A method for detecting heat-killed s. sonnei content in PE packaging cold fresh pork chop based on hyperspectral imaging technology

Abstract

This invention discloses a method for detecting the content of *O. heat-killing bacterium* in PE-packaged chilled pork chops based on hyperspectral imaging technology. The prediction method includes: using chilled pork chops inoculated with *O. heat-killing bacterium* and packaged in polyethylene (PE) film as the research object; acquiring hyperspectral images of the PE-packaged chilled pork chops using a hyperspectral imaging system and determining the *O. heat-killing bacterium* content; extracting the full-band spectral information of the images and selecting characteristic wavelengths; establishing prediction models for *O. heat-killing bacterium* content based on the full-band and characteristic wavelengths using various modeling methods; and predicting the *O. heat-killing bacterium* content of the PE-packaged chilled pork chops based on the established models. This invention enables non-destructive detection of *O. heat-killing bacterium* content in PE-packaged chilled pork chops with high accuracy and speed, thus providing a technical reference for the non-destructive detection of microbial indicators in packaged meat products.

Description

Technical Field

[0001] This invention relates to the field of hyperspectral nondestructive testing, specifically to a method for detecting the content of *Heterobacter pyridostigmine* in PE-packaged chilled pork chops based on hyperspectral imaging technology. Background Technology

[0002] Chilled meat, also known as fresh meat, refers to fresh meat whose carcasses are rapidly cooled to 0-4°C after slaughter and maintained at this temperature during subsequent storage and transportation. It boasts advantages such as easy digestibility, excellent flavor, and rich nutrition, making it undoubtedly the meat product with the greatest development potential, especially considering the dietary habits of Chinese consumers. However, its short shelf life has always been a major obstacle to the further development of chilled pork, and external microbial contamination is the primary cause of this shortened shelf life. *Heat-killing bacteria* is a Gram-positive bacterium that can grow rapidly under low-temperature, anaerobic conditions (0-4°C) and is the dominant spoilage bacterium causing the spoilage of chilled pork. Therefore, detecting *Heat-killing bacteria* in chilled pork is of great significance in evaluating its freshness.

[0003] The most common method for detecting microbial indicators in chilled pork is the plate count method specified in national standards, which is accurate and effective in observing colony morphology. In recent years, newer methods for detecting microbial counts include colony test strips and quantitative PCR. While these methods can effectively detect total bacterial counts, they require extensive preparation and specialized operation, are less efficient, and can even damage the meat being tested. Therefore, they are not suitable for large-scale online testing and cannot meet the testing needs of automated factory production and import / export trade. Consequently, the meat industry needs a rapid and non-destructive method for detecting microbial indicators in chilled pork.

[0004] Hyperspectral imaging technology, as an emerging platform technology, possesses high spectral resolution, excellent imaging capabilities, and efficient and rapid non-destructive testing capabilities. This technology combines the advantages of both spectral and imaging technologies, enabling the detection of not only the physicochemical properties of samples but also the acquisition of their spatial distribution information, thus obtaining combined detection results. Existing research indicates that hyperspectral imaging technology can be effectively applied to the non-destructive testing of microbial indicators in unpackaged chilled pork; however, this technology has not yet been applied to the microbial detection of packaged chilled pork.

[0005] Application No. 2018102251286 discloses an online rapid detection method for *Heterospora heat-killing* content in chicken meat. The method involves acquiring hyperspectral images of chicken samples from a calibration set, preprocessing the acquired spectra, identifying the target region, and extracting the average spectral data. The extracted spectral data is then substituted into a formula to obtain the final result. This invention extracts 23 optimal wavelengths from 486 wavelengths across the entire spectrum to eliminate a large amount of redundant information and extract useful information, thereby reducing the computational load of data analysis and improving the accuracy of the partial least squares model to meet the needs of large-scale online production in meat processing enterprises. Compared with existing technologies, this invention has the following advantages: It does not require preprocessing of the sample, only performs non-contact spectral scanning, and is non-destructive; it does not use any chemical reagents, making it both environmentally friendly and cost-effective; and it is easy to operate, saves time, and enables large-scale online detection of *Heterospora heat-killing* content in chicken meat.

