Biometric-based nematode identity authentication method and system

Abstract

The application provides a nematode identity authentication method and system based on biological recognition, relates to the technical field of biological recognition, and comprises the following steps: image acquisition is performed through a high-resolution microscope, data preprocessing is performed, physiological characteristics are recognized through a feature extraction model, and are converted into digital codes; a mapping label outputting a nematode species name and strain information is outputted; image shooting and physiological characteristic extraction are performed on nematodes that need to be subjected to identity recognition; a target mapping label with the highest feature similarity is outputted; label analysis is performed; and identity authentication is completed. Through the application, the technical problem that the recognition efficiency is poor in the prior art because traditional nematode identity recognition mainly depends on morphological characteristics and taxonomic methods can be solved; nematode images are collected through a high-resolution microscope; nematode physiological characteristics are recognized through a feature extraction model; and identity matching is performed through a feature database; and the technical effect of improving the identity authentication efficiency of nematodes is achieved.

Description

Technical Field

[0001] This invention relates to the field of biometrics, and in particular to a biometric-based nematode authentication method and system. Background Technology

[0002] In biological research and space biology experiments, nematodes are widely used as model organisms in various experiments, often requiring long-term observation and tracking of large numbers of individual nematodes to study their physiological and behavioral characteristics. However, the differences between individual nematodes are minute, making accurate identification and tracking difficult using traditional methods. Current nematode identification methods typically rely on traditional taxonomic and molecular biology techniques, which are not only inefficient but also prone to errors. Furthermore, as the scale of experiments increases, manual management becomes increasingly impractical. While some automated technologies such as barcodes or RFID tags are used for identification in large animals, these technologies have significant limitations in their application to tiny organisms like nematodes.

[0003] In summary, existing technologies suffer from poor identification efficiency because traditional nematode identification relies primarily on morphological features and taxonomic methods. Summary of the Invention

[0004] The purpose of this invention is to provide a biometric-based nematode identification method and system to solve the technical problem that the traditional nematode identification mainly relies on morphological features and taxonomic methods, resulting in poor identification efficiency.

[0005] In view of the above problems, the present invention provides a biometric-based nematode authentication method and system.

[0006] In a first aspect, the present invention provides a biometric-based nematode authentication method, which is implemented through a biometric-based nematode authentication system. The biometric-based nematode authentication method includes: acquiring images of individual nematodes in a space biological experiment using a high-resolution microscope to generate nematode image data; preprocessing the nematode image data to generate preprocessed image data; identifying nematode physiological features in the preprocessed image data using a feature extraction model to generate nematode physiological features; converting the physiological features into digital codes and outputting mapping labels identifying the nematode species name and strain information, storing these labels in a feature database; capturing images of a first target nematode requiring identification using the high-resolution microscope and extracting physiological features using the feature extraction model to generate target physiological features; calling the feature database to perform feature matching on the target physiological features, outputting the target mapping label with the highest feature similarity, parsing the label, and completing the authentication of the first target nematode.

[0007] Secondly, the present invention also provides a biometric-based nematode authentication system for executing the biometric-based nematode authentication method as described in the first aspect, wherein the biometric-based nematode authentication system comprises: an image acquisition module for acquiring images of individual nematodes in aerospace biological experiments using a high-resolution microscope to generate nematode image data; a data preprocessing module for preprocessing the nematode image data to generate preprocessed image data; and a physiological feature recognition module for recognizing nematode physiological features in the preprocessed image data using a feature extraction model to generate nematode image data. The system comprises: a physiological feature module; a feature conversion module, which converts the physiological features into digital codes and outputs mapping labels identifying the nematode species name and strain information, storing these labels in a feature database; an identity recognition module, which takes images of the first target nematode requiring identity recognition using the high-resolution microscope and extracts physiological features using the feature extraction model to generate target physiological features; and a feature matching module, which calls the feature database to perform feature matching on the target physiological features, outputs the target mapping label with the highest feature similarity, performs label parsing, and completes the identity authentication of the first target nematode.

