Food on-site rapid detection system

Abstract

The invention relates to the technical field of food safety detection, and provides a food on-site rapid detection system, which comprises a PDA terminal used for on-site law enforcement and rapid detection of food; the food supervision information traceability PTS platform stores food traceability detection information in a block chain carried by the food supervision information traceability PTS platform, and extracts food traceability detection information corresponding to the food electronic certificate; extracting a detection model corresponding to the food electronic certificate from the traceability detection information through an intelligent contract; determining a spectrum pesticide safety detection model in the food traceability risk increase detection model according to the food traceability detection information; identifying and detecting the food spectrum image and the food surface image through a detection model to generate detection parameters; and generating a parameter threshold according to the food traceability detection information, determining a detection result, and uploading the detection result to the block chain through the smart contract. According to the invention, detection result cheating caused by lack of personnel supervision is avoided, and rapidness and low cost of the rapid food detection supervision process are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of food safety detection, and in particular to a food on-site rapid detection system. Background Art

[0002] As food safety issues become increasingly prominent, all sectors of society have higher and higher requirements for food authenticity and safety. In order to ensure food safety, the state has successively issued a series of laws and regulations requiring food producers and operators to establish a food safety traceability system. However, the existing traceability system still has shortcomings in terms of authenticity certification and traceability efficiency.

[0003] In particular, under the current tight economic situation, many food testing departments have implemented cost control in terms of personnel, site facilities, reagents and consumables in order to reduce costs. There is a widespread phenomenon of layoffs or one person holding multiple posts, resulting in low quality of work output and lax management in many links, which has greatly affected the control of food testing.

[0004] For example, the patent document with application number 202311091008.9 only discloses how to avoid the problem of decreased data accuracy in food rapid testing results, but does not mention how to effectively supervise the results of food rapid testing.

[0005] Therefore, how to achieve rapid on-site food testing to reduce the cost of food testing and strengthen the supervision of food testing through the platform's blockchain technology is a technical problem that needs to be solved. Summary of the invention

[0006] To this end, the present invention provides a food on-site rapid detection system, which can quickly obtain visual images and spectral images of the food surface through a handheld PDA terminal, and use the blockchain of the PTS platform to perform mandatory detection of the images to determine whether the quality, microorganisms and pesticides of the food meet the standards, thereby avoiding cheating in test results due to lack of personnel supervision and achieving low cost in the rapid detection and supervision process of food.

[0007] To achieve the above object, the present invention provides a food on-site rapid detection system, comprising:

[0008] PDA terminal, which is used for on-site law enforcement rapid inspection of food, including RFID information collector for obtaining electronic food vouchers, spectral imager for obtaining food spectral images, and visual sensor for obtaining food surface images;

[0009] The food regulatory information tracing PTS platform communicates with the PDA terminal, and the blockchain it carries stores the food traceability detection information, which includes a food matching module, a detection model matching module, a pesticide detection model adding module, a detection identification module and a detection result generation module;

[0010] The food matching module is connected to the detection model matching module and the pesticide detection model adding module, and is used to extract the food traceability detection information corresponding to the food electronic certificate from the traceability detection information through the smart contract of the blockchain;

[0011] The detection model matching module is used to extract multiple detection models corresponding to the food types contained in the food electronic certificate from the traceability detection information through the smart contract of the blockchain;

[0012] The pesticide detection model adding module is used to add a spectral pesticide safety detection model in the detection model according to the food traceability risk determined by the food traceability detection information;

[0013] The detection and recognition module is connected to the detection model matching module and the pesticide detection model adding module, and is used to identify and detect the food spectrum image and the food surface image through the detection model to generate detection parameters;

[0014] The detection result generation module is connected to the detection identification module, generates a parameter threshold according to the food traceability detection information, determines the detection result by comparing the detection parameter and the parameter threshold, and uploads the detection result to the blockchain through a smart contract;

[0015] Among them, the food includes fruits and vegetables, the food traceability detection information includes variety, origin and applied pesticides, the detection models include a defect image detection model based on a convolutional neural network, a color unevenness image detection model based on a support vector machine, a spectral microbial detection model and the spectral pesticide safety detection model, and the detection parameters include at least the number of defects and color unevenness.