[0006] This scheme represents a non-destructive testing method for microbial indicators in unpackaged chilled meat, but it differs from real-world applications. In actual sales, much chilled meat is often packaged with cling film before being distributed, making the above scheme unsuitable for directly measuring microbial content in chilled meat during production and daily life. Trays combined with polyethylene (PE) cling film are a widely used packaging method for commercially available chilled pork. Therefore, monitoring the content of heat-killed Solanum bacteria in PE-packaged chilled pork is crucial for ensuring its edibility and commercial value. Summary of the Invention

[0007] To address the aforementioned issues, this invention provides a method for detecting the content of *Heterosporium oxysporum* in PE-packaged chilled pork chops based on hyperspectral imaging technology. This method can rapidly, accurately, and non-destructively detect the *Heterosporium oxysporum* content in PE-packaged chilled pork chops, thus meeting the requirements for non-destructive testing of microbial indicators in packaged meat products.

[0008] To achieve the above objectives, the present invention provides the following solution:

[0009] This invention proposes a method for detecting the content of *Heat-killing bacteria* in PE-packaged chilled pork chops based on hyperspectral imaging technology, comprising the following steps:

[0010] Step 1: Select chilled pork chops that are similar in size and uniform in thickness;

[0011] Step 2: Soak the pre-sterilized chilled pork chops in a heat-killing bacteria suspension; then cover the surface with a layer of PE plastic wrap for contact packaging.

[0012] Step 3: Acquire hyperspectral reflectance images of chilled pork chops in PE packaging from 0-9 days; calibrate the acquired hyperspectral images to obtain standard images;

[0013] Step four: After step three is completed, the heat-killed Solanum bacteria content of the packaged chilled pork chops is determined.

[0014] Step 5: Extract full-band spectral information from the hyperspectral image and establish a prediction model for the content of Thermophora thermophila based on full-band spectral information using various modeling and preprocessing methods.

[0015] Step six: Based on step five, further screen characteristic wavelengths, optimize the model, and establish a predictive model for the content of *Heterospora thermophila* based on characteristic wavelengths;

[0016] Step 7: Use the established prediction model to detect the content of *Synthia spp.* in PE-packaged chilled pork chops.

[0017] The diameter of chilled pork chops is approximately 10cm and the height is approximately 1cm.

[0018] The pre-sterilization conditions for chilled pork chops were: wiping with 75% alcohol and irradiation with ultraviolet light for 15 minutes; the concentration of the heat-killing *Synthia spp.* bacterial suspension was 10. 3 -10 4 CFU / mL; the thickness of the plastic wrap is 0.01 mm, and the oxygen permeability is 14000 cm⁻¹. 3 / m 2 24h atm, carbon dioxide transmission rate 60000cm³ 3 / m 2 24h·atm, water vapor transmission rate 20-100g / m 2 ·24h.

[0019] A visible-near-infrared hyperspectral imaging system and a short-wave infrared hyperspectral imaging system were used. The visible-near-infrared hyperspectral imaging system produced a single-wavelength image of 804×534 pixels with a spectral resolution of 2.8 nm. The distance between the camera lens and the sample was 28 cm, the exposure time was 3 ms, the acquisition speed was 7.23 mm / s, the light source intensity was 45 W, the projection angle was 45° to the horizontal, and the distance to the sample was 30 cm. The short-wave infrared hyperspectral imaging system produced a single-wavelength image of 320×472 pixels with a spectral resolution of 6.2 nm. The distance between the camera lens and the sample was 26 cm, the exposure time was 3.5 ms, the acquisition speed was 13.78 mm / s, the light source intensity was 255 W, the projection angle was 45° to the horizontal, and the distance to the sample was 31 cm.

[0020] The culture medium used was STAA agar medium.

