Algal microscopic image automatic labeling method and device, computer and storage medium

Abstract

The application discloses an algal microscopic image automatic labeling method and device, a computer and a storage medium. All artificial labeling data and automatic labeling data are combined to form a labeling database, image materials in the labeling database are cropped and / or spliced to form a comprehensive training set, and a labeling model is updated according to the comprehensive training set. The algal microscopic image automatic labeling method and device, the computer and the storage medium provided by the application can quickly obtain multiple pure algal samples of different algae from sample water samples, so that a labeling model of specific algae can be quickly trained by using light single-algal manual labeling data, and single-algal microscopic images are automatically labeled; large-scale single-algal labeling data can be quickly and accurately obtained by using the automatic labeling function of the labeling model, and a training set can be efficiently formed by cropping and splicing different algal images to simulate mixed algal samples, so that a labeling model capable of recognizing complex algal sample targets can be quickly trained.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of algal annotation, and in particular to an algal microscopic image automatic annotation method, device, computer and storage medium. BACKGROUND

[0002] The species and quantity of algae are important indicators of aquatic ecosystems, and algal microscopic image analysis plays an important role in algal population research, water quality monitoring and environmental evaluation. However, existing algal annotation datasets mainly rely on manual annotation, which is time-consuming and subjective, limiting the rapid construction of high-quality datasets.

[0003] Deep learning object detection algorithms (such as YOLO, etc.) have made significant progress in object detection tasks. These algorithms have shown great potential in building algal object detection datasets. However, due to the diversity of algal species, microscopic image detection of multiple algal targets faces great challenges. Existing object detection techniques have certain difficulties in accurately classifying different algal targets and providing effective annotation information. In the field of algal annotation, there is still a lack of an efficient automatic annotation method, making the rapid acquisition of training data a bottleneck for algal identification deep learning research. SUMMARY

[0004] The main purpose of the present application is to provide an algal microscopic image automatic annotation method, device, computer and storage medium, which aims to solve the problem that in the field of algal annotation, there is still a lack of an efficient automatic annotation method, making the rapid acquisition of training data a bottleneck for algal identification deep learning research.

[0005] To achieve the above purpose, the present application provides an algal microscopic image automatic annotation method, comprising:

[0006] S1, receiving a microscopic image of a sub-water sample, wherein the sub-water sample is a diluted sample water sample and is formed after being split and cultured, and the microscopic image corresponds to the sub-water sample;

[0007] S2, dividing all the microscopic images into artificial group image data and automatic group image data;

[0008] S3, receiving artificial annotation data and incorporating it into a training set, and updating an annotation model through the training set, wherein the artificial annotation data is annotation formed by manually annotating all the microscopic images in the artificial group image data;

[0009] S4, annotating the automatic group image data according to the annotation model to form automatic annotation data;

[0010] S5, repeating the steps of S1 to S4 for several times, and merging all the artificial annotation data and the automatic annotation data to form an annotation database, wherein the annotation database comprises image materials and material annotation attributes corresponding to the image materials;

[0011] S6, cropping and / or splicing the image materials in the annotation database to form a comprehensive training set, and updating the annotation model according to the comprehensive training set.

[0012] Further, the step of S1 comprises the following steps:

[0013] receiving a merged microscopic photograph image of a merged water sample, wherein the merged water sample is formed by combining all the sub-water samples two by two, and the merged microscopic photograph image corresponds to the merged water sample;

[0014] The step of S6 further comprises the following steps:

[0015] obtaining fusion annotation data according to the merged microscopic photograph image and the material annotation attributes corresponding to the merged microscopic photograph image;

[0016] According to the fusion annotation data, the annotation model is trained and updated.

[0017] Further, in the step of S6, it is determined whether the image material is cropped or spliced according to the image material and the material annotation attributes corresponding to the image material.

[0018] Further, in the step of S5, the suggested sub-division number corresponding to the sample water sample is given according to the artificial annotation data in the last round of steps of S1 to S4.

[0019] Further, in the step of S5, the suggested cultivation time corresponding to the sub-water sample is given according to the artificial annotation data in the last round of steps of S1 to S4.

[0020] Further, in the step of S2, the quantity ratio between the artificial group image data and the automatic group image data is between 1:2 and 1:10.

[0021] Further, in the step of S5, the steps of S1 to S4 are repeated for 2 to 5 times.

