Method, device and equipment for identifying years of pericarpium citri reticulatae and medium

Abstract

The invention discloses a pericarpium citri reticulatae year identification method, device and equipment and a medium. The problems of subjective deviation of manual observation and sample damage of chemical analysis are avoided, and the integrity of the pericarpium citri reticulatae is effectively guaranteed. Multi-modal features are extracted based on a pericarpium citri reticulatae surface image, texture trend features, wrinkle distribution features, oil chamber density features and oil chamber transmittance features of pericarpium citri reticulatae are fully extracted, and core appearance indexes of pericarpium citri reticulatae changing along with years are comprehensively covered. And inputting the multi-modal features into a preset recognition model for feature fusion to obtain the year of the dried orange peel, so that the problem of recognition errors caused by the defect that a single appearance feature is easily interfered by storage and processing conditions can be avoided, and the year recognition reliability of the dried orange peel is effectively improved.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of image recognition technology, and in particular to a method, apparatus, device, and medium for identifying the age of dried tangerine peel. Background Technology

[0002] As a traditional Chinese medicine and food ingredient, the medicinal value and flavor of dried tangerine peel increase with age, and the age directly determines its market value. Therefore, accurately identifying the age of dried tangerine peel has become an essential need in the industry, as it relates to the reputation of merchants and the rights and interests of consumers. The current mainstream identification method still relies mainly on traditional manual observation, which has obvious limitations: First, it is highly subjective. Manual identification depends on appearance features such as color and texture, but different people have different judgment standards, which can easily lead to misjudgments such as "different prices for the same peel". For example, light brown tangerine peel may be classified as 3 or 5 years old, with significant errors. Second, it is highly dependent on experience. Professional identification requires more than ten years of experience in observing samples, which is difficult for novices to master quickly. Moreover, the cost of training a qualified person to identify a tangerine peel exceeds 100,000 yuan, which is difficult for small and medium-sized businesses to afford. Storage temperature and humidity and processing technology can change the appearance of tangerine peel. For example, tangerine peel stored at high temperatures will darken in color and may be misjudged as high-age. It is impossible to accurately distinguish them by appearance alone. Besides manual observation, chemical analysis is another commonly used method, but it also has its shortcomings: chemical analysis requires the use of equipment such as high performance liquid chromatography, the cost of a single sample test exceeds 200 yuan, and the process takes 3-5 days, which is time-consuming and costly, and cannot meet the needs of batch testing; at the same time, the test will destroy the integrity of the tangerine peel, which will reduce the value of the product. The shortcomings of traditional methods have directly led to frequent market chaos, with counterfeiting practices such as "new peel, old label" being commonplace. Consumers find it difficult to distinguish between genuine and fake products. Currently, there is a lack of unified and quantifiable standards for identifying the age of aged tangerine peel, and there is an urgent need for efficient and low-cost methods for identifying the age of aged tangerine peel. Summary of the Invention

[0003] This application provides a method, apparatus, device, and medium for identifying the age of dried tangerine peel, which can effectively improve the reliability of identifying the age of dried tangerine peel.

[0004] In a first aspect, embodiments of this application provide a method for identifying the age of dried tangerine peel, including: Obtain an image of the surface of dried tangerine peel, and extract multimodal features based on the image of the dried tangerine peel surface; The multimodal features are input into a preset recognition model for feature fusion to obtain the year of the dried tangerine peel. The multimodal features include texture orientation features, wrinkle distribution features, oil cell density features, and oil cell transmittance features.

[0005] The method for identifying the age of dried tangerine peel according to the first aspect of this application has at least the following beneficial effects: It acquires surface images of the dried tangerine peel, avoiding subjective biases from manual observation and sample damage from chemical analysis. Identification through non-contact image acquisition effectively ensures the integrity of the dried tangerine peel. Multimodal features are extracted from the surface images of the dried tangerine peel, fully extracting texture direction features, wrinkle distribution features, oil cell density features, and oil cell translucency features, comprehensively covering the core appearance indicators of dried tangerine peel changes with age. These multimodal features are then input into a preset recognition model for feature fusion to obtain the age of the dried tangerine peel. By utilizing the synergistic effect of multi-dimensional features and through the comprehensive analysis and weight allocation of multi-dimensional feature information using model algorithms, the problem of identification errors caused by the susceptibility of single appearance features to interference from storage and processing conditions can be avoided, effectively improving the reliability of dried tangerine peel age identification.