[0008] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0009] Images of individual nematodes in aerospace biological experiments are acquired using a high-resolution microscope, generating nematode image data. This image data is then preprocessed to generate preprocessed image data. A feature extraction model is used to identify the physiological characteristics of the nematodes within the preprocessed image data, generating nematode physiological features. These physiological features are converted into digital codes, and mapping labels identifying the nematode species name and strain information are output and stored in a feature database. Images of a first target nematode requiring identification are then captured using the same high-resolution microscope, and its physiological features are extracted using the same feature extraction model, generating target physiological features. The feature database is then used to perform feature matching on the target physiological features, outputting the target mapping label with the highest feature similarity. Label parsing completes the identification of the first target nematode. In other words, by acquiring nematode images using a high-resolution microscope, identifying nematode physiological features using a feature extraction model, and performing identification matching using a feature database, the technical effect of improving the efficiency of nematode identification is achieved.

[0010] The above description is merely an overview of the technical solution of the present invention. To better understand the technical means of the present invention and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of the present invention more apparent, specific embodiments of the present invention are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating the biometric-based nematode authentication method of the present invention.

[0013] Figure 2 This is a schematic diagram of the biometric-based nematode authentication system of the present invention.

[0014] Figure labeling: Image acquisition module 11, data preprocessing module 12, physiological feature recognition module 13, feature conversion module 14, identity recognition module 15, feature matching module 16. Detailed Implementation

[0015] This invention provides a biometric-based nematode identification method and system, solving the technical problem of poor identification efficiency in existing technologies, where traditional nematode identification relies primarily on morphological features and taxonomic methods. By acquiring nematode images using a high-resolution microscope, identifying physiological characteristics of the nematodes using a feature extraction model, and performing identity matching through a feature database, the invention achieves a significant improvement in the efficiency of nematode identification.

[0016] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0017] Example 1, please refer to the appendix. Figure 1 This invention provides a biometric-based nematode authentication method, wherein the biometric-based nematode authentication method is applied to a biometric-based nematode authentication system, and the biometric-based nematode authentication method specifically includes the following steps:

[0018] Step 1: Collect images of individual nematodes in the space biological experiment using a high-resolution microscope to generate nematode image data.

[0019] Specifically, high-resolution imaging technology is used to image nematodes. High-resolution microscopes have extremely high magnification and resolution, enabling them to capture the minute physiological structures and features of individual nematodes. The nematodes are placed on a suitable observation platform, the microscope lens is aimed at them, and clear images are obtained by adjusting the microscope's illumination, contrast, and focus. The acquired images are stored for subsequent analysis. The use of high-resolution microscopy to acquire raw, high-quality image data ensures the accuracy of subsequent identification.

[0020] Step 2: Preprocess the nematode image data to generate preprocessed image data.

[0021] Specifically, the collected nematode image data undergoes preprocessing, including noise reduction, contrast enhancement, image segmentation, resizing, and grayscale conversion. This process eliminates factors that may interfere with feature extraction, such as uneven lighting and cluttered backgrounds, improving image quality and enhancing useful information. Nematode images can be imported into preprocessing software, where the above steps are followed to process the images using various algorithms. The preprocessed images are then checked to ensure they meet quality requirements, and further adjustments can be made if necessary. The preprocessed data is saved as a dataset, generating preprocessed image data. Image preprocessing significantly improves the usability of image data and enhances the visibility of nematode physiological characteristics.

[0022] Step 3: Use a feature extraction model to identify the physiological features of nematodes in the preprocessed image data and generate nematode physiological features.

[0023] Specifically, based on the characteristic attributes of nematodes, a preset set of nematode feature attributes is established, including body outline, mouth structure, and reproductive organ details. For each feature attribute, features are collected from different nematode individuals, generating a corresponding individual feature sample set. Individual difference analysis is performed to calculate the discriminative power of each feature. These discriminative powers are then sorted, and all feature attributes with discriminative powers greater than the preset value are selected as target feature attributes to construct a feature extraction model. Preprocessed image data is input into this feature extraction model to identify and extract the physiological characteristics of the target feature attributes. By using the feature extraction model to identify the physiological characteristics of nematodes from preprocessed image data, key physiological characteristics of nematodes can be extracted efficiently and accurately from images.

[0024] Step 4: Convert the physiological characteristics into digital codes and output mapping labels that identify the nematode species name and strain information, and store them in the feature database.