[0016] Furthermore, the defect image detection model is used to identify the number of defects on the food surface in the surface image;

[0017] The color unevenness image detection model is used to identify the color unevenness within a feature range in the surface image.

[0018] Furthermore, the color unevenness image detection model calculates the color unevenness through the square differences of brightness values ​​and RGB values ​​of multiple acquisition points.

[0019] Furthermore, the detection result generation module is used to determine a defect quantity threshold and a color unevenness threshold according to the origin and the variety, and determine whether the food quality is qualified based on a comparison between the defect quantity and the defect quantity threshold, and a comparison between the color unevenness and the color unevenness threshold.

[0020] In the above solution, the detection and judgment process is adjusted according to the food origin information of the traceability platform, thereby achieving accurate supervision of food quality.

[0021] Further, the spectral microorganism detection model includes a characteristic wavelength extraction unit and a microorganism detection unit;

[0022] The characteristic wavelength extraction unit is used to obtain the characteristic wavelength of the microorganisms in the food spectrum image through a spectral projection gradient algorithm;

[0023] The microorganism detection unit is a support vector machine model, which is used to generate a predicted total colony count based on the characteristic wavelength;

[0024] The detection result generating module is used to determine whether the food is contaminated by microorganisms based on the comparison between the predicted total colony count and the total colony count threshold;

[0025] Wherein, the microorganism includes Escherichia coli.

[0026] Furthermore, the spectral pesticide safety detection model is a principal component analysis model, which is used to identify the pesticide residues on the food surface in the food spectral image.

[0027] Furthermore, the pesticide detection model adding module includes a pesticide spectrum detection model generating unit and a pesticide spectrum model confirming unit;

[0028] The pesticide spectrum detection model generation unit is used to determine whether to add a spectral pesticide safety detection model for the applied pesticide type according to the pesticide metabolism capacity level of the variety and the historical data of the pesticide residue on the surface of the food of the same variety;

[0029] The pesticide spectral model confirmation unit uploads the confirmed spectral pesticide safety detection model to the blockchain.

[0030] Furthermore, the pesticide spectral detection model generation unit is used to extract the spectral images of foods with qualified pesticide application in the blockchain and compare them with the spectral images of foods with unqualified pesticide application, determine the added pesticide characteristic wavelength within the pesticide wavelength range, and add the added pesticide characteristic wavelength to the spectral pesticide safety detection model.

[0031] In the above scheme, effective detection and supervision of various pesticides remaining on the surface of food is achieved.

[0032] Furthermore, the PDA terminal is applied to the circulation links of food including production, storage, transportation and sales;

[0033] The food supervision information traceability PTS platform also includes a link warning module;

[0034] The link warning module is used to determine the circulation link where the test result of the same type of food is unqualified, and upload the circulation link to the blockchain, so that the regulatory department can receive the circulation link through the blockchain.

[0035] Furthermore, the link early warning module is used to send the account book recording the circulation link, the spectral image, the surface image and the detection result to the Ministry of Agriculture and Rural Affairs and the market supervision department for early warning.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1. Use a handheld PDA terminal to quickly obtain visual and spectral images of the food surface, and use the PTS platform's blockchain to conduct mandatory inspections on the images to determine whether the food quality, microorganisms, and pesticides meet the standards. This avoids cheating in test results due to lack of personnel supervision and achieves low-cost rapid food inspection and supervision.

[0038] 2. The detection and judgment process is adjusted according to the food origin information of the traceability platform, realizing accurate supervision of food quality.

[0039] 3. Effective detection and supervision of various pesticides remaining on the surface of food has been achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the general structure of a food on-site rapid detection system according to an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the detection process of a food on-site rapid detection system according to an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the PTS platform structure of a food on-site rapid detection system according to an embodiment of the present invention;

[0043] Figure 4 Schematic diagram of a microbial spectrum image of a food on-site rapid detection system according to an embodiment of the present invention.

[0044] Figure 5 Schematic diagram of the structure of a food on-site rapid detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0047] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely 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. Therefore, it cannot be understood as a limitation on the present invention.

