtain a brightness evaluation value.

[0010] The brightness enhancement module is used to compare the brightness evaluation value with the preset brightness threshold. When the brightness evaluation value is determined to be less than the preset brightness threshold, brightness enhancement processing is performed.

[0011] According to some embodiments of the present invention, the evaluation module includes:

[0012] The first calculation module is used for:

[0013] Obtain the brightness value of each pixel in the image to be recognized, and determine the maximum and minimum brightness values;

[0014] Calculate the average brightness value Z of the image to be identified;

[0015]

[0016] Where M is the length of the image to be recognized; N is the width of the image to be recognized; x is the maximum value of the horizontal coordinate of the pixel in the image to be recognized; y is the maximum value of the vertical coordinate of the pixel in the image to be recognized; and f(i,j) is the brightness value of the pixel (i,j) in the image to be recognized.

[0017] The average brightness value Z, maximum brightness value, and minimum brightness value of the image to be identified are used as brightness features to determine the brightness evaluation value S of the image to be identified.

[0018]

[0019] Among them, f max f is the maximum brightness value of the pixel in the image to be identified; min This represents the minimum brightness value of a pixel in the image to be identified.

[0020] According to some embodiments of the present invention, the identification module includes:

[0021] The segmentation module is used to segment the traceability code in the target image based on the AI ​​traceability code recognition model, determine the upper and lower boundaries and left and right boundaries of each character, determine the size of each character based on the upper and lower boundaries and left and right boundaries, determine whether the size is consistent with the preset size, identify characters whose size is inconsistent with the preset size and adjust their size.

[0022] The character content recognition module is used to recognize the character content of the adjusted traceability code based on the AI ​​traceability code recognition model, and obtain the recognition results.

[0023] According to some embodiments of the present invention, the character content recognition module is used to match the adjusted traceability code with the data table stored in the AI ​​traceability code recognition model to obtain the recognition result.

[0024] According to some embodiments of the present invention, the identification module includes:

[0025] The determination module is used for:

[0026] Based on the AI ​​traceability code recognition model, feature extraction is performed on the target image to determine the feature value of each pixel in the target image;

[0027]

[0028] Among them, D i R is the feature value of the i-th pixel; i G is the R channel value of the i-th pixel; i B is the G channel value of the i-th pixel; iThis is the B channel value of the i-th pixel;

[0029] A feature matrix D is constructed based on the feature values ​​of each pixel. The feature matrix D has L rows and M columns.

[0030] The transformation module is used to transform the feature matrix D into a vector to obtain the target feature vector.

[0031] |D*D T -λE|=0

[0032] Among them, D T λ is the transpose of the feature matrix D; E is the identity matrix of order L, and the intermediate values ​​obtained from λ are L values. The L values ​​are sorted from largest to smallest to form the target feature vector.

[0033] The matching module is used to match the target feature vector with the preset feature vector in the preset traceability code database, and determine the recognition result based on the matching result.

[0034] According to some embodiments of the present invention, it further includes: an adjustment module, used to segment the target image into N local images before the matching module matches the target feature vector with the preset feature vector in the preset traceability code database; calculate the adjustment coefficient for each local image, and perform adjustment.

[0035] According to some embodiments of the present invention, the adjustment module includes:

[0036] The second calculation module is used to calculate the energy function for each local image;

[0037]

[0038] Among them, fCS N W is the energy function of the Nth local image; N For the Nth local image; CS N Let W be the pixel matrix of the Nth local image; N -CS N || F For W N -CS N The F-norm, For weighted norm,

[0039] Where j∈L represents the value of j, and L is the target feature vector WV. N The number of values ​​contained, where d is the number of local images with a Euclidean distance less than 0.1, and K is the weighting coefficient corresponding to the number of local images with a Euclidean distance less than 0.1; |SV N | j The median value;

[0040]

[0041] Among them, |WV N | j WV is the target feature vector N The j-th value; σ N For the Nth local image W N The variance;

[0042] The third calculation module is used to calculate the adjustment coefficient LB based on the energy function of each local image. N ;

[0043]

[0044] The corresponding local image is adjusted based on the adjustment coefficient.