[0006] According to some embodiments of the first aspect of this application, the extraction of multimodal features based on the surface image of the dried tangerine peel includes: Image processing of the tangerine peel surface image is performed based on the LBP algorithm to obtain the tangerine peel texture direction and LBP histogram; The texture direction features are determined based on the texture direction of the dried tangerine peel and the peak value of the LBP histogram.

[0007] According to some embodiments of the first aspect of this application, the extraction of multimodal features based on the surface image of the dried tangerine peel includes: Image segmentation was performed on the surface image of the dried tangerine peel to obtain the wrinkle skeleton and density heat map; Based on the fold skeleton and density heat map, the fold distribution characteristics are determined.

[0008] According to some embodiments of the first aspect of this application, the extraction of multimodal features based on the surface image of the dried tangerine peel includes: Microscopic image counting was performed on the surface image of the dried tangerine peel to determine the distribution of the number of oil-producing chambers; The distribution relationship of oil chamber number is normalized to obtain the oil chamber density characteristics.

[0009] According to some embodiments of the first aspect of this application, the extraction of multimodal features based on the surface image of the dried tangerine peel includes: Microscopic image labeling was performed on the surface image of the dried tangerine peel to obtain an oil cell distribution map; Calculate the red-yellow ratio of each oil cell in the oil cell distribution diagram to obtain the set of red-yellow ratios; The red-yellow ratio set is normalized to obtain the oil cell transmittance characteristics.

[0010] According to some embodiments of the first aspect of this application, the step of inputting the multimodal features into a preset recognition model for feature fusion to obtain the tangerine peel year includes: Based on the texture direction characteristics and the preset texture lookup table, the parameters for the first year are determined; Based on the fold distribution characteristics and the preset fold distribution comparison table, the parameters for the second year are determined; Based on the oil chamber density characteristics and the preset density ratio curve, the parameters for the third year are determined; Based on the oil cell transmittance characteristics and the year color formula, the parameters for the fourth year are determined; The year of dried tangerine peel is determined based on the first year parameter, the second year parameter, the third year parameter, and the fourth year parameter.

[0011] According to some embodiments of the first aspect of this application, the year color formula is as follows:

[0012] in, Characteristics of oil cell transmittance. This is the parameter for the fourth year.

[0013] Secondly, embodiments of this application provide an operation control device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the tangerine peel year identification method as described in the first aspect.

[0014] Thirdly, embodiments of this application provide an electronic device including the operation control device as described in the second aspect.

[0015] Fourthly, embodiments of this application provide a computer storage medium storing computer-executable instructions for causing a computer to perform the tangerine peel year identification method as described in the first aspect. Attached Figure Description

[0016] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0017] Figure 1 This is a flowchart of the steps of a method for identifying the age of dried tangerine peel provided in one embodiment of this application; Figure 2 This is a flowchart of the steps of a method for extracting texture direction features provided in another embodiment of this application; Figure 3 This is a flowchart of the steps of a method for extracting fold distribution features provided in another embodiment of this application; Figure 4This is a flowchart of the steps of a method for extracting oil cell density characteristics provided in another embodiment of this application; Figure 5 This is a flowchart of the steps of a method for extracting the transmittance characteristics of oil cells according to another embodiment of this application; Figure 6 This is a flowchart of the steps for determining the age of dried tangerine peel according to another embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It is understandable that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] As a traditional Chinese medicine and food ingredient, the medicinal value and flavor of dried tangerine peel increase with age, and the age directly determines its market value. Therefore, accurately identifying the age of dried tangerine peel has become an essential need in the industry, as it relates to the reputation of merchants and the rights and interests of consumers. The current mainstream identification method still relies mainly on traditional manual observation, which has obvious limitations: First, it is highly subjective. Manual identification depends on appearance features such as color and texture, but different people have different judgment standards, which can easily lead to misjudgments such as "different prices for the same peel". For example, light brown tangerine peel may be classified as 3 or 5 years old, with significant errors. Second, it is highly dependent on experience. Professional identification requires more than ten years of experience in observing samples, which is difficult for novices to master quickly. Moreover, the cost of training a qualified person to identify a tangerine peel exceeds 100,000 yuan, which is difficult for small and medium-sized businesses to afford. Storage temperature and humidity and processing technology can change the appearance of tangerine peel. For example, tangerine peel stored at high temperatures will darken in color and may be misjudged as high-age. It is impossible to accurately distinguish them by appearance alone. Besides manual observation, chemical analysis is another commonly used method, but it also has its shortcomings: chemical analysis requires the use of equipment such as high performance liquid chromatography, the cost of a single sample test exceeds 200 yuan, and the process takes 3-5 days, which is time-consuming and costly, and cannot meet the needs of batch testing; at the same time, the test will destroy the integrity of the tangerine peel, which will reduce the value of the product. The shortcomings of traditional methods have directly led to frequent market chaos, with counterfeiting practices such as "new peel, old label" being commonplace. Consumers find it difficult to distinguish between genuine and fake products. Currently, there is a lack of unified and quantifiable standards for identifying the age of aged tangerine peel, and there is an urgent need for efficient and low-cost methods for identifying the age of aged tangerine peel.

