Microplastic type identification method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of image processing of artificial intelligence, and relates to a micro-plastic type identification method and device, computer equipment and a storage medium, and the method comprises the steps: receiving a to-be-classified fluorescence spectrum image sent by a user terminal; performing preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; the trained spectrum classification model is called to carry out category identification operation, a category identification result is obtained, and the spectrum classification model adopts a random forest and a support vector machine method to carry out classification; and outputting the type identification result to the user terminal. According to the method, rapid identification and classification of the micro-plastics can be realized, the input image is the spectral image acquired by using the microspectrometer, the visual prediction result is output by the machine learning model after spectrum extraction, and the identification accuracy of the micro-plastic spectrum is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence image processing technology, and in particular to a method, device, computer equipment and storage medium for identifying microplastic types. Background Art

[0002] Plastics play an indispensable role in industry and daily life, but environmental pollution has become a serious global problem. Microplastics (MP, <5 mm) and nanoplastics (NP, <1 μm) have been widely found in seawater, rainwater, drinking water, snow and soil, posing a significant risk to ecosystems and human health. In order to accurately characterize the size, shape and number of micro / nanoplastic particles, a variety of quantitative analysis tools have been used, including optical microscopy, electron microscopy, dynamic light scattering and nanoparticle tracking analysis. However, the limitations of existing technologies are that they require high-end instruments, time-consuming acquisition, intensive labor and complex data analysis. Especially in the case of size reduction, the weak signals of infrared and Raman spectra are easily interfered by background signals, which reduces the effectiveness and accuracy of their identification.

[0003] Fluorescence staining techniques have attracted much attention as a simple, economical and convenient method for detecting micro / nanoplastics. Nile red (NR) dye is widely used to identify plastic polymers in water, sediments and other products, helping to quantify their abundance, concentration and quantity. Compared with traditional infrared and Raman spectroscopy, fluorescence-based detection has higher sensitivity, making it a promising candidate for preliminary screening analysis of micro / nanoplastics.

[0004] However, the applicant found that the current research on fluorescent staining technology has not yet explored in depth its specificity for different components. It can be seen that the traditional micro / nanoplastic detection method based on fluorescent staining technology cannot effectively detect micro / nanoplastics with different components. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for identifying microplastic types, so as to solve the problem that the traditional micro / nanoplastic detection method based on fluorescent staining technology cannot effectively detect micro / nanoplastics with different components.

[0006] In order to solve the above technical problems, the present application embodiment provides a method for identifying microplastic types, which adopts the following technical solution:

[0007] Receiving a fluorescence spectrum image to be classified sent by a user terminal;

[0008] Performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image;

[0009] Calling a trained spectral classification model to perform a category recognition operation to obtain a category recognition result, wherein the spectral classification model uses a random forest and support vector machine method for classification;

[0010] The category identification result is output to the user terminal.

[0011] Furthermore, the step of performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image specifically includes the following steps:

[0012] Superimposing the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information;

[0013] Performing a conversion operation on the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image;

[0014] Performing a connected domain segmentation operation on the spectral binary image to obtain segmentation information, wherein the segmentation information at least includes location information of microplastics;

[0015] A spectrum corresponding to the position information is extracted from the fluorescence spectrum image to obtain the preprocessed spectrum image.

[0016] Furthermore, before the step of calling the trained spectral classification model to perform a category recognition operation to obtain a category recognition result, the following steps are also included:

[0017] Acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image;

[0018] Performing a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image;

[0019] calling an initial spectral classification model, and inputting the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model to perform a model training operation;

[0020] After the model training operation is completed, the trained spectral classification model is obtained.

[0021] Furthermore, after the step of calling the trained spectral classification model to perform a category recognition operation and obtaining a category recognition result, the following steps are also included:

[0022] Performing a visualization operation on the category recognition result to obtain a visualized category result;

[0023] The step of outputting the type identification result to the user terminal specifically includes the following steps:

[0024] The visualization category result is output to the user terminal.

