Poria cocos strain activity detection method and device

Abstract

The invention belongs to the field of biological monitoring, and particularly relates to a poria cocos strain activity detection method which comprises the following steps: S1, acquiring a poria cocos strain image; s2, preprocessing the image acquired in the step S1; s3, carrying out feature extraction on the preprocessed image, and extracting key growth features of hyphae, including growth speed, biomass and morphological features; s4, quantitative evaluation is conducted on the activity of the poria cocos strains in combination with the extracted growth speed, biomass and morphological characteristics, in the method, the growth speed, the biomass change rate and the morphological characteristics predicted through the ARIMA model can be used for generating an activity curve at the future moment, time sequence analysis is conducted on the predicted activity values, and the activity of the poria cocos strains is evaluated. According to the method, the activity trend of the strain in a period of time in the future can be judged, the risk of strain activity decline can be found in advance, the environment condition can be adjusted in time to keep the optimal growth state, the appropriate temperature environment can be selected, and the optimal activity of the poria cocos strain can be kept.

Description

Technical Field

[0001] The invention relates to the field of biological monitoring, and in particular to a method and a device for detecting the activity of Poria cocos strains. Background Art

[0002] Poria cocos is a fungus widely used in the production of traditional Chinese medicines. Its quality and yield are closely related to the vitality of the Poria cocos strain. In actual production, the vitality of the Poria cocos strain directly affects the growth rate, biomass, and final yield and medicinal value of Poria cocos. Therefore, how to quickly and accurately evaluate the vitality of Poria cocos strains is of great significance. Traditional Poria cocos vitality detection methods usually rely on manual observation and laboratory analysis, which have the problems of long detection cycle, low accuracy and complex operation.

[0003] With the development of machine vision and intelligent analysis technology, detection methods based on image processing and feature extraction have gradually become a research hotspot. By capturing the growth status of Poria cocos strains and combining the temporal characteristics of mycelial growth under different temperature conditions, rapid and non-contact monitoring of the vitality of the strains can be achieved. Using machine vision and intelligent algorithms, image data of 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 vitality of the strains.

[0004] The existing technology has not yet provided an effective solution for real-time detection and monitoring of the activity of Poria cocos strains under different temperature conditions. Summary of the invention

[0005] The present invention provides a method and device for detecting the activity of Poria cocos strains, aiming to achieve real-time monitoring of the growth status of Poria cocos strains at different temperatures.

[0006] The present invention provides the following technical solutions:

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

[0008] Step S1: collecting images of Poria cocos strains;

[0009] Step S2: preprocessing the image collected in step S1;

[0010] Step S3: performing feature extraction on the preprocessed image to extract key growth characteristics of mycelium, including growth rate, biomass and morphological characteristics;

[0011] Step S4: quantitatively evaluate the activity of the Poria cocos strains by combining the extracted growth rate, biomass and morphological characteristics.

[0012] In a possible embodiment, in step S1, the Poria cocos strains are inoculated on multiple culture media, and different culture media are placed in different temperature environments, and the temperature environment is kept constant, and a fixed shooting angle and lighting conditions are maintained during image acquisition.

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

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

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

[0016] In a possible implementation, in step S1, a Gaussian filter algorithm is used to eliminate noise, and the kernel function formula of the Gaussian filter is:

[0017]

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

[0019] In a possible implementation, in step S2, the contrast of the image is enhanced by using a histogram equalization technique, including:

[0020]

[0021] Among them, I is the gray value of the original image, I min and I max are the minimum and maximum grayscale values ​​in the image respectively, and I′ is the enhanced grayscale value.

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

[0023]

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

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

[0026] B=ρ×A

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

[0028] In a possible embodiment, the morphological characteristics include the length, width, and shape factor of the hyphae, and the shape factor can be calculated by the following formula:

[0029]

[0030] Among them, A is the coverage area of ​​mycelium, P is the circumference of mycelium, and the morphological characteristics reflect the structure and growth health of mycelium. Irregular mycelium usually indicates abnormal growth.

[0031] In a possible implementation, a time series characteristic model is constructed for the 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, φ i is the autoregressive coefficient, capturing the impact of historical data on the current state, y (t-i) The observation value at the i-th time point in the past, θ j Moving average coefficient, used to correct the residual in the model, ∈ (t-j) The error term at the jth time point in the past, ∈t is the random error term, and p and q are the orders of autoregression and moving average, respectively.