[0025] Specifically, for each extracted nematode physiological characteristic, a specific encoding method is used to convert it into a digital code, ensuring that the digital code corresponding to each physiological characteristic is unique, meaning that different nematode individuals will not generate the same identification code. The physiological characteristics of each nematode individual are classified, outputting the nematode species name and strain information. A mapping label is generated for each digital code, containing the nematode species name and strain information. The generated digital codes and mapping labels are stored in a feature database, ensuring that the nematode species name and strain information corresponding to each code can be traced. By converting physiological characteristics into digital codes and outputting mapping labels identifying nematode species names and strain information, and storing them in the feature database, the identification process is automated, reducing manual intervention and error rates.

[0026] Step 5: Take an image of the first target nematode that needs to be identified using the high-resolution microscope, and extract physiological features using the feature extraction model to generate target physiological features.

[0027] Specifically, images of the primary target nematode requiring identification are captured using a high-resolution microscope and placed on the microscope slide to ensure sufficient resolution for clear capture of the nematode's physiological details. The captured images are then imported into preprocessing software for preprocessing. Based on a previously established brightness adjustment network, brightness correction is applied to improve image quality. The corrected images are then input into a feature extraction model to identify and extract the nematode's physiological features, generating target physiological characteristics. By capturing images with a high-resolution microscope and combining this with the feature extraction model for physiological feature extraction, key physiological features can be extracted efficiently and accurately from the images of the target nematode.

[0028] Step Six: Call the feature database to perform feature matching on the target physiological features, output the target mapping label with the highest feature similarity, perform label parsing, and complete the identity authentication of the first target nematode.

[0029] Specifically, the method involves calling a feature database to match the physiological characteristics of the target nematode with the features stored in the database, including using machine learning algorithms or statistical methods to evaluate the similarity between features. The output is a label that best matches the physiological characteristics of the target nematode, containing the nematode's species name and strain information, as well as the database record most similar to the target nematode's features. The output matching labels are then interpreted, combining the information in the labels with the nematode's identity information, experimental data, or other relevant background information. Based on the label parsing results, the identity of the first target nematode is verified. This confirms the nematode's identity and may also include other relevant identification information. By calling the feature database for feature matching, outputting the target mapping label with the highest feature similarity, and parsing the label, the nematode identification method can quickly and accurately identify the nematode.

[0030] Furthermore, step three of the present invention includes:

[0031] A preset set of nematode feature attributes is established; nematode discrimination is performed on each feature attribute in the preset set of nematode feature attributes to generate the feature discrimination corresponding to each feature attribute; feature attributes with discrimination greater than the preset discrimination are extracted based on the feature discrimination, and target feature attributes are constructed; nematode feature samples are collected based on the target feature attributes to construct the feature extraction model; the preprocessed image data is input into the feature extraction model to identify nematode physiological features and generate the nematode physiological features.

[0032] Specifically, based on the physiological and morphological characteristics of nematodes, features that can effectively distinguish different nematodes are selected, such as body outline, mouth structure, and details of reproductive organs. It is ensured that the selected features comprehensively represent the physiological and morphological differences of nematodes for accurate identification and classification. These features are combined into a set called the preset nematode feature attribute set. The feature attribute set should be comprehensive and specific, covering all possible variations of nematodes. Each collected feature attribute is analyzed, and a discrimination score is generated for each feature attribute through statistical analysis or machine learning algorithms, reflecting the importance of the feature in classification. Based on the evaluation results, the feature attributes are ranked to determine which features have the highest discrimination. Based on the needs of nematode identification and experimental data, a preset discrimination threshold is set to determine whether the discrimination of a feature attribute is high enough to be included in the target feature attribute set. Based on the calculated feature discrimination, feature attributes with discrimination greater than the preset threshold are selected; these attributes are key features for distinguishing different nematode species or strains. The selected feature attributes are combined to form the target feature attribute set.

[0033] Using a target feature attribute set, corresponding feature samples are collected from nematode image data, ensuring the samples are representative and cover various possible variations of nematodes. The collected feature samples are labeled, indicating the nematode species or strain corresponding to each sample. Based on the characteristics of the feature samples and the needs of identification, appropriate machine learning or deep learning models, including support vector machines, random forests, and convolutional neural networks, are selected. The selected model is trained using the collected feature samples, and the model continuously learns how to extract target feature attributes from images. Methods such as cross-validation are used to ensure the model has good generalization ability and accuracy. The preprocessed nematode image data is input into the feature extraction model to identify and extract target feature attributes, including physiological features such as body size, texture, and color. By establishing and optimizing the feature attribute set and constructing an efficient feature extraction model, the key features of nematodes are captured more accurately.

