Meat quality detection method and system based on flexible bio-impedance imaging

Abstract

The invention discloses a meat quality detection method and a meat quality detection system based on flexible biological impedance imaging. The meat quality detection method comprises the following steps: acquiring impedance original values, PH, chromatic aberration and tenderness of a to-be-detected meat sample measured according to a preset measurement principle at a plurality of time points; correcting the impedance original value of the to-be-detected meat sample by using the correction coefficient; reconstructing the corrected impedance original value to obtain a reconstructed impedance value; obtaining the time point of meat deterioration according to the PH, color difference and tenderness at different time points; obtaining the average impedance value of all the reconstructed impedance values of the meat sample to be measured at the deterioration time point and the initial time point, calculating the impedance change rate of the meat sample to be measured at the deterioration time point and the initial measurement time point by using the reconstructed average impedance value, and comparing the impedance change rate with the pre-calculated impedance change rate of the frozen meat sample, if the impedance change rate of the to-be-detected meat sample is greater than the freezing impedance change rate, the to-be-detected meat sample is an unfrozen fish, otherwise, the to-be-detected meat sample is an iced fish. The method is simple in step, easy to detect and accurate in detection result.

Description

Technical Field

[0001] This application relates to the technical field of meat quality detection, and particularly to a method and system for detecting meat quality. Background Art

[0002] The main forms of salmon in global circulation are chilled and frozen. Chilled fish refers to fish that has been kept below 4°C without freezing after being caught, usually with a storage time within 10 days. Frozen fish refers to fish that has been frozen and stored (below -18°C) for a period of time and then thawed. The frozen storage of fish can last for 6 - 12 months, having a longer storage period. Fresh fish has high nutritional value and good taste, and its market price is higher than that of frozen fish. Some merchants, in order to make a profit, sell thawed frozen fish as chilled fish, seriously damaging the interests of consumers. Therefore, it is necessary to detect chilled fish and frozen fish. However, traditional methods for detecting the quality of fish meat, such as sensory evaluation methods, require professional testers to use their taste, smell, vision, etc. to evaluate the basic characteristic parameters of the fish meat, such as the color, smell, and taste changes, and to determine the quality of the fish meat by destroying the fish meat to measure the content of total volatile basic nitrogen (TVBN), which is cumbersome and time-consuming. Therefore, a better non-destructive and rapid detection method is urgently needed. Thus, how to quickly detect the quality of fish meat has become an urgent problem to be solved currently. Summary of the Invention

[0003] Based on this, in view of the above technical problems, a method and system for detecting meat quality based on flexible bio-impedance imaging are provided to solve the problem of cumbersome meat quality detection in the prior art.

[0004] In a first aspect, a method for detecting meat quality based on flexible bio-impedance imaging, the method includes: obtaining the original impedance values and PH values of a meat sample to be measured at multiple time points measured based on a preset measurement principle;

[0005] Using a pre-obtained correction coefficient to correct the original impedance value of the meat sample to be measured to obtain a corrected original impedance value;

[0006] Reconstructing the corrected original impedance value according to the method of optimizing pixels one by one to obtain a reconstructed impedance value;

[0007] Determining the spoilage time point of the meat sample to be measured according to the PH values at different time points;

[0008] Obtain the reconstructed impedance values of the meat sample to be tested at the spoilage time point and the initial time point, calculate the average reconstructed impedance values at the spoilage time point and the initial time point, calculate the impedance change rate of the meat sample to be tested between the spoilage time point and the initial measurement time using the average reconstructed impedance values, and compare it with the impedance change rate of the pre-calculated frozen meat sample. If the impedance change rate of the meat sample to be tested is greater than that of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish. The impedance change rate of the frozen meat sample is the impedance change rate measured after freezing the fresh meat sample.

[0009] In the above solution, optionally, the measurement principle includes:

[0010] Divide the measurement position set, the measurement number set, and the measurement time set. The measurement position set includes the front and the back.