[0034] In one possible implementation, the predicted output values ​​of the ARIMA model are used instead of the real-time measured features to construct an improved vitality function:

[0035] Where: L(T) represents the activity value of the strain at temperature T, is the growth rate predicted by ARIMA, is the biomass change rate predicted by ARIMA, representing the growth rate of mycelium coverage area, is the morphological characteristic value predicted by ARIMA, reflecting the health status of the strain, w 1 , w 2 , w 3 is a weight parameter, representing the contribution of each feature to the vitality value.

[0036] On the other hand, the present application provides a device for detecting the vitality of Poria cocos strains, including: a Poria cocos strain image acquisition module for acquiring real-time growth images of Poria cocos strains under different temperature conditions;

[0037] The Poria cocos strain image preprocessing module is used to process the collected images to improve the accuracy of subsequent analysis, including denoising, graying and contrast enhancement;

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

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

[0040] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention.

[0041] In the present invention, the growth rate, biomass change rate and morphological characteristic values ​​predicted by the ARIMA model can generate a vitality curve at a future moment. By performing a time series analysis on these predicted vitality values, the vitality trend of the strain in the future period of time can be determined. This trend analysis can detect the risk of decreased vitality of the strain in advance and adjust the environmental conditions in time to maintain the optimal growth state. Short-term vitality trend analysis can identify short-term growth state changes of the strain by predicting the vitality values ​​in the next few hours or days. This is of guiding significance for the immediate regulation of the strain. The long-term prediction ability of the ARIMA model can provide a basis for the growth plan of the Poria cocos strain over a longer time range, helping researchers to optimize the cultivation plan.

[0042] By analyzing the value of the vitality function, the vitality of the Poria cocos strain can be judged. High vitality means that the strain grows fast, the biomass increases significantly, the morphology is good, and it is in the best state. Medium vitality means that the growth state of the strain is stable, the mycelium performs well but not outstanding. Low vitality means that the strain grows slowly, the biomass increases limitedly, and the morphology may be abnormal. By performing vitality analysis on data in different time periods, the changing trend of the strain vitality can be obtained. When the temperature gradually increases or decreases, the vitality function value will show a decrease or recovery in the vitality of the strain. This helps to select a suitable temperature environment to maintain the optimal vitality of the Poria cocos strain. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a method for detecting the activity of a Poria cocos strain provided in an embodiment of the present invention;

[0044] Figure 2 This is a flow chart for activity analysis of Poria cocos strains at different temperatures. DETAILED DESCRIPTION

[0045] The embodiments of the present invention are described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0046] A method for detecting the vitality of Poria cocos strains is provided, which uses a Poria cocos strain image acquisition module to obtain real-time growth images of Poria cocos strains under different temperature conditions to provide data support for subsequent analysis. The Poria cocos strains are first inoculated on multiple different culture media, and the different culture media are placed in different temperature environments for cultivation, and are photographed regularly by a high-definition camera or an industrial camera.

[0047] Poria cocos strains are inoculated on the culture medium and placed in different temperature environments, such as 25℃, 30℃, 35℃, 40℃ and other temperature conditions for cultivation. Each temperature environment needs to be kept constant to ensure the accuracy of the data. A high-resolution industrial camera (≥2000×2000 pixels) is used for image acquisition to capture the details of mycelial growth. The time interval for image acquisition is set according to the experimental requirements. The typical setting is to capture an image every 1 hour to record the dynamic growth process of mycelium. If higher time accuracy is required, a shorter time interval can also be set. During the image acquisition process, a fixed shooting angle and lighting conditions are maintained to ensure the image consistency of mycelium at each time point. The light source needs to be evenly distributed, and LED uniform light source is used to ensure lighting consistency and avoid the influence of overexposure or shadows.

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

[0049] Since the growth of Poria cocos hyphae is mainly reflected in morphological characteristics, converting color images to grayscale images 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] Among them, R, G, and B are the red, green, and blue channel pixel values ​​of the image respectively, and I gray is the generated grayscale value.

[0052] The collected image may contain noise, which will affect the subsequent analysis. Use Gaussian filtering algorithm to eliminate noise. Gaussian filtering can smooth the image through convolution operation. The kernel function formula of Gaussian filtering is:

[0053]

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

[0055] To ensure that the difference between the hyphae and the background is more obvious, the histogram equalization technique is used to enhance the contrast of the image and adjust the distribution of pixel values ​​in the image to make the details of the hyphae more prominent. The pixel value after histogram equalization can be calculated by the following formula:

[0056]

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

[0058] The key growth characteristics of mycelium, including growth rate, biomass and morphological characteristics, were extracted through the feature extraction module.

