A fruit traceability method and system based on low-field magnetic nuclear magnetic resonance

Abstract

The application relates to the technical field of traceability identification, in particular to a fruit traceability method and system based on low-field magnetic nuclear magnetic resonance, which comprises the following steps: identifying the color classification and the shape feature of fruits according to the image of the fruits; performing low-field magnetic nuclear magnetic resonance on the pulp separated from the fruits, and determining the sweetness and the acidity of the pulp according to the low-field magnetic nuclear magnetic resonance signal; obtaining the sweetness proportion range and the acidity proportion range according to the color classification and the shape feature; judging whether the sweetness is located in the sweetness proportion range and whether the acidity is located in the acidity proportion range, if not, determining that the appearance of the fruits is fake, and if yes, determining the appearance origin of the fruits; obtaining the element content of the core separated from the fruits, and determining the element origin of the fruits according to the element content; and determining whether the origin of the fruits is fake according to whether the appearance origin and the element origin correspond to each other. The application realizes accurate detection of the appearance and the origin of fake fruits by using a small amount of fruit samples.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traceability identification, and in particular to a fruit traceability method and system based on low-field magnetic nuclear magnetic resonance. BACKGROUND

[0002] Low-field nuclear magnetic resonance technology (LF-NMR) is a technology that makes low-energy atomic nuclei magnetic moments absorb the energy provided by the alternating field strength under the interaction of constant field strength and alternating field strength, so as to jump to a high-energy state and generate a nuclear magnetic resonance signal. In the process of fruit detection, the nuclear magnetic resonance signal can reflect the distribution and state of hydrogen atoms inside the fruit sample, and the water, sugar and other components in the fruit all contain hydrogen atoms, and the water and sugar in the fruit are related to whether browning, rotting and damage occur inside the fruit. Therefore, low-field nuclear magnetic resonance technology can be used for fruit quality detection.

[0003] In the sales link, although the imported fruits have similar appearance to domestic fruits, the prices are quite different due to the reasons of import tariff and transportation cost. Therefore, the traceability determination of the origin of the fruits has great significance for regulating the market. Moreover, the origin and traceability of the fruits are regulated by the European Union laws and regulations and the food safety law of China, which requires the establishment of a traceability system for fruit safety.

[0004] At present, the main methods of fruit origin fraud are: adding dyes, preservatives and sweeteners to make the fruit flesh of domestic low-priced fruits close to the fruit flesh of high-priced imported fruits, which is difficult to distinguish the fake fruits from the appearance and taste; and label fraud, falsely labeling the production date, shelf life, origin and other information of the fruits to deceive consumers.

[0005] Therefore, how to realize the comprehensive traceability judgment of the above-mentioned appearance fraud and origin fraud by using a small amount of high-priced imported fruit samples, and accurately judge different fruit fraud methods, is a technical problem to be solved at present. SUMMARY

[0006] Therefore, the present application provides a fruit traceability method and system based on low-field magnetic nuclear magnetic resonance, which realizes rapid judgment and detection of the appearance fraud of fruits with imprecise addition of dyes, preservatives and sweeteners by using the image and pulp low-field magnetic resonance signal of the fruits, and realizes accurate detection of the origin fraud of a small amount of fruit samples by using the comprehensive judgment of the element content, image and low-field magnetic resonance signal of the fruit core.

[0007] To achieve the above purpose, the present application provides a fruit traceability method based on low-field magnetic nuclear magnetic resonance, comprising:

[0008] Obtaining an image of the fruit, identifying the color classification and shape features of the fruit according to the image;

[0009] The flesh separated from the fruit is subjected to low-field magnetic nuclear magnetic resonance, low-field magnetic resonance signals are obtained, and sweetness and acidity of the flesh are determined according to the low-field magnetic resonance signals;

[0010] The sweetness proportion range and the acidity proportion range are derived according to the color classification and the shape feature;

[0011] It is determined whether the sweetness is located in the sweetness proportion range and whether the acidity is located in the acidity proportion range, if not, it is determined that the fruit is appearance counterfeit, and if yes, the appearance origin of the fruit is determined;

[0012] The element content of the fruit core separated from the fruit is obtained, and the element origin of the fruit is determined according to the element content;

[0013] It is determined whether the fruit is origin counterfeit according to whether the appearance origin and the element origin correspond.