[0011] According to the measurement time set, obtain multiple impedance values at each time point according to the measurement position set and the measurement number set at each time point.

[0012] In the above solution, further optionally, the pre-obtained correction coefficient is obtained through the following method:

[0013] Cut the fresh meat sample into standard meat samples of the same size and thickness.

[0014] According to the measurement principle, obtain the original impedance values at multiple time points of the fresh meat sample, as well as the PH, color difference, and tenderness of the fresh meat sample at multiple time points.

[0015] The correction coefficient β is the product of the electrode number correction coefficient β1, the position correction coefficient β2, the measurement number reference coefficient β3, and the time reference coefficient β4.

[0016] The electrode number correction coefficient β1 is calculated by the following formula:

[0017]

[0018] Where x is the number of electrodes, U mx is the original impedance value collected by each electrode of the fresh meat sample obtained at one time point, is the average value of the original impedance values collected by all electrodes of the fresh fish meat sample at the corresponding time point;

[0019] The position correction coefficient β2 is calculated by the following formula:

[0020]

[0021] Where U m1 、U m2They are respectively the mean of the original front impedance value and the mean of the original back impedance value of a fresh meat sample obtained at a time point. It is the mean of all the original impedance values collected from the fresh meat sample at the same time point.

[0022] The reference coefficient β3 of the measurement times is calculated by the following formula:

[0023]

[0024] where i is the measurement times, U m1i is the original front impedance value of the i-th measurement, U m1 , U m2 They are respectively the mean of the original front impedance value and the mean of the original back impedance value of a fresh meat sample obtained at a time point, and the mean of all the original impedance values collected from the fresh meat sample at the same time point.

[0025] The reference coefficient β4 of the time is calculated by the following formula:

[0026]

[0027] where t n is the time of each measurement, i is the measurement times, U m1i is the original front impedance value of the i-th measurement, U m1 , U m2 They are respectively the mean of the original front impedance value and the mean of the original back impedance value of a fresh meat sample obtained at a time point, and the mean of all the original impedance values collected from the fresh meat sample at the same time point.

[0028] In the above solution, further optionally, the corrected impedance value obtained by correcting the original impedance value of the meat sample to be measured using the pre-obtained correction coefficient is calculated by the following formula:

[0029]

[0030] where is the original impedance value, U m is the corrected impedance value, and β is the correction coefficient.

[0031] In the above solution, optionally, the reconstructed impedance value obtained by reconstructing the corrected original impedance value according to the method of optimizing pixels one by one includes:

[0032] Using the first model to reconstruct the impedance value based on the corrected impedance value and the impedance value before correction;

[0033] The formula of the first model is:

[0034]

[0035] Among them, U m is the corrected impedance measurement data, and U m0 is the original impedance data measured before correction. n is the number of measurement data, is the first reconstructed impedance data;

[0036] The impedance value reconstructed by using the second model based on the corrected impedance value and the impedance value before correction;

[0037] The formula of the second model is:

[0038]

[0039] Among them, U m is the corrected impedance measurement data, and U m0 is the original impedance data measured before correction. n is the number of measurement data, is the second reconstructed impedance data, and λ is the regularization parameter;

[0040] Select all time points according to the set rules to use the first reconstructed impedance data or the second reconstructed impedance data as the final reconstructed impedance data; The set rules are: According to the PH value of each time point, if the PH value is greater than 7, select the smaller one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point. If the PH is less than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point. If the PH value is less than 7 and greater than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point; According to the number of the first reconstructed impedance data and the second reconstructed impedance data selected, if the number of the first reconstructed impedance data selected is greater than the number of the second reconstructed impedance data, then all time points use the first reconstructed impedance data reconstructed by the first model as the final reconstructed impedance data.

[0041] In the above solution, optionally, the determining the time point of the deterioration of the meat sample to be measured according to the PH value at different time points includes: If the PH is greater than 7, the meat quality deteriorates.