[0034] Furthermore, the present invention also includes the following steps:

[0035] Based on the aforementioned characteristic attributes, features are collected from different nematode individuals to generate a first individual feature sample set corresponding to the first characteristic attribute; individual difference analysis is performed based on the first individual feature sample set to generate a first feature discrimination index; and feature discrimination indexes corresponding to the aforementioned characteristic attributes are generated based on the first feature discrimination index.

[0036] Specifically, for each feature attribute in the pre-defined set of nematode feature attributes, corresponding feature data is collected from multiple nematode individuals. The extracted features are then categorized and organized according to the nematode individuals to construct the first body feature sample set, containing feature data from different nematode individuals. Each sample set corresponds to a specific feature attribute. Individual difference analysis is performed on the first body feature sample set to evaluate the discriminative power of the first feature attribute, reflecting its ability to distinguish nematode individuals. Similarly, a corresponding feature discriminative power is generated for each feature attribute, reflecting the ability of each feature attribute to distinguish nematode individuals. By collecting features, performing individual difference analysis, and generating feature discriminative powers for each feature attribute, the most valuable features for nematode identification can be selected.

[0037] Furthermore, step four of the present invention includes:

[0038] The physiological characteristics are converted into unique identifiers to generate the digital codes; the physiological characteristics are configured with nematode species names and strain information to establish mapping tags that have a mapping relationship with the digital codes; the physiological characteristics, the digital codes, and the mapping tags are stored in the feature database.

[0039] Specifically, for each extracted nematode physiological characteristic, it is converted into a digital code using a specific encoding method. The encoding can be a simple numerical representation or a complex encoding scheme, such as hash codes or binary encoding. It is ensured that the digital code corresponding to each physiological characteristic is unique, meaning that different nematode individuals will not generate the same identifier code. For example, body length is encoded as "001", body width as "010", and the number of segments as "100". Based on the extracted nematode physiological characteristics, the nematode species name and strain information are configured. This information can be obtained through expert knowledge, database queries, or other methods. A mapping relationship between the digital codes and the nematode species name and strain information is established using database tables, lookup tables, or other data structures. A mapping label is generated for each digital code, which can be a string or data structure containing all necessary information. A database structure suitable for storing nematode characteristic data is designed, including fields for storing physiological characteristic data, digital codes, and mapping labels; this can be implemented using MySQL. The characteristics, digital codes, and mapping labels are stored together in the database to ensure that the nematode species name and strain information corresponding to each code can be traced. Storing physiological characteristics, digital codes, and mapping labels in a feature database provides convenient and fast data support for nematode identification. It can be easily stored and compared, facilitating the automation of the identification process and reducing manual intervention and error rates.

[0040] Furthermore, step five of the present invention includes:

[0041] An image analysis brightness standard is established for the feature extraction model, wherein the image analysis brightness standard is the image brightness with the highest recognition accuracy; a brightness adjustment network is established based on the image analysis brightness standard, and the brightness adjustment network is connected to the feature extraction model to perform brightness correction before feature extraction.

[0042] Specifically, feature extraction tests are performed on multiple sets of analysis samples corresponding to different brightness levels to evaluate the recognition accuracy at each brightness level. The image brightness with the highest recognition accuracy is selected as the image analysis brightness standard, which represents the brightness level at which the model achieves optimal performance during feature extraction. Based on the image analysis brightness standard, a brightness adjustment network is designed to automatically adjust the image brightness according to the difference between the input image brightness and the image analysis brightness standard. The brightness adjustment network can be based on deep learning methods, such as convolutional neural networks (CNNs), or simpler traditional image processing algorithms. The brightness adjustment network is trained using a large amount of nematode image data. During training, the network learns how to adjust image brightness according to the image brightness standard. The trained brightness adjustment network is then connected to the feature extraction model. Before feature extraction, the brightness of the input image is corrected by the brightness adjustment network, and the output of the brightness adjustment network serves as the input to the feature extraction model. When a new nematode image is input to the system, the brightness is first evaluated and adjusted by the brightness adjustment network. If the image brightness does not match the standard brightness, the brightness adjustment network automatically adjusts the image brightness to the standard level. For example, if the brightness adjustment network detects that the brightness of the input nematode image is lower than the standard, it increases the image brightness. The brightness-corrected image is then fed into the feature extraction model for the extraction and recognition of physiological features. By automatically adjusting the image brightness, the feature extraction model is ensured to always operate under optimal brightness conditions, thereby improving the accuracy and robustness of the nematode authentication system.