[0014] Further, the step of obtaining the sweetness proportion range and the acidity proportion range comprises:

[0015] The variety purity, maturity and freshness of the fruit are determined according to the color classification and the shape feature;

[0016] The initial sweetness proportion range and the initial acidity proportion range are determined according to the variety purity and the maturity;

[0017] The initial sweetness proportion range and the initial acidity proportion range are adjusted according to the freshness to obtain the sweetness proportion range and the acidity proportion range.

[0018] Further, the step of obtaining the color classification and the shape feature comprises:

[0019] The shape feature and the color classification of the fruit in the image are determined through a neural network-based image recognition model;

[0020] The subvariety of the fruit is determined according to the color category, stem shape and epidermis shape;

[0021] The shape feature includes the stem shape, stem brightness, the epidermis shape and epidermis glossiness, and the color classification includes the color category, characteristic color area and characteristic color value.

[0022] Further, the process of determining the variety purity of the fruit according to the color classification and the shape feature is:

[0023] The variety purity is determined through an image similarity model based on the color category, the stem shape, the epidermis shape and the subvariety corresponding to the origin historical picture library.

[0024] Further, the step of determining the initial sweetness ratio range and the initial acidity ratio range according to the variety purity and the maturity includes:

[0025] The initial sweetness ratio range and the initial acidity ratio range are determined by a genetic algorithm based on the variety purity and the maturity.

[0026] The maturity is an area ratio of the area of the characteristic chroma region to an area standard value, and the variety purity is a chroma ratio of the characteristic chroma value to a chroma standard value.

[0027] In the above scheme, the determination of the ratio range for the acidity and sweetness judgment considering the fruit sample situation and the difference between the typical situations of the subdivided varieties is realized, so that the judgment of the appearance forgery of fruits added with various dyes, preservatives and sweeteners to fake the production place is more accurate.

[0028] Further, the step of determining the freshness of the fruit according to the color classification and the external shape features includes:

[0029] The stem brightness degree is corresponded to a stem brightness degree grade, the skin luster degree is corresponded to a luster degree grade, and the freshness is determined according to the stem brightness degree grade and the luster degree grade.

[0030] Further, the process of determining the sweetness and acidity of the fruit pulp according to the low-field magnetic resonance signal is:

[0031] The sweetness corresponding to the low-field magnetic resonance signal is determined by a model representing the correlation between the low-field magnetic resonance signal of a unit mass and the sweetness of the fruit.

[0032] The acidity corresponding to the low-field magnetic resonance signal is determined by a fitting model representing the correlation between the transverse relaxation time and the acidity of the fruit.

[0033] In the above scheme, the high-resolution signal of low-field magnetic nuclear magnetic resonance is utilized, and even if a small amount of dye, preservative or sweetener is added to the fruit, it can be accurately detected.

[0034] Further, the elements used to determine the element origin of the fruit include potassium, cobalt, rubidium, nickel, manganese, calcium, hydrogen stable isotopes and oxygen stable isotopes.

[0035] The element origin is determined by cluster analysis of the element content.

[0036] The appearance origin is an intercontinental origin, and the element origin is a national origin.

[0037] determine whether the geographical range of the appearance origin includes the geographical range of the element origin, if yes, the fruit does not exist origin fraud, if not, the fruit exists origin fraud.

[0038] The application also provides a fruit traceability system based on low-field magnetic nuclear magnetic resonance, which carries the fruit traceability method based on low-field magnetic nuclear magnetic resonance.

