Quality inspection method and system for food production line

Abstract

The invention relates to a quality inspection method and system for a food production line, and relates to the field of food quality inspection, and the method comprises the steps: obtaining first temperatures, colors and images of a plurality of regions on each cake blank in a detection region, estimating a second temperature of each cake blank in each region based on the first temperature of each region, determining pore characteristics of the surface of each region based on the image of each region, and determining a first quality score of each region based on the pore characteristics, determining a second quality score of each area on each cake blank based on the first temperature, the second temperature and the color of each area, and determining a total quality score of each cake blank based on the first quality score and the second quality score of each area. According to the invention, the baking quality of the cake blank can be tested more carefully and accurately.

Description

Technical Field

[0001] This application relates to the field of food quality inspection, and in particular to a quality inspection method and system for a food production line. Background Technology

[0002] As people's living standards improve and their pursuit of material well-being increases, increasingly novel and unique pastries are enriching people's lives. In the mass production of pastries, cake bases are typically used as the basic baking material. Further processing is then carried out on top of these cake bases to obtain a wide variety of pastries. Therefore, the cake base is a crucial part of the pastry production process, and its quality directly affects the final quality of the pastries.

[0003] Currently, food factories typically use molds and large baking equipment to produce cake bases in large quantities. After the cake bases are produced, they are inspected on the production line by capturing images to check features such as shape and outline. However, this inspection method is relatively simple and not suitable for more detailed and accurate quality control of the baked cake bases. Summary of the Invention

[0004] In order to achieve more detailed and accurate quality inspection of cake base baking quality, this application provides a quality inspection method and system for a food production line.

[0005] Firstly, this application provides a quality inspection method for a food production line, employing the following technical solution: A quality inspection method for a food production line, comprising: Acquire the first temperature, color, and image of multiple regions on each cake base within the detection area; The second temperature of each cake base within each region is estimated based on the first temperature of each region. The porosity features of the surface of each region are determined based on the image of each region, and a first quality score for each region is determined based on the porosity features. A second quality score is determined for each area on each cake base based on the first temperature, the second temperature, and the color of each area. The total quality score for each cake base is determined based on the first and second quality scores for each region.

[0006] By adopting the above technical solution, the first temperature, color, and images of multiple areas on each cake base within the detection area are obtained. This facilitates detailed quality inspection of the cake base. Dividing the cake base into multiple areas and inspecting each area separately ultimately yields the overall quality of the cake base, making the quality inspection more accurate. The first temperature of each area is used to estimate the second temperature inside each area, facilitating quality inspection based on baking doneness. The images of each area reveal the surface porosity characteristics, which to some extent characterize the texture, doneness, and quality of the cake base. Therefore, the first quality score for porosity characteristics can be accurately determined. The first surface temperature, the second internal temperature, and the color of each area also characterize baking doneness and quality. Thus, the second quality score for each area can be accurately determined based on the first temperature, the second temperature, and the color. After determining the first and second quality scores for each area, the overall quality score of each cake base can be accurately determined, which is more detailed and accurate than quality inspection based solely on images.

[0007] In another possible implementation, the first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. The estimation of the second temperature of each cake base within each region based on the first temperature of each region includes: Calculate the first average of the first sub-temperature of all regions, and the second average of the second sub-temperature of all regions; The internal temperature calculation function is determined based on the first average value and the second average value. Substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region. Determine the average of the first and second estimated values, where the average estimated value is the second temperature within each region.

[0008] In another possible implementation, determining the porosity features of the surface of each region based on the image of each region, and determining a first quality score for each region based on the porosity features, includes: Determine the area of ​​each stomatal feature in each region and the location of each stomatal feature; Draw the area surrounding each stomatal feature with a preset radius, centered on each stomatal feature; Calculate the distance between stomatal features in each stomatal feature group, wherein the stomatal feature group includes the stomatal feature located at the center and any remaining stomatal feature in the surrounding area; The first sub-quality score of each stomatal feature group is determined based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Determine the average distance of all stomatal feature groups corresponding to each stomatal feature; Calculate the sum of the areas and the average area of ​​all stomatal features in the surrounding region corresponding to each stomatal feature; Determine the ratio of the total area to the area of ​​the surrounding region, and determine the absolute value of the difference between the ratio and the preset ratio; Determine the absolute value of the first area difference between the average area and the preset area, and determine the second sub-quality score of the area surrounding each stomatal feature based on the absolute value of the percentage difference and the absolute value of the first area difference. The first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

[0009] In another possible implementation, determining the first sub-quality score for each stomatal feature group based on the distance between each stomatal feature group and the area of ​​each stomatal feature within each stomatal feature group includes: Determine the absolute value of the second area difference between the area of ​​each pore feature and the preset area, and determine the absolute value of the third area difference between two pore features in each group of pore features; Determine the absolute value of the distance difference between each pore feature group and the preset distance; The first sub-quality score for each stomatal feature group is determined based on the absolute value of the second area difference, the absolute value of the third area difference, and the absolute value of the distance difference.

[0010] In another possible implementation, determining the first quality score of each region based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature includes: The sum of the first sub-quality scores is obtained by summing the first sub-quality scores of all stomatal feature groups in the surrounding area corresponding to each stomatal feature. The first target average is obtained by averaging the sum of all first sub-quality scores for each region. The average of all distances within each region is used to obtain the average value of the second target. The average of all second-sub-quality scores in each region is used to obtain the average of the third objective. The first quality score for each region is obtained based on the first target average, the second target average, and the third target average.

[0011] In another possible implementation, determining the second quality score for each region on each cake base based on the first temperature, the second temperature, and the color of each region includes: Determine the absolute value of the temperature difference between the second temperature and the preset temperature, and determine the color difference between the color of each region and the preset color; Determine the temperature difference between the second temperature and the average first temperature of each region, and determine the absolute value of the second temperature difference between the temperature difference and a preset difference, wherein the first average temperature is the average of the first sub-temperature and the second sub-temperature of each region; The second quality score for each region is determined based on the absolute value of the first temperature difference, the color difference, and the absolute value of the second temperature difference.

