An automated identification method and system for antigen reagent kits based on machine vision
By automatically identifying antigen reagent kits using machine vision technology, the problems of low efficiency and data tampering in manual testing have been solved, enabling the generation of efficient and accurate test results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TONGJI ARTIFICIAL INTELLIGENCE RES INST SUZHOU CO LTD
- Filing Date
- 2023-03-17
- Publication Date
- 2026-06-30
AI Technical Summary
Existing antigen test kits rely on manual judgment, resulting in low testing efficiency and the existence of underreporting, false reporting, and human data tampering.
An automatic recognition method based on machine vision is adopted. By collecting image data of antigen reagent kits, and using QR code recognition and text recognition combined with image enhancement technology, a recognition report is generated, including steps such as dataset construction, image processing and perspective transformation.
It has improved testing efficiency, eliminated underreporting and false reporting, ensured data accuracy, and reduced human intervention.
Smart Images
Figure CN116503864B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of antigen reagent kit detection technology, and in particular to an automatic identification method and system for antigen reagent kits based on machine vision. Background Technology
[0002] Current antigen test kits rely on manual judgment for results, which not only results in low testing efficiency but also carries the risk of underreporting, false reporting, and human intervention in correct data. Summary of the Invention
[0003] In view of this, the purpose of this application is to propose an automatic identification method and system for antigen reagent kits based on machine vision, which can specifically solve the existing problems.
[0004] To achieve the above objectives, this application proposes a machine vision-based automatic identification method for antigen reagent kits, comprising:
[0005] 1) Collect past antigen kit image data to form a known dataset Z;
[0006] 2) For each image in Z, the antigen reagent kit number is obtained through QR code recognition and text recognition, and image enhancement technology is used in the process of obtaining the number;
[0007] 3) Write all the antigen reagent kit numbers obtained in the previous step into the database to form a known number set I;
[0008] 4) Obtain the image data of the antigen reagent kit that needs to be identified, and construct the input dataset X;
[0009] 5) For each image in X, obtain the antigen reagent kit number through QR code recognition and text recognition, and use image enhancement technology during the number acquisition process to obtain the current number set K;
[0010] 6) Query whether there is an intersection between the current number set K and the known number set I. If there is, mark the corresponding image pairs in the intersection and denote them as the overlapping dataset R.
[0011] 7) For each image in X, perform perspective transformation and image enhancement, locate the result area and generate a region mask, distinguish between positive and negative results, and denote it as O;
[0012] 8) Combine the overlapping dataset R with the positive and negative results O to generate a recognition report.
[0013] Furthermore, in the antigen reagent kit image data collected in steps 1) and 4), each image contains several reagent kits.
[0014] Furthermore, steps 2) and 5) specifically include the following steps:
[0015] 11) Apply histogram equalization to the image data. Create a grayscale histogram for the image and count the frequency of grayscale values appearing in the histogram. Then, perform equalization on the histogram to achieve a uniform grayscale distribution. The formula for grayscale value conversion is:
[0016] f(g) = 255∑ 0≤x≤g h(x)
[0017] Where g is the grayscale pixel value (range [0, 255]), and h(x) is the frequency of grayscale value x;
[0018] 12) Image sharpening is performed using the Unsharp Mask (USM) optimization algorithm. For image S, a Gaussian blur map G is calculated. For pixel position (i, j), the sharpened result map U is calculated using the following formula:
[0019] K=S(i,j)+Amount*(S(i,j)-G(i,j))
[0020]
[0021] Alpha is obtained by Gaussian filtering after obtaining the mask from the Gaussian blur map;
[0022] 13) During the QR code recognition stage, use an API interface that supports recognizing multiple QR codes simultaneously to identify the QR code and obtain the antigen reagent kit number.
[0023] Furthermore, in step 3), SQL statements are used to write all the antigen reagent kit numbers obtained in the previous step into the database.
[0024] Furthermore, in step 6), the obtained antigen reagent kit number is queried using an SQL statement to see if it already exists in the database. If it does, the corresponding image path is exported.
[0025] Furthermore, in step 7), the perspective transformation formula is:
[0026]
[0027] Where ( represents the original image coordinates, and (u, v, w) is the homogeneous coordinate form, The perspective transformation coefficient matrix, corresponding to the coordinates (x, y) in the transformed image, is calculated as follows:
[0028]
[0029] The pixel correspondence between the original image and the transformed image is as follows:
[0030] x=(a 11 ·u+a 12 ·v+a13 ) / (a 31 ·u+a 32 ·v+a 33 )
[0031] y = (a 21 ·u+a 22 ·v+a 23 ) / (a 31 ·u+a 32 ·v+a 33 )
[0032] Furthermore, in step 8), the Python docx library is used to generate the recognition report.
