A method and apparatus for detecting the viability of Poria cocos strains

Abstract

This invention belongs to the field of biological monitoring, specifically a method for detecting the viability of Poria cocos strains, comprising the following steps: Step S1: acquiring images of Poria cocos strains; Step S2: preprocessing the images acquired in Step S1; Step S3: extracting features from the preprocessed images, extracting key growth characteristics of the hyphae, including growth rate, biomass, and morphological characteristics; Step S4: quantitatively evaluating the viability of Poria cocos strains by combining the extracted growth rate, biomass, and morphological characteristics. In this application, the growth rate, biomass change rate, and morphological characteristic values ​​predicted by the ARIMA model can generate viability curves for future time periods. By performing time-series analysis on these predicted viability values, the viability trend of the strains over a future period can be determined, enabling early detection of the risk of decreased viability and timely adjustment of environmental conditions to maintain optimal growth. This also helps in selecting suitable temperature environments to maintain the optimal viability of Poria cocos strains.

Description

Technical Field

[0001] This invention relates to the field of biological monitoring, and in particular to a method and apparatus for detecting the viability of Poria cocos strains. Background Technology

[0002] Poria cocos is a fungus widely used in the production of traditional Chinese medicinal materials, and its quality and yield are closely related to the viability of the Poria cocos fungal strain. In actual production, the viability of the Poria cocos fungal strain directly affects the growth rate, biomass, and final yield and medicinal value of Poria cocos. Therefore, it is of great significance to quickly and accurately assess the viability of the Poria cocos fungal strain. Traditional methods for detecting the viability of Poria cocos usually rely on manual observation and laboratory analysis, which suffers from problems such as long detection cycles, low accuracy, and complex operation.

[0003] With the development of machine vision and intelligent analysis technologies, detection methods based on image processing and feature extraction have gradually become a research hotspot. By capturing the growth state of Poria cocos fungi and combining the mycelial growth time sequence characteristics under different temperature conditions, rapid and non-contact monitoring of fungal viability can be achieved. Using machine vision and intelligent algorithms, image data during the growth process of Poria cocos can be automatically collected, and features such as mycelial growth rate and biomass can be extracted to ultimately determine the viability of the fungi.

[0004] Existing technologies do not yet provide an effective solution for the real-time detection and monitoring of the viability of Poria cocos strains under different temperature conditions. Summary of the Invention

[0005] This invention provides a method and device for detecting the viability of Poria cocos strains, which aims to enable real-time monitoring of the growth status of Poria cocos strains at different temperatures.

[0006] This invention provides the following technical solution:

[0007] On the one hand, this application provides a method for detecting the viability of Poria cocos strains, comprising the following steps:

[0008] Step S1: Image acquisition of Poria cocos strain;

[0009] Step S2: Preprocess the image acquired in step S1;

[0010] Step S3: Extract features from the preprocessed image to extract key growth features of the hyphae, including growth rate, biomass, and morphological features;

[0011] Step S4: Quantitatively assess the viability of the Poria cocos strain by combining the extracted growth rate, biomass, and morphological characteristics.

[0012] In one possible implementation, in step S1, the Poria cocos strain is inoculated onto multiple culture media, and the different culture media are placed in different temperature environments with constant temperature. During the image acquisition process, a fixed shooting angle and lighting conditions are maintained.

[0013] In one possible implementation, in step S2, the color image is converted to a grayscale image, and the grayscale conversion formula is:

[0014] I gray = 0.299×R + 0.587×G + 0.114×B

[0015] Where R, G, and B are the pixel values ​​of the red, green, and blue channels of the image, respectively, and I... gray This is the generated grayscale value.

[0016] In one possible implementation, in step S1, a Gaussian filtering algorithm is used to eliminate noise. The kernel function formula for Gaussian filtering is:

[0017]

[0018] Where σ is the standard deviation of the Gaussian kernel.

[0019] In one possible implementation, step S2 involves using histogram equalization to enhance image contrast, including:

[0020]

[0021] Where I is the gray value of the original image, I min and I max and represent the minimum and maximum gray values ​​in the image, respectively, and I′ represents the enhanced gray value.

