Packaging production date identification method and system based on AI dynamic illumination adjustment

Abstract

The invention discloses a goods production date identification method and system based on AI dynamic illumination adjustment, and is mainly applied to the field of intelligent warehousing. The method is realized through the following steps: firstly, obtaining an image of a to-be-identified cargo and extracting surface data including a feature vector of the cargo; secondly, matching optimal illumination parameters, such as a light source incident angle, color temperature and illumination combination, by using a pre-established RAG commodity knowledge base; then, dynamically adjusting a light source to form an adaptive lighting environment, and supplementing light to the production date area; and finally, acquiring an image under adaptive illumination. The innovation point of the invention is that the light source is actively controlled, the goods date recognition rate and the environmental interference resistance are improved, and goods made of various materials such as metal, plastic, paper and the like are supported. When goods made of new materials are encountered, a manual calibration mode can be triggered to record optimal light source parameters and update the knowledge base. The method effectively solves the problems of dependence on ambient light compensation and weak anti-interference capability in the traditional identification technology, and has a wide application prospect.

Description

Technical Field

[0001] The present invention relates to the field of intelligent warehousing, and in particular to a method and system for identifying the production date of goods based on AI dynamic lighting adjustment. Background Art

[0002] In the warehousing sector, especially for food and pharmaceuticals, food or medicine must be stored within their expiration date. Expired food or medicine must be removed from shelves and destroyed. Currently, manual identification of production dates is required for both incoming and outgoing goods. Existing methods for automatically identifying product production dates use various sensors, imaging technologies, and data processing algorithms. This technology is widely used in industries such as food safety, pharmaceuticals, and cargo to ensure product quality and consumer safety. In the food industry, product expiration date detection technology is particularly important, effectively preventing expired products from being mixed with expired products.

[0003] Chinese patent document CN118896962B discloses a method for detecting foreign matter in food and cargo. Specifically, the method involves adjusting the shooting parameters of an image capture device based on the intensity of ambient light to capture images of the food and cargo. The captured images are then corrected based on the color temperature of the ambient light to produce corrected images of the food and cargo. While this approach can improve image analysis accuracy by correcting image color deviations under varying lighting conditions, it suffers from the following deficiencies: It relies solely on ambient light compensation, lacks active light source control, and exhibits weak resistance to environmental interference.

[0004] Therefore, it is necessary to propose further solutions to solve the above technical problems. Summary of the Invention

[0005] The present invention provides a method for identifying the production date of goods based on AI dynamic lighting adjustment to solve the above technical problems.

[0006] The object of the present invention is achieved through the following technical solutions:

[0007] The method for identifying the production date of goods based on AI dynamic lighting adjustment includes the following steps:

[0008] S1: Acquire an image of the goods to be identified, and extract surface data based on the image, wherein the surface data at least includes a feature vector of the goods;

[0009] S2: Based on the feature vector of the product, the optimal lighting parameters corresponding to the feature vector of the product are matched through the pre-established RAG product knowledge base. The optimal lighting parameters include the incident angle of the light source, color temperature and illumination combination;

[0010] S3: Dynamically adjust the incident angle, color temperature, and illumination combination of the light source according to the optimal lighting parameters to create a lighting environment suitable for the current goods in the target area, and trigger a fill light operation for the production date area;

[0011] S4: Collect images of the date marking area on the surface of the goods under an adapted lighting environment, and use an OCR recognition algorithm to extract the date character information in the image.

[0012] Furthermore, the feature matching algorithm is based on learning, analysis and processing of a neural network model, where the input layer receives images of goods and the output layer maps to feature vector labels of the goods.

[0013] Furthermore, the step S2 further includes the following steps:

[0014] S21: When it is detected that the surface data of the current product cannot match the corresponding optimal lighting parameters, it is prompted that the product is a new material, triggering the manual calibration mode, recording the optimal light source parameters of the product and storing them in the RAG product knowledge base.

[0015] Furthermore, step S2 further includes the following steps: performing a spectral reflectance test on common goods to select a lighting parameter combination that maximizes the contrast of the production date area; and storing the test data into a structured data table according to the characteristic vectors of the goods.

[0016] Furthermore, the step S1 further includes the following steps:

[0017] S11: Based on the feature vector of the product, access a pre-built RAG product knowledge base, wherein the RAG product knowledge base stores feature vectors of multiple pre-stored products;

[0018] S12: Based on the feature vector of the product, calculate the cosine similarity between the feature vector of the product and each feature vector in the RAG product knowledge base;

[0019] S13: Filter the pre-stored goods with the highest cosine similarity that exceeds the preset threshold. If the threshold is not reached, it is prompted that the goods are of new material and repeat step S21.