[0033] To achieve the above objectives, this application also proposes an automated antigen reagent kit identification system based on machine vision, comprising:
[0034] The data collection module is used to collect past antigen kit image data to form a known dataset Z;
[0035] Previously, the numbering module was used to obtain the antigen kit number for each image in Z through QR code recognition and text recognition, and image enhancement technology was used to assist in the numbering process.
[0036] The number writing module is used to write all the antigen reagent kit numbers obtained in the previous step into the database, forming a known number set I;
[0037] The current image acquisition module is used to acquire the image data of the antigen reagent kit that needs to be identified, forming the input dataset X;
[0038] The current numbering module is used to obtain the antigen reagent kit number for each image in X through QR code recognition and text recognition, and to obtain the current number set K by using image enhancement technology during the numbering process.
[0039] The query module is used to query whether there is an intersection between the current number set K and the known number set I. If there is, the corresponding image pairs in the intersection are marked and denoted as the overlapping dataset R.
[0040] The result discrimination module is used to perform perspective transformation and image enhancement on each image in X, locate the result area and generate a region mask, and distinguish the yin and yang results, denoted as O;
[0041] The identification report module is used to combine the overlapping dataset R and the positive / negative results O to generate an identification report.
[0042] In summary, the advantages of this application and the user experience it brings are as follows:
[0043] First, by combining advanced computer vision technologies, including text recognition, image enhancement, and image classification, the efficiency is greatly improved compared to manual deduplication.
[0044] Second, this application can quickly screen antigen results, which largely eliminates the phenomena of concealment, misreporting, and data tampering of antigen test results. Attached Figure Description
[0045] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.
[0046] Figure 1 A flowchart illustrating an automatic identification method for antigen kits based on machine vision according to an embodiment of this application is shown.
[0047] Figure 2 This diagram illustrates a first example of an antigen kit identification (single-image single-kit) report.
[0048] Figure 3 This diagram illustrates a second example of an antigen kit identification (single-image single-kit) report.
[0049] Figure 4 This diagram illustrates a first example of an antigen kit identification (single-image multi-kit) report.
[0050] Figure 5 This diagram illustrates a second example of an antigen kit identification (single-image, multiple kit) report.
[0051] Figure 6 A schematic diagram of a machine vision-based automatic identification system for antigen reagent kits according to an embodiment of this application is shown.
[0052] Figure 7 A schematic diagram of the structure of an electronic device provided in one embodiment of this application is shown.
[0053] Figure 8 A schematic diagram of a storage medium provided in one embodiment of this application is shown. Detailed Implementation
[0054] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.
[0055] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0056] Figure 1 This is a flowchart illustrating the implementation of the method in this application. The specific implementation method is as follows:
[0057] 1. Collect past antigen reagent kit image data to form a known dataset;
[0058] 2. After applying image enhancement technology to each image in the known antigen reagent kit image dataset, the antigen reagent kit number is obtained through QR code recognition and text recognition;
[0059] 3. Enter the known antigen reagent kit numbers into the database;
[0060] 4. Obtain the image data of the antigen reagent kit that needs to be identified, and construct the input dataset;
[0061] 5. For each input image, the antigen reagent kit number is obtained through QR code recognition and text recognition, and image enhancement technology is used in the process to obtain the current set of numbers;
[0062] 6. Query whether the current set of numbers already exists in the database. If it does, mark the corresponding image pair and denote it as the overlapping dataset R.
[0063] 7. For each input image, perform perspective transformation and image enhancement, locate the result area and generate a region mask, distinguish between positive and negative results, and record it as O;
[0064] 8. Combine the overlapping dataset R with the positive and negative results O to generate a recognition report.
[0065] Specifically, the implementation process for each step is as follows:
[0066] Step 1: Collect past antigen reagent kit image data to form a known dataset Z. The collected antigen reagent kit image data can contain several kits in a single image.