[0025] In order to solve the above technical problems, the present application also provides a device for identifying the types of microplastics, which adopts the following technical solution:

[0026] An image acquisition module, used for receiving a fluorescence spectrum image to be classified sent by a user terminal;

[0027] A first preprocessing module, used for performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image;

[0028] A category recognition module is used to call a trained spectral classification model to perform category recognition operations and obtain category recognition results, wherein the spectral classification model uses random forest and support vector machine methods for classification;

[0029] A result output module is used to output the category identification result to the user terminal.

[0030] Furthermore, the first preprocessing module includes:

[0031] A superposition submodule, used for superimposing the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information;

[0032] A conversion submodule, used for performing a conversion operation on the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image;

[0033] A connected domain division submodule, used for performing a connected domain division operation on the spectral binary image to obtain division information, wherein the division information at least includes location information of microplastics;

[0034] The spectrum extraction submodule is used to extract the spectrum corresponding to the position information from the fluorescence spectrum image to obtain the preprocessed spectrum image.

[0035] Furthermore, the device also includes:

[0036] A training image acquisition module, used to acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image;

[0037] A second preprocessing module is used to perform a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image;

[0038] A model training module, used for calling an initial spectral classification model, and inputting the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model for model training operation;

[0039] The training completion module is used to obtain the trained spectral classification model after completing the model training operation.

[0040] Furthermore, the device further comprises: a visualization module, and the result output module comprises: a result output submodule, wherein:

[0041] A visualization module, used to perform a visualization operation on the category recognition result to obtain a visualized category result;

[0042] The result output submodule is used to output the visualization type result to the user terminal.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0044] It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the microplastic type identification method as described above are implemented.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0046] The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the method for identifying microplastic types as described above.

[0047] The present application provides a method for identifying microplastic species, including: receiving a fluorescence spectrum image to be classified sent by a user terminal; performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; calling a trained spectrum classification model to perform a species identification operation to obtain a species identification result, wherein the spectrum classification model uses a random forest and support vector machine method for classification; and outputting the species identification result to the user terminal. Compared with the prior art, the present application can realize the rapid identification and classification of microplastics, the input image is a spectrum image collected by a micro-spectrometer, and after spectrum extraction, the machine learning model outputs a visual prediction result, which effectively improves the recognition accuracy of microplastic spectra. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0050] Figure 2 This is a flowchart of the implementation of the method for identifying microplastic types provided in Example 1 of the present application;

[0051] Figure 3 This is a data schematic diagram of the microplastic classification results provided in Example 1 of the present application;

[0052] Figure 4 It is a schematic diagram of comparative data with the Raman spectroscopy classification method provided in Example 1 of the present application;

[0053] Figure 5 This is a data schematic diagram of the multi-dimensional information statistics of microplastics provided in Example 1 of the present application;

[0054] Figure 6 It is a schematic diagram of the structure of a device for identifying microplastic types provided in Example 2 of the present application;

[0055] Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0057] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0058] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0059] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0060] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0061] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0062] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0063] It should be noted that the microplastic type identification method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the microplastic type identification device is generally set in the server / terminal device.

[0064] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0065] Embodiment 1

[0066] Continue to refer Figure 2, shows a flow chart of an embodiment of a method for identifying microplastic species according to the present application. The method for identifying microplastic species comprises: step S201, step S202, step S203 and step S204.

[0067] In step S201, a fluorescence spectrum image to be classified sent by a user terminal is received.

[0068] In the embodiments of the present application, the user terminal refers to a terminal device used to execute the image processing method for preventing document abuse provided by the present application. The user terminal can be a mobile terminal such as a mobile phone, a smart phone, a laptop computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, etc., as well as a fixed terminal such as a digital TV, a desktop computer, etc. It should be understood that the examples of user terminals here are only for convenience of understanding and are not used to limit the present application.