[0012] In another possible implementation, the method further includes: If a target cake base has a total quality score lower than a preset score, the robotic arm is controlled to grab the target cake base and move it out of the detection area.

[0013] Secondly, this application provides a quality inspection system for a food production line, which adopts the following technical solution: A quality inspection system for a food production line includes: The data acquisition module is used to acquire the first temperature, color, and image of multiple areas on each cake base within the detection area; The temperature prediction module is used to predict the second temperature of each cake base within each region based on the first temperature of each region. The first determining module is used to determine the pore features of the surface of each region based on the image of each region, and to determine a first quality score for each region based on the pore features. The second determining module is used to determine the second quality score of each area on each cake base based on the first temperature, the second temperature, and the color of each area. The third determination module is used to determine the total quality score of each cake base based on the first quality score and the second quality score of each region.

[0014] By adopting the above technical solution, the data acquisition module acquires the first temperature, color, and images of multiple areas on each cake base within the detection area, facilitating subsequent detailed quality inspection of the cake base. Furthermore, dividing the cake base into multiple areas and inspecting each area separately ultimately yields the overall quality of the cake base, making quality inspection more accurate. The temperature prediction module estimates the second temperature within each area based on the first temperature, facilitating quality inspection based on baking doneness. The images of each area reveal the surface porosity characteristics, which to some extent characterize the cake base's texture, doneness, and quality. Therefore, the first determination module can accurately determine the first quality score based on porosity characteristics. Similarly, the first surface temperature, the second internal temperature, and the color of each area characterize baking doneness and quality. Therefore, the second determination module can accurately determine the second quality score for each area based on the first temperature, the second temperature, and the color. After determining the first and second quality scores for each area, the third determination module can accurately determine the overall quality score of each cake base, which is more detailed and accurate than quality inspection based solely on images.

[0015] In another possible implementation, the first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. The temperature estimation module, when estimating the second temperature of each cake base within each region based on the first temperature of each region, is specifically used for: Calculate the first average of the first sub-temperature of all regions, and the second average of the second sub-temperature of all regions; The internal temperature calculation function is determined based on the first average value and the second average value. Substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region. Determine the average of the first and second estimated values, where the average estimated value is the second temperature within each region.

[0016] In another possible implementation, when the first determining module determines the porosity features of the surface of each region based on the image of each region, and determines a first quality score for each region based on the porosity features, it is specifically used for: Determine the area of ​​each stomatal feature in each region and the location of each stomatal feature; Draw the area surrounding each stomatal feature with a preset radius, centered on each stomatal feature; Calculate the distance between stomatal features in each stomatal feature group, wherein the stomatal feature group includes the stomatal feature located at the center and any remaining stomatal feature in the surrounding area; The first sub-quality score of each stomatal feature group is determined based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Determine the average distance of all stomatal feature groups corresponding to each stomatal feature; Calculate the sum of the areas and the average area of ​​all stomatal features in the surrounding region corresponding to each stomatal feature; Determine the ratio of the total area to the area of ​​the surrounding region, and determine the absolute value of the difference between the ratio and the preset ratio; Determine the absolute value of the first area difference between the average area and the preset area, and determine the second sub-quality score of the area surrounding each stomatal feature based on the absolute value of the percentage difference and the absolute value of the first area difference. The first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

[0017] In another possible implementation, when the first determining module determines the first sub-quality score of each stomatal feature group based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group, it is specifically used for: Determine the absolute value of the second area difference between the area of ​​each pore feature and the preset area, and determine the absolute value of the third area difference between two pore features in each group of pore features; Determine the absolute value of the distance difference between each pore feature group and the preset distance; The first sub-quality score for each stomatal feature group is determined based on the absolute value of the second area difference, the absolute value of the third area difference, and the absolute value of the distance difference.

[0018] In another possible implementation, when the first determining module determines the first quality score of each region based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature, it is specifically used for: The sum of the first sub-quality scores is obtained by summing the first sub-quality scores of all stomatal feature groups in the surrounding area corresponding to each stomatal feature. The first target average is obtained by averaging the sum of all first sub-quality scores for each region. The average of all distances within each region is used to obtain the average value of the second target. The average of all second-sub-quality scores in each region is used to obtain the average of the third objective. The first quality score for each region is obtained based on the first target average, the second target average, and the third target average.

[0019] In another possible implementation, the second determining module, when determining the second quality score for each region on each cake base based on the first temperature, the second temperature, and the color of each region, is specifically used for: Determine the absolute value of the temperature difference between the second temperature and the preset temperature, and determine the color difference between the color of each region and the preset color; Determine the temperature difference between the second temperature and the average first temperature of each region, and determine the absolute value of the second temperature difference between the temperature difference and a preset difference, wherein the first average temperature is the average of the first sub-temperature and the second sub-temperature of each region; The second quality score for each region is determined based on the absolute value of the first temperature difference, the color difference, and the absolute value of the second temperature difference.

[0020] In another possible implementation, the quality inspection system for the food production line further includes: The control module is used to control the robotic arm to grab the target cake base when there is a target cake base with a total quality score lower than a preset score, so as to move the target cake base out of the detection area.

[0021] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device comprising: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one configuration being for: executing a quality inspection method for a food production line as shown in any possible implementation of the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, causes the computer to perform a quality inspection method for a food production line as described in any one of the first aspects.