[0067] Step 2: Apply histogram equalization, an image enhancement technique, to the collected known dataset Z. This creates a grayscale histogram and counts the frequency of grayscale values appearing in the histogram. Then, perform equalization on the histogram to achieve a uniform grayscale distribution. The formula for grayscale value conversion is:
[0068] f(g) = 255∑ 0≤≤≤g h(x)
[0069] Where g is the grayscale pixel value (range [0, 255]), and h(x) is the frequency of grayscale value x. Further image sharpening, a technique used in image enhancement, is applied using the USM optimization algorithm. For image S, a Gaussian blur map G is calculated. For pixel position (i, j), the sharpened result image U is calculated as follows:
[0070] K=S(i,j)+Amount*(S(i,j)-G(i,j))
[0071]
[0072] Here, Alpha is obtained by Gaussian filtering after obtaining the mask from the Gaussian blur image. After image enhancement, an API interface that supports simultaneous recognition of multiple QR codes is called to perform QR code recognition and obtain the antigen reagent kit number.
[0073] Step 3: Write the obtained antigen reagent kit numbers into the database using SQL statements to form a known number set I.
[0074] In step 3), the database statements used are as follows:
[0075] CREATE DATABASE ANTIGEN_KIT;
[0076] USE ANTIGEN_KIT;
[0077] CREATE TABLE existing_antigen_kit(antigen_kit_id VARCHAR(32),img_pathVARCHAR(64));
[0078] INSERT INTO existing_antigen_kit VALUES("***","***")
[0079] Step 4: Collect the image data of the antigen reagent kits that need to be identified to form the input dataset X. The collected antigen reagent kit image data can contain several reagent kits in a single image.
[0080] Step 5: After applying histogram equalization and image sharpening to the collected input dataset X, call the API interface that supports simultaneous recognition of multiple QR codes to perform QR code recognition. At the same time, use the ASTER network and ACE Loss to perform text recognition and obtain the antigen kit number.
[0081] Step 6: Use an SQL statement to query whether the obtained antigen reagent kit number already exists in the database. If it exists, export the corresponding image path.
[0082] The database statements used are as follows:
[0083] SELECT*FROM existing_antigen_kit WHERE antigen_kit_id="***".
[0084] Step 7: Perform perspective transformation and image enhancement on the collected input dataset X, locate the result region and generate a region mask, distinguish between light and dark results, and denote it as O. The perspective transformation formula is:
[0085]
[0086] Where ( represents the original image coordinates, and (u, v, w) is the homogeneous coordinate form, The perspective transformation coefficient matrix, corresponding to the coordinates (x, y) in the transformed image, is calculated as follows:
[0087]
[0088] The pixel correspondence between the original image and the transformed image is as follows:
[0089] x=(a 11 ·u+a 12 ·v+a 13 ) / (a 31 ·u+a 32 ·v+a 33 )
[0090] y = (a 21 ·u+a 22 ·v+a 23 ) / (a 31 ·u+a 32 ·v+a 33 )
[0091] Step 8: Combine the overlapping dataset R and the yin-yang results O, and use Python's docx library to generate a recognition report.
[0092] Figure 2 This diagram illustrates a first example of an antigen kit identification (single-image single-kit) report. As shown, it identifies a problem with the antigen test result for one person.
[0093] Figure 3 This diagram illustrates a second example of an antigen kit identification (single-image single-kit) report. As shown, it identifies two individuals with problematic antigen test results.
[0094] Figure 4 This diagram illustrates a first example of an antigen kit identification (single-image, multi-kit) report. As shown, two households' antigen test results were identified as problematic.
[0095] Figure 5 This diagram illustrates a second example of an antigen kit identification (single-image, multiple kit) report. As shown, it identifies a problem with the antigen test result for one household.
[0096] The application provides a machine vision-based automatic antigen reagent kit identification system, which is used to execute the machine vision-based automatic antigen reagent kit identification method described in the above embodiments, such as... Figure 6 As shown, the system includes:
[0097] Data collection module 601 is used to collect past antigen kit image data to form a known dataset Z;
[0098] Previously, the numbering module 602 was used to obtain the antigen reagent kit number for each image in Z through QR code recognition and text recognition, and image enhancement technology was used to assist in the numbering process;
[0099] The number writing module 603 is used to write all the antigen reagent kit numbers obtained in the previous step into the database to form a known number set I;
[0100] The current image acquisition module 604 is used to acquire the image data of the antigen reagent kit that needs to be identified, forming the input dataset X;
[0101] The current numbering module 605 is used to obtain the antigen reagent kit number for each image in X through QR code recognition and text recognition, and to obtain the current number set K by using image enhancement technology during the numbering process.
[0102] The query module 606 is used to query whether there is an intersection between the current number set K and the known number set I. If there is, the corresponding image pair in the intersection is marked and denoted as the overlapping dataset R.