[0039] a visual sensor configured to acquire an image of the fruit;

[0040] a low-field magnetic resonance analyzer configured to acquire a low-field magnetic resonance signal of the fruit core by low-field magnetic resonance;

[0041] an inductively coupled plasma mass spectrometer configured to acquire an element content of the fruit core;

[0042] a control device in communication with the visual sensor, the inductively coupled plasma mass spectrometer, and the low-field magnetic resonance analyzer, configured to determine whether the fruit is appearance fake and appearance origin according to the image and the low-field magnetic resonance signal, and determine whether the fruit is origin fake according to the appearance origin and the element content.

[0043] Further, the control device carries a detection system cloud platform to generate a fruit detection report including the image, the low-field magnetic resonance signal, the element content, whether the appearance is fake, and whether the origin is fake.

[0044] In the above scheme, the centralized management of the detection equipment by the cloud platform realizes the rapidization and standardization of the detection process.

[0045] Compared with the prior art, the application has the advantages that,

[0046] 1. The image of the fruit and the low-field magnetic resonance signal of the fruit pulp realize rapid judgment and detection of appearance fake of the fruit with imprecise addition of dyestuff, preservative, and sweetener, and the element content of the fruit core and the image and the low-field magnetic resonance signal realize accurate detection of origin fake using a small amount of fruit sample.

[0047] 2. The determination of the proportion range for acidity and sweetness judgment considering the fruit sample situation and the typical situation difference of the subdivided varieties makes the judgment of appearance fake and origin fake of the fruit with multiple dyestuff, preservative, and sweetener more accurate.

[0048] 3. The high-resolution signal of low-field magnetic nuclear magnetic resonance is used to realize accurate and rapid detection of the fruit even if a small amount of dyestuff, preservative, or sweetener is added.

[0049] 4. The centralized management of the detection equipment through the cloud platform realizes the rapidization and standardization of the detection process. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 A schematic diagram of the general process of the fruit traceability method based on low-field magnetic nuclear magnetic resonance of the embodiment of the application;

[0051] Figure 2 A schematic diagram of the judgment process of the production place fraud of the embodiment of the application;

[0052] Figure 3 A schematic diagram of the correlation model fitting of the low-field magnetic resonance signal of the unit mass and the sweetness of the fruit, taking the carlberry as an example, of the embodiment of the application;

[0053] Figure 4 A schematic diagram of the general structure of the fruit traceability system based on low-field magnetic nuclear magnetic resonance of the embodiment of the application. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present application clearer, the present application will be further described below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0055] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0056] It should be noted that in the description of the present application, the terms indicating the direction or position relationship such as "upper", "lower", "left", "right", "inner", "outer" and the like are based on the direction or position relationship shown in the drawings, which is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0057] In addition, it should also be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through an intermediate medium, or the internal communication of two elements. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances.

[0058] As Figures 1 to 4As shown, the present application provides a fruit traceability method and system based on low-field magnetic nuclear magnetic resonance, which realizes rapid judgment and detection of appearance forgery of fruits with inaccurate dyeing agent, preservative and sweetener by using images and low-field magnetic resonance signals of fruit pulp, and realizes accurate detection of origin forgery by using a small amount of fruit samples through comprehensive judgment of element content, images and low-field magnetic resonance signals of fruit kernels.

[0059] wherein, Figure 1 It is a general flowchart of the fruit traceability method based on low-field magnetic nuclear magnetic resonance of the embodiment of the present application. Figure 2 It is a judgment flowchart of origin forgery of the embodiment of the present application. Figure 3 It is a fitting diagram of the correlation model of low-field magnetic resonance signals of a unit mass and fruit sweetness of the embodiment of the present application. Figure 4 It is a general structure diagram of the fruit traceability system based on low-field magnetic nuclear magnetic resonance of the embodiment of the present application.