[0023] In summary, this application includes at least one of the following beneficial technical effects: This method acquires the first temperature, color, and images of multiple areas on each cake base within the detection area. This facilitates detailed quality inspection of the cake base. Furthermore, dividing the cake base into multiple areas allows for individual quality inspection of each area, ultimately leading to a more accurate overall quality assessment. The first temperature of each area is used to estimate the second temperature within that area, facilitating quality inspection based on baking doneness. Images of each area reveal the surface porosity characteristics, which to some extent characterize the cake base's texture, doneness, and quality. Therefore, the first quality score for porosity characteristics can be accurately determined. Similarly, the first surface temperature, second internal temperature, and color of each area characterize baking doneness and quality. Thus, the second quality score for each area can be accurately determined based on the first temperature, second temperature, and color. Finally, by determining the first and second quality scores for each area, the overall quality score of each cake base can be accurately determined, resulting in a more detailed and accurate assessment compared to image-based quality inspection alone. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating a quality inspection method for a food production line according to an embodiment of this application.

[0025] Figure 2 This is a schematic diagram of the structure of a quality inspection system for a food production line according to an embodiment of this application.

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0027] The present application will be further described in detail below with reference to the accompanying drawings.

[0028] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0031] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0032] This application provides a quality inspection method for a food production line, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, S104, and S105, wherein, S101, acquire the first temperature, color, and image of multiple areas on each cake base within the detection area.

[0033] In this embodiment, a square mold is typically used for baking cake bases. The square mold contains multiple sub-molds arranged in a grid pattern. A metered amount of mixed flour is extruded into these sub-molds using an extrusion device. The mold is then transported to the baking equipment by a conveyor belt for baking. After baking, the mold is transported to the next stage by the same conveyor belt. During the process from baking to the next stage, an infrared temperature camera and a color camera can be installed above the conveyor belt. Both cameras are vertically aligned with a specific area on the conveyor belt, which serves as the detection area. Once the mold moves into the detection area, the infrared temperature camera captures the first temperature of multiple areas on each cake base, while the color camera captures the color and image of multiple areas on each cake base. Both the infrared temperature camera and the color camera are connected to electronic equipment via wires, allowing the electronic equipment to acquire the first temperature, color, and image of multiple areas on each cake base. Specifically, the cake base can be divided into two rows of multiple areas, each including a portion of the upper surface and a portion of the side surface. Since each area includes a portion of the upper surface and a portion of the side surface, the subsequent quality analysis of each area is more comprehensive and accurate.

[0034] S102, based on the first temperature of each region, predicts the second temperature of each cake base within each region.

[0035] In this embodiment of the application, the infrared temperature measuring camera collects the first temperature of the surface of each area. Therefore, in order to better analyze the baking quality of each cake base, the electronic device estimates the second temperature inside each area based on the first temperature of each area. After obtaining the first temperature of the surface and the second temperature inside each area, the baking quality of the cake base can be accurately and comprehensively analyzed.

[0036] S103, determine the pore features of the surface of each region based on the image of each region, and determine the first quality score of each region based on the pore features.

[0037] In this embodiment, the electronic device inputs the image of each region into a trained network model for feature recognition, thereby identifying the pore features on the surface of each region. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. A training sample set is pre-prepared, containing a large number of training samples. Each training sample includes an image of pores on the cake base and a corresponding label, such as "Image 1, Pore Features". The electronic device inputs the training sample set into the initial network model for supervised training, thereby obtaining a trained network model. Pore features can reflect characteristics such as the texture, doneness, and quality of the cake base; therefore, the electronic device determines a first quality score for each region based on the performance of the pore features on the surface of each region.

[0038] S104, based on the first temperature, the second temperature, and the color of each area, determines the second quality score for each area on each cake base.

[0039] In the embodiments of this application, the first temperature, the second temperature, and the color of the surface of each region are also key factors characterizing the baking doneness and quality of the cake base. Therefore, the electronic device can accurately determine the second quality score of each region by comprehensively analyzing the first temperature, the second temperature, and the color.

[0040] S105, determine the total quality score of each cake base based on the first quality score and the second quality score of each region.

[0041] In the embodiments of this application, after the electronic device determines the first quality score and the second quality score of each region on each cake base, it sums the first quality score and the second quality score of each region to obtain the overall quality score of each region. Then, it sums the overall quality scores of all regions of each cake base to obtain the total quality score of each cake base. By comprehensively analyzing the pore characteristics, the first surface temperature, the second internal temperature, and the color of each cake base, the cake base quality detection is more comprehensive, detailed, and accurate.

[0042] In one possible implementation of this application embodiment, the first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. Step S102 estimates the second temperature of each cake base within each region based on the first temperature of each region, specifically including steps S1021 (not shown in the figure), S1022 (not shown in the figure), S1023 (not shown in the figure), and S1024 (not shown in the figure). S1021, calculate the first average value of the first sub-temperature of all regions, and the second average value of the second sub-temperature of all regions.

[0043] In this embodiment, multiple infrared temperature cameras can be positioned above the detection area. These cameras are positioned at different angles towards the cake base, allowing the acquisition of a first sub-temperature on the upper surface and a second sub-temperature on the sides of each area of ​​the cake base. The electronic device averages the first sub-temperatures of the upper surface of all areas on each cake base to obtain a first average value, which represents the overall baking temperature of the upper surface of each cake base. Similarly, the electronic device averages the second sub-temperatures of the sides of all areas on each cake base to obtain a second average value, which represents the overall baking temperature of the sides of each cake base.

[0044] S1022, determine the internal temperature calculation function based on the first average value and the second average value.

[0045] In this embodiment, after the electronic device determines the first average value and the second average value, since the first average value and the second average value respectively represent the baking temperature of the upper surface and side of each cake base, and there is a certain proportional relationship between the baking temperature of the upper surface and side of the cake base and the internal baking temperature, the electronic device determines the average difference between the first average value and the second average value. The first average value, the second average value, and the average difference are used as the characteristic temperature and characteristic value of each cake base. The electronic device can determine the matching internal temperature calculation function from multiple preset internal temperature calculation functions based on the aforementioned first average value, second average value, and average difference. Workers can determine the internal temperature calculation function under different first average values, second average values, and average differences through numerous experiments in advance, and determine the correspondence between each internal temperature calculation function and the first average value, second average value, and average difference, and then store this information in the electronic device. This allows the electronic device to find the corresponding internal temperature calculation function after determining the first average value, second average value, and average difference for each cake base. Since the internal temperature of the baked cake base is higher than the surface temperature, the internal temperature calculation function can be a linear function, such as y=1.5x.