[0042] In the above solution, optionally, the impedance change rate is calculated by the following method:

[0043]

[0044] Among them, is the average impedance value at the deterioration time point, is the average impedance value at the initial moment, and S1 is the impedance change rate at the deterioration point.

[0045] Second aspect, a meat quality detection system based on flexible bio-impedance imaging is provided. The system includes:

[0046] A data acquisition module: configured to acquire the original impedance values and PH values of a meat sample to be measured at multiple time points measured based on a preset measurement principle.

[0047] An impedance value correction module: configured to correct the original impedance values of the meat sample to be measured by using a pre-acquired correction coefficient to obtain corrected original impedance values.

[0048] A reconstructed impedance module: configured to reconstruct the corrected original impedance values according to a method of optimizing pixels one by one to obtain reconstructed impedance values.

[0049] A spoilage time point calculation module: configured to determine the spoilage time point of the meat sample to be measured according to the PH values at different time points.

[0050] A judgment module: configured to acquire the reconstructed impedance values of the meat sample to be measured at the spoilage time point and the initial time point, calculate the average reconstructed impedance values at the spoilage time point and the initial time point, calculate the impedance change rate of the meat sample to be measured at the spoilage time point and the initial measurement moment by using the average reconstructed impedance values, compare it with the impedance change rate of a frozen meat sample calculated in advance. If the impedance change rate of the meat sample to be measured is greater than the impedance change rate of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish. The impedance change rate of the frozen meat sample is the impedance change rate measured after freezing a fresh meat sample.

[0051] Third aspect, a computer device is provided, including a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of a meat quality detection method based on flexible bio-impedance imaging described in the first aspect above are implemented.

[0052] Fourth aspect, a computer program product is provided, including a computer program / instructions. It is characterized in that when the computer program / instructions are executed by a processor, the steps of a meat quality detection method based on flexible bio-impedance imaging described in the first aspect above are implemented.

[0053] This application has at least the following beneficial effects:

[0054] In this application, the impedance values of a meat sample to be measured at multiple time points are measured, and the impedance values are corrected using a correction factor to overcome the influences brought by different electrodes, different acquisition times, different acquisition time points, and different acquisition positions, so that the impedance values are more accurate. At the same time, the method of optimizing pixels one by one is used to reconstruct the corrected original impedance values to obtain the reconstructed impedance values, which can further optimize the accuracy of the measured data, so as to extract the image impedance values subsequently to calculate the impedance change rate, and then obtain the time point of meat quality deterioration through the PH, color difference, and tenderness at different time points. According to the comparison between the impedance change rate of the meat sample to be measured at the deterioration time point and the initial measurement time and the impedance change rate of the frozen meat sample, if the impedance change rate of the meat sample to be measured is greater than that of the frozen meat sample, it is thawed meat; if it is less, it is chilled fish. Therefore, the steps of this application are simple and easy to detect, and the detection results are accurate. Description of the Drawings

[0055] Figure 1 It is a flowchart of a method for detecting meat quality based on flexible bioimpedance imaging provided in an embodiment of this application;

[0056] Figure 2 It is a detailed flowchart of a method for detecting meat quality based on flexible bioimpedance imaging provided in an embodiment of this application

[0057] Figure 3 It is a schematic flowchart of reconstructing impedance values provided in an embodiment of this application;

[0058] Figure 4 It is a schematic diagram of the change of meat sample deterioration over time in an embodiment of this application;

[0059] Figure 5 It is a structural diagram of a system for detecting meat quality based on flexible bioimpedance imaging provided in an embodiment of this application. Detailed Description of the Embodiment

[0060] In order to make the purpose, technical solutions and advantages of this application clearer, the following further details this application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0061] In one embodiment, as Figure 1 shown, a method for detecting meat quality based on flexible bioimpedance imaging is provided, and the method includes:

[0062] Step S1: Obtain the original impedance values and PH of a meat sample to be measured at multiple time points measured based on a preset measurement principle;