[0021] ENVI 5.1 was used to extract the spectral reflectance of chilled pork chops and perform image segmentation. The average spectral reflectance of the target region was used as the spectral information of the chilled pork chops. The modeling methods used included partial least squares (PLS) and support vector machine (SVM). The preprocessing methods used included standard normal variate (SNV), multiplicative scatter correction (MSC), orthogonal signal correction (OSC), smoothing, and first derivative (1st).

[0022] Feature wavelength selection methods include the Successive projections algorithm (SPA) and the Competitive adaptive reweighted sampling (CARS).

[0023] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0024] This invention applies hyperspectral imaging technology to the detection of *Heterostilbene* content in PE-packaged chilled pork chops, enabling rapid, accurate, and non-destructive detection of *Heterostilbene* content, thus providing assistance for the non-destructive detection of microbial indicators in packaged meat products. Attached Figure Description

[0025] Figure 1 This is a flowchart of a method for detecting the content of heat-killing bacteria in PE-packaged chilled pork chops based on hyperspectral imaging technology.

[0026] Figure 2 The process of extracting average hyperspectral data from hyperspectral images of chilled pork chops in PE packaging.

[0027] Figure 3 Reflectance spectra of chilled pork chop samples packaged in PE in the 400-1000nm visible-near infrared band (a) and the 1000-2000nm short-wave infrared band (b).

[0028] Figure 4 The optimal modeling results for the entire spectrum of chilled pork chops packaged in PE packaging.

[0029] Figure 5Results of SPA screening in the 400-1000nm band for PE packaged chilled pork chops.

[0030] Figure 6 Results of SPA screening in the 1000-2000nm band for PE packaged chilled pork chops.

[0031] Figure 7 The optimal modeling results for screening characteristic wavelengths for PE-packaged chilled pork chop SPA are shown in the figure.

[0032] Figure 8 CARS screening results for chilled pork chops in PE packaging in the 400-1000nm band.

[0033] Figure 9 CARS screening results for chilled pork chops in PE packaging in the 1000-2000nm band.

[0034] Figure 10 The optimal modeling results for screening characteristic wavelengths for PE-packaged chilled pork chop SPA are shown in the figure. Detailed Implementation

[0035] The technical solution of the present invention will be further described in detail with reference to the following specific examples.

[0036] The purpose of this invention is to provide a method for detecting the content of *Typhonium pyridae* in PE-packaged chilled pork chops based on hyperspectral imaging technology. This method can quickly, accurately, and non-destructively detect the content of *Typhonium pyridae* in PE-packaged chilled pork chops, thereby meeting the requirements for non-destructive testing of microbial indicators in packaged meat products.

[0037] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] like Figure 1 As shown, the present invention provides a method for detecting the content of *Heterobacter pyridostigmine* in PE-packaged chilled pork chops based on hyperspectral imaging technology, comprising the following steps:

[0039] Step 1: Select chilled pork chops that are similar in size and uniform in thickness;

[0040] Step 2: Soak the pre-sterilized chilled pork chops in a heat-killing bacteria suspension; then cover the surface with a layer of PE plastic wrap for contact packaging.

[0041] Step 3: Acquire hyperspectral reflectance images of chilled pork chops in PE packaging from 0-9 days; calibrate the acquired hyperspectral images to obtain standard images;

[0042] Step four: After step three is completed, the heat-killed Solanum bacteria content of the packaged chilled pork chops is determined.

[0043] Step 5: Extract full-band spectral information from the hyperspectral image and establish a prediction model for the content of Thermophora thermophila based on full-band spectral information using various modeling and preprocessing methods.

[0044] Step six: Based on step five, further screen characteristic wavelengths, optimize the model, and establish a predictive model for the content of *Heterospora thermophila* based on characteristic wavelengths;

[0045] Step 7: Use the established prediction model to detect the content of *Synthia spp.* in PE-packaged chilled pork chops.

[0046] Step one specifically includes:

[0047] In a sterile laminar flow hood, chilled pork chops are evenly cut into round pieces with a diameter of about 10cm and a height of about 1cm.

[0048] Step two specifically includes:

[0049] (1) The fully activated *Heterospora thermophila* was diluted with 0.85% sterile physiological saline to prepare a *Heterospora thermophila* suspension, and the concentration of the suspension was adjusted to 10. 3 -10 4 CFU / mL.