[0046] S1023, substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region.

[0047] In the embodiments of this application, the electronic device substitutes the first sub-temperature and the second sub-temperature of each region into the determined internal temperature calculation function to obtain the first estimated value and the second estimated value of the internal temperature of each region.

[0048] S1024, determine the average estimate of the first estimate and the second estimate.

[0049] The average estimated value is the second temperature within each region.

[0050] In this embodiment of the application, to improve the accuracy of the predicted second temperature within each region, the electronic device averages the first predicted value and the second predicted value to obtain an average predicted value, which is the second temperature within each region. A more accurate predicted second temperature is obtained by selecting a suitable internal temperature calculation function and substituting the first and second sub-temperatures of each region into the internal temperature calculation function.

[0051] One possible implementation of this application embodiment is that step S103 determines the pore features of the surface of each region based on the image of each region, and determines a first quality score for each region based on the pore features. Specifically, this includes steps S1031 (not shown in the figure), S1032 (not shown in the figure), S1033 (not shown in the figure), S1034 (not shown in the figure), S1035 (not shown in the figure), S1036 (not shown in the figure), S1037 (not shown in the figure), S1038 (not shown in the figure), and S1039 (not shown in the figure). S1031, determine the area of ​​each stomatal feature in each region and the location of each stomatal feature.

[0052] In this embodiment of the application, after the electronic device identifies the pore features in each region, it performs contour recognition on each pore feature in each region to obtain the contour of each pore feature. Then, it counts the number of pixels within the contour range of each pore feature, using the number of pixels to represent the area of ​​each pore feature. The electronic device can perform denoising processing on the image of each region, and then perform grayscale transformation on the denoised image to obtain a grayscale image. From the grayscale image, it determines the locations where grayscale values ​​change stepwise to obtain the contour of each pore feature.

[0053] After the electronic device determines the pore features of each region, it maps the contour of each pore feature into the image of each region. Then, it maps the image with the mapped contours into a preset rectangular coordinate system to obtain the coordinates of the center position of the contour of each pore feature. These coordinates are used to characterize the position of each pore feature.

[0054] S1032, draw the surrounding area of ​​each pore feature with a preset radius as the center.

[0055] In the embodiments of this application, the preset radius can be one centimeter. The electronic device uses each pore feature in each region as the center and then draws a circular region with a radius of one centimeter. The circular region is the area surrounding each pore feature.

[0056] S1033, calculate the distance between stomatal features in each stomatal feature group.

[0057] The stomatal feature group includes the stomatal feature located at the center and any remaining stomatal feature in the surrounding area.

[0058] In this embodiment of the application, the electronic device groups each pore feature, which serves as the center point, with each remaining pore feature in the surrounding area into a pore feature group. Then, the electronic device calculates the distance between the two pore features in each pore feature group using a two-point distance formula.

[0059] S1034, determine the first sub-quality score of each stomatal feature group based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group.

[0060] In this embodiment, the distance between two pore features within each pore feature group characterizes the baking quality of each region to some extent; distances that are too large or too small will affect the baking quality. Furthermore, the area relationship between two pore features within each pore feature group also affects the baking configuration of each region. Therefore, the electronic device determines a first sub-quality score for each pore feature group based on a comprehensive analysis of the distance corresponding to each pore feature group and the area of ​​the two pore features within the group. The first sub-quality score characterizes the baking quality of the local region where each pore feature group is located.

[0061] S1035, determine the average distance of all stomatal feature groups corresponding to each stomatal feature.

[0062] In this embodiment of the application, after the electronic device determines all pore feature groups corresponding to each pore feature as the center, it calculates the average distance of all pore feature groups. The average distance represents the overall distance level of all pore features in the surrounding area of ​​each pore feature.

[0063] S1036, calculate the sum of the areas of all stomatal features in the surrounding area corresponding to each stomatal feature and the average area.

[0064] In this embodiment of the application, after the electronic device determines the surrounding area corresponding to each pore feature, it sums the areas of all pore features within that area, including the pore feature at the center, to obtain the total area. Then, it averages the areas of all pore features to obtain the average area.

[0065] S1037, determine the ratio of the total area to the area of ​​the surrounding area, and determine the absolute value of the difference between the ratio and the preset ratio.

[0066] In this embodiment, the electronic device can calculate the area of ​​the surrounding area using the circular area calculation formula combined with the radius of the surrounding area. Then, it divides the sum of the areas of all pore features within the surrounding area by the area of ​​the surrounding area to obtain the proportion. A preset proportion is used as the ratio of the sum of the areas of all pore features within the surrounding area of ​​a given pore feature to the area of ​​the surrounding area when baking is successful. Therefore, the electronic device subtracts the preset proportion from the proportion corresponding to each pore feature as the center to obtain the absolute value of the proportion difference. Taking the absolute value of the absolute value of the proportion difference yields the absolute value of the proportion difference. The absolute value of the proportion difference represents the difference in area between the total area of ​​all pore features within the surrounding area when each pore feature is the center and when baking is successful.

[0067] S1038, determine the absolute value of the first area difference between the average area and the preset area, and determine the second sub-quality score of the area surrounding each stomatal feature based on the absolute value of the percentage difference and the absolute value of the first area difference.

[0068] In the embodiments of this application, the average area represents the average area of ​​each pore feature in the surrounding area when each pore feature is the center. The preset area is the area of ​​the pore feature when baking is qualified. The electronic device calculates the difference between the average area and the preset area and takes the absolute value to obtain the absolute value of the first area difference. The absolute value of the first area difference is the difference between the area of ​​all pore features in the surrounding area when each pore feature is the center and the pore area when baking is qualified.