[0063] Step S2: Correct the original impedance value of the meat sample to be measured by using the pre-obtained correction coefficient to obtain the corrected original impedance value;

[0064] Step S3: Reconstruct the corrected original impedance value according to the method of optimizing pixels one by one to obtain the reconstructed impedance value;

[0065] Step S4: Determine the spoilage time point of the meat sample to be measured according to the pH values at different time points;

[0066] Step S5: Obtain the reconstructed impedance values of the meat sample to be measured at the spoilage time point and the initial time point, calculate the average reconstructed impedance value at the spoilage time point and the initial time point, calculate the impedance change rate of the meat sample to be measured at the spoilage time point and the initial measurement moment by using the average reconstructed impedance value, and compare it with the impedance change rate of the frozen meat sample pre-calculated. If the impedance change rate of the meat sample to be measured is greater than the impedance change rate of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish; the impedance change rate of the frozen meat sample is the impedance change rate measured after freezing the fresh meat sample.

[0067] In the above method, by measuring the impedance values of the meat sample to be measured at multiple time points and correcting the impedance values by using the correction coefficient, the influences brought by different electrodes, different acquisition times, different acquisition time points, and different acquisition positions are overcome, so that the impedance values are more accurate; at the same time, by using the method of optimizing pixels one by one to reconstruct the corrected original impedance value to obtain the reconstructed impedance value, the accuracy of the measured data can be further optimized, so as to extract the image impedance value to calculate the impedance change rate subsequently. Then, the spoilage time point of the meat quality is obtained through the pH, color difference, and tenderness at different time points. By comparing the impedance change rate of the meat sample to be measured at the spoilage time point and the initial measurement moment with the impedance change rate of the frozen meat sample, if the impedance change rate of the meat sample to be measured is greater than the impedance change rate of the frozen meat sample, it is thawed meat after freezing; if it is less, it is chilled fish. Therefore, the steps of this application are simple and easy to detect, and the detection result is accurate.

[0068] In one embodiment, the measurement principle includes:

[0069] Dividing the measurement position set, the measurement times set, and the measurement time set; the measurement position set includes the front and the back;

[0070] According to the measurement time set, obtain multiple impedance values at each time point according to the measurement position set and the measurement times set at each time point.

[0071] In this embodiment, the meat sample to be measured is processed to clean the surface impurities, and then measured by attaching an integrated flexible impedance electrode patch to the surface of the meat sample. After one measurement, impurities will appear on the surface of the patch, and small tweezers are needed to clean it. After cleaning, it can be reused. Due to the large number of measurements, the adhesiveness of the electrode patch will decrease, and it needs to be replaced after ten measurements. The measurement is carried out after the temperature of the measurement area of the meat sample to be measured is greater than or equal to 1°C and the surface impurities are processed. The above operations are repeated in the next time period until the entire measurement time set is completed.

[0072] When measuring the impedance value of frozen fish, it is grouped and stored under sealed sterilization conditions. In the next measurement time set, the frozen group is taken out and thawed until the temperature of the meat sample measurement area is greater than or equal to 1°C before measurement. The above operations are repeated in the next time period until the entire measurement time set is completed.

[0073] In one embodiment, the pre-obtained correction coefficient is obtained by the following method:

[0074] Cut the fresh meat sample into standard meat samples of the same size and thickness;

[0075] According to the measurement principle, obtain the original impedance values at multiple time points of the fresh meat sample, as well as the PH, color difference, and tenderness of the fresh meat sample at multiple time points;

[0076] The correction coefficient β is the product of the electrode number correction coefficient β1, the position correction coefficient β2, the measurement number reference coefficient β3, and the time reference coefficient β4;

[0077] The electrode number correction coefficient β1 is calculated by the following formula:

[0078]

[0079] Where x is the number of electrodes, U mx is the original impedance value collected by each electrode of the fresh meat sample at a time point, is the average value of the original impedance values collected by all electrodes of the fresh fish meat sample at the corresponding time point;