[0069] In an embodiment of the present application, the fluorescence spectrum image to be classified can be obtained through a microplastic filtering and collection operation, a fluorescent dye marking and staining operation, and a fluorescence spectrum microscopic imaging operation, specifically:

[0070] (1) The main purpose of the microplastic filtration and collection operation is to enrich microplastics from the target water source. The main process is as follows:

[0071] ① Use vacuum filtration (membrane pore size 0.1μm) to filter the target water source so that microplastics are enriched on the filter membrane;

[0072] ② Rinse the filter membrane with ethanol and collect the rinse liquid;

[0073] ③ Vacuum evaporate the flushing liquid and concentrate the flushing liquid;

[0074] (2) The operation process of fluorescent dye labeling and staining is as follows:

[0075] ① Add 0.4 mg / L Nile Red (solvent acetone) solution in a volume ratio of 1:3 to the original flushing solution, and dye at 50°C for 30 minutes.

[0076] ② Drop the stained solution onto a glass slide and seal the slide after drying;

[0077] (3) Fluorescence spectral microscopy imaging is performed using a microscope with a spectral imager. The sample is moved by a translation stage to complete the acquisition of spectral images. The excitation light wavelength is 488nm.

[0078] In step S202, a preprocessing operation is performed on the fluorescence spectrum image to obtain a preprocessed spectrum image.

[0079] In an embodiment of the present application, the preprocessing operation may be to superimpose the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information; to convert the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image; to perform a connected domain division operation on the spectral binary image to obtain division information; and to extract the spectrum corresponding to the position information from the fluorescence spectrum image to obtain a preprocessed spectral image.

[0080] In step S203, the trained spectral classification model is called to perform a category recognition operation to obtain a category recognition result, wherein the spectral classification model uses a random forest and support vector machine method for classification.

[0081] In the embodiment of the present application, the spectral classification model is a classification model based on machine learning, and the spectral classification model uses random forest (RF) and support vector machine (SVM) methods for classification.

[0082] In the embodiment of the present application, the steps of using random forest to classify the micro-nano plastic spectrum are as follows:

[0083] 1) Data preparation: Each sample in the spectral database is represented as a feature vector containing the values ​​of P feature channels. Each sample is also associated with a label indicating the category to which it belongs.

[0084] 2) Bootstrap sampling: For each decision tree in the random forest, the same number of samples (usually the same size as the original training set) are randomly drawn with replacement from the training dataset to create a new training subset. This process is called bootstrap sampling.

[0085] 3) Decision tree construction: Use the training subset obtained by bootstrapping to build a decision tree. During the construction process, each time a node needs to be split, a subset (for example, sqrt(P) features) is randomly selected from the P feature channels, and then the best features and split points are found in this subset to maximize information gain or minimize impurity.

[0086] 4) Repeated construction: Repeat the above 2-4 processes to build multiple decision trees (for example, hundreds or thousands of trees). Each tree is built independently and in parallel, using a different bootstrap sampling subset.

[0087] 5) Out-of-bag data evaluation: Due to the characteristics of bootstrap sampling, there will be some samples that are not selected during the training process of each decision tree. These samples are called out-of-bag data (OOB). These samples can be used to evaluate the performance of each tree without the need for an additional validation set.

[0088] 6) Ensemble voting: After training, the random forest model consists of all decision trees. When predicting, for a new spectral sample, each decision tree will independently give its own prediction results, and then determine the final prediction results by voting (classification problem) or averaging (regression problem).

[0089] In practical applications, the spectral data to be tested is adjusted to the same format as that in the database and put into the trained random forest model to obtain the classification results.

[0090] In step S204, the category identification result is output to the user terminal.

[0091] In an embodiment of the present application, a method for identifying microplastic species is provided, including: receiving a fluorescence spectrum image to be classified sent by a user terminal; performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; calling a trained spectrum classification model to perform a species identification operation to obtain a species identification result, wherein the spectrum classification model uses a random forest and support vector machine method for classification; and outputting the species identification result to the user terminal. Compared with the prior art, the present application can realize the rapid identification and classification of microplastics, the input image is a spectrum image collected using a micro-spectrometer, and after spectrum extraction, the machine learning model outputs a visual prediction result, which effectively improves the recognition accuracy of the microplastic spectrum.