[0022] In one possible implementation, in step S3, the growth rate of the hyphae is calculated by analyzing the continuous time-series images:

[0023]

[0024] Among them, V growth A represents the growth rate of mycelium. t+1 A and represent the mycelial coverage area at time points t+1 and t, respectively, and Δt is the time interval.

[0025] In one possible implementation, the biomass of the mycelium is estimated using a biomass model:

[0026] B = ρ × A

[0027] Where B is the biomass of the hyphae, A is the coverage area of ​​the hyphae, and ρ is the hyphae density coefficient determined experimentally.

[0028] In one possible implementation, morphological characteristics include hyphae length, width, and shape factor, the shape factor of which can be calculated using the following formula:

[0029]

[0030] Where A is the coverage area of ​​the hyphae and P is the perimeter of the hyphae. Morphological characteristics reflect the structure and health status of the hyphae. Irregularly shaped hyphae usually indicate abnormal growth.

[0031] In one possible implementation, a time-series characteristic model is constructed from growth rate and biomass data collected at different time points:

[0032]

[0033] Where: y(t) represents the growth characteristics (growth rate, biomass, or morphological characteristics) at the current moment, c is the mean of the time series, and φ is the mean of the time series. i It is the autoregressive coefficient, which captures the influence of historical data on the current state, y (t-i) The observation value at the i-th time point in the past, θ j The moving average coefficient is used to correct for residuals in the model. (t-j) The error term at the j-th time point in the past, ∈t is the random error term, and p and q are the orders of the autoregression and moving average, respectively.

[0034] In one possible implementation, an improved vitality function is constructed by replacing the real-time measured features with the predicted output values ​​of the ARIMA model:

[0035] Where: L(T) represents the activity value of the bacterial strain at temperature T. This is the growth rate predicted by ARIMA. This is the biomass change rate predicted by ARIMA, representing the rate of increase in mycelial coverage area. These are the morphological feature values ​​predicted by ARIMA, reflecting the health status of the strain. w1, w2, and w3 are weight parameters, representing the contribution of each feature to the viability value.

[0036] On the other hand, this application provides a Poria cocos strain viability detection device, including: a Poria cocos strain image acquisition module, used to acquire real-time growth images of Poria cocos strain under different temperature conditions;

[0037] The Poria cocos strain image preprocessing module is used to process the acquired images to improve the accuracy of subsequent analysis, including denoising, grayscale conversion, and contrast enhancement.

[0038] The Poria cocos mycelium image feature extraction module is used to extract features from preprocessed images, including key growth features of mycelium, such as growth rate, biomass, and morphological features.

[0039] The Poria cocos strain viability analysis module is used to analyze the temporal characteristics of mycelial growth at different temperatures and determine the viability of the strain.

[0040] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention.

[0041] In this invention, the growth rate, biomass change rate, and morphological characteristic values ​​predicted using the ARIMA model can generate future vitality curves. By performing time-series analysis on these predicted vitality values, the vitality trend of the strain over a future period can be determined. This trend analysis can identify the risk of declining strain vitality in advance, allowing for timely adjustments to environmental conditions to maintain optimal growth. Short-term vitality trend analysis, by predicting vitality values ​​for the next few hours or days, can identify short-term changes in the strain's growth status. This is instructive for real-time strain regulation. The long-term predictive capability of the ARIMA model can provide a basis for the growth plan of Poria cocos strains over a longer timeframe, helping researchers optimize culture protocols.

[0042] By analyzing the value of the viability function, the viability of the Poria cocos strain can be determined. High viability indicates rapid growth, significant increase in biomass, good morphology, and optimal condition. Medium viability indicates stable growth with good but not prominent mycelial growth. Low viability indicates slow growth, limited biomass increase, and potential morphological abnormalities. Viability analysis of data from different time periods reveals trends in strain viability. As temperature gradually increases or decreases, the viability function value will show a decrease or recovery in strain viability. This helps in selecting a suitable temperature environment to maintain the optimal viability of the Poria cocos strain. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of a method for detecting the viability of Poria cocos strains provided in an embodiment of the present invention;

[0044] Figure 2 This is a flowchart illustrating the activity analysis of Poria cocos strains at different temperatures. Detailed Implementation

[0045] The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0046] A method for detecting the viability of Poria cocos strains involves acquiring real-time growth images of the strains under different temperature conditions using a Poria cocos strain image acquisition module, providing data support for subsequent analysis. The Poria cocos strains are first inoculated onto multiple different culture media, which are then cultured at varying temperatures. Images are taken periodically using a high-definition camera or industrial camera.