[0080] The position correction coefficient β2 is calculated by the following formula:

[0081]

[0082] Where U m1 and U m2 are respectively the average value of the original front impedance value and the average value of the original back impedance value of the fresh meat sample obtained at a time point, is the average value of all the original impedance values collected by the fresh meat sample at the same time point;

[0083] The reference coefficient β3 for the number of measurements is calculated by the following formula:

[0084]

[0085] where i is the number of measurements, and U m1i is the original value of the front impedance for the i-th measurement, and U m1 , U m2 are respectively the mean value of the original front impedance and the mean value of the original back impedance of the fresh meat sample obtained at a time point, which is the mean value of all the original impedance values collected at the same time point of the fresh meat sample;

[0086] The reference coefficient β4 for time is calculated by the following formula:

[0087]

[0088] where t n is the time of each measurement, i is the number of measurements, and U m1i is the original value of the front impedance for the i-th measurement, and U m1 , U m2 are respectively the mean value of the original front impedance and the mean value of the original back impedance of the fresh meat sample obtained at a time point, which is the mean value of all the original impedance values collected at the same time point of the fresh meat sample.

[0089] In one embodiment, the corrected impedance value obtained by correcting the original impedance value of the meat sample to be measured with the pre-obtained correction coefficient is calculated by the following formula:

[0090]

[0091] where is the original impedance value, U m is the corrected impedance value, and β is the correction coefficient.

[0092] In one embodiment, as Figure 3 shown, the reconstructed impedance value obtained by reconstructing the corrected original impedance value according to the method of optimizing pixels one by one includes:

[0093] For the corrected original impedance value, imaging is performed, and the impedance is reconstructed by the method of optimizing pixels one by one. Specifically, the spatial reconstructed image is obtained by image processing. It consists of N pixels, and the corresponding number of PBPO models need to be trained. This model reconstructs the image using two methods and selects the better pixels as the finally optimized pixels;

[0094] Reconstruct the impedance value using the first model based on the corrected impedance value and the impedance value before correction;

[0095] The formula of the first model is as follows:

[0096]

[0097] where U m is the corrected impedance measurement data, U m0 is the original impedance data measured before correction, n is the number of measurement data, is the first reconstructed impedance data;

[0098] the impedance value reconstructed by the second model based on the corrected impedance value and the impedance value before correction;

[0099] The formula of the second model is as follows:

[0100]

[0101] where U m is the corrected impedance measurement data, U m0 is the original impedance data measured before correction, n is the number of measurement data, is the second reconstructed impedance data, and λ is the regularization parameter;

[0102] Select all time points according to the set rule to use the first reconstructed impedance data or the second reconstructed impedance data as the finally reconstructed impedance data; the set rule is: according to the PH value of each time point, if the PH value is greater than 7, select the smaller one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point, if the PH is less than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point, if the PH value is less than 7 and greater than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data at the corresponding time point; according to the number of the first reconstructed impedance data and the second reconstructed impedance data selected, if the number of the first reconstructed impedance data selected is greater than the number of the second reconstructed impedance data, then use the first reconstructed impedance data reconstructed by the first model at all time points as the finally reconstructed impedance data.

[0103] In one embodiment, determining the spoilage time point of the meat sample to be measured according to the PH value at different time points includes: when the PH is greater than 7, the meat quality spoils.

[0104] Generally speaking, when the PH value is greater than 7, the meat quality spoils, but in actual judgment, tenderness and color difference value will be combined for auxiliary judgment.

[0105] Specifically, after measuring the pH, color difference, and tenderness, the data is processed to determine the true quality of the fish meat. When measuring, the pH is determined by referring to the method in GB 5009.237-2016 "Determination of pH of Foods", the tenderness is determined by referring to the method in NT / T 1180-2006 "Determination of Meat Tenderness", and the color difference is determined by whiteness measurement. The formula is as follows:

[0106]

[0107] Where, W is the whiteness; L is the brightness of the color; a is the redness of the color; b is the yellowness of the color.