[0092] In some optional implementations of this embodiment, step S202 specifically includes the following steps:

[0093] The fluorescence spectrum image is superimposed along the spectral dimension to obtain an intensity image without spectral information;

[0094] The intensity image without spectral information is converted according to the regional adaptive threshold algorithm to obtain a spectral binary image;

[0095] Performing a connected domain partitioning operation on the spectral binary image to obtain partitioning information, wherein the partitioning information at least includes location information of microplastics;

[0096] The spectrum corresponding to the position information is extracted from the fluorescence spectrum image to obtain a preprocessed spectrum image.

[0097] In the implementation of this embodiment, the spectral image preprocessing confirms the location and shape of microplastics by performing feature extraction and analysis on the collected original spectral image, and finally extracts the fluorescence spectrum of microplastics by numbering. Specifically:

[0098] ① The spectral image I raw The intensity image I without spectral information is generated by superposition along the spectral dimension. o ;

[0099] ② For intensity image Io Apply the region adaptive threshold algorithm to transform the image into a binary image;

[0100] ③ Perform connected domain analysis and division on the binary image to obtain the quantity, location, shape, size and edge information of microplastics;

[0101] ④ For each microplastic location, raw Extract the spectrum to obtain the fluorescence spectra of all microplastic particles;

[0102] ⑤ Output the spectral and morphological information of all identified microplastic particles.

[0103] In some optional implementations of this embodiment, before the above step S203, the following step of obtaining a trained spectral classification model is also included:

[0104] Acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image;

[0105] Performing a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image;

[0106] Calling the initial spectral classification model, and inputting the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model to perform a model training operation;

[0107] After the model training operation is completed, a trained spectral classification model is obtained.

[0108] In the implementation of this embodiment, in order to obtain a trained spectral classification model, it is first necessary to establish a single microplastic spectral library. Specifically, different single microplastics of known types are subjected to the above-mentioned microplastic staining operation, fluorescence spectral image collection operation and spectral image preprocessing operation, and then a fluorescence spectral database of different types of microplastics can be obtained. Secondly, in order to achieve rapid fluorescence spectral classification of microplastics, it is necessary to establish a spectral classification model based on machine learning, and then input the spectra and microplastic types in the microplastic spectral library into the machine learning model for training, and obtain a trained microplastic fluorescence spectral classification machine learning model.

[0109] In some optional implementations of this embodiment, after the step of calling the trained spectral classification model to perform a category recognition operation and obtaining a category recognition result, the following steps are also included:

[0110] Performing visualization operation on the category recognition results to obtain visualized category results;

[0111] The above step of outputting the type identification result to the user terminal specifically includes the following steps:

[0112] Output the visualization category results to the user terminal.

[0113] In the embodiment of the present application, after obtaining the type identification result, in order to more intuitively display the type identification result, the classification results can be statistically analyzed to obtain the quantity, morphology and size distribution information of each microplastic. The microplastic type is given a pseudo color, fused with the binary image and displayed side by side with the original spectral image.

[0114] In practical applications, such as Figure 3 As shown, the present application can realize the rapid identification and classification of microplastics. The input image is a spectral image collected by a micro-spectrometer, and after spectral extraction, the machine learning model outputs a visual prediction result. It can be seen that the spectra of different types of microplastics are clearly identified. The present application can achieve a classification accuracy of 99.84%.

[0115] In practical applications, the current mainstream optical microplastic classification method is based on Raman spectroscopy. However, compared with fluorescence, the signal intensity of Raman light is weak and the required excitation light energy is strong, which limits its application when dealing with large quantities of small-sized samples. Figure 4 As shown, by comparing with the Raman spectroscopy classification method, it is found that when collecting spectra of microplastics in the micron range, the average Raman spectrum collection time of a single microplastic is about 200s, while the fluorescence spectrum only requires 0.08s. The acquisition speed of about 2500 times makes the microplastic image acquisition based on fluorescence spectroscopy simple. Similarly, the weak Raman light signal also leads to its detection limit of microplastic size being inferior to the fluorescence method. At present, the classification method based on Raman spectroscopy is approximately limited to a size range greater than 500nm, while the fluorescence spectrum used in this application can image and classify microplastics with a size of about 100nm.