[0021] This application provides a method for identifying the age of dried tangerine peel. It acquires surface images of the peel, avoiding subjective biases from manual observation and sample damage from chemical analysis. Identification is performed through non-contact image acquisition, effectively ensuring the integrity of the peel. Multimodal features are extracted from the surface images, fully capturing texture direction, wrinkle distribution, oil cell density, and oil cell translucency, comprehensively covering the core appearance indicators of tangerine peel changes over time. These multimodal features are then input into a pre-defined recognition model for feature fusion to obtain the peel's age. By utilizing the synergistic effect of multi-dimensional features and employing a model algorithm for comprehensive analysis and weight allocation of multi-dimensional feature information, the method avoids the problem of single appearance features being susceptible to interference from storage and processing conditions, thus improving the reliability of tangerine peel age identification.

[0022] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0023] like Figure 1 As shown, Figure 1 This application provides a method for identifying the age of dried tangerine peel, which includes, but is not limited to, the following steps: Step S110: Obtain an image of the surface of dried tangerine peel and extract multimodal features based on the image of the surface of dried tangerine peel; Step S120: Input the multimodal features into the preset recognition model for feature fusion to obtain the tangerine peel's age; Among them, the multimodal features include texture orientation features, wrinkle distribution features, oil cell density features, and oil cell transmittance features.

[0024] Understandably, acquiring images of the tangerine peel surface avoids the subjective bias of manual observation and the sample damage caused by chemical analysis. Non-contact image acquisition for identification effectively ensures the integrity of the tangerine peel. Multimodal features are extracted from the tangerine peel surface images, fully extracting texture direction, wrinkle distribution, oil cell density, and oil cell translucency features. This comprehensively covers the core appearance indicators of tangerine peel changing with age. Specifically, texture direction gradually becomes more regular with aging, wrinkle distribution density and depth increase regularly, oil cell density decreases year by year with the loss of volatile oils, and oil cell translucency gradually increases due to internal component transformation. These multimodal features are then input into a preset recognition model for feature fusion to obtain the tangerine peel's age. Utilizing the synergistic effect of multi-dimensional features, through the comprehensive analysis and weight allocation of multi-dimensional feature information by the model algorithm, the problem of identification errors caused by the susceptibility of single appearance features to interference from storage and processing conditions can be avoided, effectively improving the reliability of tangerine peel age identification.

[0025] Understandably, moisture loss and organic matter transformation affect the texture characteristics of aged tangerine peel. The older the tangerine peel, the more complex its texture. Uneven loss of moisture and volatile oils affects the distribution of wrinkles, with older peels exhibiting deeper wrinkles. Moisture loss and physical shrinkage affect the density of oil cavities, with older peels showing higher density. The oxidation of volatile oils affects the translucency of the oil cavities, with older peels exhibiting more pronounced translucent color.

[0026] Additionally, refer to Figure 2 In one embodiment, Figure 1 Step S110 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S210: Based on the LBP algorithm, perform image processing on the surface image of dried tangerine peel to obtain the texture direction of dried tangerine peel and LBP histogram; Step S220: Determine the texture direction characteristics based on the texture direction of the tangerine peel and the peak value of the LBP histogram.