[0048] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] like Figures 1 to 5 As shown, the present invention provides a food on-site rapid detection system, which can quickly obtain visual images and spectral images of the food surface through a handheld PDA terminal, and detect the images through the blockchain of the PTS platform to determine whether the quality, microorganisms and pesticides of the food meet the standards, thereby avoiding cheating in the test results due to lack of personnel supervision and achieving low cost in the rapid detection and supervision process of food.

[0050] like Figures 1 to 5 As shown, this embodiment proposes a food on-site rapid detection system, including: a PDA terminal, which is used to perform on-site law enforcement rapid inspection of food, including an RFID information collector for obtaining food electronic certificates, a spectral imager for obtaining food spectral images, and a visual sensor for obtaining food surface images;

[0051] The food regulatory information tracing PTS platform communicates with the PDA terminal, and the blockchain it carries stores the traceability detection information of the food, which includes a food matching module, a detection model matching module, a pesticide detection model adding module, a detection identification module and a detection result generation module; the food matching module is connected to the detection model matching module and the pesticide detection model adding module, and is used to extract the food traceability detection information corresponding to the food electronic certificate from the traceability detection information through the smart contract of the blockchain; the detection model matching module is used to extract multiple detection models corresponding to the food types contained in the food electronic certificate from the traceability detection information through the smart contract of the blockchain; the pesticide detection model adding module is used to increase the spectral pesticide safety detection model in the detection model according to the food traceability risk determined by the food traceability detection information. ; The detection and identification module is connected to the detection model matching module and the pesticide detection model adding module, and is used to identify and detect the food spectral image and the food surface image through the detection model to generate detection parameters; the detection result generation module is connected to the detection and identification module, generates a parameter threshold according to the food traceability detection information, and determines the detection result by comparing the detection parameter and the parameter threshold, and uploads the detection result to the blockchain through a smart contract; wherein, the food includes fruits and vegetables, and the food traceability detection information includes variety, origin and applied pesticides, and the detection models include a defect image detection model based on a convolutional neural network, a color unevenness image detection model based on a support vector machine, a spectral microbial detection model and the spectral pesticide safety detection model, and the detection parameters include at least the number of defects and color unevenness.

[0052] Specifically, see Figure 5 The PDA terminal has an RFID information collector, and wirelessly communicates with the spectral imager and the visual sensor, and uploads the food spectral image and food surface image to the food regulatory information traceability PTS platform through the PDA terminal. The PDA terminal and the food regulatory information traceability PTS platform realize real-time communication and interconnection through the LoRa gateway and NB-IoT communication. The microcontroller of the PDA terminal is a low-power single-chip microcomputer powered by solar energy, which has a sleep mode and a communication mode to realize the interconnection and interoperability of the perception layer, transmission layer and application layer without power supply or charging.

[0053] It is understandable that the PTS platform for food regulatory information traceability uses blockchain to ensure the authenticity, immutability and traceability of traceability information. This puts every transfer of food in the supply chain under regulatory vision. Once an abnormality is found, it can be quickly identified, accurately traced, and processed as soon as possible. Therefore, the PTS platform for food regulatory information traceability monitors the online status and test data of each monitoring point in real time, automatically performs data analysis and statistics, and generates regulatory reports to help regulatory authorities keep abreast of food safety conditions. The platform supports multi-level permission settings to achieve hierarchical access and management of data to ensure data security.

[0054] Furthermore, the image quality detection model includes a defect image detection model, and the detection parameters include the number of defects; the defect image detection model is an image recognition model based on a convolutional neural network, which is used to identify the number of defects on the food surface in the surface image.

[0055] Specifically, the convolutional neural network of the defect image detection model is implemented based on the convolutional neural network of YOLOv8 and the WHU-Hi dataset. The WHU-Hi dataset is strictly preprocessed to ensure the quality and accuracy of the data. YOLOv8 is the next generation algorithm model developed by Ultra Lyticics after the YOLOv5 algorithm, supporting image classification and object detection tasks. The convolutional neural network model includes: a new backbone network, a new Ancher-Free detection head and a new loss function. The YOLOv8 convolutional neural network model is used to implement detection based on the YOLOv8 model and the WHU-Hi dataset, and the Pys ide6 library is used to build a detection sub-interface system on the food regulatory information traceability PTS platform to complete the development of the detection interface of the spectral image and the food surface image. By adjusting the detection confidence threshold and IOU threshold of the YOLOv8 model, the accuracy of the detection is more appropriate.