[0116] In practical applications, such as Figure 5 As shown, the present application can conduct large-scale statistics on the size, morphology and type distribution of microplastics. The figure shows the statistical results of multi-dimensional information after staining and imaging of microplastics in a certain mineral water. It can be seen that in mineral water, elliptical and circular microplastics account for the vast majority (51.2% and 38.6), accompanied by a small amount of rod-shaped microplastics (9.2%). At the same time, about half of the microplastics are concentrated in the range of 3-10μm (52.3%), and some microplastics are distributed in the range of 1-3μm and <1μm. There are fewer microplastics with a size of >10μm (7.7%). In terms of microplastic types, PVC, PS and PET occupy the main part of microplastics (46.8%, 35.9% and 17.2%).

[0117] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0118] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0120] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0121] Embodiment 2

[0122] Further references Figure 6 , as a response to the above Figure 2 The present application provides an embodiment of a device for identifying microplastic types. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0123] like Figure 6 As shown, the microplastic type identification device 200 of this embodiment includes:

[0124] The image acquisition module 210 is used to receive the fluorescence spectrum image to be classified sent by the user terminal;

[0125] A first preprocessing module 220 is used to perform a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image;

[0126] The category recognition module 230 is used to call the trained spectral classification model to perform category recognition operation and obtain category recognition results, wherein the spectral classification model uses random forest and support vector machine methods for classification;

[0127] The result output module 240 is used to output the category identification result to the user terminal.

[0128] In this embodiment, a device 200 for identifying microplastic species is provided, including: an image acquisition module 210 for receiving a fluorescence spectrum image to be classified sent by a user terminal; a first preprocessing module 220 for performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; a species identification module 230 for calling a trained spectrum classification model to perform a species identification operation to obtain a species identification result, wherein the spectrum classification model uses a random forest and support vector machine method for classification; a result output module 240 for outputting the species identification result to the user terminal. Compared with the prior art, the present application can realize the rapid identification and classification of microplastics, the input image is a spectrum image collected by a micro-spectrometer, and after spectrum extraction, the machine learning model outputs a visual prediction result, which effectively improves the recognition accuracy of the microplastic spectrum.

[0129] In some optional implementations of this embodiment, the first preprocessing module 220 includes:

[0130] The superposition submodule is used to perform superposition operations on the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information;

[0131] A conversion submodule is used to convert the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image;

[0132] A connected domain division submodule is used to perform a connected domain division operation on the spectral binary image to obtain division information, wherein the division information at least includes the location information of microplastics;

[0133] The spectrum extraction submodule is used to extract the spectrum corresponding to the position information in the fluorescence spectrum image to obtain a preprocessed spectrum image.

[0134] In some optional implementations of this embodiment, the microplastic type identification device 200 further includes:

[0135] A training image acquisition module, used to acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image;

[0136] A second preprocessing module is used to perform a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image;

[0137] A model training module is used to call the initial spectral classification model, and input the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model to perform a model training operation;

[0138] The training completion module is used to obtain a trained spectral classification model after completing the model training operation.

[0139] In some optional implementations of this embodiment, the microplastic type identification device 200 further includes: a visualization module, and the result output module 240 includes: a result output submodule, wherein:

[0140] A visualization module is used to perform visualization operations on the category recognition results to obtain visualization category results;

[0141] The result output submodule is used to output the visualization category results to the user terminal.

[0142] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0143] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0144] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0145] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In this embodiment, the memory 310 is generally used to store an operating system and various application software installed on the computer device 300, such as computer-readable instructions for a method for identifying microplastic types. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0146] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In this embodiment, the processor 320 is used to run computer-readable instructions or process data stored in the memory 310, such as computer-readable instructions for running the microplastic species identification method.

[0147] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0148] The computer device provided in this application can realize the rapid identification and classification of microplastics. The input image is a spectral image collected using a micro-spectrometer. After spectral extraction, the machine learning model outputs a visual prediction result, which effectively improves the recognition accuracy of the microplastic spectrum.