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

[0060]

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

[0062] The mycelium biomass can be calculated from the mycelium coverage area and the experimentally determined density coefficient. The mycelium area is separated from the background by binarization of the image, and the mycelium coverage area is estimated, and the mycelium biomass is estimated by the biomass model:

[0063] B=ρ×A

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

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

[0066]

[0067] Among them, A is the coverage area of ​​mycelium, P is the circumference of mycelium, and the morphological characteristics reflect the structure and growth health of mycelium. Irregular mycelium usually indicates abnormal growth.

[0068] By analyzing the time series characteristics extracted during the mycelium growth process (such as the change curves of growth rate and biomass), the vitality of the fungus species can be judged more accurately.

[0069] A time series feature model was constructed for the growth rate and biomass data collected at different time points. The ARIMA model was used to fit the growth curve to obtain the growth trend of Poria cocos mycelium at different temperatures. The collected Poria cocos mycelium 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 is used to predict the characteristic changes at the current moment through the mycelium growth characteristics of the previous moments; the integral (I) part eliminates the trend term through differential calculation, processes non-stationary data, and extracts the true growth changes of the mycelium; the moving average (MA) part reduces the noise impact by calculating the error term of the previous moment and improves the prediction accuracy. 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, φ i is the autoregressive coefficient, capturing the impact of historical data on the current state, y (t-i) The observation value at the i-th time point in the past, θ j Moving average coefficient, used to correct the residual in the model, ∈ (t-j) The error term at the jth time point in the past, ∈t is the random error term, and p and q are the orders of autoregression and moving average, respectively.

[0072] By fitting different characteristic data, the predicted value at each moment can be obtained, reflecting the growth trend of the strain at different temperatures. The ARIMA model performs time series prediction on the three characteristics of Poria cocos strain growth (growth rate, biomass change rate, and morphological characteristics). By fitting the time series data of each feature, the predicted values ​​of these features at future moments can be obtained. These predicted values ​​are used to reflect the future growth trend of the strain and provide a basis for vitality assessment. The output of the ARIMA model is: predicted growth rate, predicted biomass change rate, and predicted morphological characteristic values. After being optimized by the ARIMA model, these predicted values ​​can more accurately describe the growth characteristics of mycelium.

[0073] Based on the time series feature model, a vitality function is constructed to quantify the growth status of the strain. It is assumed that the growth rate of mycelium is the highest and the biomass increases the fastest at a suitable temperature, while the growth rate and biomass changes will slow down or stop at an unsuitable temperature. The predicted output value of the ARIMA model is used to replace the real-time measured features to construct an improved vitality function. Based on these predicted features, the vitality function can more accurately quantify the growth performance of the strain. The vitality function expression is as follows:

[0074]

[0075] Where: L(T) represents the activity value of the bacterial strain at temperature T. is the growth rate predicted by ARIMA. is the biomass change rate predicted by ARIMA, representing the growth rate of mycelium coverage area. is the morphological characteristic value predicted by ARIMA, reflecting the health status of the strain. 1 , w 2 , w 3 is a weight parameter, representing the contribution of each feature to the vitality value.

[0076] The growth rate, biomass change rate and morphological characteristic values ​​predicted by the ARIMA model can generate a vitality curve for the future. By performing a time series analysis on these predicted vitality values, the vitality trend of the strain in the future can be determined. This trend analysis can detect the risk of decreased vitality of the strain in advance and adjust the environmental conditions in time to maintain the optimal growth state. Short-term vitality trend analysis can identify short-term growth state changes of the strain by predicting the vitality values ​​in the next few hours or days. This is of guiding significance for the immediate regulation of the strain. The long-term prediction ability of the ARIMA model can provide a basis for the growth plan of Poria cocos strains over a longer period of time and help researchers optimize the cultivation plan.

[0077] By analyzing the value of the vitality function, the vitality of the Poria cocos strain can be judged. High vitality means that the strain grows fast, the biomass increases significantly, the morphology is good, and it is in the best state. Medium vitality means that the growth state of the strain is stable, the mycelium performs well but not outstanding. Low vitality means that the strain grows slowly, the biomass increases limitedly, and the morphology may be abnormal. By performing vitality analysis on data in different time periods, the changing trend of the strain vitality can be obtained. When the temperature gradually increases or decreases, the vitality function value will show a decrease or recovery in the vitality of the strain. This helps to select a suitable temperature environment to maintain the optimal vitality of the Poria cocos strain.