[0056] Among them, the WHU-Hi dataset contains images of many common fruits and vegetables, such as Shanghai greens, potatoes, sweet potato leaves, Guangdong Chinese cabbage, oats, lettuce, water spinach, red amaranth, carrots, cauliflower, celery, eggplant, spinach, garlic sprouts, broccoli, peppers, chicken feather vegetables, cucumbers, cherries, apples, pears, etc. In order to minimize the distortion of the images without affecting the detection accuracy, all images are resized to 640x640 and the original aspect ratio is maintained. In addition, in order to enhance the generalization ability and robustness of the model, data enhancement techniques are used, including random rotation, scaling, cropping, and color transformation, to expand the dataset and reduce the risk of overfitting.

[0057] It should be noted that the defects described in this embodiment are downy mildew less than 5 square centimeters, leaf spot less than 5 square centimeters, surface pits / damage, and yellow leaves / rot.

[0058] Furthermore, the image quality detection model also includes a color unevenness image detection model, and the detection parameters also include color unevenness; the color unevenness image detection model is an image recognition model based on a support vector machine, which is used to identify the color unevenness within a feature range in the surface image.

[0059] It is understood that support vector machine (SVM) is a supervised learning method for classification based on margin maximization, which can be applied to high-dimensional data. The color unevenness image detection model uses the SVC program in sklearn.SVM, selects RBF as the kernel function, and combines the random search method to select the kernel function in 0.1-1000 and 1*10 -6 The optimal penalty factor and kernel function hyperparameters are searched within -10. Then, the feature range in the surface image can be identified according to the feature range annotated in the WHU-Hi dataset. The feature range is the middle of the skin for fruits and the middle of the leaves for vegetables.

[0060] Furthermore, the color unevenness image detection model calculates the color unevenness through the square differences of brightness values ​​and RGB values ​​of multiple acquisition points.

[0061] The color unevenness is calculated using the color difference formula, specifically:

[0062]

[0063] Wherein, △L, △A, △B are the square differences of the values ​​of multiple acquisition points within the feature range, △L is the brightness difference, △A is the red-green difference of the RGB value, △B is the yellow-blue difference of the RGB value, and the comprehensive color difference △E is the comprehensive color difference, i.e., the color unevenness.

[0064] Furthermore, the detection result generation module is used to determine a defect quantity threshold and a color unevenness threshold according to the origin and the variety, and determine whether the food quality is qualified based on a comparison between the defect quantity and the defect quantity threshold, and a comparison between the color unevenness and the color unevenness threshold.

[0065] Specifically, the detection result generation module is used to determine the defect quantity threshold according to the temperature of the origin and the variety; the detection result generation module is used to generate the color unevenness threshold according to the temperature of the origin and the light duration; the detection result adjustment module is used to determine whether the food quality is qualified based on the comparison between the defect quantity and the defect quantity threshold, and the comparison between the color unevenness and the color unevenness threshold.

[0066] It is understandable that, for example, under high temperature conditions, the metabolic rate of fruits and vegetables is accelerated, which may cause the skin to mature too quickly and shrink. If the fruits and vegetables maintain this maturity during transportation, it means that the quality of the fruits and vegetables is qualified. Therefore, it is impossible to determine whether the food has changed during transportation through a fixed defect quantity threshold.

[0067] Specifically, the average temperature and temperature range of the origin in the last three months are taken as conditions. The temperature range can reflect whether extreme weather conditions occur. The threshold value of the number of defects of the corresponding level is determined by grading the average temperature and the temperature range. Specifically, the climate condition level includes defect levels one to five which increase in sequence, and the grading standards are average temperature less than 10℃ and / or temperature range greater than 5℃, average temperature greater than 10℃ and less than 15℃ and temperature range greater than 5℃, average temperature greater than 15℃ and less than 25℃ or temperature range greater than 8℃, average temperature greater than 15℃ and less than 25℃ and temperature range greater than 8℃, average temperature greater than 25℃ or temperature range greater than 10℃. The defect quantity thresholds corresponding to defect levels 1 to 5 are respectively increased by 4, 8, 10, 15 and 20 on the initial defect quantity thresholds corresponding to the varieties to generate the defect quantity thresholds. The defect quantity thresholds are all set according to the detection window area of ​​the surface image described in this embodiment. The defect quantity thresholds corresponding to the defect level can also be adjusted according to its visual sensor or the set detection window area. The surface images corresponding to the defect levels are uploaded to the blockchain for easy supervision. For example, the initial defect quantity of Shanghai green, sweet potato leaves, Guangdong cabbage, oats, lettuce, water spinach, and red amaranth is 10.