[0108] In one embodiment, the impedance change rate is calculated by the following method:

[0109]

[0110] Where, is the average impedance value at the spoilage time point, is the average impedance value at the initial moment, and S1 is the impedance change rate at the spoilage point;

[0111] Specifically, the reconstructed average impedance value is used to calculate the impedance change rate. The quality of the fish meat over time is determined by measuring three quality parameters, and the time point t at which the meat quality deteriorates is found. The principle is that the quality of chilled fresh meat and frozen meat will continuously decline over time. The meat sample with the fastest quality change is found, and the time point at which it deteriorates is determined through quality parameters such as pH, color difference, and tenderness, so as to calculate the image change rate S0 of the fresh meat sample.

[0112] In one embodiment, a meat quality detection system based on flexible bio-impedance imaging is provided. The system includes:

[0113] Data acquisition module: used to acquire the original impedance values and pH of the meat sample to be measured at multiple time points measured based on preset measurement principles;

[0114] Impedance value correction module: used to correct the original impedance value of the meat sample to be measured using a pre-acquired correction coefficient to obtain the corrected original impedance value;

[0115] Reconstructed impedance module: used to reconstruct the corrected original impedance value to obtain the reconstructed impedance value according to the method of optimizing pixels one by one;

[0116] Spoilage time point calculation module: used to determine the spoilage time point of the meat sample to be measured according to the pH values at different time points;

[0117] Judgment module: It is used to obtain the reconstructed impedance values of the meat sample to be tested at the spoilage time point and the initial time point, calculate the average reconstructed impedance values at the spoilage time point and the initial time point, calculate the impedance change rate of the meat sample to be tested from the spoilage time point to the initial measurement moment using the average reconstructed impedance values, and compare it with the impedance change rate of the frozen meat sample calculated in advance. If the impedance change rate of the meat sample to be tested is greater than that of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish. The impedance change rate of the frozen meat sample is the impedance change rate measured after freezing the fresh meat sample.

[0118] In this embodiment, the data acquisition module is an impedance image measurement module, which is used to connect to the integrated flexible impedance electrode patch to measure the original impedance image data of the meat sample. It includes an isolated IO module, a USB connection module, a power supply module, and a measurement and control module. The isolated IO module connects the impedance imaging system to external devices to achieve functions such as data acquisition, signal control, and information interaction. The USB module is used to connect to the interface module of an external computer. The power supply module provides energy for the impedance imaging system to operate, and the measurement and control module is externally connected to the electrode to measure the impedance imaging data of the fish meat.

[0119] The processing module includes an impedance value correction module, a reconstructed impedance module, a spoilage time point calculation module, and a judgment module, which are used to process the measured original impedance image data to calculate the image change rate and determine the quality of the meat sample. The original impedance image data obtained by the image measurement module is processed through a reference coefficient and PBPO optimization to obtain an impedance image. The average impedance of the region of interest is calculated from the impedance image after processing, and the image change rate of the meat sample to be tested is calculated. The image change rate of the meat sample to be tested is compared with the image change rate of the frozen meat sample to determine whether it is chilled or thawed meat.

[0120] It also includes an output module, which is used to output the result of discriminating the meat sample, and an error reporting and repair module is set up, which can detect system calculation errors and perform recalculation and repair functions. It includes a system error reporting and repair module and a visualization output module. System error reporting and repair module: It is used to remind the user whether the measurement result is normal and detect whether the previous modules are running normally. If a calculation failure occurs, this module can be used to perform a repeated calculation to solve the failure. If a major system failure occurs and repeated calculation can no longer solve the problem, it will remind the user that a failure has occurred and wait for a professional engineer to repair it. Visualization output module: It outputs the fish meat discrimination result and is associated with the system error reporting and repair module, displays whether the system is running normally or abnormally, reminds the user whether the measurement result is normal, and makes the user more trusting of the machine.