[0045] To achieve the above objectives, a second aspect of the present invention proposes a transcoding and encapsulation method, applying the AI ​​source code recognition system described above, comprising:

[0046] The traceability code recognition system based on AI identifies the traceability code engraved inside the packaged bottle, and the recognition result is obtained.

[0047] The recognition result is converted into a QR code; the QR code includes the product's production source information, production date information, and production model information.

[0048] The QR code is recorded onto a pre-set object using laser technology.

[0049] This invention proposes an AI traceability code recognition system and transcoding and encapsulation method, which facilitates the recognition of traceability codes, accurately determines whether the traceability codes are qualified, and facilitates the association of the determined traceability codes with QR codes on preset objects to accurately achieve product traceability tracking.

[0050] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0051] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0052] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0053] Figure 1This is a block diagram of an AI traceability code recognition system according to an embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram of the image to be identified for a traceability code according to an embodiment of the present invention;

[0055] Figure 3 This is a schematic diagram of recording a QR code onto a preset object according to an embodiment of the present invention;

[0056] Figure 4 This is a flowchart of a transcoding and encapsulation method according to an embodiment of the present invention. Detailed Implementation

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0058] like Figures 1-2 As shown, a first aspect of the present invention proposes an AI traceability code recognition system, comprising:

[0059] The acquisition module is used to acquire the image to be identified of the traceability code engraved inside the packaged bottle;

[0060] The preprocessing module is used to preprocess the image to be recognized to obtain the target image;

[0061] The recognition module is used to identify target images based on the AI ​​traceability code recognition model and obtain recognition results.

[0062] The working principle of the above technical solution is as follows: The acquisition module uses a high-resolution camera or image acquisition device to ensure that the details of the traceability code can be clearly captured. It is primarily responsible for capturing images of the traceability code engraved inside the packaged bottle. Based on an AI traceability code recognition model, the preprocessed target image is recognized, and the recognition result is output. This model is trained based on deep learning technology and can accurately recognize characters, patterns, or barcodes in the traceability code.

[0063] The beneficial effects of the above technical solution are: It facilitates the identification of traceability codes, accurately determines their validity, and facilitates accurate product traceability by associating the identified traceability code with the QR code on the bottle cap. The AI ​​traceability code identification system improves identification efficiency, reduces manual intervention costs, and enhances the accuracy of data tracking and verification. By accurately identifying the traceability code inside the packaged bottle, companies can more effectively track the production, distribution, and sales processes of their products, ensuring product quality and safety. Simultaneously, consumers can scan the traceability code to verify the authenticity and origin of the product, enhancing their trust in the brand.

[0064] In one embodiment, the identification module, when identifying a target image based on an AI traceability code identification model, includes identifying a location marker and quickly locating the traceability code in the target image based on the location marker, which facilitates improving the identification rate.

[0065] According to some embodiments of the present invention, the preprocessing module includes:

[0066] The evaluation module is used to evaluate the brightness features of the image to be identified and obtain a brightness evaluation value.

[0067] The brightness enhancement module is used to compare the brightness evaluation value with the preset brightness threshold. When the brightness evaluation value is determined to be less than the preset brightness threshold, brightness enhancement processing is performed.

[0068] The working principle of the above technical solution is as follows: The preset brightness threshold is set according to the actual application scenario and image acquisition conditions. The preset brightness threshold is used to trigger brightness enhancement processing when the image brightness is insufficient, but at the same time, unnecessary processing should be avoided when the image brightness is already sufficient.

[0069] The beneficial effects of the above technical solution are as follows: through the collaborative work of the evaluation module and the brightness enhancement module, the preprocessing module can ensure that the image to be identified has an appropriate brightness level, thereby improving the accuracy and reliability of traceability code recognition.

[0070] According to some embodiments of the present invention, the evaluation module includes:

[0071] The first calculation module is used for:

[0072] Obtain the brightness value of each pixel in the image to be recognized, and determine the maximum and minimum brightness values;

[0073] Calculate the average brightness value Z of the image to be identified;

[0074]

[0075] Where M is the length of the image to be recognized; N is the width of the image to be recognized; x is the maximum value of the horizontal coordinate of the pixel in the image to be recognized; y is the maximum value of the vertical coordinate of the pixel in the image to be recognized; and f(i,j) is the brightness value of the pixel (i,j) in the image to be recognized.

