Bacteria image data analysis system and method based on image processing

Abstract

The invention discloses a bacterial image data analysis system and method based on image processing, and relates to the field of image data analysis, the system comprises an image acquisition module, an image preprocessing module, a feature extraction module, a bacterial identification and counting module and a data processing module; the image acquisition module is used for intelligently adjusting magnification times to acquire images of bacteria in the culture dish; the image preprocessing module is used for preprocessing the collected image, so that the definition and the resolution of the image are improved; identifying specific bacterial features through the feature extraction module; the bacteria in the collected image are recognized through the bacteria recognition and counting module, and the number of the bacteria is counted; the data processing module is used for processing the number of bacteria to generate a growth curve of the bacteria; by intelligently segmenting the area and adjusting the magnification times when the bacterium image is collected, the integrity and definition of the collected bacterium image are enhanced from the collection source, so that the efficiency and accuracy of bacterium counting are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data analysis, and in particular to a bacterial image data analysis system and method based on image processing. Background Art

[0002] In life science research and production practice, bacterial growth patterns and separation and identification methods are two important research directions. Understanding bacterial growth patterns can better control and optimize the bacterial growth environment and improve production efficiency. The correct bacterial separation and identification methods can effectively distinguish different bacterial species, which is of great significance for disease diagnosis and treatment, new drug development, etc. In existing technologies, the main method for studying bacterial growth patterns is to observe and record the growth status of bacteria in different environments, and then draw conclusions through statistics and analysis; selecting identification culture media is a traditional method, by designing special culture media so that only specific bacteria can grow in them, thereby achieving the purpose of identification; PCR technology is a modern molecular biology method, by amplifying bacterial DNA, and then detecting the amplification results by electrophoresis and other methods, so as to determine the type of bacteria.

[0003] There are still some problems in the practical application of existing technologies. The traditional turbidimetric method can only measure the concentration of bacterial solution at a certain moment and cannot monitor the growth status of bacteria in real time. The operation is cumbersome, the workload is large, and it is prone to system errors. In terms of bacterial counting, manual counting is prone to errors and is inefficient. Therefore, how to improve these technologies and improve the efficiency and accuracy of bacterial counting and growth status monitoring is a problem that needs to be urgently solved in this field. Summary of the invention

[0004] The object of the present invention is to provide a bacterial image data analysis system and method based on image processing to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions: a bacterial image data analysis system based on image processing, the system comprising an image acquisition module, an image preprocessing module, a feature extraction module, a bacterial identification and counting module and a data processing module;

[0006] The image acquisition module is used to intelligently time and intelligently select magnification to acquire images of bacteria;

[0007] Preprocessing the collected image by the image preprocessing module;

[0008] Extracting the appearance and structural features of specific bacteria through the feature extraction module, and storing these feature information;

[0009] Identify specific bacteria in the collected image and count the number of the bacteria by the bacteria identification and counting module;

[0010] The data processing module analyzes and processes the time of each image acquisition and the data of the number of bacteria corresponding to the acquisition time and generates a bacterial growth curve.

[0011] Furthermore, the image acquisition module performs intelligent timed image acquisition of the bacteria in the culture dish through a high-resolution microscope combined with a digital imaging system, intelligently sets the time interval for image acquisition according to changes in the growth rate of the bacteria, and records the image acquisition time during image acquisition, and uses different magnifications according to the distribution status of the bacteria to acquire images of the bacteria at different culture times.

[0012] Furthermore, the image preprocessing module includes a noise removal unit, an image enhancement unit and a threshold segmentation unit; the noise removal unit removes random noise in the image by means of median filtering and Gaussian filtering. Different types of noise will be generated during image acquisition due to external factors or circuit influences during transmission, affecting the clarity of the image. These influences are removed by the noise removal program to improve the image clarity; the image enhancement unit uses image contrast adjustment and histogram equalization to enhance the contrast between the bacterial image in the image and the background in the image; the threshold segmentation unit uses a grayscale threshold or a morphology-based segmentation method to separate the bacterial image from the background image to generate a binary image. The binary image is clearer and more vivid, which is conducive to the subsequent observation and counting of bacteria in the image.