[0068] It is understandable that the temperature and light duration of the place of origin affect the growth and development process of fruits and vegetables, and thus affect the color of their skin. The place of origin does not only refer to the geographical location where the fruits and vegetables grow, but also includes whether they are produced in a planting shed, which is a natural light or artificial light source. The light duration is the average daily light duration, which is determined based on the average sunshine duration of the place of origin in the past three months, and the sunshine duration of artificial light sources is stipulated to be 13 hours / day.

[0069] Specifically, the temperature and light duration levels include growth levels one to five that increase in sequence, and the grading standards are: average temperature less than 10°C and / or light duration less than 12 hours / day, average temperature greater than 10°C and less than 15°C and light duration greater than 12 hours / day and less than or equal to 13 hours / day, average temperature greater than 15°C and less than 25°C or light duration greater than 12 hours / day and less than or equal to 13 hours / day, average temperature greater than 15°C and less than 25°C and light duration greater than 13 hours / day and less than or equal to 14 hours / day, average temperature greater than 25°C or light duration greater than 14 hours / day. The color unevenness thresholds corresponding to growth levels one to five are 10, 15, 20, 30, and 40, respectively, and the surface images corresponding to the growth levels are uploaded to the blockchain for easy supervision.

[0070] Preferably, when the number of defects exceeds the defect number threshold and the color unevenness exceeds the color unevenness threshold, the food quality is judged to be unqualified to avoid inaccurate single judgment.

[0071] In the above solution, the detection and judgment process is adjusted according to the food origin information of the traceability platform, thereby achieving accurate supervision of food quality.

[0072] Furthermore, the spectral microbial detection model includes a characteristic wavelength extraction unit and a microbial detection unit; the characteristic wavelength extraction unit is used to obtain the characteristic wavelength of the microorganisms in the food spectral image through a spectral projection gradient algorithm; the microbial detection unit is a support vector machine model, used to generate a predicted total colony count based on the characteristic wavelength; the detection result generation module is used to determine whether the food is contaminated by microorganisms based on a comparison between the predicted total colony count and a total colony count threshold; wherein the microorganisms include Escherichia coli.

[0073] The spectral projection gradient algorithm (SPA) is used to screen the characteristic bands because the original full-band spectral image data is large and contains a lot of redundant and collinear information, which will seriously reduce the prediction accuracy and operation speed of the model. The spectral projection gradient algorithm adopts the method of forward selection of characteristic bands. This method selects a wavelength under the initial conditions, loops forward, calculates the projection vectors of other wavelengths at this wavelength in turn, selects the wavelength corresponding to the vector with the largest projection value, and combines it with the initial wavelength until the cycle ends. Therefore, the characteristic bands extracted by the spectral projection gradient algorithm have the performance of small collinearity and low redundancy, and can represent the spectral information of the whole sample.

[0074] Specifically, see Figure 4 , which represents the pseudo-color images of apple samples with different contamination levels, Figure 4The portion selected by the dotted line with a long middle segment and sparseness is determined as the portion where microbial colonies exist. The pseudo-color image is obtained by extracting the corresponding microbial colony characteristic wavelength / content characteristic wavelength from the full band of the spectral imager, that is, the microbial colony characteristic wavelength is set to the characteristic wavelength range of pesticides, that is, 200 to 340 nm, and a support vector machine model is generated. The more microbial colonies there are, the color in the pseudo-color image gradually changes from blue to yellow and then to red. In this way, the grayscale image predicted by pseudo-color processing can intuitively judge the degree of microbial contamination on the surface of fruits and vegetables.

[0075] Furthermore, the spectral pesticide safety detection model is a principal component analysis model, which is used to identify the pesticide residues on the food surface in the food spectral image.