[0069] The absolute values ​​of the percentage difference and the first area difference are key factors characterizing the baking quality of the surrounding area centered on each pore feature in terms of pore area representation. Therefore, the staff assigns corresponding weights to the absolute values ​​of the percentage difference and the first area difference and stores them in the electronic device. After determining the absolute values ​​of the percentage difference and the first area difference for the surrounding area centered on each pore feature, the electronic device normalizes these values ​​to obtain their corresponding normalized values. The electronic device then uses the corresponding coefficients to perform weighted calculations on these normalized values ​​to obtain the second sub-quality score for the surrounding area of ​​each pore feature.

[0070] S1039, the first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

[0071] In the embodiments of this application, the first sub-quality score of each pore feature group, the average distance of all pore feature groups corresponding to each pore feature, and the second sub-quality score are all key factors affecting the first quality score of each region on the cake base in terms of pores. Therefore, the electronic device can accurately determine the first quality score of each region by comprehensively analyzing the above four factors, including the first sub-quality score of each pore feature group. It should be noted that the higher the first quality score, the lower the baking quality; that is, the quality score is inversely proportional to the baking quality.

[0072] One possible implementation of this application embodiment is that step S1034 determines the first sub-quality score of each stomatal feature group based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Specifically, this includes steps Sa (not shown in the figure), Sb (not shown in the figure), and Sc (not shown in the figure). Sa, determine the absolute value of the second area difference between the area of ​​each pore feature and the preset area, and determine the absolute value of the third area difference between two pore features in each group of pore features.

[0073] In this embodiment, the electronic device calculates the absolute value of the difference between the area of ​​each pore feature in each pore feature group and the preset area of ​​the pores when baking is qualified, obtaining a second absolute value of area difference for each pore feature. The second absolute value of area difference represents the difference between the area of ​​each pore feature and the area of ​​the pores when baking is qualified; a larger second absolute value indicates poorer baking quality. The electronic device also calculates the absolute value of the difference between the areas of two pore features in each pore feature group, obtaining a third absolute value of area difference. The third absolute value of area difference represents the area difference between two pore features within each pore feature group; a larger area difference between two pore features within the same group indicates poorer baking quality.

[0074] Sb determines the absolute value of the distance difference between each pore feature group and the preset distance.

[0075] In this embodiment of the application, the preset distance is used as the qualified distance between two pore features in the same group when the baking is qualified. The electronic device calculates the distance difference between the distance of each pore feature group and the preset distance and takes the absolute value to obtain the absolute value of the distance difference. The larger the absolute value of the distance difference, the worse the baking quality.

[0076] Sc determines the first sub-quality score for each stomatal feature group based on the absolute values ​​of the second area difference, the third area difference, and the distance difference.

[0077] In the embodiments of this application, as summarized above, the absolute values ​​of the second area difference, the third area difference, and the distance difference are all key factors affecting the quality of the local area where each pore feature group is located. The staff assigns corresponding weights to the absolute values ​​of the second area difference, the third area difference, and the distance difference, and stores them in the electronic device. The electronic device normalizes the three factors, including the absolute value of the second area difference, and then uses their respective weights to perform a weighted calculation on the normalized values ​​to obtain the first sub-quality score for each pore feature group. It should be noted that the higher the first sub-quality score, the lower the baking quality, and the inverse relationship exists.

[0078] One possible implementation of this application embodiment is that step S1039 determines the first quality score of each region based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature. Specifically, this includes steps one, two, three, four, and five. Step 1: Sum the first sub-quality scores of all stomatal feature groups in the surrounding area corresponding to each stomatal feature to obtain the total first sub-quality score.

[0079] In the embodiments of this application, after the electronic device determines the first sub-quality score of all pore feature groups in the surrounding area when each pore feature is the center, it sums all the first sub-quality scores to obtain the total first sub-quality score, which is the baking quality of the surrounding area when each pore feature is the center.

[0080] Step 2: Calculate the average of the sum of all first sub-quality scores for each region to obtain the first target average.

[0081] In the embodiments of this application, the electronic device calculates the average of the sum of all first sub-quality scores in each region to obtain a first target average value. The first target average value represents the overall baking quality level of the surrounding region when all pore features in each region are centered.

[0082] Step 3: Calculate the average of all distances within each region to obtain the second target average.

[0083] In this embodiment of the application, the electronic device averages the average distances between all pore features in each region and their surrounding regions when all pore features are centered, to obtain a second target average value. The second target average value represents the overall distance level between all pore features in each region.

[0084] Step four: Calculate the average of all second sub-quality scores in each region to obtain the third target average.

[0085] In the embodiments of this application, the electronic device calculates the average of the second sub-quality scores of the surrounding areas when all pore features in each region are centered to obtain the third target average value, which represents the baking level of the overall pore area performance of each region.

[0086] Step 5: Obtain the first quality score for each region based on the average value of the first target, the average value of the second target, and the average value of the third target.

[0087] In the embodiments of this application, the first target average value, the second target average value, and the third target average value are all key factors affecting the first quality score of stomatal characteristics in each region. The staff assigns corresponding weights to the first target average value, the second target average value, and the third target average value and stores them in the electronic device. The electronic device normalizes the first target average value, the second target average value, and the third target average value to obtain normalized values. The electronic device then uses the corresponding weights to perform a weighted calculation on the normalized values ​​to obtain the first quality score for each region. It should be noted that the higher the first quality score, the lower the baking quality.

[0088] One possible implementation of this application embodiment is that, in step S104, a second quality score is determined for each region on each cake base based on a first temperature, a second temperature, and the color of each region. Specifically, this includes steps S1041 (not shown in the figure), S1042 (not shown in the figure), and S1043 (not shown in the figure). S1041, determine the absolute value of the temperature difference between the second temperature and the preset temperature, and determine the color difference between the color of each area and the preset color.