[0013] Further, the feature extraction module uses machine learning to identify the external structure and in vitro features of specific bacteria, including the outline, area, perimeter and surface features of bacteria, and stores the identified bacterial features in a memory, storing the characteristic information of bacteria as a basis for identifying specific bacteria, these extracted features.

[0014] Furthermore, the bacteria identification and counting module identifies specific bacteria in the image by comparing and analyzing the bacteria feature information in the memory, counts the number of the bacteria in the image, and stores the number of bacteria and the time when the image was collected.

[0015] Furthermore, the data processing module analyzes and processes the counted number of bacteria at different growth stages, and uses the time of each image acquisition in the memory and the number of bacteria corresponding to the acquisition time to draw a bacterial growth curve with the bacterial growth time as the horizontal axis and the number of bacteria as the vertical axis, and analyzes the growth status of the bacteria based on the growth curve.

[0016] A bacterial image data analysis method based on image processing, characterized in that it includes the following steps:

[0017] S1: Intelligently set the time interval and magnification of image acquisition to collect images of bacteria in the culture dish;

[0018] S2: pre-process the collected bacterial images to eliminate interference information;

[0019] S3: extracting and storing the characteristics of specific bacteria, identifying the specific bacteria based on the extracted characteristics of the bacteria, and counting the bacteria;

[0020] S4: Generate a bacterial growth curve according to the number of collected bacteria and the corresponding collection time.

[0021] Furthermore, in step S1: when collecting images, the time interval for collecting images is set according to the growth rate of bacteria, and the magnification of the high-power microscope is set according to the number of bacteria;

[0022] Four image acquisition time intervals are set, namely Δt1, Δt2, Δt3, and Δt4; the comparison results of the four image acquisition time intervals are Δt1>Δt3>Δt4>Δt2; in the initial stage of bacterial culture, the image acquisition time interval Δt1 of the bacterial growth retardation period is directly used. During the bacterial culture process, the image acquisition time interval is changed according to the change of bacterial growth rate; the bacterial growth rate changes continuously with the change of culture time, and the bacterial growth rate is calculated by analyzing the difference between the two consecutive bacterial counts and the time interval between the two image acquisitions:

[0023]

[0024] Among them, N m N represents the number of bacteria collected and counted in the mth bacterial image collection. m-1 represents the number of bacteria counted in the m-1th bacterial image acquisition, m represents the number of image acquisitions; v represents the growth rate of bacteria under different culture times; Δt represents the time interval between two adjacent image acquisitions, and its value is substituted into one of the four values ​​of Δt1, Δt2, Δt3, and Δt4 according to the actual situation; in the initial stage of bacterial culture, the image acquisition time interval is Δt1, and the growth rate of bacteria changes with the growth time of bacteria. When the bacterial growth rate becomes v1, the image acquisition time interval is set to change from Δt1 to Δt2; when the bacterial growth rate becomes v2, the image acquisition time interval is set to change from Δt2 to Δt3; when the bacterial growth rate becomes v3, the image acquisition time interval is set to change from Δt3 to Δt4;

[0025] The magnification is set according to the total number of bacteria at different periods, and a scanning judgment program and a detection area segmentation program are added. When scanning and judging, the percentage of the area with colony distribution in the total area is used to judge whether to perform further area segmentation; the critical condition for judging whether to perform observation area segmentation is set. When the percentage of the area with bacteria distribution in the total area is greater than z, the first area segmentation is performed to divide the detection area into x parts; wherein z represents the ratio of the area with bacteria distribution to the total observation area; after being divided into x parts, the magnification of each divided area is increased and scanned and judged again. When the percentage of the area with bacteria distribution in the divided area to the area after the first segmentation is greater than z′, the second area segmentation is performed on the divided area to divide it into y parts, wherein z′ represents the ratio of the area with bacteria distribution in each image area to the area of ​​this area after the first segmentation, and then the magnification is increased to collect the bacteria distribution image in each area respectively.