[0076] It is understandable that the principal component analysis model is a multivariate statistical method based on the idea of ​​dimensionality reduction, which is used to transform numerous indicators into a few comprehensive indicators. The higher the contribution rate of the principal component, the stronger its influence. This method considers the relationship between the original variables, finds a comprehensive alternative target for the relevant variables, and minimizes information loss during the conversion process.

[0077] Specifically, multiple points in the food spectral image are taken as evaluation objects, and the characteristic wavelengths of multiple pesticides are used as indicator variables. The principal component comprehensive score is calculated through the principal component analysis model, and the principal component comprehensive score is used as the pesticide residue on the food surface.

[0078] Specifically, see Figure 4 , which represents the pseudo-color images of apple samples with different contamination levels, Figure 4 The portion selected by the denser dotted line is determined as the portion where pesticide residues exist. The pseudo-color image is obtained by extracting the corresponding pesticide characteristic wavelength / content characteristic wavelength from the full band of the spectral imager, that is, the pesticide characteristic wavelength is set to the characteristic wavelength range of the pesticide, that is, 340nm to 690nm. The types of pesticides such as cypermethrin, imidacloprid, benzyl dichlorvos, soybean seed dressing agent and organophosphorus pesticides can be detected through the principal component analysis model. The more pesticide residues there are, the color in the pseudo-color image gradually changes from blue to yellow and then to red. In this way, the grayscale image predicted by pseudo-color processing can intuitively judge the degree of internal contamination of the fruit.

[0079] Furthermore, the pesticide detection model adding module includes a pesticide spectral detection model generation unit and a pesticide spectral model confirmation unit; the pesticide spectral detection model generation unit is used to determine whether to add a spectral pesticide safety detection model of the applied pesticide type based on the pesticide metabolism capacity level of the variety and the historical data of pesticide residues on the food surface of the same variety; the pesticide spectral model confirmation unit uploads the confirmed spectral pesticide safety detection model to the blockchain.

[0080] Different fruit and vegetable varieties have different physiological structures, biochemical characteristics and genetic backgrounds, resulting in some fruit and vegetable varieties having stronger enzyme systems that can metabolize and degrade pesticides more effectively, while other varieties have weaker metabolic capabilities.

[0081] Specifically, the pesticide application amount of fruit and vegetable varieties recorded on the platform at the production end is graded to determine the pesticide metabolism level L. The number of times C when the pesticide residue exceeds the pesticide residue threshold is determined based on the historical data of pesticide residue on the surface of the same batch and the same variety of food. The product of the pesticide metabolism level L and the number C is compared with the pesticide detection model increase threshold to determine whether to add the spectral pesticide safety detection model of the applied pesticide type.

[0082] Furthermore, the pesticide spectral detection model generation unit is used to extract the spectral images of foods with qualified pesticide application in the blockchain and compare them with the spectral images of foods with unqualified pesticide application, determine the added pesticide characteristic wavelength within the pesticide wavelength range, and add the added pesticide characteristic wavelength to the spectral pesticide safety detection model.

[0083] Specifically, the characteristic wavelength of pesticides is added as a new indicator variable and added to the original sample matrix, so that the number of columns of the original sample matrix is ​​increased.

[0084] In the above scheme, effective detection and supervision of various pesticides remaining on the surface of food is achieved.

[0085] Furthermore, the PDA terminal is applied to the circulation links of food including production, storage, transportation and sales; the food regulatory information traceability PTS platform also includes a link warning module; the link warning module is used to determine the circulation link where the test result of the same variety of food is unqualified, and upload the circulation link to the blockchain, so that the regulatory department can receive the circulation link through the blockchain.

[0086] Furthermore, the link early warning module is used to send the account book recording the circulation link, the spectral image, the surface image and the detection result to the Ministry of Agriculture and Rural Affairs and the market supervision department for early warning.

[0087] Specifically, the quality level generation algorithm is: In the formula, Q is the quality grade, S is the defect area, W is the detection window area, the defect degree is expressed by the ratio of the defect area to the detection window area, L is the correction value for different spectral imagers, k is the setting parameter, and k is set according to the defect type information. More specifically, the setting parameters k for the defect type information of dent, corrosion, discoloration, and deformation are 1, 8, 5, and 2, respectively. The value of the unqualified quality grade is greater than 15, the value of the risky quality grade is less than or equal to 15 and greater than 5, and the value of the good quality grade is less than or equal to 5.