[0050] (2) Wipe with 75% alcohol and sterilize under ultraviolet light for 15 min. Immerse the pre-sterilized chilled pork chop samples in heat-killing bacteria suspension for 15 s, and then cover all samples with a layer of sterile polyethylene plastic wrap for contact packaging and store at 4°C.

[0051] (3) The thickness of the polyethylene cling film is 0.01 mm, and the oxygen permeability is 14000 cm⁻¹. 3 / m 2 24h atm, carbon dioxide transmission rate 60000cm³ 3 / m 2 24h·atm, water vapor transmission rate 20-100g / m 2 ·24h.

[0052] Step three specifically includes:

[0053] (1) Acquisition of hyperspectral images: Hyperspectral reflectance images of chilled pork chops were acquired by line scanning using a visible-near-infrared hyperspectral imaging system and a short-wave infrared hyperspectral imaging system. The single-wavelength image pixel of the visible-near-infrared hyperspectral imaging system was 804×534, and the spectral resolution of the imaging spectrometer was 2.8nm. After several preliminary experiments, the distance between the camera lens and the sample was set to 28cm, the exposure time was 3ms, the platform movement speed was 7.23mm / s, the light source intensity was set to 45W, the projection angle was at a 45° angle to the horizontal, and the distance from the sample was 30cm to minimize the influence of shadows on the hyperspectral images. The single-wavelength image pixel of the short-wave infrared hyperspectral imaging system is 320×472, and the spectral resolution of the imaging spectrometer is 6.2nm. After multiple preliminary experiments, the distance between the camera lens and the sample was set to 26cm, the exposure time was 3.5ms, the platform movement speed was 13.78mm / s, the light source intensity was set to 255W, the projection angle was at a 45° angle to the horizontal, and the distance to the sample was 31cm, so as to reduce the influence of shadows on the hyperspectral image.

[0054] (2) Hyperspectral Image Correction: Before acquiring hyperspectral images, dark correction and white correction are required to reduce the thickness differences between samples, weaken the camera's dark current effect, and reduce the influence of ambient light on the hyperspectral images. Dark correction uses a dark cap with very low reflectivity to the camera lens, while white correction uses a white polytetrafluoroethylene (PTFE) plate. The corrected reflectance image is then calculated using the following formula:

[0055]

[0056] Where R is the corrected reflectance image, I0 is the initial reflectance image, and B... r It is a dark reference image, I r It is a white reference image, which, after image correction, can be used for subsequent extraction and modeling of spectral values.

[0057] Step four specifically includes:

[0058] Following the procedure outlined in GB / T 4789.2-2016 "National Food Safety Standard - Microbiological Examination of Food: Determination of Total Colony Count", 10g of chilled pork ribs were aseptically cut at appropriate refrigeration intervals. The ribs were then minced using sterilized scissors and placed in a sterile homogenizing bag containing 90mL of 0.85% physiological saline. The bag was then placed in a shaking incubator and shaken for 10 minutes. Multiple dilutions were sequentially applied at a 1:9 ratio. Three suitable dilutions were homogenized, and 0.1mL of each was transferred to cooled, solidified STAA agar medium. The bacterial suspension was then evenly spread onto the medium using a spreader, one spreader per dilution. After spreading, the medium was incubated at 30±1℃ for 48 hours before bacterial counting.

[0059] Step five specifically includes:

[0060] (1) Extraction of full-band spectral information from hyperspectral images: The spectral reflectance of chilled pork chop samples was extracted and the images were segmented using the image processing software ENVI 5.1. The specific process for spectral information extraction is as follows: Figure 2 As shown, first, open the corrected hyperspectral image of the target sample. Then, using ENVI 5.1 software, select the region of interest and extract the spectral reflectance of the target region. Finally, use the average spectral reflectance of the target region as the spectral information of the chilled pork chop sample. The extracted spectral information is shown below. Figure 3 As shown.