[0026] Furthermore, in step S2: the collected image is preprocessed to remove irrelevant information in the image and improve the contrast and clarity of the collected bacterial image; random noise in the image is removed by median filtering and Gaussian filtering to improve the quality of the image; the contrast between the bacteria and the background in the image is enhanced by image contrast adjustment and histogram equalization; the bacteria are separated from the background by grayscale threshold or morphology-based segmentation method to generate a binary image.

[0027] Further, in step S3: the bacteria to be counted are identified according to the characteristics of the stored bacteria, and then the number of bacteria in all the collected images is counted and the final number of bacteria is counted to obtain the total number N of bacteria in the images collected at this moment; the formula for summing up and calculating the total number of bacteria is:

[0028]

[0029] Where i = 1, 2, 3, ..., x; j = 1, 2, 3, ..., y; where i is the number of the segmented observation area during the first segmentation, and j is the number of the segmented observation area during the second segmentation; n ij It is the number of bacteria in each segmented small area. Through the above calculation, the total number of bacteria N at this moment can be obtained. Then, according to the total number of bacteria corresponding to the image acquisition time, the bacterial growth curve is drawn. According to the bacterial growth curve, the growth status of bacteria can be analyzed to see if there are any abnormalities.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The bacterial images are collected by combining high-resolution microscope and digital imaging system, which saves manpower and material resources and improves the collection efficiency and accuracy.

[0032] 2. Through intelligent analysis, different intervals for collecting bacterial images are selected according to the bacterial growth rate. A shorter time interval is used in the stage where the bacterial growth rate is faster to make the collected data more complete. A longer time interval is used in the stage where the bacterial number changes slowly to improve the collection efficiency.

[0033] 3. Intelligently selecting the number of segmentation times and the number of segmented regions according to the distribution ratio of bacteria can capture clearer bacterial images, making it easier to identify and count the bacteria in the image later. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a structural schematic diagram of a bacterial image data analysis system based on image processing of the present invention;

[0035] Figure 2 The figure is a flow chart of a bacterial image data analysis method based on image processing according to the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] like Figure 1-Figure 2 As shown, the present invention provides a technical solution, a bacterial image data analysis system based on image processing, the system includes an image acquisition module, an image preprocessing module, a feature extraction module, a bacterial identification and counting module and a data processing module;

[0038] The image acquisition module is used to intelligently time and intelligently select magnification to acquire images of bacteria;

[0039] Preprocessing the collected image by the image preprocessing module;

[0040] Extracting the appearance and structural features of specific bacteria through the feature extraction module, and storing these feature information;

[0041] Identify specific bacteria in the collected image and count the number of the bacteria by the bacteria identification and counting module;

[0042] The data processing module analyzes and processes the time of each image acquisition and the data of the number of bacteria corresponding to the acquisition time and generates a bacterial growth curve.

[0043] The image acquisition module performs intelligent timed image acquisition of the bacteria in the culture dish through a high-resolution microscope combined with a digital imaging system, intelligently sets the time interval for image acquisition according to changes in the growth rate of the bacteria, and records the image acquisition time during image acquisition. Different magnifications are used according to the distribution status of the bacteria to acquire images of the bacteria at different culture times.

[0044] The image preprocessing module includes a noise removal unit, an image enhancement unit and a threshold segmentation unit; the noise removal unit removes random noise in the image by means of median filtering and Gaussian filtering. Different types of noise will be generated during image acquisition due to external factors or circuit influences during transmission, affecting the clarity of the image. These influences are removed by a noise removal program to improve the image clarity; the image enhancement unit uses image contrast adjustment and histogram equalization to enhance the contrast between the bacterial image in the image and the background in the image; the threshold segmentation unit uses a grayscale threshold or a morphology-based segmentation method to separate the bacterial image from the background image to generate a binary image.

[0045] The feature extraction module uses machine learning to identify the external structure and in vitro features of specific bacteria, including the outline, area, perimeter and surface features of the bacteria, and stores the identified bacterial features in a memory, storing the bacterial feature information as a basis for identifying specific bacteria.