[0043] Furthermore, the present invention also includes the following steps:

[0044] Multiple sets of brightness analysis samples are constructed, wherein each set of brightness analysis samples includes a set of nematode image samples corresponding to an image brightness and a set of identification information containing actual physiological characteristics; the multiple sets of brightness analysis samples are respectively input into the feature extraction model for feature extraction testing, and the image brightness with the highest recognition accuracy is output to generate the image analysis brightness standard.

[0045] Specifically, multiple sets of brightness analysis samples are constructed, each targeting different image brightness levels. Each set includes a series of nematode image samples corresponding to a given image brightness, and a set of identification information containing actual physiological characteristics. The identification information set should include the nematode species name, strain information, and other known physiological characteristics. Each set of brightness analysis samples is input into a feature extraction model to extract features from each image and identify the physiological characteristics of the nematodes in the image. For each brightness level sample set, the differences between the physiological characteristics output by the model and the actual identification information set are compared to evaluate the recognition accuracy of the feature extraction model. Based on the accuracy evaluation results, the image brightness with the highest recognition accuracy is determined as the optimal operating point for the model. The image brightness with the highest recognition accuracy is then determined as the image analysis brightness standard. For example, with three sample sets—low brightness, medium brightness, and high brightness nematode image sample sets and their corresponding identification information sets—these three sets of samples are input into the feature extraction model for testing and recognition accuracy evaluation. It is found that the medium brightness sample set has the highest recognition accuracy. Therefore, medium brightness is determined as the image analysis brightness standard. By testing and evaluating sample sets at different brightness levels, the image brightness with the highest recognition accuracy is determined, and an image analysis brightness standard is generated, which helps to optimize the image acquisition and processing process.

[0046] Furthermore, step six of the present invention includes:

[0047] The feature database is traversed, and the similarity is compared with the target physiological features to generate the target mapping label with the highest feature similarity; the target mapping label is associated and parsed to generate the identity authentication result of the first target nematode.

[0048] Specifically, the feature database is traversed, and the physiological characteristics in the database are compared with those of the target nematode. Similarity comparison may employ Euclidean distance, cosine similarity, or other related algorithms to assess the degree of similarity between features. For each record in the database, a similarity score is calculated between the target physiological characteristics and the mapping label containing the species name and strain information of the nematode most similar to the target nematode's physiological characteristics. The target mapping label is interpreted according to specific rules to extract the nematode species name and strain information contained within it. The parsed nematode species name and strain information are associated with the identity information of the first target nematode, combining the information in the label with the nematode's experimental data, research background, or other relevant information. An identity authentication result for the first target nematode is generated, confirming the nematode's identity, including other relevant identification information such as the nematode's origin and experimental conditions. Through feature similarity comparison and identity authentication result generation, the nematode identity authentication method can quickly and accurately identify the nematode, helping to ensure the efficiency and accuracy of experiments and research.

[0049] In summary, the biometric-based nematode authentication method provided by this invention has the following technical effects:

[0050] Images of individual nematodes in aerospace biological experiments are acquired using a high-resolution microscope, generating nematode image data. This image data is then preprocessed to generate preprocessed image data. A feature extraction model is used to identify the physiological characteristics of the nematodes within the preprocessed image data, generating nematode physiological features. These physiological features are converted into digital codes, and mapping labels identifying the nematode species name and strain information are output and stored in a feature database. Images of a first target nematode requiring identification are then captured using the same high-resolution microscope, and its physiological features are extracted using the same feature extraction model, generating target physiological features. The feature database is then used to perform feature matching on the target physiological features, outputting the target mapping label with the highest feature similarity. Label parsing completes the identification of the first target nematode. In other words, by acquiring nematode images using a high-resolution microscope, identifying nematode physiological features using a feature extraction model, and performing identification matching using a feature database, the technical effect of improving the efficiency of nematode identification is achieved.