[0061] (2) Prediction model for the content of *Heat-killing bacteria* in PE-packaged chilled pork chops: Before modeling, all samples were divided into a calibration set and a prediction set. One sample out of every four samples was selected for the prediction set, resulting in a final ratio of 3:1 between the calibration and prediction sets. It was also important to ensure that the variation range of *Heat-killing bacteria* content in the calibration set covered the variation range of the prediction set. The modeling methods used included partial least squares (PLS) and support vector machine (SVM). The preprocessing methods used included standard normal variate (SNV), multiplicative scatter correction (MSC), orthogonal signal correction (OSC), smoothing, and first derivative (1st). The results showed that the OSC-PLS model in the 400-1000 nm band and the 1st-PLS model in the 1000-2000 nm band had better performance, with their respective prediction coefficients (R0) being significantly higher. p 2 The R² values ​​are 0.943 and 0.675, respectively, and the root mean square error of prediction (RMSEP) are 0.402 log CFU / g and 0.940 log CFU / g, respectively. Comparing the R² values ​​of the two models... p 2 The RMSEP results show that the modeling results for the 400-1000nm band are significantly better than those for the 1000-2000nm band. Furthermore, the relative percent deviation (RPD) of the model built for the 400-1000nm spectral band reaches 4.188, greater than 3.0, indicating excellent predictive ability. In contrast, the RPD of the model built for the 1000-2000nm spectral band is 1.791, less than 2.5, indicating poorer predictive ability. The best modeling results are as follows: Figure 4 As shown, the model established using full-band spectral information in the 400-1000nm visible-near-infrared band has good predictive performance and can be used for non-destructive detection of the heat-killing bacteria content in PE-packaged chilled pork chops.

[0062] Step six specifically includes:

[0063] (1) Extraction of characteristic wavelengths based on the SPA algorithm: The SPA algorithm was used to screen the characteristic wavelengths in the visible-near infrared band of 400-1000nm for PE-packaged chilled pork chops samples. Figure 5 This study examines the changes in root mean square error (RMSE) with the increase of the number of feature variables and the distribution of these feature variables during the SPA screening process. A smaller RMSE indicates higher model accuracy. Figure 5 (a) It can be seen that when the number of characteristic wavelengths is greater than 14, the root mean square error gradually tends to stabilize. Therefore, 14 characteristic wavelengths are selected as the output result. The distribution of specific characteristic variables is as follows: Figure 5 As shown in (b), the 14 characteristic wavelengths finally selected are 422.85, 432.34, 437.77, 496.95, 557.32, 575.77, 584.32, 600.03, 634.49, 653.25, 692.39, 765.33, 815.13, and 999.09 nm. Figure 6 This study investigates the changes in root mean square error (RMSE) and the distribution of characteristic variables as the number of characteristic variables increases during the screening of characteristic wavelengths in the 1000-2000 nm short-wave infrared band for PE-packaged chilled pork rib samples using SPA (Spectrophotometric Analysis and Spatial Analysis) method. Figure 6 (a) It can be seen that when the number of characteristic wavelengths is greater than 14, the root mean square error gradually tends to stabilize. Therefore, 14 characteristic wavelengths are also selected as the output result. The distribution of specific characteristic variables is as follows: Figure 6 As shown in (b), the 14 final selected characteristic wavelengths are 994.80, 1013.63, 1039.10, 1144.75, 1185.73, 1269.53, 1290.82, 1377.01, 1420.62, 1604.23, 1736.26, 1823.13, 1866.00, and 1971.02 nm. The optimal modeling result is as follows: Figure 7 As shown.