[0046] The bacteria identification and counting module identifies specific bacteria in the image by comparing and analyzing the bacteria feature information in the memory, counts the number of the bacteria in the image, and stores the number of bacteria and the time when the image was collected.

[0047] The data processing module analyzes and processes the number of bacteria counted at different growth stages, uses the time of each image acquisition in the memory and the number of bacteria corresponding to the acquisition time, takes the bacterial growth time as the horizontal axis and the number of bacteria as the vertical axis, draws a bacterial growth curve, and analyzes the bacterial growth status based on the growth curve.

[0048] A bacterial image data analysis method based on image processing, characterized in that it includes the following steps:

[0049] S1: Intelligently set the time interval and magnification of image acquisition to collect images of bacteria in the culture dish;

[0050] S2: pre-process the collected bacterial images to eliminate interference information;

[0051] S3: extracting and storing the characteristics of specific bacteria, identifying the specific bacteria based on the extracted characteristics of the bacteria, and counting the bacteria;

[0052] S4: Generate a bacterial growth curve according to the number of collected bacteria and the corresponding collection time.

[0053] In step S1: when collecting images, the time interval for collecting images is set according to the growth rate of bacteria, and the magnification of the high-power microscope is set according to the number of bacteria;

[0054] Four image acquisition time intervals are set, namely Δt1, Δt2, Δt3, and Δt4; the comparison results of the four image acquisition time intervals are Δt1>Δt3>Δt4>Δt2; in the initial stage of bacterial culture, the image acquisition time interval Δt1 of the bacterial growth retardation period is directly used. During the bacterial culture process, the image acquisition time interval is changed according to the change of bacterial growth rate; the bacterial growth rate changes continuously with the change of culture time, and the bacterial growth rate is calculated by analyzing the difference between the two consecutive bacterial counts and the time interval between the two image acquisitions:

[0055]

[0056] Among them, N m N represents the number of bacteria collected and counted in the mth bacterial image collection. m-1 represents the number of bacteria counted in the m-1th bacterial image acquisition, m represents the number of image acquisitions; v represents the growth rate of bacteria under different culture times; Δt represents the time interval between two adjacent image acquisitions, and its value is substituted into one of the four values ​​of Δt1, Δt2, Δt3, and Δt4 according to the actual situation; in the initial stage of bacterial culture, the image acquisition time interval is Δt1, and the growth rate of bacteria changes with the growth time of bacteria. When the bacterial growth rate becomes v1, the image acquisition time interval is set to change from Δt1 to Δt2; when the bacterial growth rate becomes v2, the image acquisition time interval is set to change from Δt2 to Δt3; when the bacterial growth rate becomes v3, the image acquisition time interval is set to change from Δt3 to Δt4;

[0057] The magnification is set according to the total number of bacteria at different periods, and a scanning judgment program and a detection area segmentation program are added. When scanning and judging, the percentage of the area with colony distribution in the total area is used to judge whether to perform further area segmentation; the critical condition for judging whether to perform observation area segmentation is set. When the percentage of the area with bacteria distribution in the total area is greater than z, the first area segmentation is performed to divide the detection area into x parts; wherein z represents the ratio of the area with bacteria distribution to the total observation area; after being divided into x parts, the magnification of each divided area is increased and scanned and judged again. When the percentage of the area with bacteria distribution in the divided area to the area after the first segmentation is greater than z′, the second area segmentation is performed on the divided area to divide it into y parts, wherein z′ represents the ratio of the area with bacteria distribution in each image area to the area of ​​this area after the first segmentation, and then the magnification is increased to collect the bacteria distribution image in each area respectively.

[0058] In step S2: the collected image is preprocessed to remove irrelevant information in the image and improve the contrast and clarity of the collected bacterial image; the random noise in the image is removed by median filtering and Gaussian filtering to improve the quality of the image; the contrast between the bacteria and the background in the image is enhanced by image contrast adjustment and histogram equalization; the bacteria are separated from the background by gray threshold or morphology-based segmentation method to generate a binary image.