[0022] The application also provides a device for running the above method, comprising:

[0023] The storage module is configured to receive a microscopic photograph image of a sub-water sample, wherein the sub-water sample is formed by diluting a sample water sample and sub-dividing and culturing, and the microscopic photograph image corresponds to the sub-water sample;

[0024] The classification module is used for dividing all the microscopic shooting images into artificial group image data and automatic group image data.

[0025] The first training forming module is used for receiving artificial annotation data and entering a training set, and updating an annotation model through the training set, wherein the artificial annotation data is annotation formed by the artificial group image data through artificial annotation.

[0026] The first training working module is used for annotating the automatic group image data according to the annotation model to form automatic annotation data.

[0027] The library forming module is used for repeating the steps of S1 to S4 for several times, and combining all the artificial annotation data and the automatic annotation data to form an annotation database, wherein the annotation database comprises image materials and material annotation attributes corresponding to the image materials.

[0028] The second training forming module is used for cropping and / or splicing the image materials in the annotation database to form a comprehensive training set, and updating the annotation model according to the comprehensive training set.

[0029] The present application also provides a computer comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned algal microscopic image automatic annotation method when executing the computer program.

[0030] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the above-mentioned algal microscopic image automatic annotation method when executed by a processor.

[0031] The algal microscopic image automatic annotation method, device, computer and storage medium provided by the present application can quickly obtain a plurality of pure algal samples of different algae from sample water samples, so that the annotation model of a specific alga can be quickly trained by using light and single algal manual annotation data to automatically annotate single algal microscopic images; large-scale single algal annotation data can be quickly and accurately obtained by using the automatic annotation function of the annotation model, and a training set can be efficiently formed by cropping and splicing different algal images to simulate mixed algal samples, so that the annotation model capable of recognizing complex algal sample targets can be quickly trained; the defects of the automatic annotation model in the classification work are overcome, and in the single algal background, only a small amount of artificial annotation data set is needed to efficiently form the annotation model, and then large-scale automatic annotation work is realized, which not only promotes the development of intelligent algal recognition technology, but also has important significance for the research and application in the related field. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1is a step schematic diagram of an embodiment of the algal microscopic image automatic labeling method of the present application.

[0033] Figure 2 is a conceptual schematic diagram of an embodiment of the device running the algal microscopic image automatic labeling method of the present application.

[0034] The implementation of the object of the present application, functional characteristics and advantages will be further described with reference to the accompanying drawings. DETAILED DESCRIPTION

[0035] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0036] Those skilled in the art can understand that, unless specifically stated, the singular forms "a", "an" and "the" used herein also include the plural forms. It should be further understood that the use of the phrase "comprising" in the specification of the present application means that the features, integers, steps, operations, elements, units, modules and / or components exist, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, units, modules, components and / or combinations thereof. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or there can be intermediate elements. In addition, "connected" or "coupled" used herein can include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit and all combinations of the associated listed items.

[0037] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as that generally understood by those skilled in the art to which the present application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have meanings consistent with those in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as such.

[0038] Referring to Figure 1 , in an embodiment of the present application, an algal microscopic image automatic labeling method comprises:

[0039] S1, receiving a microscopic image of a sub-water sample, wherein the sub-water sample is a diluted sample water sample and is formed after being split and cultured, and the microscopic image corresponds to the sub-water sample;

[0040] S2, dividing all the microscopic images into artificial group image data and automatic group image data;

[0041] S3, receiving artificial annotation data into a training set, and updating the annotation model through the training set, wherein the artificial annotation data is annotation formed by artificial annotation of all the microscopic shooting images in the artificial group image data;

[0042] S4, annotating the automatic group image data according to the annotation model to form automatic annotation data;

[0043] S5, repeating the steps of S1 to S4 for several times, and merging all the artificial annotation data and the automatic annotation data to form an annotation database, wherein the annotation database comprises image materials and material annotation attributes corresponding to the image materials;

[0044] S6, cropping and / or splicing the image materials in the annotation database to form a comprehensive training set, and updating the annotation model according to the comprehensive training set.

[0045] In the prior art, in the field of algal annotation, there is still a lack of an efficient automatic annotation method, so that the rapid acquisition of training data becomes a bottleneck for limiting the research of algal identification deep learning.

[0046] In the present application, in the step of S1, microscopic shooting images of sub-water samples are received, wherein the sub-water samples are formed by diluting sample water samples and culturing after being separated, and the microscopic shooting images correspond to the sub-water samples. In a typical process, the diluted sample water samples are transferred to a 96-well plate for expansion culture, and the dilution degree ensures that at most one algal individual is in each well. After a period of cultivation, multiple individuals of a single alga can be obtained in each well.