[0078] The present application also provides a device for detecting the vitality of Poria cocos strains, comprising:

[0079] A 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 collected images to improve the accuracy of subsequent analysis, including denoising, graying and contrast enhancement;

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

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

[0083] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention; the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for detecting the activity of Poria cocos strains, characterized in that: The steps include: Step S1: collecting images of Poria cocos strains; Step S2: preprocessing the image collected in step S1; Step S3: performing feature extraction on the preprocessed image to extract key growth characteristics of mycelium, including growth rate, biomass and morphological characteristics; Step S4: quantitatively evaluate the activity of the Poria cocos strains by combining the extracted growth rate, biomass and morphological characteristics.

2. A method for detecting the activity of Poria cocos strains according to claim 1, characterized in that: In the step S1, the Poria cocos strains are inoculated on multiple culture media, and different culture media are placed in different temperature environments, and the temperature environment is kept constant, and a fixed shooting angle and lighting conditions are maintained during image acquisition.

3. A method for detecting the activity of Poria cocos strains according to claim 2, characterized in that: In step S2, the color image is converted into a grayscale image, and the grayscale conversion formula is: I gray =0.299×R+0.587×G+0.114×B Among them, R, G, and B are the red, green, and blue channel pixel values ​​of the image respectively, and I gray is the generated grayscale value. In step S1, a Gaussian filter algorithm is used to eliminate noise, and the kernel function formula of the Gaussian filter is: Here, σ is the standard deviation of the Gaussian kernel.

4. A method for detecting the activity of Poria cocos strains according to claim 3, characterized in that: In step S2, the contrast of the image is enhanced by using a histogram equalization technique, including: Among them, I is the gray value of the original image, I min and I max are the minimum and maximum grayscale values ​​in the image respectively, and I′ is the enhanced grayscale value.

5. A method for detecting the activity of Poria cocos strains according to claim 4, characterized in that: In step S3, the growth rate of hyphae is calculated by analyzing the continuous time series images: Among them, V growth is the growth rate of mycelium, A t+1 and A represent the mycelium coverage area at time points t+1 and t, respectively, and Δt is the time interval.

6. A method for detecting the activity of Poria cocos strains according to claim 5, characterized in that: Estimate the mycelial biomass using the biomass model: B=ρ×A Among them, B is the biomass of mycelium, A is the coverage area of ​​mycelium, and ρ is the mycelium density coefficient determined experimentally.

7. A method for detecting the activity of Poria cocos strains according to claim 6, characterized in that: The morphological characteristics include the length, width and shape factor of the hyphae. The shape factor can be calculated by the following formula: Among them, A is the coverage area of ​​mycelium, P is the circumference of mycelium, and the morphological characteristics reflect the structure and growth health of mycelium. Irregular mycelium usually indicates abnormal growth.

8. A method for detecting the activity of Poria cocos strains according to claim 7, characterized in that: For the growth rate and biomass data collected at different time points, a time series characteristic model is constructed: 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, φ i is the autoregressive coefficient, capturing the impact of historical data on the current state, y (t-i) The observation value at the i-th time point in the past, θ j Moving average coefficient, used to correct the residual in the model, ∈ (t-j) The error term at the jth time point in the past, ∈t is the random error term, and p and q are the orders of autoregression and moving average, respectively.

9. A method for detecting the activity of Poria cocos strains according to claim 8, characterized in that: Use the predicted output values ​​of the ARIMA model instead of the real-time measured features to construct an improved vitality function: Where: L(T) represents the activity value of the strain at temperature T, is the growth rate predicted by ARIMA, is the biomass change rate predicted by ARIMA, representing the growth rate of mycelium coverage area, is the morphological characteristic value predicted by ARIMA, reflecting the health status of the strain, w1, w2, and w3 are weight parameters, representing the contribution of each characteristic to the vitality value.

10. A device for detecting the vitality of a Poria cocos strain, used to perform the steps of the method for detecting the vitality of a Poria cocos strain as claimed in any one of claims 1 to 9, comprising: A 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 collected images to improve the accuracy of subsequent analysis, including denoising, graying and contrast enhancement; The Poria cocos strain image feature extraction module is used to extract features from the preprocessed images and extract key growth features of mycelium, including growth rate, biomass and morphological features; The Poria cocos strain activity analysis module is used to analyze the temporal characteristics of mycelium growth at different temperatures and determine the activity of the strain.

Images