[0059] In step S3: the bacteria to be counted are identified according to the characteristics of the stored bacteria, and then the number of bacteria in all collected images is counted and the final number of bacteria is counted to obtain the total number N of bacteria in the images collected at this moment; the formula for summing up and calculating the total number of bacteria is:

[0060]

[0061] Where i = 1, 2, 3, ..., x; j = 1, 2, 3, ..., y; where i is the number of the segmented observation area during the first segmentation, and j is the number of the segmented observation area during the second segmentation; n ij It is the number of bacteria in each segmented small area. Through the above calculation, the total number of bacteria N at this moment can be obtained. Then, according to the total number of bacteria corresponding to the image acquisition time, the bacterial growth curve is drawn. According to the bacterial growth curve, the growth status of bacteria can be analyzed to see if there are any abnormalities.

[0062] Embodiment 1: A bacterial image data analysis method based on image processing, characterized in that it comprises the following steps:

[0063] S1: Intelligently set the time interval and magnification of image acquisition to acquire images of E. coli in the culture dish;

[0064] S2: pre-processing the collected E. coli images to eliminate interference information;

[0065] S3: extracting and storing the characteristics of specific E. coli, identifying specific bacteria based on the extracted characteristics of E. coli, and counting the bacteria;

[0066] S4: Generate a bacterial growth curve according to the number of collected Escherichia coli and its corresponding collection time.

[0067] In step S1: when collecting images, the time interval for collecting images is set according to the growth rate of Escherichia coli, and the magnification of the high-power microscope is set according to the number of Escherichia coli; four image collection time intervals are set, namely Δt1=120min, Δt2=40min, Δt3=90min, and Δt4=60min; the size comparison results of the four image collection time intervals are Δt1>Δt3>Δt4>Δt2; in the initial stage of Escherichia coli culture, the time interval Δt1=120min for image collection during the slow growth period of Escherichia coli is directly used, and during the Escherichia coli culture process, the time interval for image collection is changed according to the change of the growth rate of Escherichia coli; the growth rate of Escherichia coli changes continuously with the change of culture time, and the growth rate of Escherichia coli is calculated by analyzing and calculating the difference between the two consecutive numbers of Escherichia coli that have been counted and the time interval between the two collected images:

[0068]

[0069] Among them, N m N represents the number of E. coli counted in the mth E. coli image acquisition. m-1 Indicates the number of E. coli counted in the m-1th E. coli image acquisition, m indicates the number of image acquisitions; v indicates the growth rate of E. coli under different culture times; Δt is the time interval between two adjacent image acquisitions, and its value is substituted into one of the four values ​​of Δt1, Δt2, Δt3, and Δt4 according to the actual situation; in the initial stage of E. coli culture, the image acquisition time interval is Δt1, and the growth rate of E. coli changes with the growth time of E. coli. When the growth rate of E. coli becomes v1, the image acquisition time interval is set to change from Δt1 to Δt2; when the growth rate of E. coli becomes v2, the image acquisition time interval is set to change from Δt2 to Δt3; when the growth rate of E. coli becomes v3, the image acquisition time interval is set to change from Δt3 to Δt4;

[0070] The magnification is set according to the total number of Escherichia coli at different periods, and a scanning judgment program and a detection area segmentation program are added. During the scanning judgment, the percentage of the area with colony distribution in the total area is used to judge whether to perform further area segmentation; a critical condition for judging whether to perform observation area segmentation is set. When the percentage of the area with Escherichia coli distribution in the total area is greater than z=30%, the first area segmentation is performed to divide the detection area into 100 parts; wherein z represents the ratio of the area with Escherichia coli distribution to the total observation area; after being divided into 100 parts, the magnification of each divided area is increased and scanned and judged again. When the percentage of the area with Escherichia coli distribution in the divided area is greater than z′=20% of the area after the first segmentation, the second area segmentation is performed on the divided area to divide it into 50 parts, wherein z′ represents the ratio of the area with Escherichia coli distribution in each image area to the area of ​​this area after the first segmentation, and then the magnification is increased to collect the Escherichia coli distribution image in each area.