[0027] It is understandable that the regularity and orderliness of the surface structure of dried tangerine peel can be used to identify its age. Moisture loss and organic matter transformation affect the texture characteristics of the peel; the older the peel, the more complex, clearer, and more defined its texture. Image processing of the tangerine peel surface image using the LBP algorithm yields the texture direction and LBP histogram. The core advantage of the LBP algorithm lies in its ability to quantify the subtle texture changes that occur on the peel surface with age. The LBP histogram exhibits gray-level invariance. This means that even if the overall lighting conditions of the image change, as long as the relative gray-level relationship between pixels in a local area remains unchanged, the image features will remain stable. In actual tangerine peel image capture, subtle differences in lighting are inevitable. This characteristic of the LBP histogram effectively improves the robustness of subsequent texture direction feature extraction and reduces the interference of environmental factors on the recognition results. Then, based on the texture direction and the peak value of the LBP histogram, the texture direction features are determined.

[0028] Understandably, newer aged tangerine peel corresponds to a more concentrated and relatively narrow peak distribution in its LBP histogram, indicating a simpler texture. Older tangerine peel, on the other hand, has a finer and more regular surface texture, resulting in a more dispersed peak distribution and more burrs in its LBP histogram, indicating a more complex texture. For example, 1-year-old tangerine peel has a relatively fine and regular texture with weak granularity and large gaps; 10-year-old tangerine peel has a coarser texture with more pronounced bumps and distinct granules, exhibiting further cracking on the original coarse texture. In this case, the LBP histogram will show more dispersed peaks and more burrs. By analyzing the morphology of the LBP histogram (such as peak concentration and distribution range), the intuitive perception of the tangerine peel's texture can be transformed into objective data, revealing texture characteristics and providing crucial information for determining the age of the tangerine peel.

[0029] Additionally, refer to Figure 3 In one embodiment, Figure 1 Step S110 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S310: Perform image segmentation on the surface image of dried tangerine peel to obtain the wrinkle skeleton and density heat map; Step S320: Determine the fold distribution characteristics based on the fold skeleton and density heat map.

[0030] This can be understood as performing image segmentation on an image of the dried tangerine peel surface to accurately extract the wrinkle contours, resulting in a wrinkle skeleton and a density heatmap. The wrinkle skeleton clearly represents the direction, length, and number of branches of the wrinkles, accurately representing the complexity of the texture. The density heatmap represents the concentration of wrinkles in different regions; a higher coefficient of variation for area indicates a higher directional distribution of wrinkles, which assesses the regularity of the texture and accurately represents the uniformity of wrinkle distribution. Based on the wrinkle skeleton and density heatmap, the wrinkle distribution characteristics are determined. The wrinkle distribution characteristics obtained based on the quantified wrinkle skeleton and density heatmap can effectively improve the reliability of dried tangerine peel age identification.

[0031] Understandably, the longer the tangerine peel is aged, the more disordered its wrinkles become. Uneven water loss leads to variations in the density of the wrinkles, resulting in a less uniform distribution of wrinkles.

[0032] It should be noted that the fold skeleton can be obtained by extracting the skeleton from the surface image of dried tangerine peel using the Zhang-Suen algorithm. In the extracted fold skeleton, each skeleton pixel (coordinates (x, y)) represents the position through which a fold passes. The density heatmap can be generated using the kernel density estimation method.

[0033] Additionally, refer to Figure 4 In one embodiment, Figure 1 Step S110 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S410: Perform microscopic image counting on the surface image of dried tangerine peel to determine the distribution relationship of the number of oil-producing chambers; Step S420: Normalize the distribution relationship of oil chamber number to obtain oil chamber density characteristics.

[0034] Understandably, performing microscopic image counting on the surface of dried tangerine peel can effectively ensure the reliability of the data and determine the distribution relationship of the number of oil cells. Normalizing the distribution relationship of the number of oil cells makes the oil cell data uniform, avoiding the influence of dimensions caused by different physical sizes or image acquisition parameters, and obtaining the oil cell density characteristics can effectively improve the speed and accuracy of subsequent data processing.

[0035] It is understood that, in one embodiment, the integrity and density of oil cells are positively correlated with the content of active substances such as hesperidin and volatile oils in dried tangerine peel, and are important indicators for evaluating the quality of dried tangerine peel. Aged dried tangerine peel typically exhibits higher oil cell density characteristics. For example, 1-year-old dried tangerine peel has fewer oil cells per unit area, while 10-year-old dried tangerine peel has more. The surface image of 1-year-old dried tangerine peel shows relatively full and evenly distributed oil cells; after image processing, the number of oil cells in 1-year-old dried tangerine peel is 248, the oil cell density is 200 per megapixel, and the oil cell radius is concentrated between 16 and 20 confidence levels. The surface image of 10-year-old dried tangerine peel shows relatively wrinkled and unevenly distributed oil cells; after image processing, the number of oil cells in 10-year-old dried tangerine peel is 418, the oil cell density is 248 per megapixel, and the oil cell radius is concentrated between 10 and 14 confidence levels.