[0076] The average brightness value Z, maximum brightness value, and minimum brightness value of the image to be identified are used as brightness features to determine the brightness evaluation value S of the image to be identified.

[0077]

[0078] Among them, f max f is the maximum brightness value of the pixel in the image to be identified; minThis represents the minimum brightness value of a pixel in the image to be identified.

[0079] The working principle of the above technical solution is as follows: The first calculation module first traverses every pixel in the image to be recognized, accurately acquiring its brightness value. Then, among all the acquired brightness values, the maximum and minimum brightness values ​​are determined. The average brightness value of the image to be recognized is calculated. Based on the average brightness value Z, the maximum brightness value, and the minimum brightness value of the image to be recognized, the brightness evaluation value of the image to be recognized is determined. A comprehensive brightness feature assessment is provided by comprehensively considering the deviation between pixel brightness and average brightness (i.e., the dispersion of brightness distribution) and the difference between the maximum and minimum brightness values. The brightness evaluation value S not only reflects the overall distribution of image brightness but also embodies the dynamic range of brightness values ​​(i.e., the difference between the maximum and minimum brightness). When the image brightness distribution is relatively uniform, the deviation between pixel brightness and average brightness will be small, resulting in a relatively low S value. Conversely, if there are significant brightness changes or contrast enhancements in the image, the deviation between pixel brightness and average brightness will increase, thereby increasing the S value.

[0080] The beneficial effects of the above technical solution are as follows: The first calculation module accurately calculates the brightness features of the image to be identified, providing a solid foundation for subsequent brightness enhancement processing. This not only helps improve the accuracy of traceability code recognition but also ensures the efficient operation of the entire AI traceability code recognition system.

[0081] According to some embodiments of the present invention, the identification module includes:

[0082] The segmentation module is used to segment the traceability code in the target image based on the AI ​​traceability code recognition model, determine the upper and lower boundaries and left and right boundaries of each character, determine the size of each character based on the upper and lower boundaries and left and right boundaries, determine whether the size is consistent with the preset size, identify characters whose size is inconsistent with the preset size and adjust their size.

[0083] The character content recognition module is used to recognize the character content of the adjusted traceability code based on the AI ​​traceability code recognition model, and obtain the recognition results.

[0084] The working principle of the above technical solution is as follows: The segmentation module first uses an AI traceability code recognition model to accurately segment the traceability code in the target image. This process aims to clearly distinguish each character in the traceability code, laying the foundation for subsequent character content recognition. Image segmentation algorithms from deep learning technologies are employed, such as semantic segmentation, instance segmentation, or edge detection-based segmentation methods. After character segmentation, the module further determines the upper and lower boundaries and left and right boundaries of each character. The size of each character is calculated based on the boundary information and compared with a preset size. The preset size is usually based on the standard design specifications of traceability codes to ensure recognition accuracy. If a character size is found to be inconsistent with the preset size, the module will adjust the size of these characters. Adjustment methods may include scaling, stretching, or interpolation to ensure that all characters have a consistent size in subsequent recognition processes. After character segmentation and size adjustment, the character content recognition module will accurately recognize the character content of the adjusted traceability code based on the AI ​​traceability code recognition model. Using Optical Character Recognition (OCR) technology from deep learning, this technology can automatically recognize character content in an image and convert it into an editable text format. The character content recognition module will output the recognition results. This result includes the complete character sequence in the trace code and the confidence score for each character.

[0085] The beneficial effects of the above technical solution are as follows: the segmentation module and the character content recognition module in the recognition module work together to achieve accurate segmentation and character content recognition of the traceability code in the target image. This process not only improves the accuracy of recognition but also ensures the efficient operation of the entire AI traceability code recognition system.

[0086] According to some embodiments of the present invention, the character content recognition module is used to match the adjusted traceability code with the data table stored in the AI ​​traceability code recognition model to obtain the recognition result.