[0047] Poria cocos inoculum was inoculated onto a culture medium and cultured in different temperature environments, such as 25℃, 30℃, 35℃, and 40℃. Each temperature environment needed to be kept constant to ensure data accuracy. A high-resolution industrial camera (≥2000×2000 pixels) was used for image acquisition to capture details of mycelial growth. The image acquisition time interval was set according to experimental needs, typically one image every hour to record the dynamic growth process of the mycelium. For higher temporal accuracy, a shorter time interval could be set. A fixed shooting angle and lighting conditions were maintained during image acquisition to ensure image consistency across different time points. The light source needed to be evenly distributed, using a uniform LED light source to ensure consistent illumination and avoid the effects of overexposure or shadows.

[0048] The acquired images require a series of preprocessing operations to ensure the accuracy of image analysis. After image acquisition, the image preprocessing module is responsible for performing a series of processing operations on the raw images to improve the accuracy and robustness of subsequent analysis.

[0049] Since the growth of Poria cocos mycelium is mainly reflected in morphological characteristics, converting a color image to a grayscale image can reduce computational complexity while retaining sufficient feature information. The grayscale conversion formula is:

[0050] I gray = 0.299×R + 0.587×G + 0.114×B

[0051] Where R, G, and B are the pixel values ​​of the red, green, and blue channels of the image, respectively, and I... gray This is the generated grayscale value.

[0052] The acquired images may contain noise, affecting subsequent analysis. A Gaussian filtering algorithm is used to eliminate noise. Gaussian filtering smooths the image through convolution operations; the kernel function formula for Gaussian filtering is:

[0053]

[0054] Where σ is the standard deviation of the Gaussian kernel.

[0055] To ensure a more pronounced difference between the mycelium and the background, histogram equalization is used to enhance image contrast and adjust the distribution of pixel values, making the details of the mycelium stand out more. The pixel values ​​after histogram equalization can be calculated using the following formula:

[0056]

[0057] Where I is the grayscale value of the original image, I min and I max and represent the minimum and maximum gray values ​​in the image, respectively, and I′ represents the enhanced gray value.

[0058] Key growth characteristics of mycelia, including growth rate, biomass, and morphological features, are extracted using the feature extraction module.

[0059] The growth rate of mycelia is calculated by analyzing continuous time-series images. The growth rate is defined as the rate of change in the area covered by mycelia within a fixed time interval. The specific formula is as follows:

[0060]

[0061] Among them, V growth A represents the growth rate of the mycelium. t+1 A and represent the mycelial coverage area at time points t+1 and t, respectively, and Δt is the time interval.

[0062] Mycelial biomass can be calculated from the mycelial coverage area and an experimentally determined density coefficient. By binarizing the image, the mycelial region is separated from the background, allowing for estimation of the mycelial coverage area. Finally, the mycelial biomass is estimated using a biomass model.

[0063] B = ρ × A

[0064] Where B is the biomass of the hyphae, A is the coverage area of ​​the hyphae, and ρ is the hyphae density coefficient determined experimentally.

[0065] Morphological characteristics are another key indicator of hyphal health, including hyphal length, width, and shape factor. The shape factor can be calculated using the following formula:

[0066]

[0067] Where A is the coverage area of ​​the hyphae and P is the perimeter of the hyphae. Morphological characteristics reflect the structure and health status of the hyphae. Irregularly shaped hyphae usually indicate abnormal growth.

[0068] By analyzing the temporal characteristics extracted during mycelial growth (such as the curves of changes in growth rate and biomass), the viability of the fungal strain can be determined more accurately.