[0071] In step S2: preprocessing the collected image to remove irrelevant information in the image and improve the contrast and clarity of the collected Escherichia coli image; removing random noise in the image by median filtering and Gaussian filtering to improve the quality of the image; enhancing the contrast between the Escherichia coli and the background in the image by image contrast adjustment and histogram equalization; separating the Escherichia coli from the background by gray threshold or morphology-based segmentation method to generate a binary image.

[0072] In step S3: the E. coli to be counted is identified according to the characteristics of the stored E. coli, and then the number of E. coli in all collected images is counted and the final number of E. coli is counted to obtain the total number N of E. coli in the images collected at this moment; the total number of E. coli is calculated by summing up:

[0073]

[0074] Where i = 1, 2, 3, ..., 100; j = 1, 2, 3, ..., 50; where i is the number of the segmented observation area during the first region segmentation, and j is the number of the segmented observation area during the second region segmentation; n ij is the number of E. coli in each segmented area. The number of E. coli in each segmented area is collected through experiments. ij Afterwards, the total amount N of E. coli at this moment can be obtained through the above calculation, and then the growth curve is drawn according to the total number of E. coli corresponding to the image acquisition time, and the growth state of E. coli is analyzed according to the growth curve.

[0075] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A bacterial image data analysis system based on image processing, characterized in that: The system includes an image acquisition module, an image preprocessing module, a feature extraction module, a bacteria recognition and counting module, and a data processing module; The image acquisition module is used to intelligently time and intelligently select magnification to acquire images of bacteria; Preprocessing the collected image by the image preprocessing module; Extracting the appearance and structural features of specific bacteria through the feature extraction module, and storing these feature information; Identify specific bacteria in the collected image and count the number of the bacteria by the bacteria identification and counting module; The data processing module analyzes and processes the time of each image acquisition and the data of the number of bacteria corresponding to the acquisition time and generates a bacterial growth curve.

2. The bacterial image data analysis system based on image processing according to claim 1, characterized in that: The image acquisition module performs intelligent timed image acquisition of the bacteria in the culture dish through a high-resolution microscope combined with a digital imaging system, intelligently sets the time interval for image acquisition according to changes in the growth rate of the bacteria, and records the image acquisition time during image acquisition. Different magnifications are used according to the distribution status of the bacteria to acquire images of the bacteria at different culture times.

3. The bacterial image data analysis system based on image processing according to claim 1, characterized in that: The image preprocessing module includes a noise removal unit, an image enhancement unit and a threshold segmentation unit; The noise removal unit removes random noise in the image by means of median filtering and Gaussian filtering; the image enhancement unit enhances the contrast between the bacterial image in the image and the background in the image by means of image contrast adjustment and histogram equalization; the threshold segmentation unit separates the bacterial image from the background image by using a gray threshold or a morphology-based segmentation method to generate a binary image.

4. The bacterial image data analysis system based on image processing according to claim 1, characterized in that: The feature extraction module uses machine learning to identify the external structure and in vitro features of specific bacteria, including the outline, area, perimeter and surface features of the bacteria, and stores the identified bacterial features in a memory, storing the bacterial feature information as a basis for identifying specific bacteria.

5. The bacterial image data analysis system based on image processing according to claim 1, characterized in that: The bacteria identification and counting module compares and analyzes the bacteria features in the captured image with the bacteria feature information in the memory to identify specific bacteria in the image, counts the number of the bacteria in the image, and stores the number of bacteria and the time when the image was captured.

6. The bacterial image data analysis system based on image processing according to claim 1, characterized in that: The data processing module analyzes and processes the number of bacteria counted at different growth stages, uses the time of each image acquisition in the memory and the number of bacteria corresponding to the acquisition time, takes the bacterial growth time as the horizontal axis and the number of bacteria as the vertical axis, draws a bacterial growth curve, and analyzes the bacterial growth status based on the growth curve.