[0036] Additionally, refer to Figure 5 In one embodiment, Figure 1 Step S110 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S510: Microscopic image marking is performed on the surface image of dried tangerine peel to obtain an oil cell distribution map; Step S520: Calculate the red-yellow ratio of each oil cell in the oil cell distribution map to obtain the red-yellow ratio set; Step S530: Normalize the red-yellow ratio set to obtain the oil cell transmittance characteristics.

[0037] This can be understood as follows: Microscopic image labeling is performed on the surface of the dried tangerine peel to obtain an oil cell distribution map. Then, the red-yellow ratio of each oil cell in the distribution map is calculated to obtain a set of red-yellow ratios. The age of the dried tangerine peel is determined by the correlation between longer aging time and higher oxidation levels, corresponding to lower light transmittance in the oil cells. The red-yellow ratio set is then normalized to improve data reliability and obtain the light transmittance characteristics of the oil cells.

[0038] It should be noted that after obtaining the oil cell distribution map, the RGB values ​​of all pixels in each oil cell region can be extracted from the corresponding position in the original color micrograph based on the oil cell distribution map. The average gray value of all pixels in the R (red) channel and G (green) channel of the region is then calculated to obtain the red-yellow ratio of the oil cell.

[0039] Understandably, in one embodiment, the translucency characteristics of the oil cells of 1-year-old tangerine peel are that the translucency is yellowish, the red-yellow ratio is 0.663, and the color distribution is mainly concentrated below 0.8, with a uniform color distribution. The translucency characteristics of the oil cells of 10-year-old tangerine peel are that the translucency is dark reddish and the translucency is significantly lower than that of 1-year-old peel, the red-yellow ratio is 0.799, and the color distribution is mainly concentrated above 0.8, with a more concentrated color distribution.

[0040] Additionally, refer to Figure 6 In one embodiment, Figure 1 Step S120 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S610: Determine the parameters for the first year based on the texture direction characteristics and the preset texture reference table; Step S620: Determine the parameters for the second year based on the fold distribution characteristics and the preset fold distribution comparison table; Step S630: Determine the parameters for the third year based on the oil chamber density characteristics and the preset density ratio curve; Step S640: Determine the parameters for the fourth year based on the oil cell transmittance characteristics and the year color formula; Step S650: Determine the year of the tangerine peel based on the parameters of the first year, the second year, the third year, and the fourth year.

[0041] Understandably, the first year parameter is determined based on texture direction characteristics and a preset texture reference table. For example, the preset texture reference table is a comparison chart of texture length and direction for different years, and the texture direction characteristics represent the texture length and direction of the tangerine peel surface. The second year parameter is determined based on wrinkle distribution characteristics and a preset wrinkle distribution reference table. For example, the wrinkle distribution characteristics represent the number of wrinkles on the tangerine peel surface, and the preset wrinkle distribution reference table is a comparison table of the number of wrinkles and the year of the tangerine peel. The third year parameter is determined based on oil cell density characteristics and a preset density ratio curve. For example, the oil cell density characteristics represent the number of oil cells per unit area on the tangerine peel surface, and the preset density ratio curve is a comparison curve showing the number of oil cells per unit area on the tangerine peel surface increasing with age. The fourth year parameter is determined based on oil cell translucency characteristics and the year color formula. Based on quantified data, the visualization, standardization, and reliability of tangerine peel year identification can be effectively improved. Based on the parameters of the first year, the second year, the third year, and the fourth year, and by leveraging the synergistic effect of multi-dimensional features, the model algorithm comprehensively analyzes and assigns weights to the multi-dimensional feature information. This avoids the problem of identification errors caused by the susceptibility of single appearance features to interference from storage and processing conditions, and effectively improves the reliability of tangerine peel year identification.

[0042] It is understood that, in one embodiment, the average value can be calculated based on the first year parameter, the second year parameter, the third year parameter, and the fourth year parameter, and then the year of the tangerine peel can be determined based on a preset mapping table and the average value.

[0043] In one embodiment, the year color formula is:

[0044] in, Characteristics of oil cell transmittance. This is the parameter for the fourth year.