[0087] The working principle of the above technical solution is as follows: During training, the AI ​​traceability code recognition model learns and stores a large number of traceability code character samples and their corresponding labels (i.e., character content). These samples and labels are organized and stored in a data table for use in subsequent character recognition processes. When the character content recognition module receives the adjusted traceability code image, it extracts the character features from the image and matches these features with the character samples stored in the data table. Once the best-matching character sample is found, the character content recognition module outputs the label corresponding to that sample as the recognition result. This process ensures the accuracy and reliability of the recognition results.

[0088] The beneficial effects of the above technical solution are as follows: the character content recognition module achieves accurate recognition of the adjusted traceability code character content by matching it with the data table stored in the AI ​​traceability code recognition model.

[0089] According to some embodiments of the present invention, the identification module includes:

[0090] The determination module is used for:

[0091] Based on the AI ​​traceability code recognition model, feature extraction is performed on the target image to determine the feature value of each pixel in the target image;

[0092]

[0093] Among them, D i R is the feature value of the i-th pixel; i G is the R channel value of the i-th pixel; i B is the G channel value of the i-th pixel; i This is the B channel value of the i-th pixel;

[0094] A feature matrix D is constructed based on the feature values ​​of each pixel. The feature matrix D has L rows and M columns.

[0095] The transformation module is used to transform the feature matrix D into a vector to obtain the target feature vector.

[0096] |D*D T -λE|=0

[0097] Among them, D T λ is the transpose of the feature matrix D; E is the identity matrix of order L, and the intermediate values ​​obtained from λ are L values. The L values ​​are sorted from largest to smallest to form the target feature vector.

[0098] The matching module is used to match the target feature vector with the preset feature vector in the preset traceability code database, and determine the recognition result based on the matching result.

[0099] The working principle of the above technical solution is as follows: The determination module first uses an AI traceability code recognition model to extract features from the target image, facilitating the extraction of key information that can represent traceability code characters. For each pixel in the target image, the determination module calculates a feature value based on the values ​​of its three channels: R (red), G (green), and B (blue). The contribution of the three RGB channels to the feature value is considered comprehensively, but with different weights, based on the distribution characteristics of the traceability code characters in the color space. After calculating the feature values ​​of all pixels, the determination module organizes these feature values ​​into a feature matrix D. The feature matrix D has dimensions of L rows and M columns, where L and M represent the number of rows and columns of the target image, respectively. The conversion module performs vector transformation on the feature matrix D to obtain the target feature vector; the matching module matches the target feature vector with preset feature vectors in a preset traceability code database. The preset traceability code database contains a large number of known traceability code feature vectors and their corresponding labels (i.e., traceability code content). The matching process uses metrics such as cosine similarity and Euclidean distance to calculate the similarity between the target feature vector and the preset feature vectors. Based on the matching results, the matching module will find the preset feature vector that is most similar to the target feature vector and output its corresponding label as the recognition result.

[0100] The beneficial effects of the above technical solution are as follows: the recognition module achieves accurate recognition of the traceability code in the target image through the collaborative work of the determination module, the conversion module and the matching module.

[0101] According to some embodiments of the present invention, it further includes: an adjustment module, used to segment the target image into N local images before the matching module matches the target feature vector with the preset feature vector in the preset traceability code database; calculate the adjustment coefficient for each local image, and perform adjustment.

[0102] The working principle of the above technical solution is as follows: The adjustment module first segments the target image into N local images. The purpose of this step is to divide a large image into smaller, more easily processed regions so that individual feature extraction and adjustment can be performed on each region. For each segmented local image, the adjustment module calculates an adjustment coefficient. After calculating the adjustment coefficient, the adjustment module adjusts each local image. The adjustment operation reduces noise, improves image quality, and enhances the recognizability of traceability code characters.

[0103] The beneficial effects of the above technical solution are as follows: The introduction of the adjustment module further improves the recognition process, enhancing the accuracy and efficiency of traceability code recognition. Through local image segmentation and adjustment, it ensures that each region can enter the subsequent feature extraction and matching process in its optimal state, thereby improving the performance of the entire recognition system.