[0064] (2) Extraction of characteristic wavelengths based on CARS algorithm: CARS was used to screen characteristic wavelengths in the 400-1000nm visible-near infrared band of PE packaged chilled pork chops samples. Figure 8 In the diagram, (a), (b), and (c) represent the changes in sampling variance, root mean square error of cross-validation, and regression coefficient path as the number of sampling runs increases, respectively. Figure 8 As shown in (a), the number of sampling variations shows a decreasing trend as the number of sampling runs increases. Figure 8(b) shows that the root mean square error of cross-validation exhibits a trend of first decreasing slowly and then increasing rapidly with the increase of the number of sampling runs. This indicates that during the entire sampling process, after removing all irrelevant variables, the removal of effective variables begins. The optimal point is when the root mean square error of cross-validation reaches its minimum value, signifying that all irrelevant variables have been removed. Figure 8 (c) It can be seen that when the number of sampling runs reaches 27, the 25 variables retained are the characteristic wavelengths to be screened, which are 406.69, 425.56, 428.27, 429.62, 455.52, 571.51, 585.75, 598.60, 622.98, 638.82, 640.26, 653.25, 657.59, 661.93, 663.38, 666.27, 692.39, 711.31, 769.72, 772.65, 774.11, 845.91, 850.31, 949.72, and 999.09 nm. Figure 9 In the figures (a), (b), and (c), the changes in sampling variance, root mean square error of cross-validation, and regression coefficient path as the number of sampling runs increased during the screening of characteristic wavelengths in the 1000-2000 nm short-wave infrared band using CARS for PE-packaged chilled pork chops samples are shown. Similarly, Figure 9 (a) indicates that as the number of sampling runs increases, the sampling variance shows a decreasing trend, while... Figure 9 (b) Determine the optimal point at which all irrelevant variables are removed based on the minimum root mean square error of cross-validation. Figure 9 (c) It can be seen that when the number of sampling runs reaches 23, the 21 retained variables are the selected characteristic wavelengths, which are 994.80, 1007.33, 1032.70, 1039.10, 1124.52, 1144.75, 1199.54, 1248.37, 1255.41, 1312.21, 1319.37, 1326.54, 1427.91, 1604.23, 1611.59, 1655.72, 1685.08, 1758.09, 1794.32, 1823.13, and 1922.44 nm. The optimal modeling result is as follows: Figure 10 As shown.

[0065] (3) SPA was used to screen characteristic wavelengths in both bands, and 14 characteristic wavelengths were selected in each band. Among them, the SPA-OSC-PLS model in the 400-1000nm band and the SPA-OSC-PLS model in the 1000-2000nm band showed better predictive performance for the content of *Heterospora thermophila*, and their respective R... p 2The RMSEP values ​​were 0.919 and 0.665, respectively; the RMSEP values ​​were 0.476 log CFU / g and 0.959 log CFU / g, respectively; and the RPD values ​​were 3.537 and 1.755, respectively. CARS was used to screen characteristic wavelengths in two bands, identifying 25 and 21 characteristic wavelengths respectively. The CARS-SNV-PLS model in the 400-1000 nm band and the CARS-OSC-PLS model in the 1000-2000 nm band showed the best prediction results for *Heterospora thermophila* content, with their respective RMSEP values ​​being 0.476 log CFU / g and 0.959 log CFU / g, respectively. p 2 The values ​​were 0.924 and 0.756, respectively; the RMSEP was 0.458 log CFU / g and 0.841 log CFU / g, respectively; and the RPD was 3.676 and 2.002, respectively. The results indicate that the model established using the characteristic wavelengths of the 400-1000 nm visible-near-infrared band has good predictive performance and can be used for the non-destructive detection of *Heat-killing* content in PE-packaged chilled pork chops.

[0066] This invention discloses a method for detecting the content of *O. heat-killing bacterium* in PE-packaged chilled pork chops based on hyperspectral imaging technology. Traditional methods for detecting microbial indicators require extensive preparation and specialized operation, resulting in low efficiency and even damage to the meat being tested. These methods cannot meet the needs of automated factory production and import / export trade. While hyperspectral imaging technology is well-suited for non-destructive testing of microbial indicators in unpackaged chilled pork, it has not yet been applied to the microbial detection of packaged chilled pork. Therefore, this invention applies hyperspectral imaging technology to the detection of *O. heat-killing bacterium* content in PE-packaged chilled pork chops, thus providing a technical reference for hyperspectral imaging detection of microbial indicators in packaged chilled pork.

[0067] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions claimed by the present invention.