[0051] Example 2: Based on the same inventive concept as the biometric-based nematode authentication method in the foregoing examples, this invention also provides a biometric-based nematode authentication system. Please refer to the appendix. Figure 2 The biometric-based nematode authentication system includes:

[0052] Image acquisition module 11 is used to acquire images of individual nematodes in aerospace biological experiments using a high-resolution microscope and generate nematode image data.

[0053] The data preprocessing module 12 is used to preprocess the nematode image data to generate preprocessed image data.

[0054] Physiological feature recognition module 13 is used to identify nematode physiological features in the preprocessed image data through a feature extraction model, and generate nematode physiological features.

[0055] Feature conversion module 14 is used to convert the physiological characteristics into digital codes and output mapping labels that identify the nematode species name and strain information, and store them in the feature database.

[0056] The identity recognition module 15 is used to take images of the first target nematode that needs to be identified by the high-resolution microscope, and to extract physiological features by the feature extraction model to generate target physiological features.

[0057] The feature matching module 16 is used to call the feature database, perform feature matching on the target physiological features, output the target mapping label with the highest feature similarity, perform label parsing, and complete the identity authentication of the first target nematode.

[0058] Furthermore, the physiological feature recognition module 13 in the biometric-based nematode authentication system is also used for:

[0059] A preset set of nematode feature attributes is established; nematode discrimination is performed on each feature attribute in the preset set of nematode feature attributes to generate the feature discrimination corresponding to each feature attribute; feature attributes with discrimination greater than the preset discrimination are extracted based on the feature discrimination, and target feature attributes are constructed; nematode feature samples are collected based on the target feature attributes to construct the feature extraction model; the preprocessed image data is input into the feature extraction model to identify nematode physiological features and generate the nematode physiological features.

[0060] Furthermore, the biometric-based nematode authentication system also includes a feature discrimination generation module, used for:

[0061] Based on the aforementioned characteristic attributes, features are collected from different nematode individuals to generate a first individual feature sample set corresponding to the first characteristic attribute; individual difference analysis is performed based on the first individual feature sample set to generate a first feature discrimination index; and feature discrimination indexes corresponding to the aforementioned characteristic attributes are generated based on the first feature discrimination index.

[0062] Furthermore, the feature conversion module 14 in the biometric-based nematode authentication system is also used for:

[0063] The physiological characteristics are converted into unique identifiers to generate the digital codes; the physiological characteristics are configured with nematode species names and strain information to establish mapping tags that have a mapping relationship with the digital codes; the physiological characteristics, the digital codes, and the mapping tags are stored in the feature database.

[0064] Furthermore, the identity recognition module 15 in the biometric-based nematode authentication system is also used for:

[0065] An image analysis brightness standard is established for the feature extraction model, wherein the image analysis brightness standard is the image brightness with the highest recognition accuracy; a brightness adjustment network is established based on the image analysis brightness standard, and the brightness adjustment network is connected to the feature extraction model to perform brightness correction before feature extraction.

[0066] Furthermore, the identity recognition module 15 in the biometric-based nematode authentication system is also used for:

[0067] Multiple sets of brightness analysis samples are constructed, wherein each set of brightness analysis samples includes a set of nematode image samples corresponding to an image brightness and a set of identification information containing actual physiological characteristics; the multiple sets of brightness analysis samples are respectively input into the feature extraction model for feature extraction testing, and the image brightness with the highest recognition accuracy is output to generate the image analysis brightness standard.

[0068] Furthermore, the feature matching module 16 in the biometric-based nematode authentication system is also used for:

[0069] The feature database is traversed, and the similarity is compared with the target physiological features to generate the target mapping label with the highest feature similarity; the target mapping label is associated and parsed to generate the identity authentication result of the first target nematode.

[0070] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The biometric-based nematode authentication method and specific examples in Embodiment 1 are also applicable to the biometric-based nematode authentication system of this embodiment. Through the foregoing detailed description of the biometric-based nematode authentication method, those skilled in the art can clearly understand the biometric-based nematode authentication system of this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As the system disclosed in the embodiments corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0071] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0072] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A biometric-based nematode authentication method, characterized in that, include: Images of individual nematodes in space biological experiments were acquired using a high-resolution microscope, generating nematode image data. The nematode image data is preprocessed to generate preprocessed image data; The preprocessed image data is used to identify the physiological features of nematodes using a feature extraction model, thereby generating nematode physiological features. The physiological characteristics are converted into digital codes, and mapping labels that identify nematode species names and strain information are output and stored in the feature database. The high-resolution microscope is used to capture images of the first target nematode that needs to be identified, and the physiological features are extracted using the feature extraction model to generate the target physiological features. The feature database is invoked to perform feature matching on the target physiological features, output the target mapping label with the highest feature similarity, perform label parsing, and complete the identity authentication of the first target nematode. Also includes: Establish an image analysis brightness standard for the feature extraction model, wherein the image analysis brightness standard is the image brightness with the highest recognition accuracy; A brightness adjustment network is established based on the image analysis brightness standard, and the brightness adjustment network is connected to the feature extraction model to perform brightness correction before feature extraction.