[0121] Login interface, which is used for users to register and log in to their accounts.

[0122] Database module, which is used to store various data and is called to support the normal operation of other systems.

[0123] For the specific limitations of a meat quality detection system based on flexible bio-impedance imaging, reference can be made to the limitations of a meat quality detection method based on flexible bio-impedance imaging in the above text, which will not be elaborated here. Each module in the above-mentioned meat quality detection system based on flexible bio-impedance imaging can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0124] In one embodiment, a computer device is provided, and this computer device can be a server. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the above-mentioned meat quality detection method based on flexible bio-impedance imaging.

[0125] In one embodiment, a computer program product is further provided, including a computer program / instructions, and when the computer program / instructions are executed by the processor, they involve all or part of the processes in the method of the above embodiment.

[0126] Those of ordinary skill in the art can understand that to implement all or part of the processes in the method of the above embodiment, it can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database, or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0127] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0128] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for detecting the quality of meat based on flexible bio-impedance imaging, characterized in that, The method includes: Obtaining the original impedance values and pH at multiple time points of the meat sample to be measured based on a preset measurement principle; Using the pre-obtained correction coefficient to correct the original impedance value of the meat sample to be measured to obtain the corrected original impedance value; Reconstructing the corrected original impedance value according to the method of optimizing pixels one by one to obtain the reconstructed impedance value; Determining the spoilage time point of the meat sample to be measured according to the pH values at different time points; Obtaining the reconstructed impedance values of the meat sample to be measured at the spoilage time point and the initial time point, calculating the average reconstructed impedance value at the spoilage time point and the initial time point, calculating the impedance change rate of the meat sample to be measured at the spoilage time point and the measurement initial moment using the average reconstructed impedance value, and comparing it with the impedance change rate of the frozen meat sample calculated in advance. If the impedance change rate of the meat sample to be measured is greater than the impedance change rate of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish; the impedance change rate of the frozen meat sample is the impedance change rate measured after freezing the fresh meat sample.

2. The method for detecting meat quality based on flexible bio-impedance imaging according to claim 1, wherein, The measurement principle includes: Dividing the measurement position set, the measurement times set, and the measurement time set; the measurement position set includes the front and the back; Obtaining multiple impedance values at each time point according to the measurement position set and the measurement times set at each time point according to the measurement time set.

3. The method for detecting meat quality based on flexible bioimpedance imaging according to claim 2, wherein The pre-obtained correction coefficient is obtained through the following method: Cutting the fresh meat sample into standard meat samples of the same size and thickness; Obtaining the original impedance values at multiple time points of the fresh meat sample according to the measurement principle, as well as the pH, color difference, and tenderness of the fresh meat sample at multiple time points; The correction coefficient β is the product of the electrode number correction coefficient β1, the position correction coefficient β2, the measurement times reference coefficient β3, and the time reference coefficient β4; The electrode number correction coefficient β1 is calculated through the following formula: where x is the number of electrodes, and U mx is the original impedance value collected by each electrode of the obtained fresh meat sample at a time point, is the mean value of the original impedance values collected by all electrodes of the fresh fish sample at the corresponding time point; The position correction coefficient β2 is calculated through the following formula: Among them, U m1 , U m2 are respectively the mean of the original front impedance value and the mean of the original back impedance value of the fresh meat sample obtained at a time point, is the mean of all the original impedance values collected from the fresh meat sample at the same time point; The measurement times reference coefficient β3 is calculated through the following formula: where i is the number of measurements, and U m1i is the original value of the front impedance for the i-th measurement, and U m1 , U m2 are the mean of the original values of the front impedance and the mean of the original values of the back impedance of the fresh meat sample obtained at a time point, respectively, and are the mean of all the original impedance values collected at the same time point of the fresh meat sample; The time reference coefficient β4 is calculated through the following formula: Among them, t n is the time of each measurement, i is the number of measurements, and U m1i is the original value of the front impedance of the i-th measurement, and U m1 , U m2 are respectively the mean value of the original values of the front impedance of the fresh meat samples obtained at a time point and the mean value of the original values of the reverse impedance, and the mean value of all the original impedance values collected at the same time point of the fresh meat samples.