[0149] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the microplastic type identification method as described above.

[0150] The computer-readable storage medium provided in this application can realize the rapid identification and classification of microplastics. The input image is a spectral image collected using a micro-spectrometer. After spectral extraction, the machine learning model outputs a visual prediction result, which effectively improves the recognition accuracy of the microplastic spectrum.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0152] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for identifying microplastic types, characterized in that: The steps include: Receiving a fluorescence spectrum image to be classified sent by a user terminal; Performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; Calling a trained spectral classification model to perform a category recognition operation to obtain a category recognition result, wherein the spectral classification model uses a random forest and support vector machine method for classification; The category identification result is output to the user terminal.

2. The method for identifying microplastic species according to claim 1, characterized in that: The step of performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image specifically comprises the following steps: Superimposing the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information; Performing a conversion operation on the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image; Performing a connected domain segmentation operation on the spectral binary image to obtain segmentation information, wherein the segmentation information at least includes location information of microplastics; A spectrum corresponding to the position information is extracted from the fluorescence spectrum image to obtain the preprocessed spectrum image.

3. The method for identifying microplastic species according to claim 1, characterized in that: Before the step of calling the trained spectral classification model to perform a category recognition operation to obtain a category recognition result, the following steps are also included: Acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image; Performing a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image; calling an initial spectral classification model, and inputting the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model to perform a model training operation; After the model training operation is completed, the trained spectral classification model is obtained.

4. The method for identifying microplastic species according to claim 3, characterized in that: After the step of calling the trained spectral classification model to perform a category recognition operation and obtaining a category recognition result, the following steps are also included: Performing a visualization operation on the category recognition result to obtain a visualized category result; The step of outputting the type identification result to the user terminal specifically includes the following steps: The visualization category result is output to the user terminal.

5. A device for identifying microplastic types, characterized in that: include: An image acquisition module, used for receiving a fluorescence spectrum image to be classified sent by a user terminal; A first preprocessing module, used for performing a preprocessing operation on the fluorescence spectrum image to obtain a preprocessed spectrum image; A category recognition module is used to call a trained spectral classification model to perform category recognition operations and obtain category recognition results, wherein the spectral classification model uses random forest and support vector machine methods for classification; A result output module is used to output the category identification result to the user terminal.

6. The microplastic type identification device according to claim 5, characterized in that: The first preprocessing module comprises: A superposition submodule, used for superimposing the fluorescence spectrum image along the spectral dimension to obtain an intensity image without spectral information; A conversion submodule, used for performing a conversion operation on the intensity image without spectral information according to a regional adaptive threshold algorithm to obtain a spectral binary image; A connected domain division submodule, used for performing a connected domain division operation on the spectral binary image to obtain division information, wherein the division information at least includes location information of microplastics; The spectrum extraction submodule is used to extract the spectrum corresponding to the position information from the fluorescence spectrum image to obtain the preprocessed spectrum image.

7. The microplastic type identification device according to claim 5, characterized in that: The device also includes: A training image acquisition module, used to acquire a model training image set, wherein the model training image set includes a fluorescence spectrum training image and category information corresponding to the fluorescence spectrum training image; A second preprocessing module is used to perform a preprocessing operation on the fluorescence spectrum training image to obtain a preprocessed spectrum training image; A model training module, used for calling an initial spectral classification model, and inputting the preprocessed spectral training image and the category information corresponding to the preprocessed spectral training image into the initial spectral classification model for model training operation; The training completion module is used to obtain the trained spectral classification model after completing the model training operation.

8. The microplastic type identification device according to claim 5, characterized in that: The device further comprises: a visualization module, and the result output module comprises: a result output submodule, wherein: The visualization module is used to perform a visualization operation on the category recognition result to obtain a visualized category result; The result output submodule is used to output the visualization type result to the user terminal.

9. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the microplastic type identification method as described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the microplastic type identification method as described in any one of claims 1 to 4.

Images