Claims

1. A method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops based on hyperspectral imaging technology, characterized in that... Includes the following steps: Step 1: Select chilled pork chops that are similar in size and uniform in thickness; Step 2: Soak the pre-sterilized chilled pork chops in a suspension of heat-killing bacteria. Use PE cling film to cover its surface; Step 3: Collect hyperspectral reflectance images of chilled pork chops in PE packaging from 0 to 9 days to obtain spectral information of chilled pork chops in PE packaging sold in the market within 0 to 9 days; calibrate the collected hyperspectral images to obtain standard images; Step four: After step three is completed, the heat-killed Solanum bacteria content of the packaged chilled pork chops is determined. Step 5: Extract the full-band spectral information of the 400-1000 nm visible-near infrared band from the hyperspectral image. After preprocessing, establish a prediction model for the content of *Heterospora thermophila* based on the full-band spectral information. In Step 5, ENVI 5.1 is used to extract the spectral reflectance of chilled pork chops and perform image segmentation. Finally, the average spectral reflectance of the target area is used as the spectral information of the chilled pork chops. Feature wavelengths of the full-band spectral information of the 400-1000 nm visible-near infrared band are screened. Based on the spectral information of the feature wavelengths, the orthogonal signal correction method (OSC) is used for preprocessing, and partial least squares (PLS) is used to establish the model. Step 6: Use the established prediction model to detect the content of *Synthia spp.* in PE-packaged chilled pork chops.

2. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 1, characterized in that: In step one, the diameter of the chilled pork chop is approximately 10 cm and the height is approximately 1 cm.

3. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 1, characterized in that: In step two, the pre-sterilization conditions for the chilled pork chops are: wiping with 75% alcohol and irradiation with ultraviolet light for 15 minutes; the concentration of the heat-killing *Synthia spp.* bacterial suspension is 10. 3 -10 4 CFU / mL; the thickness of the plastic wrap is 0.01 mm, and the oxygen permeability is 14000 cm⁻¹. 3 / m 2 24h atm, carbon dioxide transmission rate 60000 cm⁻¹ 3 / m 2 24h·atm, water vapor transmission rate 20-100g / m 2 ·24h.

4. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 1, characterized in that: Step three utilizes a visible-near-infrared hyperspectral imaging system and a short-wave infrared hyperspectral imaging system. The visible-near-infrared hyperspectral imaging system has a single-wavelength image resolution of 804×534 pixels and a spectral resolution of 2.8 nm. The distance between the camera lens and the sample is 28 cm, the exposure time is 3 ms, the acquisition speed is 7.23 mm / s, the light source intensity is 45 W, the projection angle is 45° to the horizontal, and the distance to the sample is 30 cm. The short-wave infrared hyperspectral imaging system has a single-wavelength image resolution of 320×472 pixels and a spectral resolution of 6.2 nm. The distance between the camera lens and the sample is 26 cm, the exposure time is 3.5 ms, the acquisition speed is 13.78 mm / s, the light source intensity is 255 W, the projection angle is 45° to the horizontal, and the distance to the sample is 31 cm.

5. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 1, characterized in that: The selective medium used for the quantification of *Heat-killing Fever* in step four is STAA agar medium.

6. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 1, characterized in that: Feature wavelength selection methods include the continuous projection algorithm (SPA) and the competitive adaptive reweighting algorithm (CARS).

7. The method for detecting the content of *Synthia spp.* in PE-packaged chilled pork chops according to claim 6, characterized in that: Based on the full-band spectral information of the 400-1000 nm visible-near infrared band, the continuous projection algorithm SPA is used to screen characteristic wavelengths. Based on the spectral information of the characteristic wavelengths, the orthogonal signal correction method OSC is used for preprocessing, and the partial least squares PLS is used to establish the model. or Based on the full-band spectral information of the 400-1000 nm visible-near infrared band, the competitive adaptive reweighting algorithm CARS is used to screen characteristic wavelengths. Based on the spectral information of the characteristic wavelengths, the standard normal variable method SNV is used for preprocessing, and the partial least squares PLS is used to establish the model.

Images