[0060] As Figures 1 to 4 shown, the present embodiment proposes a fruit traceability method and system based on low-field magnetic nuclear magnetic resonance, which includes: acquiring images of fruits, identifying color classification and shape features of the fruits according to the images; performing low-field magnetic nuclear magnetic resonance on fruit pulp separated from the fruits, acquiring low-field magnetic resonance signals, and determining sweetness and acidity of the fruit pulp according to the low-field magnetic resonance signals; obtaining a sweetness proportion range and an acidity proportion range according to the color classification and the shape features; judging whether the sweetness is within the sweetness proportion range and whether the acidity is within the acidity proportion range, and if not, determining that the fruits have appearance forgery, and if so, determining the appearance origin of the fruits; acquiring element content of fruit kernels separated from the fruits, determining the element origin of the fruits according to the element content; and determining whether the fruits have origin forgery according to whether the appearance origin and the element origin correspond.

[0061] It should be noted that the fruits described in the present embodiment are all stone fruits, and their scientific name is drupe.

[0062] It should be noted that when it is determined that the fruits have appearance forgery, the detection can be stopped, it is determined that the fruit quality / origin traceability is unqualified, and then more complex element content detection of the fruits is not needed, thereby accelerating the detection efficiency.

[0063] Further, the step of acquiring the sweetness proportion range and the acidity proportion range includes: determining variety purity, maturity and freshness of the fruits according to the color classification and the shape features; determining an initial sweetness proportion range and an initial acidity proportion range according to the variety purity and the maturity; and adjusting the initial sweetness proportion range and the initial acidity proportion range according to the freshness to obtain the sweetness proportion range and the acidity proportion range.

[0064] Further, the step of acquiring the color classification and the shape feature comprises: determining the shape feature and the color classification of the fruit in the image through a neural network-based image recognition model; and determining the variety of the fruit according to the color category, stem shape and skin shape; wherein the shape feature comprises the stem shape, stem brightness, the skin shape and skin glossiness, and the color classification comprises the color category, characteristic color area and characteristic color value.

[0065] Specifically, the image recognition model is implemented through a YOLOv8-based convolutional neural network and a Kitti dataset. YOLOv8 is the next generation algorithm model developed by Ultralytics Company after YOLOv5 algorithm, and currently supports image classification, object detection and instance segmentation tasks. The image recognition model comprises a new backbone network, a new Ancher-Free detection head and a new loss function. Therefore, the embodiment uses the YOLOv8 object detection algorithm to realize a fruit database system based on the YOLOV8 model and the Kitti dataset, and uses the Pyside6 library to build an interface system to complete the development of the fruit detection page. By adjusting the detection confidence threshold and the IOU threshold, the accuracy of the detection is more suitable.

[0066] The Kitti dataset used in the embodiment labels six categories of fruit, including stem shape, stem brightness, skin shape, skin glossiness, color category and fruit variety, and the dataset contains a total of 9450 images. The categories in the dataset have a large number of rotations and different lighting conditions, which helps to train a more robust detection model. The Kitti detection and recognition dataset used in the experiment contains 8000 training images and 1450 validation images. Since the YOLOv8 algorithm has a size limit for input images, all images need to be adjusted to the same size. In order to reduce the distortion of the images as much as possible without affecting the detection accuracy, all images are adjusted to a size of 640x640 while maintaining the original width-height ratio. In addition, in order to enhance the generalization ability and robustness of the model, data augmentation techniques are used, including random rotation, scaling, cropping and color transformation, to expand the dataset and reduce the risk of overfitting. After the image recognition model identifies the fruit variety, it is run again to identify the characteristic color area and the characteristic color value of the fruit.

[0067] Further, the step of determining the purity of the variety of the fruit according to the color classification and the shape feature comprises: comparing the color category, the stem shape and the skin shape with the corresponding origin historical image library of the variety through an image similarity model to determine the purity of the variety.

[0068] Specifically, each fruit variety is provided with an image similarity model, and the image library of each image similarity model has fruit images of multiple different maturity and freshness. The image similarity model is implemented by using the image encoder of the CLIP model: inputting the image into the image encoder of the CLIP model to obtain an image embedding. The cosine similarity between the image embedding and all image embeddings of the origin historical picture library is calculated, and the cosine similarity is taken as the fruit similarity. The cosine similarity is the product of the image vector of the image embedding and the image vector of the image embedding, divided by the vector length.