[0104] According to some embodiments of the present invention, the adjustment module includes:

[0105] The second calculation module is used to calculate the energy function for each local image;

[0106]

[0107] Among them, fCS N W is the energy function of the Nth local image; N For the Nth local image; CS N Let W be the pixel matrix of the Nth local image; N -CS N || F For W N -CS N The F-norm, For weighted norm,

[0108] Where j∈L represents the value of j, and L is the target feature vector WV. N The number of values ​​contained, where d is the number of local images with a Euclidean distance less than 0.1, and K is the weighting coefficient corresponding to the number of local images with a Euclidean distance less than 0.1; |SV N | j The median value;

[0109]

[0110] Among them, |WV N | j WV is the target feature vector N The j-th value; σ N For the Nth local image W N The variance;

[0111] The third calculation module is used to calculate the adjustment coefficient LB based on the energy function of each local image. N ;

[0112]

[0113] The corresponding local image is adjusted based on the adjustment coefficient.

[0114] The working principle of the above technical solution is as follows: the energy function is an index that measures the difference between a local image and a certain ideal state. ‖W N -CS N || F For W N -CS N The F-norm measures the difference between the two. The adjustment coefficient LB is calculated based on the energy function of each local image. NThe difference between the energy function and a threshold based on a weighted norm is considered. If the difference is greater than 0, the adjustment coefficient is set to that difference value; otherwise, it is set to 0.

[0115] The beneficial effects of the above technical solution are as follows: By calculating the energy function and adjustment coefficients of each local image, the adjustment module can achieve fine-grained adjustment of the local image, improving the accuracy of traceability code recognition. The adjustment module can perform personalized adjustments based on the characteristics of different local images, enhancing the adaptability of the entire recognition system. By improving image quality, the adjustment module helps improve the robustness of the recognition system to adverse factors such as changes in illumination and noise interference. Through the collaboration of the second and third calculation modules, the adjustment module achieves fine-grained adjustment of the local image, providing higher-quality image input for subsequent feature extraction and matching processes.

[0116] like Figures 3-4 As shown, to achieve the above objectives, a second aspect of the present invention proposes a transcoding and encapsulation method, applying the AI ​​source code recognition system described above, including steps S1-S3:

[0117] S1. The traceability code engraved inside the packaged bottle is identified using an AI traceability code recognition system to obtain the recognition result;

[0118] S2. Convert the recognition result into a QR code; the QR code includes the product's production source information, production date information, and production model information;

[0119] S3. Using laser technology, QR codes are recorded onto preset objects.

[0120] The working principle and beneficial effects of the above technical solution are as follows: An advanced AI traceability code recognition system is used to accurately identify the meticulously engraved traceability code inside the packaged bottle. Key information in the traceability code (such as production source, production date, and production model) is converted into a QR code format. An efficient QR code generation algorithm is employed to ensure that the generated QR code contains rich information while maintaining a small size and high readability. Using precise laser technology, the QR code generated in step S2 is accurately imprinted onto a pre-set object. The pre-set object includes at least one of the following: the bottle cap, the bottom of the bottle, the bottle wall, and the packaging body. The QR code is firmly recorded on the pre-set object, facilitating consumers to scan and query product information, while also increasing the product's anti-counterfeiting and traceability. The automated recognition and conversion process significantly shortens the product information processing and packaging time. The combination of AI recognition and laser marking technology provides the product with a difficult-to-copy anti-counterfeiting label. Consumers can easily obtain product details by simply scanning the QR code on the bottle cap, improving the user experience. A comprehensive traceability system helps enterprises respond quickly to quality issues and protect consumer rights. By integrating an AI traceability code recognition system with laser technology, the system achieves efficient conversion and encapsulation of product information from traceability codes to QR codes. This not only improves production efficiency but also enhances the anti-counterfeiting and traceability of products, bringing consumers a more convenient and secure shopping experience.