[0088] Specifically, the quality grade is the weighted average of the pre-quality grade and the above-mentioned quality grade Q. In the production stage, pesticide residues may be too much and will be removed by themselves in the subsequent transportation stage, so image detection is more preferred to prevent food with obvious defects from circulation. At this time, the weights are 0.3 and 0.7 respectively; in the storage stage, image detection is more preferred, and the weights are 0.4 and 0.6 respectively; in the transportation stage, spectral detection is more preferred, and the weights are 0.6 and 0.4 respectively, to avoid further circulation of food with pesticide residues; in the sales stage, spectral detection and image detection are equally important, and their weights are 0.5 and 0.5 respectively.

[0089] Furthermore, the food regulatory information traceability PTS platform also includes a boundary extraction module, which is used to perform optical correction and background deletion on the spectral image to determine the food boundary of the surface image.

[0090] In the above scheme, accurate judgment of the quality grade of food is achieved through visual sensors.

[0091] Furthermore, the supervision cloud platform also includes an early warning module, which determines the link where the quality level is reduced based on the comparison results of multiple quality levels of food in multiple links of the supervision cloud platform, and generates early warning information.

[0092] Furthermore, the food regulatory information traceability PTS platform also includes a regulatory report generation module, which is used to generate a topological regulatory report based on the electronic credentials, odor data, spectral image, surface image and quality grade of food in multiple links, and send and display the test report to the user terminal.

[0093] In the above solution, the supervision cloud platform is used to realize the interconnection and interoperability of supervision information in the production, storage, transportation and sales links of food, realize intelligent judgment of potential risk points, and provide decision-making support for regulatory authorities.

[0094] See also Figure 3Taking food safety supervision in a certain area as an example, the regulatory department uses the PDA terminal provided in this embodiment to carry out an integrated intelligent supervision system for on-site food safety law enforcement rapid inspection and monitoring, and conducts rapid inspections on food production, circulation and other links within the jurisdiction. After obtaining the test data through the rapid detection PDA terminal, it is uploaded to the food supervision information traceability PTS platform in real time. The food supervision information traceability PTS platform automatically screens, corrects and warns based on the test data, and promptly feeds back the results to the regulatory department. At the same time, the regulatory department can view historical test data, analyze risk trends, and formulate targeted regulatory measures through the system. In addition, the system also supports full traceability through electronic certificates to ensure that food quality is controllable.

[0095] The integrated intelligent supervision system of PDA terminal and food supervision information traceability PTS platform provided in this embodiment realizes the on-site rapid inspection and monitoring of food safety law enforcement. By integrating rapid detection instrument, detection cloud platform, data management module and intelligent analysis module, it realizes rapid detection, real-time supervision and full traceability of food safety. The system has the advantages of wide detection range, high accuracy and simple operation, which can significantly improve the efficiency and level of food safety supervision and ensure the food safety of the people.

[0096] It is understandable that the visual and spectral images of the food surface can be quickly obtained through the handheld PDA terminal, and the PTS platform blockchain can be used to conduct mandatory inspections on the images to determine whether the food quality, microorganisms and pesticides meet the standards, thereby avoiding cheating in the test results due to lack of personnel supervision and achieving low cost in the process of rapid food inspection and supervision. The inspection and judgment process can be adjusted according to the food origin information of the traceability platform, and accurate supervision of food quality can be achieved. Effective inspection and supervision of various pesticides remaining on the surface of food can be achieved.