2. The biometric-based nematode authentication method as described in claim 1, characterized in that, The preprocessed image data is subjected to nematode physiological feature identification using a feature extraction model to generate nematode physiological features, including: Establish a pre-defined set of nematode feature attributes; The nematode discrimination score is identified for each feature attribute in the preset nematode feature attribute set, and the feature discrimination score corresponding to each feature attribute is generated. Based on the feature discrimination, feature attributes with discrimination greater than a preset discrimination are extracted, and target feature attributes are constructed. The feature extraction model is constructed by collecting nematode feature samples based on the target feature attributes; The preprocessed image data is input into the feature extraction model to identify the physiological features of nematodes and generate the physiological features of nematodes.

3. The biometric-based nematode authentication method as described in claim 2, characterized in that, Perform nematode discrimination identification on each feature attribute in the preset nematode feature attribute set, and generate the feature discrimination score corresponding to each feature attribute, including: Based on the aforementioned characteristic attributes, feature collection is performed on different nematode individuals to generate the first body feature sample set corresponding to the first characteristic attribute; Based on the first individual feature sample set, perform individual difference analysis to generate the first feature discrimination score; The feature discrimination scores corresponding to each feature attribute are generated based on the first feature discrimination score.

4. The biometric-based nematode authentication method as described in claim 1, characterized in that, The physiological characteristics are converted into digital codes, and mapping labels identifying nematode species names and strain information are output and stored in a feature database, including: The physiological characteristics are converted into unique identifiers to generate the digital code; Configure the nematode species name and strain information for the physiological characteristics, and establish a mapping label that has a mapping relationship with the digital code; The physiological characteristics, the digital codes, and the mapping labels are stored in the feature database.

5. The biometric-based nematode authentication method as described in claim 1, characterized in that, The feature database is invoked to perform feature matching on the target physiological features, outputting the target mapping label with the highest feature similarity, and performing label parsing to complete the identity authentication of the first target nematode, including: The feature database is traversed, and the similarity is compared with the target physiological features to generate the target mapping label with the highest feature similarity; The target mapping label is associated and parsed to generate the identity authentication result of the first target nematode.

6. The biometric-based nematode authentication method as described in claim 1, characterized in that, The image analysis brightness standard for the feature extraction model includes: Construct multiple sets of brightness analysis samples, wherein each set of brightness analysis samples includes a set of nematode image samples corresponding to the brightness of an image and a set of identification information containing actual physiological characteristics; The multiple sets of brightness analysis samples are respectively input into the feature extraction model for feature extraction testing, and the image brightness with the highest recognition accuracy is output to generate the image analysis brightness standard.

7. A biometric-based nematode authentication system, characterized in that, The steps for implementing the biometric-based nematode authentication method according to any one of claims 1 to 6, wherein the biometric-based nematode authentication system comprises: The image acquisition module is used to acquire images of individual nematodes in aerospace biological experiments using a high-resolution microscope and generate nematode image data. The data preprocessing module is used to preprocess the nematode image data to generate preprocessed image data. A physiological feature recognition module is used to identify nematode physiological features in the preprocessed image data through a feature extraction model, and generate nematode physiological features. The feature conversion module is used to convert the physiological features into digital codes and output mapping labels that identify the nematode species name and strain information, which are then stored in the feature database. An identity recognition module is used to capture images of the first target nematode that needs to be identified using the high-resolution microscope, and to extract physiological features using the feature extraction model to generate target physiological features. The feature matching module is used to call the feature database, perform feature matching on the target physiological features, output the target mapping label with the highest feature similarity, perform label parsing, and complete the identity authentication of the first target nematode.

Images