[0069] A time-series characteristic model was constructed using growth rate and biomass data collected at different time points. The ARIMA model was used to fit the growth curves, revealing the growth trend of *Poria cocos* mycelia at different temperatures. The collected *Poria cocos* mycelial growth status data (growth rate, biomass, and morphological characteristics) were used as time series input for time-series analysis. The ARIMA model is suitable for analyzing time-series data with seasonal trends or fluctuations. The autoregressive (AR) part of the ARIMA model predicts the current time-to-time characteristic changes based on the mycelial growth characteristics of previous time points; the integral (I) part eliminates the trend term through differencing, processes non-stationary data, and extracts the true growth changes of the mycelia; the moving average (MA) part reduces noise and improves prediction accuracy by calculating the error term from previous time points. The ARIMA model formula is:

[0070]

[0071] Where: y(t) represents the growth characteristics (growth rate, biomass, or morphological characteristics) at the current moment, c is the mean of the time series, and φ is the mean of the time series. i It is the autoregressive coefficient, which captures the influence of historical data on the current state, y (t-i) The observation value at the i-th time point in the past, θ j The moving average coefficient is used to correct for residuals in the model. (t-j) The error term at the j-th time point in the past, ∈t is the random error term, and p and q are the orders of the autoregression and moving average, respectively.

[0072] By fitting data with different characteristics, predicted values ​​can be obtained at each time point, reflecting the growth trend of the fungus at different temperatures. The ARIMA model performs time-series predictions on three characteristics of Poria cocos fungus growth (growth rate, biomass change rate, and morphological characteristics). By fitting the time-series data for each characteristic, predicted values ​​for these characteristics at future times can be obtained. These predicted values ​​are used to reflect the future growth trend of the fungus and provide a basis for viability assessment. The output of the ARIMA model is: predicted growth rate, predicted biomass change rate, and predicted morphological characteristic value. After optimization by the ARIMA model, these predicted values ​​can more accurately describe the growth characteristics of the mycelium.

[0073] Based on a time-series feature model, a viability function is constructed to quantify the growth status of fungal strains. It is assumed that mycelial growth rate is highest and biomass increase is fastest at suitable temperatures, while growth rate and biomass changes slow down or stop at unsuitable temperatures. An improved viability function is constructed by replacing real-time measured features with the predicted output values ​​of the ARIMA model. Based on these predicted features, the viability function can more accurately quantify the growth performance of fungal strains. The expression for the viability function is as follows:

[0074]

[0075] Where: L(T) represents the activity value of the bacterial strain at temperature T. This is the growth rate predicted by ARIMA. It is the biomass change rate predicted by ARIMA, representing the rate of increase in mycelial coverage area. These are the morphological feature values ​​predicted by ARIMA, reflecting the health status of the bacterial species. w1, w2, and w3 are weighting parameters, representing the contribution of each feature to the viability value.

[0076] The growth rate, biomass change rate, and morphological characteristics predicted using the ARIMA model can generate future viability curves. Time-series analysis of these predicted viability values ​​can determine the viability trend of the strain over a future period. This trend analysis can identify the risk of declining viability in advance, allowing for timely adjustments to environmental conditions to maintain optimal growth. Short-term viability trend analysis, by predicting viability values ​​for the next few hours or days, can identify short-term changes in the strain's growth status. This is instructive for real-time strain regulation. The long-term predictive capability of the ARIMA model can provide a basis for the growth planning of Poria cocos strains over a longer timeframe, helping researchers optimize culture protocols.

[0077] By analyzing the value of the viability function, the viability of the Poria cocos strain can be determined. High viability indicates rapid growth, significant increase in biomass, good morphology, and optimal condition. Medium viability indicates stable growth with good but not prominent mycelial growth. Low viability indicates slow growth, limited biomass increase, and potential morphological abnormalities. Viability analysis of data from different time periods reveals trends in strain viability. As temperature gradually increases or decreases, the viability function value will show a decrease or recovery in strain viability. This helps in selecting a suitable temperature environment to maintain the optimal viability of the Poria cocos strain.

[0078] This application also provides a device for detecting the viability of Poria cocos strains, including:

[0079] The Poria cocos strain image acquisition module is used to acquire real-time growth images of Poria cocos strains under different temperature conditions.

[0080] The Poria cocos strain image preprocessing module is used to process the acquired images to improve the accuracy of subsequent analysis, including denoising, grayscale conversion, and contrast enhancement.

[0081] The Poria cocos mycelium image feature extraction module is used to extract features from preprocessed images, including key growth features of mycelium, such as growth rate, biomass, and morphological features.