[0047] In the step of S2, all the microscopic shooting images are divided into artificial group image data and automatic group image data. The artificial group image data is artificially annotated in the subsequent process, and the automatic group image data is automatically annotated by the annotation model in the subsequent process. The proportion between the artificial group image data and the automatic group image data can be relatively large, such as 1:1 to 1:20.

[0048] In the step of S3, artificial annotation data is received into a training set, and the annotation model is updated through the training set. The artificial annotation data is annotation formed by artificial annotation of all the microscopic shooting images in the artificial group image data. When there is no annotation model, the process of updating the annotation model refers to generating the annotation model.

[0049] In the step of S4, the automatic group image data is annotated according to the annotation model to form automatic annotation data. In this process, the annotation model can quickly complete the annotation process of the automatic group image data.

[0050] In the steps of S5 and S6, the steps of S1 to S4 are repeated several times, and all the manually annotated data and the automatically annotated data are merged to form a labeling database. The labeling database includes image materials and material labeling attributes corresponding to the image materials. The image materials in the labeling database are cropped and / or spliced to form a comprehensive training set, and the labeling model is updated according to the comprehensive training set. Through the formation of the comprehensive training set, a more complex training process can be performed on the labeling model, and the above training process does not need to introduce manual work. Certain logical rules can be set in the selection process of cropping and splicing the image materials, for example, if the material labeling attribute of the image material shows only one kind of algae, then the image material can be cropped and spliced, and if the material labeling attribute of the image material shows multiple kinds of algae, then the image material can be spliced. It is particularly pointed out that, in the process of repeating the steps of S1 to S4, the proportion of the manual group image data and the automatic group image data in the microscopic shooting images is not limited to be fixed, and even all the microscopic shooting images can be divided into automatic group image data, thereby avoiding the consumption of manual work. At this time, the labeling model cannot be updated in the step of S3.

[0051] In one embodiment step:

[0052] (1) Collecting wild water samples, diluting with algae culture medium and transferring to 96-well plates for expansion, the dilution degree ensures that each well has at most one algae individual, after a period of cultivation, multiple individuals of single algae can be obtained in each well.

[0053] (2) Collecting single algae in different wells to shoot microscopic images under a microscope, the microscopic images are divided into manual group image data and automatic group image data at a ratio of 1:5. Since there is only single algae, the manual annotation efficiency is higher than that of complex wild samples.

[0054] (3) For single algae, using the manual annotation data for manual group image data as a training set, combined with the yolov11 model, since there is only single algae, an effective labeling model for the algae can be quickly established, and then accurate and fast automatic annotation work is performed.

[0055] Repeat the above (1) to (3), replace manual annotation with automatic annotation by the optimized labeling model, quickly obtain a large amount of labeled images and data, form mixed algae images by cropping and splicing different types of algae images, and generate a large-scale training set to provide a labeling data basis for further complex algae sample target detection.

[0056] In summary, the sample water sample is expanded to quickly obtain multiple pure algae samples of different algae, so that the annotation model of specific algae can be quickly trained by using lightweight single algae manual annotation data, and the single algae microscopic image can be automatically annotated; the automatic annotation function of the annotation model is used to quickly and accurately obtain large-scale single algae annotation data, and by cropping and splicing different algae images to simulate mixed algae samples, a training set can be efficiently formed, and an annotation model capable of identifying complex algae sample targets can be quickly trained; the defects of the automatic annotation model in classification work are overcome. In the context of a single algae, only a small amount of manually annotated data set is required to efficiently form a annotation model, and then large-scale automatic annotation work can be achieved, which can not only promote the development of intelligent algae recognition technology, but also has important significance for research and application in related fields.

[0057] In one embodiment, the step S1 includes:

[0058] receiving a combined microscopic image of a combined water sample, wherein the combined water sample is formed by combining all the sub-water samples in pairs, and the combined microscopic image corresponds to the combined water sample;

[0059] The step of S6 further includes:

[0060] Obtaining fused annotation data according to the combined microscopic image and the material annotation attribute corresponding to the combined microscopic image;

[0061] The annotation model is trained and updated according to the fused annotation data.

[0062] In this embodiment, after obtaining the microscopic image in step S1, all sub-water samples can be combined in pairs to provide a basis for subsequent work, thereby obtaining a merged microscopic image. The merged microscopic image is not manually annotated, but the annotation results (material annotation attributes) of the two sub-water samples that make up the merged water sample are combined as the annotation result of the merged water sample (fused annotation data). Based on the fused annotation data, the annotation model is trained and updated. The above method of merging water samples and fusing annotation data can increase the capacity of the training library while almost no increase in workload, while doubling the complexity of the fused annotation data provided, thus providing a basis for training and updating the annotation model.