4. The method for detecting meat quality based on flexible bio-impedance imaging according to claim 3, characterized in that, The correction of the original impedance value of the meat sample to be measured using the pre-obtained correction coefficient to obtain the corrected impedance value is calculated through the following formula: Among them, is the original impedance value, U m is the impedance value after correction, and β is the correction coefficient.

5. The method for detecting meat quality based on flexible bioimpedance imaging according to claim 1, wherein The reconstruction of the corrected original impedance value according to the method of optimizing pixels one by one to obtain the reconstructed impedance value includes: Reconstructing the impedance value using the first model based on the corrected impedance value and the impedance value before correction; The formula of the first model is: Among them, U m is the impedance measurement data after correction, and U m0 is the original impedance data measured before correction. n is the number of measurement data, is the first reconstructed impedance data; Reconstructing the impedance value using the second model based on the corrected impedance value and the impedance value before correction; The formula of the second model is: Among them, U m is the corrected impedance measurement data, and U m0 is the original impedance data measured before correction. n is the number of measurement data, is the impedance data reconstructed for the second time, and λ is the regularization parameter; Select all time points according to the set rules to determine whether the first reconstructed impedance data or the second reconstructed impedance data is used as the finally reconstructed impedance data; the set rules are as follows: according to the pH value at each time point, if the pH value is greater than 7, select the smaller one of the first reconstructed impedance data and the second reconstructed impedance data corresponding to the time point; if the pH is less than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data corresponding to the time point; if the pH value is less than 7 and greater than 6, select the larger one of the first reconstructed impedance data and the second reconstructed impedance data corresponding to the time point; according to the number of the first reconstructed impedance data and the second reconstructed impedance data selected, if the number of the first reconstructed impedance data selected is greater than the number of the second reconstructed impedance data, then all time points use the first reconstructed impedance data reconstructed by the first model as the finally reconstructed impedance data.

6. The method for detecting meat quality based on flexible bio-impedance imaging according to claim 1, characterized in that, Determining the spoilage time point of the meat sample to be measured according to the pH value at different time points includes: when the pH is greater than 7, the meat quality deteriorates.

7. The method for detecting meat quality based on flexible bio-impedance imaging according to claim 1, wherein The impedance change rate is calculated in the following way: Among them, is the average impedance value at the spoilage time point, is the average impedance value at the initial moment, and S1 is the impedance change rate at the spoilage point.

8. A meat quality detection system based on flexible bio-impedance imaging, characterized in that, The system includes: Data acquisition module: used to acquire the original impedance values and pH values of the meat sample to be measured at multiple time points measured based on the preset measurement principle; Impedance value correction module: used to correct the original impedance value of the meat sample to be measured by using the pre-acquired correction coefficient to obtain the corrected original impedance value; Reconstructed impedance module: used to reconstruct the corrected original impedance value to obtain the reconstructed impedance value according to the method of optimizing pixels one by one; Spoilage time point calculation module: used to determine the spoilage time point of the meat sample to be measured according to the pH value at different time points; Judgment module: used to acquire the reconstructed impedance values of the meat sample to be measured at the spoilage time point and the initial time point, calculate the average reconstructed impedance values at the spoilage time point and the initial time point, calculate the impedance change rate of the meat sample to be measured at the spoilage time point and the measurement initial moment by using the average reconstructed impedance values, and compare it with the impedance change rate of the frozen meat sample calculated in advance. If the impedance change rate of the meat sample to be measured is greater than the impedance change rate of the frozen meat sample, it is thawed fish; if it is less, it is chilled fish; the impedance change rate of the frozen meat sample is the impedance change rate measured after freezing the fresh meat sample.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, it implements the steps of the method described in any one of claims 1 to 7.

Images