[0082] The Poria cocos strain viability analysis module is used to analyze the temporal characteristics of mycelial growth at different temperatures and determine the viability of the strain.

[0083] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. In the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for detecting the viability of Poria cocos strains, characterized in that, Includes the following steps: Step S1: Image acquisition of Poria cocos strain; Step S2: Preprocess the image acquired in step S1; Step S3: Extract features from the preprocessed image to extract key growth features of the hyphae, including growth rate, biomass, and morphological features; Step S4: Quantitatively assess the viability of the Poria cocos strain by combining the extracted growth rate, biomass, and morphological characteristics. Use the predicted output of the ARIMA model to replace the real-time measured features, and construct an improved viability function: in: Indicates temperature Below, the vitality value of the bacterial strain, This is the growth rate predicted by ARIMA. This is the biomass change rate predicted by ARIMA, representing the rate of increase in mycelial coverage area. These are morphological characteristic values ​​predicted by ARIMA, reflecting the health status of the fungal species. , , It is a weighting parameter that represents the contribution of each feature to the vitality value.

2. The method for detecting the viability of Poria cocos strains according to claim 1, characterized in that, In step S1, the Poria cocos strain is inoculated onto multiple culture media, and the different culture media are placed in different temperature environments with constant temperature. During the image acquisition process, a fixed shooting angle and lighting conditions are maintained.

3. The method for detecting the viability of Poria cocos strains according to claim 2, characterized in that, In step S2, the color image is converted to a grayscale image. The grayscale conversion formula is as follows: in, , , These are the pixel values ​​of the red, green, and blue channels of the image, respectively. The generated grayscale value; In step S1, a Gaussian filtering algorithm is used to eliminate noise. The kernel function formula for Gaussian filtering is: in, It is the standard deviation of the Gaussian kernel.

4. The method for detecting the viability of Poria cocos strains according to claim 3, characterized in that, In step S2, histogram equalization is used to enhance the contrast of the image, including: in, The grayscale value of the original image. and These are the minimum and maximum gray values ​​in the image, respectively. This is the enhanced grayscale value.

5. The method for detecting the viability of Poria cocos strains according to claim 4, characterized in that, In step S3, the growth rate of mycelium is calculated by analyzing continuous time-series images: in, The growth rate of the mycelium, and Representing time points and The area of ​​mycelial coverage at that time For time intervals.

6. The method for detecting the viability of Poria cocos strains according to claim 5, characterized in that, Estimating mycelial biomass using a biomass model: in, For mycelial biomass, The area covered by the mycelium. The mycelial density coefficient was determined experimentally.

7. The method for detecting the viability of Poria cocos strains according to claim 6, characterized in that, Morphological characteristics include hyphal length, width, and shape factor. The shape factor can be calculated using the following formula: in, The area covered by the mycelium. The circumference of the hyphae reflects their structure and health status. Irregularly shaped hyphae usually indicate abnormal growth.

8. The method for detecting the viability of Poria cocos strains according to claim 7, characterized in that, A time-series feature model was constructed based on growth rate and biomass data collected at different time points: in: It indicates the growth characteristics (growth rate, biomass, or morphological characteristics) at the current moment. The mean of a time series, These are autoregressive coefficients, which capture the impact of historical data on the current state. The observation value at the i-th time point in the past, The moving average coefficient is used to correct for residuals in the model. The error term at the j-th time point in the past, It is a random error term. and These are the orders of the autoregression and moving average, respectively.

9. A device for detecting the viability of Poria cocos strains, used to perform the steps of the method for detecting the viability of Poria cocos strains as described in any one of claims 1-8, comprising: The Poria cocos strain image acquisition module is used to acquire real-time growth images of Poria cocos strains under different temperature conditions. The Poria cocos strain image preprocessing module is used to process the acquired images to improve the accuracy of subsequent analysis, including denoising, grayscale conversion, and contrast enhancement. The Poria cocos mycelium image feature extraction module is used to extract features from preprocessed images, including key growth features of mycelium, such as growth rate, biomass, and morphological features. The Poria cocos strain viability analysis module is used to analyze the temporal characteristics of mycelial growth at different temperatures and determine the viability of the strain.

Images