[0089] In the embodiments of this application, the preset temperature is used as the temperature at which the cake base is baked to a qualified standard. The electronic device calculates the difference between the second temperature inside each region and the preset temperature and takes the absolute value to obtain the absolute value of the first temperature difference. The larger the absolute value of the first temperature difference, the greater the deviation between the second temperature inside the region and the preset temperature at the baking standard, and the lower the baking quality.

[0090] The electronic device pre-stores a formula for calculating the ΔE94 (CIE 1994) color difference. It extracts the L (lightness), a (red-green hue), and b (yellow-blue hue) values ​​for each region of the image. Then, it calculates the lightness difference ΔL, hue difference Δa, and Δb between each region's L, a, and b and the color at which baking is successful. Subsequently, weighted parameters (kL lightness weight factor, K1 first contrast factor, K2 second contrast factor) set for the cake baking scenario, along with standard observer visual characteristic parameters (Sl lightness sensitivity factor, Sc chroma sensitivity factor, Sh hue sensitivity factor), are used to calculate the ΔE94 value. The smaller this value, the closer the two colors are.

[0091] S1042, determine the temperature difference between the second temperature and the average first temperature of each region, and determine the absolute value of the second temperature difference between the temperature difference and the preset difference, wherein the average first temperature is the average of the first sub-temperature and the second sub-temperature of each region.

[0092] In this embodiment of the application, the electronic device averages the first sub-temperature and the second sub-temperature of each region to obtain a first average temperature. Then, the electronic device subtracts the second temperature of each region from the first average temperature to obtain a temperature difference value. A preset difference value is used as the temperature difference between the inside and the surface of the cake base when the baking is qualified. The electronic device calculates the second temperature difference value between the temperature difference value of each region and the preset difference value, and takes the absolute value to obtain the absolute value of the second temperature difference value. The larger the absolute value of the second temperature difference value, the worse the baking quality of the cake base.

[0093] S1043, determine the second quality score for each region based on the absolute value of the first temperature difference, the color difference, and the absolute value of the second temperature difference.

[0094] In this embodiment, the absolute values ​​of the first temperature difference, color difference, and second temperature difference are all key factors affecting the second quality score of each area. The staff assigns corresponding weights to each of these values ​​and stores them in the electronic device. The electronic device normalizes each of these values ​​to obtain their respective normalized values. Then, the electronic device uses their respective weights to perform a weighted calculation to obtain the accurate second quality score for each area. It should be noted that a higher second quality score indicates lower baking quality.

[0095] In one possible implementation of this application embodiment, step S106 (not shown in the figure) is included after step S105, wherein... S106 If there is a target cake base with a total quality score lower than the preset score, the robot arm is controlled to grab the target cake base and move it out of the detection area.

[0096] In this embodiment, since the total quality score is inversely proportional to the baking quality, the electronic device can use the reciprocal of the total quality score for easier calculation and processing. The preset score is also set based on the reciprocal of the total quality score; the larger the reciprocal of the total quality score, the higher the baking quality. The preset score serves as the dividing point for whether the cake base quality is too low. The electronic device compares the total quality score of each cake base with the preset score to determine whether a target cake base exists within the detection area. A multi-degree-of-freedom robotic arm can be installed downstream of the detection area on the conveyor belt, with a robotic hand mounted on it. After identifying the target cake base, the electronic device determines its position within the detection area. For example, if the detection area is grid-like, the electronic device determines the grid where the target cake base is located and then controls the robotic arm to move to the grid where the target cake base is located to grab it. The robotic arm can then transport the target cake base to the defective product collection area, thereby improving the yield rate.

[0097] In other embodiments, the electronic device may also determine a second temperature variance and a second temperature average for each cake base based on a second temperature in each region. The difference between the second temperature variance, the second temperature average, and the preset internal temperature of the cake base when baking is successful is used to determine the baking temperature score for each sub-mold; a higher score indicates better baking. The average and variance of the total quality score for all cake bases within the detection area are determined. The mold's quality score is determined based on the average and variance of the total quality score. Finally, the presence of any abnormalities in the mold is determined based on the baking temperature score of each sub-mold and the overall mold quality score. The electronic device counts abnormal sub-molds whose tempering scores are lower than a preset tempering score. It sums the tempering scores of all sub-molds to obtain a total tempering score. The total tempering score, the number of abnormal sub-molds, and the mold quality score are normalized. Workers assign and store corresponding weights for each of these factors. The electronic device normalizes these three factors separately. It then performs a weighted calculation on the normalized values ​​to obtain a mold inspection score. This inspection score is compared to a preset threshold indicating whether the mold is abnormal. If the score is lower, the mold is abnormal, requiring inspection, replacement, or maintenance to improve the yield rate. The electronic device outputs the mold's number, allowing workers to promptly identify the abnormal mold. For example, the electronic device sends the abnormal mold's number to the worker's terminal device, informing them of the abnormality.

[0098] The above embodiments describe a quality inspection method for a food production line from the perspective of process flow. The following embodiments describe a quality inspection system 20 for a food production line from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0099] This application provides a quality inspection system 20 for a food production line, such as... Figure 2 As shown, a quality inspection system 20 for a food production line may specifically include: The data acquisition module 201 is used to acquire the first temperature of multiple areas on each cake base within the detection area, the color of multiple areas, and the image of multiple areas; Temperature prediction module 202 is used to predict the second temperature of each cake base within each region based on the first temperature of each region. The first determining module 203 is used to determine the pore features of the surface of each region based on the image of each region, and to determine the first quality score of each region based on the pore features. The second determining module 204 is used to determine the second quality score of each area on each cake base based on the first temperature, the second temperature and the color of each area; The third determining module 205 is used to determine the total quality score of each cake base based on the first quality score and the second quality score of each region.