[0121] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An AI provenance code recognition system, characterized by, The method comprises the following steps: An acquisition module is configured to acquire a to-be-identified image of an engraved traceability code in a packaging bottle; A preprocessing module is configured to perform image preprocessing on the to-be-identified image to obtain a target image; An identification module is configured to identify the target image based on an AI traceability code identification model to obtain an identification result; Further, the method comprises the following steps: An adjustment module is configured to divide the target image into N local images before the matching module matches the target feature vector with a preset feature vector in a preset traceability code database; an adjustment coefficient of each local image is calculated and the local image is adjusted based on the adjustment coefficient. The adjustment module comprises: where fCS N is the energy function of the Nth local image; W N is the Nth local image; CS N is the pixel matrix of the Nth local image; ‖W N -CS N ‖ F is the F-norm of W N -CS N , ‖CS N ‖ w* is the weighted norm, Wherein, j∈L is the value of j is L, L is the target feature vector WV N The number of values contained, d is the number of local images with a Euclidean distance less than 0.1, K is the weighting coefficient corresponding to the number of local images with a Euclidean distance less than 0.1; |SV N | j Is the intermediate value; where |WV N | j is the jth value of the target feature vector W N V; σ N is the variance of the Nth local image W N ​ a third calculation module, configured to calculate an adjustment coefficient LB based on an energy function of each local image N ; A second calculation module is configured to calculate an energy function of each local image; 2. The AI provenance code identification system of claim 1, wherein, The corresponding local image is adjusted based on the adjustment coefficient. The preprocessing module comprises: An evaluation module is configured to evaluate a brightness feature of the to-be-identified image to obtain a brightness evaluation value; 3. The AI provenance code identification system of claim 2, wherein, A brightness enhancement module is configured to compare the brightness evaluation value with a preset brightness threshold value, and perform brightness enhancement processing when it is determined that the brightness evaluation value is less than the preset brightness threshold value. The evaluation module comprises: A first calculation module is configured to: Acquire a brightness value of each pixel point in the to-be-identified image to determine a maximum brightness value and a minimum brightness value; Calculate an average brightness value Z of the to-be-identified image; Wherein, M is the length of the to-be-identified image; N is the width of the to-be-identified image; x is the maximum value of the horizontal coordinate of the pixel point in the to-be-identified image; y is the maximum value of the vertical coordinate of the pixel point in the to-be-identified image; f(i,j) is the brightness value of the pixel point (i,j) in the to-be-identified image; wherein f max is the maximum luminance value of the pixel points in the image to be identified; f min is the minimum luminance value of the pixel points in the image to be identified.

4. The AI provenance code identification system of claim 1, wherein, The average brightness value Z, the maximum brightness value and the minimum brightness value of the to-be-identified image are determined as the brightness feature to determine the brightness evaluation value S of the to-be-identified image. The identification module comprises: A segmentation module is configured to perform character segmentation on the traceability code in the target image based on the AI traceability code identification model to determine the upper and lower boundaries and the left and right boundaries of each character, determine the size of each character according to the upper and lower boundaries and the left and right boundaries, judge whether the size is consistent with a preset size, determine the character with an inconsistent size and perform size adjustment; 5. The AI provenance code identification system of claim 4, wherein, A character content identification module is configured to perform character content identification on the adjusted traceability code based on the AI traceability code identification model to obtain an identification result.

6. The AI provenance code identification system of claim 1, wherein, The character content identification module is configured to match the adjusted traceability code with a data table stored in the AI traceability code identification model to obtain the identification result. The identification module comprises: A determination module is configured to: wherein D i is the eigenvalue of the i-th pixel point; R i is the R channel value of the i-th pixel point; G i is the G channel value of the i-th pixel point; B i is the B channel value of the i-th pixel point; Perform feature extraction on the target image based on the AI traceability code identification model to determine a feature value of each pixel point in the target image; Construct a feature matrix D based on the feature value of each pixel point, wherein the feature matrix D is L rows and M columns; |D*D T -λE| = 0 where D T is the transpose of the feature matrix D; E is an identity matrix of order L, and the intermediate values λ solved are L values, which are sorted in descending order to form the target feature vector; A conversion module is configured to perform vector conversion on the feature matrix D to obtain a target feature vector; 7. A transcoding packaging method, applying the AI provenance code identification system according to any one of claims 1-6, characterized in that, A matching module is configured to match the target feature vector with a preset feature vector in a preset traceability code database, and determine an identification result according to a matching result. The method comprises the following steps: An AI traceability code identification system is used to identify the traceability code engraved in the packaging bottle to obtain an identification result; A two-dimensional code is converted according to the identification result; the two-dimensional code comprises product production source information, production date information and production model information. Based on laser technology, a two-dimensional code is recorded on a preset object.

Images