[0069] The variety purity refers to the genetic purity of the fruit variety, that is, the consistency of its genetic characteristics with a specific variety. The higher the variety purity of the fruit, the closer the sweetness and acidity of the fruit to the purebred fruit. Further, the sweetness ratio range, the acidity ratio range, and the individual condition of the fruit are obtained.

[0070] Further, the step of determining the initial sweetness ratio range and the initial acidity ratio range according to the variety purity and the maturity includes: determining the initial sweetness ratio range and the initial acidity ratio range according to the variety purity and the maturity by a genetic algorithm; wherein the maturity is an area ratio of the characteristic chroma area to an area standard value, and the variety purity is a chroma ratio of the characteristic chroma value to a chroma standard value.

[0071] It can be understood that as the fruit matures, its color gradually changes from green to purple, red, yellow or white characteristic of the fruit variety, and the color gradually becomes uniform, the flesh gradually becomes plump and juicy, and the sweetness gradually reaches the highest value. Generally speaking, the deeper the color of the fruit, the higher the sweetness (sugar content). Therefore, by the ratio of the characteristic chroma area to the area standard value and the ratio of the characteristic chroma value to the chroma standard value, the maturity of the fruit can be reflected, and the higher the maturity of the fruit, the higher the sweetness.

[0072] According to the detection of fruits of multiple different variety purities in the growth process by a handheld sugar detector and a handheld acidity detector, it is found that the maturity, variety purity, and sweetness, acidity have a linear corresponding relationship curve that can be fitted, and there is a linear corresponding relationship. Therefore, it is inferred that the variety purity, the area ratio, and the chroma ratio can be used to determine the sweetness ratio range and the acidity ratio range of fruits of different maturity.

[0073] Specifically, the sweetness and acidity of the fruit of the recorded variety purity during the growth process are recorded, and a genetic algorithm (BP) is input. Through the evolution calculation of the genetic algorithm, the optimal objective function is obtained. For example, by taking multiple sets of sweetness, fruit similarity, area ratio of area standard value of characteristic color area, and color ratio of characteristic color value and color standard value as training parameters, the optimal objective function such as y1=arcctg(cos(x1 / (x1+x2+0.0001))+0.0023)×cos(x1+x2+x3+0.0015)) and y2=arcctg(cos(x1 / (x1+x2+0.0025))+0.0023)×cos(x1+x2+x3+0.0035)) can be obtained, wherein y1 is a predicted sweetness standard value, y2 is a predicted acidity standard value, x1, x2, and x3 are the variety purity, the area ratio, and the color ratio, respectively. The predicted sweetness standard value plus or minus a set value is used as the initial sweetness proportion range of the sweetness, and the set value is preferably 5%, which can also be adjusted according to the typical degree of the fruit variety, and the maximum should not exceed 10%. Similarly, the predicted acidity standard value plus or minus a set value is used as the initial acidity proportion range of the sweetness, and the set value is preferably 7%, which can also be adjusted according to the typical degree of the fruit variety, and the maximum should not exceed 15%.

[0074] Specifically, the sub-varieties of the fruit correspond to color categories, stem shapes, and skin shapes, respectively. The color category of the red Fuji apple is red, the stem shape is woody, and the skin shape is smooth. The color category of the green apple is green, the stem shape is purple-brown, and the skin shape is oblate. The color category of the Gala apple is yellow, the stem shape is green and smooth, and the skin shape is waxy.

[0075] The sub-varieties can also be sub-varieties of cherries, such as the Santina variety, which has a color category of deep red or purple black, no stem shape data, and a skin shape of heart-shaped and slightly flat (since the characteristics of Santina are obvious and clear, it can be distinguished only by color category and skin shape). The Regina variety has a color category of brown red, jujube red, or yellow red, no stem shape data, and a skin shape of larger round. The Brooks variety has a color category of light red, a straight stem shape, and a skin shape of smaller oval. The Rainier variety has a color category of red and yellow or pink, no stem shape data, and a skin shape of larger ingot shape. The Lapin variety has a color category of brown red and a skin shape of medium. The Bing variety has a color category of deep red, a long stem shape, and a skin shape of medium round.