[0100] This application discloses a quality inspection system 20 for a food production line. The data acquisition module 201 acquires the first temperature, color, and images of multiple areas on each cake base within the detection area. This facilitates detailed quality inspection of the cake base. Furthermore, dividing the cake base into multiple areas and inspecting each area separately results in a more accurate overall quality assessment. The temperature prediction module 202 predicts the second temperature within each area based on the first temperature, facilitating quality inspection based on baking doneness. The system also obtains the surface porosity characteristics of each area from the images. The appearance of air pockets can characterize the texture, doneness, and quality of a cake base to a certain extent. Therefore, the first determining module 203 can accurately determine the first quality score in terms of air pocket appearance based on the air pocket characteristics. The first surface temperature, the second internal temperature, and the color of each area also characterize the baking doneness and quality. Therefore, the second determining module 204 can accurately determine the second quality score of each area based on the first temperature, the second temperature, and the color. After determining the first quality score and the second quality score of each area, the third determining module 205 can accurately determine the overall quality score of each cake base, which is more detailed and accurate than simply relying on image quality inspection.

[0101] In one possible implementation of this application embodiment, the first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. When the temperature estimation module 202 estimates the second temperature of each cake base within each region based on the first temperature of each region, it is specifically used for: Calculate the first average of the first sub-temperature of all regions, and the second average of the second sub-temperature of all regions; The internal temperature calculation function is determined based on the first average value and the second average value. Substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region. Determine the average of the first and second estimates, where the average estimate is the second temperature within each region.

[0102] In one possible implementation of this application embodiment, when the first determining module 203 determines the porosity features of the surface of each region based on the image of each region, and determines the first quality score of each region based on the porosity features, it is specifically used for: Determine the area of ​​each stomatal feature in each region and the location of each stomatal feature; Draw the area surrounding each stomatal feature with a preset radius, centered on each stomatal feature; Calculate the distance between stomatal features in each stomatal feature group, which includes the stomatal feature at the center and any remaining stomatal feature in the surrounding area; The first sub-quality score of each stomatal feature group is determined based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Determine the average distance of all stomatal feature groups corresponding to each stomatal feature; Calculate the sum of the areas and the average area of ​​all stomatal features in the surrounding region corresponding to each stomatal feature; Determine the ratio of the total area to the area of ​​the surrounding area, and determine the absolute value of the difference between the ratio and the preset ratio; The absolute value of the first area difference between the average area and the preset area is determined, and the second sub-quality score of the area surrounding each stomatal feature is determined based on the absolute value of the percentage difference and the absolute value of the first area difference. The first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

[0103] In one possible implementation of this application embodiment, when the first determining module 203 determines the first sub-quality score of each stomatal feature group based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group, it is specifically used for: Determine the absolute value of the second area difference between the area of ​​each pore feature and the preset area, and determine the absolute value of the third area difference between two pore features in each group of pore features; Determine the absolute value of the distance difference between each pore feature group and the preset distance; The first sub-quality score for each stomatal feature group is determined based on the absolute value of the second area difference, the absolute value of the third area difference, and the absolute value of the distance difference.

[0104] In one possible implementation of this application embodiment, when the first determining module 203 determines the first quality score of each region based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature, it is specifically used for: The sum of the first sub-quality scores is obtained by summing the first sub-quality scores of all stomatal feature groups in the surrounding area corresponding to each stomatal feature. The first target average is obtained by averaging the sum of all first sub-quality scores for each region. The average of all distances within each region is used to obtain the average value of the second target. The average of all second-sub-quality scores in each region is used to obtain the average of the third objective. The first quality score for each region is obtained based on the average of the first objective, the average of the second objective, and the average of the third objective.

[0105] In one possible implementation of this application embodiment, when the second determining module 204 determines the second quality score of each region on each cake base based on the first temperature, the second temperature, and the color of each region, it is specifically used for: Determine the absolute value of the temperature difference between the second temperature and the preset temperature, and determine the color difference between the color of each region and the preset color. Determine the temperature difference between the second temperature and the average first temperature of each region, and determine the absolute value of the second temperature difference between the temperature difference and a preset difference. The average first temperature is the average of the first sub-temperature and the second sub-temperature of each region. The second quality score for each region is determined based on the absolute value of the first temperature difference, the color difference, and the absolute value of the second temperature difference.

[0106] In one possible implementation of this application, a quality inspection system 20 for a food production line further includes: The control module is used to control the robotic arm to grab the target cake base when there is a target cake base with a total quality score lower than the preset score, so as to remove the target cake base from the detection area.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the quality inspection system 20 for a food production line described above can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0108] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of this application.

[0109] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0110] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0111] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0112] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0113] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0114] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, the embodiments of this application acquire the first temperature, color, and images of multiple areas on each cake base within the detection area. This facilitates detailed quality inspection of the cake base. Furthermore, dividing the cake base into multiple areas and inspecting each area separately ultimately yields the overall quality of the cake base, making quality inspection more accurate. The first temperature of each area is used to estimate the second temperature inside each area, thus facilitating quality inspection based on baking doneness. The images of each area reveal the surface porosity characteristics of each area. The porosity characteristics, to a certain extent, characterize the texture, doneness, and quality of the cake base. Therefore, the first quality score in terms of porosity can be accurately determined based on the porosity characteristics. The first surface temperature, the second internal temperature, and the color of each area also characterize baking doneness and quality. Therefore, the second quality score of each area can be accurately determined based on the first temperature, the second temperature, and the color. After determining the first and second quality scores of each area, the overall quality score of each cake base can be accurately determined, which is more detailed and accurate than quality inspection based solely on images.

[0115] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0116] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A quality inspection method for a food production line, characterized in that, include: Acquire the first temperature, color, and image of multiple regions on each cake base within the detection area; The second temperature of each cake base within each region is estimated based on the first temperature of each region. The porosity features of the surface of each region are determined based on the image of each region, and a first quality score for each region is determined based on the porosity features. A second quality score is determined for each area on each cake base based on the first temperature, the second temperature, and the color of each area. The total quality score for each cake base is determined based on the first and second quality scores for each region.