[0020] Furthermore, step S12 further includes the following steps: based on the feature vector to be retrieved, using the formula:

[0021] Obtain the cosine similarity between the feature vector of the goods and each feature vector in the RAG product knowledge base.

[0022] Furthermore, the feature vector of the goods is a 512-dimensional feature vector extracted by the CLIP model encoder.

[0023] Furthermore, in step S1, the goods are photographed by using a camera to obtain an image of the goods to be identified.

[0024] The second aspect of the present invention provides a system based on AI dynamic lighting adjustment, including a dynamic adjustment light source module and a visual recognition module. The dynamic adjustment light source module adjusts the incident angle, color temperature and illumination parameter combination of the light source in real time according to the lighting adjustment parameters; the visual recognition module includes an image acquisition unit and an AI analysis unit. The image acquisition unit obtains the cargo image through a scanning device or a shooting device; the AI ​​analysis unit is used to identify the characteristics of the cargo and generate lighting adjustment parameters; wherein, the dynamic adjustment light source module receives the lighting adjustment parameters generated by the AI ​​analysis unit to form a lighting environment adapted to the characteristics of the cargo in the target area.

[0025] A third aspect of the present invention provides a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of the method according to claims 1 to 8 are implemented.

[0026] The beneficial technical effects achieved by the present invention are:

[0027] 1. The present invention establishes an optical parameter database and presets corresponding illumination intensities according to different cargo materials. It supports cargo made of metal, plastic, and paper. This not only improves the recognition rate of the production date of the goods, but also has a wide range of applications.

[0028] 2. By dynamically adjusting the intensity of the light source and actively adapting to the material characteristics, it has strong resistance to environmental interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 It is a schematic diagram of the method for identifying the production date of goods based on AI dynamic lighting adjustment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] See also Figure 1 As shown in the figure, the method for identifying the production date of goods based on AI dynamic lighting adjustment applied by the present invention includes the following steps:

[0033] S1: Acquire an image of the goods to be identified, and extract surface data based on the image, wherein the surface data at least includes a feature vector of the goods;

[0034] S2: Based on the feature vector of the product, the optimal lighting parameters corresponding to the feature vector of the product are matched through the pre-established RAG product knowledge base. The optimal lighting parameters include the incident angle of the light source, color temperature and illumination combination;

[0035] S3: Dynamically adjust the incident angle, color temperature, and illumination combination of the light source according to the optimal lighting parameters to create a lighting environment suitable for the current goods in the target area, and trigger a fill light operation for the production date area;

[0036] S4: Collect images of the date marking area on the surface of the goods under an adapted lighting environment, and use an OCR recognition algorithm to extract the date character information in the image.

[0037] Furthermore, the feature matching algorithm is based on learning, analysis and processing of a neural network model, where the input layer receives images of goods and the output layer maps to feature vector labels of the goods.

[0038] Furthermore, the step S2 further includes the following steps:

[0039] S21: When it is detected that the surface data of the current product cannot match the corresponding optimal lighting parameters, it is prompted that the product is a new material, triggering the manual calibration mode, recording the optimal light source parameters of the product and storing them in the RAG product knowledge base.

[0040] Furthermore, step S2 further includes the following steps: performing a spectral reflectance test on common goods to select a lighting parameter combination that maximizes the contrast of the production date area; and storing the test data into a structured data table according to the characteristic vectors of the goods.

[0041] Furthermore, the step S1 further includes the following steps:

[0042] S11: Based on the feature vector of the product, access a pre-built RAG product knowledge base, wherein the RAG product knowledge base stores feature vectors of multiple pre-stored products;

[0043] S12: Based on the feature vector of the product, calculate the cosine similarity between the feature vector of the product and each feature vector in the RAG product knowledge base;

[0044] S13: Filter the pre-stored goods with the highest cosine similarity that exceeds the preset threshold. If the threshold is not reached, it is prompted that the goods are of new material and repeat step S21.

[0045] Furthermore, step S12 further includes the following steps: based on the feature vector to be retrieved, using the formula:

[0046] Obtain the cosine similarity between the feature vector of the goods and each feature vector in the RAG product knowledge base.

[0047] Furthermore, the feature vector of the goods is a 512-dimensional feature vector extracted by the CLIP model encoder.

[0048] Furthermore, in step S1, the goods are photographed by using a camera to obtain an image of the goods to be identified.