[0076] For example, the ratio of sweetness of the Santina variety ranges from 14 to 22, in grams per 100 grams of pulp. The ratio of acidity of the Santina variety ranges from 7 to 13, in grams per 100 grams of pulp.

[0077] Further, according to the color classification and the shape feature, the step of determining the freshness of the fruit comprises: corresponding the stem vividness to a stem vividness grade, corresponding the skin glossiness to a glossiness grade, and determining the freshness according to the stem vividness grade and the glossiness grade.

[0078] Specifically, the chroma ratio is an RGB ratio of the characteristic chroma value to a chroma standard value, and the stem vividness is an RGB ratio of the RGB average value of the stem color of the fruit in the image to a standard tender green color, in percentage. The skin glossiness is the reflectivity of the surface of the fruit, in percentage.

[0079] Specifically, the stem vividness grade comprises stem grade one to stem grade five in ascending order, with the ratio being 40% to 44%, 45% to 49%, and more than 60% in ascending order. The glossiness grade comprises glossiness grade one to glossiness grade five in ascending order, with the ratio being 0% to 3%, 4% to 7%, and more than 16% in ascending order. When the stem vividness grade is lower than stem grade two and the glossiness grade is lower than glossiness grade two, the freshness grade is determined to be low. When the stem vividness grade is greater than or equal to stem grade three or the glossiness grade is greater than or equal to glossiness grade three, the freshness grade is determined to be medium. When the stem vividness grade is greater than or equal to stem grade three and the glossiness grade is greater than or equal to glossiness grade three, the freshness grade is determined to be high. For the low freshness grade, the initial sweetness ratio range is reduced by 2 to obtain the sweetness ratio range, and the initial acidity ratio range is reduced by 0.5 to obtain the acidity ratio range. For the medium freshness grade, the initial sweetness ratio range and the initial acidity ratio range are not changed to obtain the sweetness ratio range and the acidity ratio range. For the high freshness grade, the sweetness ratio range is increased by 2, and the acidity ratio range is increased by 0.5, to obtain the sweetness ratio range and the acidity ratio range. It should be noted that the above process is preferably applied to the traceability detection of cherries.

[0080] Further, according to the low-field magnetic resonance signal, the step of determining the sweetness and the acidity of the pulp comprises: determining the sweetness corresponding to the low-field magnetic resonance signal through a model representing the correlation between the low-field magnetic resonance signal per unit mass and the sweetness of the fruit; and determining the acidity corresponding to the low-field magnetic resonance signal through a fitting model representing the correlation between the transverse relaxation time and the acidity of the fruit.

[0081] Specifically, the sweetness of the fruit is detected by using a sugar content detector, and a relationship between the amplitude of the low-field magnetic resonance signal (NMR) and the sweetness of the fruit is determined as an inverse function, i.e., a correlation model, specifically y=-25x+88. In the formula, y is the sweetness, and x is the amplitude of the low-field magnetic resonance signal.

[0082] Specifically, the acidity of the fruit is detected by using an acidity detector, and a relationship between the amplitude of the transverse relaxation time (T2) and the acidity of the fruit is determined as an inverse function, i.e., a correlation model, specifically y=-19x+21. In the formula, y is the acidity, and x is the transverse relaxation time.

[0083] In the above scheme, since the stem shape, epidermal shape and color type of the fruit are strongly related to the variety and origin of the fruit, the similarity with the fruit historical picture library is first determined to determine the proportion range, and then the proportion range is adjusted according to the freshness of the fruit, so that the appearance forgery of the fruit added with multiple dyes, preservatives and sweeteners can be accurately determined.