2. The quality inspection method for a food production line according to claim 1, characterized in that, The first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. The estimation of the second temperature within each region of each cake base based on the first temperature of each region includes: Calculate the first average of the first sub-temperature of all regions, and the second average of the second sub-temperature of all regions; The internal temperature calculation function is determined based on the first average value and the second average value. Substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region. Determine the average of the first and second estimated values, where the average estimated value is the second temperature within each region.

3. The quality inspection method for a food production line according to claim 1, characterized in that, The process of determining the porosity features of the surface of each region based on the image of each region, and determining a first quality score for each region based on the porosity features, includes: Determine the area of ​​each stomatal feature in each region and the location of each stomatal feature; Draw the area surrounding each stomatal feature with a preset radius, centered on each stomatal feature; Calculate the distance between stomatal features in each stomatal feature group, wherein the stomatal feature group includes the stomatal feature located at the center and any remaining stomatal feature in the surrounding area; The first sub-quality score of each stomatal feature group is determined based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Determine the average distance of all stomatal feature groups corresponding to each stomatal feature; Calculate the sum of the areas and the average area of ​​all stomatal features in the surrounding region corresponding to each stomatal feature; Determine the ratio of the total area to the area of ​​the surrounding region, and determine the absolute value of the difference between the ratio and the preset ratio; Determine the absolute value of the first area difference between the average area and the preset area, and determine the second sub-quality score of the area surrounding each stomatal feature based on the absolute value of the percentage difference and the absolute value of the first area difference. The first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

4. The quality inspection method for a food production line according to claim 3, characterized in that, The determination of the first sub-quality score for each stomatal feature group based on the distance between each stomatal feature group and the area of ​​each stomatal feature within each stomatal feature group includes: Determine the absolute value of the second area difference between the area of ​​each pore feature and the preset area, and determine the absolute value of the third area difference between two pore features in each group of pore features; Determine the absolute value of the distance difference between each pore feature group and the preset distance; The first sub-quality score for each stomatal feature group is determined based on the absolute value of the second area difference, the absolute value of the third area difference, and the absolute value of the distance difference.

5. The quality inspection method for a food production line according to claim 3, characterized in that, The determination of the first quality score for each region based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature includes: The sum of the first sub-quality scores is obtained by summing the first sub-quality scores of all stomatal feature groups in the surrounding area corresponding to each stomatal feature. The first target average is obtained by averaging the sum of all first sub-quality scores for each region. The average of all distances within each region is used to obtain the average value of the second target. The average of all second-sub-quality scores in each region is used to obtain the average of the third objective. The first quality score for each region is obtained based on the first target average, the second target average, and the third target average.

6. The quality inspection method for a food production line according to claim 1, characterized in that, The determination of the second quality score for each region on each cake base based on the first temperature, the second temperature, and the color of each region includes: Determine the absolute value of the temperature difference between the second temperature and the preset temperature, and determine the color difference between the color of each region and the preset color; Determine the temperature difference between the second temperature and the average first temperature of each region, and determine the absolute value of the second temperature difference between the temperature difference and a preset difference, wherein the first average temperature is the average of the first sub-temperature and the second sub-temperature of each region; The second quality score for each region is determined based on the absolute value of the first temperature difference, the color difference, and the absolute value of the second temperature difference.

7. The quality inspection method for a food production line according to claim 1, characterized in that, The method further includes: If a target cake base has a total quality score lower than a preset score, the robotic arm is controlled to grab the target cake base and move it out of the detection area.

8. A quality inspection system for a food production line, characterized in that, include: The data acquisition module is used to acquire the first temperature, color, and image of multiple areas on each cake base within the detection area; The temperature prediction module is used to predict the second temperature of each cake base within each region based on the first temperature of each region. The first determining module is used to determine the pore features of the surface of each region based on the image of each region, and to determine a first quality score for each region based on the pore features. The second determining module is used to determine the second quality score of each area on each cake base based on the first temperature, the second temperature, and the color of each area. The third determination module is used to determine the total quality score of each cake base based on the first quality score and the second quality score of each region.

9. A quality inspection system for a food production line according to claim 8, characterized in that, The first temperature of each region includes a first sub-temperature of the upper surface of the region and a second sub-temperature of the side surface of the region. When the temperature estimation module estimates the second temperature of each cake base within each region based on the first temperature of each region, it is specifically used for: Calculate the first average of the first sub-temperature of all regions, and the second average of the second sub-temperature of all regions; The internal temperature calculation function is determined based on the first average value and the second average value. Substitute the first and second sub-temperatures of each region into the internal temperature calculation function to obtain the first and second estimated values ​​within each region. Determine the average of the first and second estimated values, where the average estimated value is the second temperature within each region.

10. A quality inspection system for a food production line according to claim 8, characterized in that, When the first determining module determines the porosity features of the surface of each region based on the image of each region, and determines the first quality score of each region based on the porosity features, it is specifically used for: Determine the area of ​​each stomatal feature in each region and the location of each stomatal feature; Draw the area surrounding each stomatal feature with a preset radius, centered on each stomatal feature; Calculate the distance between stomatal features in each stomatal feature group, wherein the stomatal feature group includes the stomatal feature located at the center and any remaining stomatal feature in the surrounding area; The first sub-quality score of each stomatal feature group is determined based on the distance of each stomatal feature group and the area of ​​each stomatal feature in each stomatal feature group. Determine the average distance of all stomatal feature groups corresponding to each stomatal feature; Calculate the sum of the areas and the average area of ​​all stomatal features in the surrounding region corresponding to each stomatal feature; Determine the ratio of the total area to the area of ​​the surrounding region, and determine the absolute value of the difference between the ratio and the preset ratio; Determine the absolute value of the first area difference between the average area and the preset area, and determine the second sub-quality score of the area surrounding each stomatal feature based on the absolute value of the percentage difference and the absolute value of the first area difference. The first quality score of each region is determined based on the first sub-quality score of each stomatal feature group, the average distance of all stomatal feature groups corresponding to each stomatal feature, and the second sub-quality score of the surrounding region corresponding to each stomatal feature.

Images