[0063] In one embodiment, in step S6, it is determined whether the image material is cropped or spliced ​​based on the image material and the material annotation attributes corresponding to the image material.

[0064] In the step of S6, the comprehensive training set needs to be formed, and the way of forming the comprehensive training set can be cropping or splicing, but no evaluation criteria are given for choosing which way, so the formation of the comprehensive training set is not optimized. In the present embodiment, considering that the annotation database has all the image materials and the material annotation attributes corresponding to the image materials, for example, the material annotation attribute corresponding to a certain image material shows that there are 3 different algae, and the number of each is 8, 9 and 7 respectively, then the recommended processing method for this image material is cropping, for example, the material annotation attribute corresponding to a certain image material shows that there is 1 kind of algae, and the number is 2, then the recommended processing method for this image material is splicing. Specifically, whether to crop or splice the image material is determined according to the species and number of algae in the image material and the material annotation attribute corresponding to the image material.

[0065] In one embodiment, in the step of S5, the suggested number of sub-samples corresponding to the sample water is given according to the manual annotation data in the last round of steps S1 to S4.

[0066] In the present embodiment, considering that the steps S1 to S4 need to be repeatedly executed for multiple times, in order to meet the condition that the components in the sub-samples are single algae (the efficiency and accuracy of manual annotation and automatic annotation are both high), the number of sub-samples for the sample water in the next round of steps S1 to S4 can be given according to the condition of the manual annotation data. For example, if the manual annotation data in the last round of steps S1 to S4 shows that the number of algae is too small, then the suggested number of sub-samples for reduction is given according to the specific condition; for example, if the manual annotation data in the last round of steps S1 to S4 shows that the number of algae is too large, then the suggested number of sub-samples for increase is given according to the specific condition.

[0067] In one embodiment, in the step of S5, the suggested cultivation time of the sub-samples is given according to the manual annotation data in the last round of steps S1 to S4.

[0068] In the present embodiment, considering that the steps S1 to S4 need to be repeatedly executed for multiple times, in order to meet the condition that the components in the sub-samples are single algae (the efficiency and accuracy of manual annotation and automatic annotation are both high), the suggested cultivation time of the sub-samples in the next round of steps S1 to S4 can be given according to the condition of the manual annotation data. For example, if the manual annotation data in the last round of steps S1 to S4 shows that the number of algae is too large, then the suggested cultivation time for reduction is given according to the specific condition; for example, if the manual annotation data in the last round of steps S1 to S4 shows that the number of algae is too small, then the suggested cultivation time for increase is given according to the specific condition.

[0069] In one embodiment, in step S2, the ratio of the number of the manually grouped image data to the number of the automatically grouped image data is between 1:2 and 1:10.

[0070] In this embodiment, a suitable ratio of manually grouped image data to automatically grouped image data is provided, thereby improving the efficiency and accuracy of the overall annotation without increasing the manual workload.

[0071] In one embodiment, in step S5, steps S1 to S4 are repeated 2 to 5 times.

[0072] In this embodiment, an appropriate number of repetitions of S1 to S4 is given to improve the efficiency and accuracy of the overall labeling without high manual workload.

[0073] The present invention also provides a device for executing the above method, comprising:

[0074] The storage module 10 is configured to receive a microscopic image of a sub-water sample, wherein the sub-water sample is formed by diluting the sample water sample and then splitting and culturing it, and the microscopic image corresponds to the sub-water sample;

[0075] a classification module 20, configured to classify all the microscopic images into manually grouped image data and automatically grouped image data;

[0076] A first training forming module 30 is configured to receive manually annotated data and incorporate it into a training set, and to update the annotation model using the training set, wherein the manually annotated data is manually annotated for all the microscopic images in the manual set of image data;

[0077] A first training module 40 is configured to annotate the automatically grouped image data according to the annotation model to form automatically annotated data;

[0078] a library forming module 50 for repeating steps S1 to S4 several times and merging all the manual annotation data and the automatic annotation data to form an annotation database, wherein the annotation database includes image materials and material annotation attributes corresponding to the image materials;

[0079] The second training forming module 60 is configured to cut and / or splice the image materials in the annotation database to form a comprehensive training set, and update the annotation model according to the comprehensive training set.

[0080] In this embodiment, the working method of the device will not be described in detail here, and reference will be made to the aforementioned method content.