[0084] Further, the elements for determining the element origin of the fruit include potassium, cobalt, rubidium, nickel, manganese, calcium, hydrogen stable isotopes and oxygen stable isotopes; and the element origin is determined according to the cluster analysis of the content of the elements.

[0085] It can be understood that potassium, cobalt, rubidium, nickel, manganese, calcium, hydrogen stable isotopes and oxygen stable isotopes are related to the soil and climate of the fruit growing area, so that the origin information of the fruit can be accurately determined by cluster analysis.

[0086] Further, the appearance origin is intercontinental origin information, and the element origin is national origin information; it is judged whether the geographical range of the appearance origin includes the geographical range of the element origin, if yes, the fruit does not exist origin forgery, if not, the fruit exists origin forgery.

[0087] Specifically, the fruit variety corresponds to the appearance origin of an intercontinental region, for example, the appearance origin of the Santina variety is South America, and the element origin is Chile.

[0088] The embodiment also provides a fruit traceability system based on low-field magnetic nuclear magnetic resonance, which carries the fruit traceability method based on low-field magnetic nuclear magnetic resonance.

[0089] Further, the control device carries a detection system cloud platform to generate a fruit detection report including the image, the low-field magnetic resonance signal, the element content, whether the appearance is fake, and whether the origin is fake.

[0090] In the above scheme, the centralized management of the detection equipment by the cloud platform realizes the rapidity and standardization of the detection process.

[0091] Specifically, the control device is a server and a computer, the server controls the visual sensor, the low-field magnetic resonance analyzer and the inductively coupled plasma mass spectrometer through the Internet of Things, and carries each model described in the embodiment to realize the judgment of traceability fraud.

[0092] It can be understood that, through the image of the fruit and the low-field magnetic resonance signal of the fruit pulp, the rapid judgment and detection of the appearance of the fruit with imprecise dyeing agent, preservative and sweetener is realized, through the comprehensive judgment of the element content of the fruit core and the image and the low-field magnetic resonance signal, the accurate detection of the origin fraud using a small amount of fruit sample is realized. The determination of the proportion range for acidity and sweetness judgment considering the differences between fruit sample conditions and typical conditions of varieties is realized, which makes the judgment of the appearance of the fruit with multiple dyeing agents, preservatives and sweeteners to fake origin more accurate. The high-resolution signal of low-field magnetic nuclear magnetic resonance is used to realize that even if the fruit adds a very small amount of dyeing agent, preservative or sweetener, it can also be accurately and quickly detected. Through the centralized management of the detection equipment by the cloud platform, the rapidity and standardization of the detection process are realized.

[0093] So far, the technical scheme of the present application has been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without departing from the principles of the present application, and the technical scheme after the changes or replacements will fall within the protection scope of the present application.

[0094] The above description is only the preferred embodiment of the present application, and is not intended to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for tracing the origin of fruits based on low-field magnetic resonance nuclear magnetic resonance, characterized in that, include: Acquire images of fruits, and identify the color classification and shape characteristics of fruits based on the images; Low-field nuclear magnetic resonance is performed on the fruit pulp separated from the fruit to obtain low-field magnetic resonance signals, and the sweetness and acidity of the fruit pulp are determined based on the low-field magnetic resonance signals. The range of sweetness ratio and the range of acidity ratio are derived based on the color classification and the shape characteristics. Determine whether the sweetness is within the sweetness ratio range and whether the acidity is within the acidity ratio range. If not, determine that the fruit has a counterfeit appearance. If so, determine the origin of the fruit. Obtain the elemental content of the fruit kernels separated from the fruit, and determine the elemental origin of the fruit based on the elemental content; Whether the origin of a fruit is falsified is determined by whether the origin of its appearance corresponds to the origin of its elements.

2. The fruit traceability method based on low-field nuclear magnetic resonance according to claim 1, characterized in that, The steps for obtaining the sweetness ratio range and the acidity ratio range include: The varietal purity, ripeness, and freshness of the fruit are determined based on the color classification and the shape characteristics. The initial sweetness ratio range and the initial acidity ratio range are determined based on the varietal purity and the maturity. The initial sweetness ratio range and the initial acidity ratio range are adjusted according to the freshness to obtain the sweetness ratio range and the acidity ratio range.