[0045] In addition, one embodiment of this application provides an operation control device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0046] The processor and memory can be connected via a bus or other means.

[0047] The non-transient software program and instructions required to implement the tangerine peel year recognition method of the above embodiments are stored in memory. When executed by a processor, the tangerine peel year recognition method of the above embodiments is executed, for example, the method described above is executed. Figure 1 Method steps S110 to S120 in the middle Figure 2 Method steps S210 to S220 in the middle Figure 3Method steps S310 to S320 in the middle Figure 4 Method steps S410 to S420 in the middle Figure 5 Method steps S510 to S530 in the middle Figure 6 Method steps S610 to S650.

[0048] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0049] Furthermore, one embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or controller, for example, by a processor in the above-described operation control device embodiment, causing the processor to execute the tangerine peel year identification method in the above-described embodiment, for example, to execute the above-described... Figure 1 Method steps S110 to S120 in the middle Figure 2 Method steps S210 to S220 in the middle Figure 3 Method steps S310 to S320 in the middle Figure 4 Method steps S410 to S420 in the middle Figure 5 Method steps S510 to S530 in the middle Figure 6Method steps S610 to S650 are described above. Those skilled in the art will understand that all or some of the steps in the methods disclosed above, and the system, can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0050] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0051] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for identifying the age of dried tangerine peel, characterized in that, include: Obtain an image of the surface of dried tangerine peel, and extract multimodal features based on the image of the dried tangerine peel surface; The multimodal features are input into a preset recognition model for feature fusion to obtain the year of the dried tangerine peel. The multimodal features include texture orientation features, wrinkle distribution features, oil cell density features, and oil cell transmittance features.

2. The method for identifying the age of dried tangerine peel according to claim 1, characterized in that, The extraction of multimodal features based on the surface image of the dried tangerine peel includes: Image processing of the tangerine peel surface image is performed based on the LBP algorithm to obtain the tangerine peel texture direction and LBP histogram; The texture direction features are determined based on the texture direction of the dried tangerine peel and the peak value of the LBP histogram.

3. The method for identifying the age of dried tangerine peel according to claim 1, characterized in that, The extraction of multimodal features based on the surface image of the dried tangerine peel includes: Image segmentation was performed on the surface image of the dried tangerine peel to obtain the wrinkle skeleton and density heat map; Based on the fold skeleton and density heat map, the fold distribution characteristics are determined.

4. The method for identifying the age of dried tangerine peel according to claim 1, characterized in that, The extraction of multimodal features based on the surface image of the dried tangerine peel includes: Microscopic image counting was performed on the surface image of the dried tangerine peel to determine the distribution of the number of oil-producing chambers; The distribution relationship of oil chamber number is normalized to obtain the oil chamber density characteristics.

5. The method for identifying the age of dried tangerine peel according to claim 1, characterized in that, The extraction of multimodal features based on the surface image of the dried tangerine peel includes: Microscopic image labeling was performed on the surface image of the dried tangerine peel to obtain an oil cell distribution map; Calculate the red-yellow ratio of each oil cell in the oil cell distribution diagram to obtain the set of red-yellow ratios; The red-yellow ratio set is normalized to obtain the oil cell transmittance characteristics.

6. The method for identifying the age of dried tangerine peel according to claim 1, characterized in that, The step of inputting the multimodal features into a preset recognition model for feature fusion to obtain the tangerine peel's age includes: Based on the texture direction characteristics and the preset texture lookup table, the parameters for the first year are determined; Based on the fold distribution characteristics and the preset fold distribution comparison table, the parameters for the second year are determined; Based on the oil chamber density characteristics and the preset density ratio curve, the parameters for the third year are determined; Based on the oil cell transmittance characteristics and the year color formula, the parameters for the fourth year are determined; The year of dried tangerine peel is determined based on the first year parameter, the second year parameter, the third year parameter, and the fourth year parameter.

7. The method for identifying the age of dried tangerine peel according to claim 6, characterized in that, The formula for the year's color is: in, The light transmittance characteristics of the oil chamber, This refers to the parameter for the fourth year.

8. An operation control device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for identifying the age of dried tangerine peel as described in any one of claims 1 to 7.

9. An electronic device, characterized in that, Includes the operation control device as described in claim 8.

10. A computer storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method for identifying the age of dried tangerine peel as described in any one of claims 1 to 7.

Images