[0081] The application further provides a computer comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above-mentioned automatic algae microscopic image labeling method when executing the computer program.

[0082] The computer device comprises a processor, a storage, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The storage of the computer device comprises a non-volatile storage medium and an internal storage. The non-volatile storage medium stores an operating system and a computer program. The internal storage provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a file storage method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0083] The application further provides a computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned automatic algae microscopic image labeling method.

[0084] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium provided by the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (RambuS) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM) and the like.

[0085] In summary, the algal microscopic image automatic labeling method, device, computer and storage medium provided by the present application can quickly obtain a plurality of pure algal samples of different algae by expanding the sample water sample, so as to quickly train the labeling model of a specific alga by using the manual labeling data of a light single alga, and automatically label the microscopic image of a single alga; the large-scale single algal labeling data can be quickly and accurately obtained by using the automatic labeling function of the labeling model, the training set can be efficiently formed by cutting and splicing the images of different algae to simulate mixed algal samples, and the labeling model capable of recognizing the target of a complex algal sample can be quickly trained; the defects of the automatic labeling model in classification work are overcome, and in the single algal background, only a small amount of artificial labeling data set is needed to efficiently form the labeling model, and then the large-scale automatic labeling work is realized, which not only promotes the development of intelligent algal recognition technology, but also has important significance for the research and application in related fields.

[0086] The above-mentioned is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation using the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for automatically annotating algae microscopic images, characterized in that: include: S1. Receive a microscopic image of a sub-water sample, wherein the sub-water sample is formed by diluting a sample water sample and then splitting and culturing it, and the microscopic image corresponds to the sub-water sample; S2, dividing all the microscopic images into manual group image data and automatic group image data; S3, receiving manually annotated data and incorporating it into a training set, and updating the annotation model using the training set, wherein the manually annotated data is manually annotated for all the microscopic images in the manual group of image data; S4, annotating the automatically grouped image data according to the annotation model to form automatically annotated data; S5, repeating steps S1 to S4 several times, and merging all the manual annotation data and the automatic annotation data to form an annotation database, wherein the annotation database includes image materials and material annotation attributes corresponding to the image materials; S6. Cutting and / or splicing the image materials in the annotation database to form a comprehensive training set, and updating the annotation model according to the comprehensive training set; In the step S5, a recommended number of splits corresponding to the water sample is given based on the manually labeled data in the previous round of steps S1 to S4; In the step S5, a recommended incubation time corresponding to the sub-water sample is given based on the manually labeled data in the previous round of steps S1 to S4; The step S1 then includes: receiving a combined microscopic image of a combined water sample, wherein the combined water sample is formed by combining all the sub-water samples in pairs, and the combined microscopic image corresponds to the combined water sample; The step of S6 further includes: Obtaining fused annotation data according to the combined microscopic image and the material annotation attribute corresponding to the combined microscopic image; Training and updating the annotation model according to the fused annotation data; In the step S6, it is determined whether the image material is cropped or spliced ​​according to the image material and the material annotation attributes corresponding to the image material.

2. The automatic annotation method for algae microscopic images according to claim 1, characterized in that: In the step S2, the ratio of the number of the manually grouped image data to the number of the automatically grouped image data is between 1:2 and 1:

10.

3. The automatic annotation method for algae microscopic images according to claim 1, characterized in that: In the step S5, the steps S1 to S4 are repeated 2 to 5 times.

4. A device for running the method according to any one of claims 1 to 3, characterized in that: include: A storage module (10) is used to receive a microscopic image of a sub-water sample, wherein the sub-water sample is formed by diluting the sample water sample and then splitting and culturing it, and the microscopic image corresponds to the sub-water sample; A classification module (20) is used to classify all the microscopic images into manual group image data and automatic group image data; A first training forming module (30) is used to receive manually annotated data and incorporate it into a training set, and to update the annotation model using the training set, wherein the manually annotated data is manually annotated for all the microscopic images in the manual group image data; A first training working module (40) is used to annotate the automatic group image data according to the annotation model to form automatic annotation data; A library forming module (50) is used to repeat the above steps S1 to S4 several times, and merge all the manual annotation data and the automatic annotation data to form an annotation database, wherein the annotation database includes image materials and material annotation attributes corresponding to the image materials; The second training forming module (60) is used to cut and / or splice the image materials in the annotation database to form a comprehensive training set, and update the annotation model according to the comprehensive training set.

5. A computer comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for automatically annotating algae microscopic images according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for automatically annotating algae microscopic images according to any one of claims 1 to 3 are implemented.

Images