3. The fruit traceability method based on low-field magnetic resonance according to claim 2, characterized in that, The steps for obtaining the color classification and the shape features include: The shape features and color classification of the fruit in the image are determined by an image recognition model based on a neural network. Fruit varieties are further subdivided based on color, stem shape, and skin appearance. The external features include the stem shape, stem vibrancy, epidermal shape, and epidermal gloss; the color classification includes the color type, characteristic chromaticity area, and characteristic chromaticity value.

4. The fruit traceability method based on low-field magnetic resonance according to claim 3, characterized in that, The process of determining the varietal purity of fruit based on the color classification and the shape characteristics is as follows: The purity of a variety is determined by an image similarity model based on the color type, stem morphology, epidermal shape, and historical image library of the corresponding production areas of the subdivided varieties.

5. The fruit traceability method based on low-field nuclear magnetic resonance according to claim 3, characterized in that, The steps for determining the initial sweetness ratio range and the initial acidity ratio range based on the varietal purity and the maturity include: The initial sweetness ratio range and the initial acidity ratio range are determined by a genetic algorithm based on the varietal purity and the maturity. Wherein, the maturity is the ratio of the area of ​​the characteristic chromaticity region to the area standard value, and the varietal purity is the ratio of the characteristic chromaticity value to the chromaticity standard value.

6. The fruit traceability method based on low-field magnetic resonance according to claim 3, characterized in that, The process of determining the freshness of fruit based on the color classification and the shape characteristics is as follows: The freshness is determined by mapping the stem vibrancy to a stem vibrancy grade and the epidermal gloss to a gloss grade.

7. The fruit traceability method based on low-field magnetic resonance according to claim 1, characterized in that, The steps for determining the sweetness and acidity of the fruit pulp based on the low-field magnetic resonance signal include: The sweetness corresponding to the low-field magnetic resonance signal is determined by a correlation model characterizing the low-field magnetic resonance signal per unit mass and the sweetness of fruit. The acidity corresponding to the low-field magnetic resonance signal is determined by a fitting model characterizing the relationship between transverse relaxation time and fruit acidity.

8. The fruit traceability method based on low-field magnetic resonance according to any one of claims 1 to 6, characterized in that, The elements used to determine the elemental origin of fruits include potassium, cobalt, rubidium, nickel, manganese, calcium, hydrogen stable isotopes, and oxygen stable isotopes. The origin of the element is determined by cluster analysis of the element content; The origin of the appearance is intercontinental, and the origin of the elements is national. Determine whether the geographical range of the appearance origin includes the geographical range of the element origin. If so, the fruit does not have an origin falsification; otherwise, the fruit has an origin falsification.

9. A fruit traceability system based on low-field magnetic resonance nuclear magnetic resonance, characterized in that, The fruit traceability system is equipped with the fruit traceability method based on low-field magnetic resonance as described in any one of claims 1 to 8, and the fruit traceability system includes: A visual sensor is used to acquire images of the fruit; A low-field magnetic resonance analyzer is used to obtain low-field magnetic resonance signals from the kernels of fruits. Inductively coupled plasma mass spectrometry is used to obtain the elemental content of fruit kernels; The control device communicates with the inductively coupled plasma mass spectrometer and the low-field magnetic resonance analyzer to determine whether the fruit has a counterfeit appearance and origin based on the image and the low-field magnetic resonance signal, and to determine whether the fruit has a counterfeit origin based on the origin and the element content.

10. The fruit traceability system based on low-field magnetic resonance according to claim 9, characterized in that, The control device is equipped with a detection system cloud platform to generate a fruit detection report that includes the image, the low-field magnetic resonance signal, the element content, whether the appearance is counterfeited, and whether the place of origin is faked.

Images