[0097] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A food on-site rapid detection system, characterized in that: include: PDA terminal, which is used for on-site law enforcement rapid inspection of food, including RFID information collector for obtaining electronic food vouchers, spectral imager for obtaining food spectral images, and visual sensor for obtaining food surface images; The food regulatory information tracing PTS platform communicates with the PDA terminal, and the blockchain it carries stores the food traceability detection information, which includes a food matching module, a detection model matching module, a pesticide detection model adding module, a detection identification module and a detection result generation module; The food matching module is connected to the detection model matching module and the pesticide detection model adding module, and is used to extract the food traceability detection information corresponding to the food electronic certificate from the traceability detection information through the smart contract of the blockchain; The detection model matching module is used to extract multiple detection models corresponding to the food types included in the food electronic certificate from the traceability detection information through the smart contract of the blockchain; The pesticide detection model adding module is used to add a spectral pesticide safety detection model in the detection model according to the food traceability risk determined by the food traceability detection information; The detection and recognition module is connected to the detection model matching module and the pesticide detection model adding module, and is used to identify and detect the food spectrum image and the food surface image through the detection model to generate detection parameters; The detection result generation module is connected to the detection identification module, generates a parameter threshold according to the food traceability detection information, determines the detection result by comparing the detection parameter and the parameter threshold, and uploads the detection result to the blockchain through a smart contract; Among them, the food includes fruits and vegetables, the food traceability detection information includes variety, origin and applied pesticides, the detection models include a defect image detection model based on a convolutional neural network, a color unevenness image detection model based on a support vector machine, a spectral microbial detection model and the spectral pesticide safety detection model, and the detection parameters include at least the number of defects and color unevenness.

2. The food on-site rapid detection system according to claim 1, characterized in that: The defect image detection model is used to identify the number of defects on the food surface in the surface image; The color unevenness image detection model is used to identify the color unevenness within a feature range in the surface image.

3. The food on-site rapid detection system according to claim 2, characterized in that: The color unevenness image detection model calculates the color unevenness through the square difference of brightness values ​​and RGB values ​​of multiple acquisition points.

4. The food on-site rapid detection system according to claim 3, characterized in that: The detection result generation module is used to determine the defect quantity threshold and the color unevenness threshold according to the origin and the variety, and determine whether the food quality is qualified based on the comparison between the defect quantity and the defect quantity threshold, and the comparison between the color unevenness and the color unevenness threshold.

5. The on-site rapid food detection system according to any one of claims 1 to 4, characterized in that: The spectral microorganism detection model includes a characteristic wavelength extraction unit and a microorganism detection unit; The characteristic wavelength extraction unit is used to obtain the characteristic wavelength of the microorganisms in the food spectrum image through a spectral projection gradient algorithm; The microorganism detection unit is a support vector machine model, which is used to generate a predicted total colony count based on the characteristic wavelength; The detection result generating module is used to determine whether the food is contaminated by microorganisms based on the comparison between the predicted total colony count and the total colony count threshold; Wherein, the microorganism includes Escherichia coli.

6. The on-site rapid food detection system according to any one of claims 1 to 4, characterized in that: The spectral pesticide safety detection model is a principal component analysis model, which is used to identify the pesticide residues on the food surface in the food spectral image.

7. The food on-site rapid detection system according to claim 6, characterized in that: The pesticide detection model adding module includes a pesticide spectrum detection model generating unit and a pesticide spectrum model confirming unit; The pesticide spectrum detection model generation unit is used to determine whether to add a spectral pesticide safety detection model for the applied pesticide type according to the pesticide metabolism capacity level of the variety and the historical data of the pesticide residue on the surface of the food of the same variety; The pesticide spectral model confirmation unit uploads the confirmed spectral pesticide safety detection model to the blockchain.

8. The food on-site rapid detection system according to claim 7, characterized in that: The pesticide spectral detection model generation unit is used to extract the spectral images of foods with qualified pesticide application in the blockchain and compare them with the spectral images of foods with unqualified pesticide application, determine the added pesticide characteristic wavelength within the pesticide wavelength range, and add the added pesticide characteristic wavelength to the spectral pesticide safety detection model.

9. The on-site rapid food detection system according to any one of claims 1 to 4, characterized in that: The PDA terminal is applied to the circulation links of food including production, storage, transportation and sales; The food supervision information traceability PTS platform also includes a link warning module; The link warning module is used to determine the circulation link where the test result of the same type of food is unqualified, and upload the circulation link to the blockchain, so that the regulatory department can receive the circulation link through the blockchain.

10. The food on-site rapid detection system according to claim 9, characterized in that: The link warning module is used to send the account book recording the circulation link, the spectral image, the surface image and the detection result to the Ministry of Agriculture and Rural Affairs and the market supervision department for early warning.

Images