7. A bacterial image data analysis method based on image processing, characterized in that: The following steps are involved: S1: Intelligently set the time interval and magnification of image acquisition to collect images of bacteria in the culture dish; S2: pre-process the collected bacterial images to eliminate interference information; S3: extracting and storing the characteristics of specific bacteria, identifying the specific bacteria based on the extracted characteristics of the bacteria, and counting the bacteria; S4: Generate a bacterial growth curve according to the number of collected bacteria and the corresponding collection time.

8. The bacterial image data analysis method based on image processing according to claim 7, characterized in that: In step S1: when collecting images, the time interval for collecting images is set according to the growth rate of bacteria, and the magnification of the high-power microscope is set according to the number of bacteria; Four image acquisition time intervals are set, namely Δt1, Δt2, Δt3, and Δt4; the comparison results of the four image acquisition time intervals are Δt1>Δt3>Δt4>Δt2; in the initial stage of bacterial culture, the image acquisition time interval Δt1 of the bacterial growth retardation period is directly used. During the bacterial culture process, the image acquisition time interval is changed according to the change of the bacterial growth rate; the bacterial growth rate is calculated by analyzing the difference between the two consecutive bacterial counts and the time interval between the two image acquisitions: Among them, N m N represents the number of bacteria collected and counted in the mth bacterial image collection. m-1 represents the number of bacteria counted in the m-1th bacterial image acquisition, m represents the number of image acquisitions; v represents the growth rate of bacteria under different culture times; Δt represents the time interval between two adjacent image acquisitions, and its value is substituted into one of the four values ​​of Δt1, Δt2, Δt3, and Δt4 according to the actual situation; in the initial stage of bacterial culture, the image acquisition time interval is Δt1, and the growth rate of bacteria changes with the growth time of bacteria. When the bacterial growth rate becomes v1, the image acquisition time interval is set to change from Δt1 to Δt2; when the bacterial growth rate becomes v2, the image acquisition time interval is set to change from Δt2 to Δt3; when the bacterial growth rate becomes v3, the image acquisition time interval is set to change from Δt3 to Δt4; The magnification is set according to the total number of bacteria at different periods, and a scanning judgment program and a detection area segmentation program are added. When scanning and judging, the percentage of the area with colony distribution in the total area is used to judge whether to perform further area segmentation; the critical condition for judging whether to perform observation area segmentation is set. When the percentage of the area with bacteria distribution in the total area is greater than z, the first area segmentation is performed to divide the detection area into x parts; wherein z represents the ratio of the area with bacteria distribution to the total observation area; after being divided into x parts, the magnification of each divided area is increased and scanned and judged again. When the percentage of the area with bacteria distribution in the divided area to the area after the first segmentation is greater than z′, the second area segmentation is performed on the divided area to divide it into y parts, wherein z′ represents the ratio of the area with bacteria distribution in each image area to the area of ​​this area after the first segmentation, and then the magnification is increased to collect the bacteria distribution image in each area respectively.

9. The bacterial image data analysis method based on image processing according to claim 7, characterized in that: In step S2: the collected image is preprocessed to remove irrelevant information in the image and improve the contrast and clarity of the collected bacterial image; the random noise in the image is removed by median filtering and Gaussian filtering to improve the quality of the image; the contrast between the bacteria and the background in the image is enhanced by image contrast adjustment and histogram equalization; the bacteria are separated from the background by gray threshold or morphology-based segmentation method to generate a binary image.

10. The bacterial image data analysis method based on image processing according to claim 8, characterized in that: In step S3: the bacteria to be counted are identified according to the characteristics of the stored bacteria, and then the number of bacteria in all collected images is counted and the final number of bacteria is counted to obtain the total number N of bacteria in the images collected at this moment; the formula for summing up and calculating the total number of bacteria is: Where i = 1, 2, 3, ..., x; j = 1, 2, 3, ..., y; Where i is the segmentation at the first region segmentation Observation area No., j is the number of the segmented observation area during the second segmentation; n ij It is a statistical The number of bacteria in each segmented area.

Images