[0049] The present invention also provides a system based on AI dynamic lighting adjustment, including a dynamic adjustment light source module and a visual recognition module. The dynamic adjustment light source module adjusts the incident angle, color temperature and illumination parameter combination of the light source in real time according to the lighting adjustment parameters; the visual recognition module includes an image acquisition unit and an AI analysis unit. The image acquisition unit obtains the cargo image through a scanning device or a shooting device; the AI ​​analysis unit is used to identify the characteristics of the cargo and generate lighting adjustment parameters; wherein, the dynamic adjustment light source module receives the lighting adjustment parameters generated by the AI ​​analysis unit, and forms a lighting environment adapted to the characteristics of the cargo in the target area.

[0050] In addition, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for identifying the production date of goods based on AI dynamic lighting adjustment.

[0051] From the above, it can be seen that the present invention establishes a RAG product knowledge base and presets corresponding illumination intensity according to different product feature vectors. It supports goods made of metal, plastic, and paper. It not only improves the recognition rate of the product production date, but also can actively adapt to the material characteristics by dynamically adjusting the light source intensity, and has strong resistance to environmental interference.

[0052] The above is a detailed introduction to the method for identifying the production date of goods based on AI dynamic lighting adjustment provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the ideas and methods of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

[0053] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying the production date of goods based on AI dynamic lighting adjustment, characterized in that: The following steps are involved: S1: Acquire an image of the goods to be identified, and extract surface data based on the image, wherein the surface data at least includes a feature vector of the goods; S2: Based on the feature vector of the product, the optimal lighting parameters corresponding to the feature vector of the product are matched through the pre-established RAG product knowledge base. The optimal lighting parameters include the incident angle of the light source, color temperature and illumination combination; S3: Dynamically adjust the incident angle, color temperature, and illumination combination of the light source according to the optimal lighting parameters to create a lighting environment suitable for the current goods in the target area, and trigger a fill light operation for the production date mark area printed on the goods; S4: Collect images of the date marking area on the surface of the goods under an adapted lighting environment, and use an OCR recognition algorithm to extract the date character information in the image.

2. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 1 is characterized in that: The feature matching algorithm is based on learning, analysis and processing of a neural network model. The input layer receives the image of the goods, and the output layer maps it to the feature vector label of the goods.

3. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 1 is characterized in that: The step S2 further includes the following steps: S21: When it is detected that the surface data of the current goods cannot match the corresponding optimal lighting parameters, it is prompted that the goods are of new materials, and the manual calibration mode is triggered. The optimal light source parameters of the goods are recorded and stored in the RAG product knowledge base.

4. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 1 is characterized in that: Step S2 further includes the following steps: performing a spectral reflectance test on common goods to select a lighting parameter combination that maximizes the contrast of the production date area; and storing the test data into a structured data table according to the characteristic vectors of the goods.

5. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 1 is characterized in that: The step S1 further includes the following steps: S11: Based on the feature vector of the product, access a pre-built RAG product knowledge base, wherein the RAG product knowledge base stores feature vectors of multiple pre-stored products; S12: Based on the feature vector of the product, calculate the cosine similarity between the feature vector of the product and each feature vector in the RAG product knowledge base; S13: Filter the pre-stored goods with the highest cosine similarity that exceeds the preset threshold. If the threshold is not reached, it is prompted that the goods are of new material and repeat step S21.

6. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 4 is characterized in that: Step S12 also includes the following steps: based on the feature vector to be retrieved, using the formula: Obtain the cosine similarity between the feature vector of the goods and each feature vector in the RAG product knowledge base.

7. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 6 is characterized in that: The feature vector of the goods is a 512-dimensional feature vector extracted by the CLIP model encoder.

8. The method for identifying the production date of goods based on AI dynamic lighting adjustment according to claim 1 is characterized in that: In step S1, the goods are photographed using a camera to obtain an image of the goods to be identified.

9. A system based on AI dynamic lighting adjustment, characterized in that: It includes a dynamically adjustable light source module and a visual recognition module. The dynamically adjustable light source module adjusts the incident angle, color temperature and illumination parameter combination of the light source in real time according to the lighting adjustment parameters; the visual recognition module includes an image acquisition unit and an AI analysis unit. The image acquisition unit obtains the cargo image through a scanning device or a shooting device; the AI ​​analysis unit is used to identify the characteristics of the cargo and generate lighting adjustment parameters; wherein, the dynamically adjustable light source module receives the lighting adjustment parameters generated by the AI ​​analysis unit to form a lighting environment adapted to the characteristics of the cargo in the target area.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 8 are implemented.

Images