[0103] The result discrimination module 607 is used to perform perspective transformation and image enhancement on each image in X, locate the result area and generate a region mask, and distinguish the yin and yang results, which is denoted as O;
[0104] The identification report module 608 is used to integrate the overlapping dataset R and the positive / negative results O to generate an identification report.
[0105] The machine vision-based automatic identification system for antigen reagent kits provided in the above embodiments of this application and the machine vision-based automatic identification method for antigen reagent kits provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.
[0106] This application also provides an electronic device corresponding to the machine vision-based automatic antigen reagent kit identification method provided in the foregoing embodiments, to execute the machine vision-based automatic antigen reagent kit identification method. This application does not limit the scope of the embodiments.
[0107] Please refer to Figure 7 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 7 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202, and a communication interface 203. The processor 200, the communication interface 203, and the memory 201 are connected via the bus 202. The memory 201 stores a computer program that can run on the processor 200. When the processor 200 runs the computer program, it executes the automatic identification method for antigen reagent kits based on machine vision provided in any of the foregoing embodiments of this application.
[0108] The memory 201 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 203 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.
[0109] Bus 202 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. Memory 201 is used to store programs. After receiving an execution instruction, processor 200 executes the program. The automatic identification method for antigen reagent kits based on machine vision disclosed in any of the foregoing embodiments of this application can be applied to processor 200, or implemented by processor 200.
[0110] The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 200 or by instructions in software form. The processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 201. The processor 200 reads the information in memory 201 and, in conjunction with its hardware, completes the steps of the above method.
[0111] The electronic device provided in this application embodiment and the automatic identification method for antigen reagent kits based on machine vision provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.
[0112] This application also provides a computer-readable storage medium corresponding to the machine vision-based automatic antigen reagent kit identification method provided in the foregoing embodiments. Please refer to [link / reference]. Figure 8 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the automatic identification method for antigen reagent kits based on machine vision provided in any of the foregoing embodiments.
[0113] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.
[0114] The computer-readable storage medium provided in the above embodiments of this application and the automatic identification method for antigen reagent kits based on machine vision provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.
[0115] It should be noted that:
[0116] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages is for the purpose of disclosing the best mode of implementation of this application.
[0117] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0118] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.
[0119] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.
[0120] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
[0121] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation system according to the embodiments of this application. This application can also be implemented as a device or system program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
[0122] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several systems, several of these systems may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.
[0123] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A machine vision-based automatic identification method for an antigen kit, characterized by, include: 1) Collect past antigen kit image data to form known dataset ; 2) For each image in , the antigen kit number is obtained through QR code recognition and text recognition, and image enhancement technology is supplemented during the process of obtaining the number; 3) Write all the antigen reagent kit numbers obtained in the previous step into the database to form a known number set I; 4) Obtain the image data of the antigen reagent kit that needs to be identified, and form the input dataset X; 5) For each image in X, obtain the antigen reagent kit number through QR code recognition and text recognition, and use image enhancement technology during the number acquisition process to obtain the current number set K; 6) Query whether there is an intersection between the current number set K and the known number set I. If there is, mark the corresponding image pair in the intersection and denote it as the overlapping dataset R; 7) For each image in X, perform perspective transformation and image enhancement, locate the result region and generate a region mask, distinguish between positive and negative results, and denote it as O; in step 7), the perspective transformation formula is: in, The original image coordinates, In homogeneous coordinate form, This is the perspective transformation coefficient matrix, and its corresponding coordinates in the transformed image. The calculation formula is: The pixel correspondence between the original image and the transformed image is as follows: 8) Combine the overlapping dataset R with the yin-yang results O to generate a recognition report.
2. The automatic identification method for antigen reagent kits based on machine vision according to claim 1, characterized in that, In the antigen kit image data collected in steps 1) and 4), each image contains several kits.
3. The automatic identification method for antigen reagent kits based on machine vision according to claim 1, characterized in that, Steps 2) and 5) specifically include the following steps: 11) Apply histogram equalization to the image data. Create a grayscale histogram for the image and count the frequency of grayscale values appearing in the histogram. Then, perform equalization on the histogram to achieve a uniform grayscale value distribution. The formula for grayscale value conversion is: in, These are the pixel values of the grayscale image. The grayscale value is The frequency; 12) Use image sharpening, employing the Unsharp Mask (USM) optimization algorithm, for the image Calculate Gaussian blur map For pixel position Sharpening result image The calculation formula is: in, This is the result of Gaussian filtering after obtaining the mask from the Gaussian blur image; 13) During the QR code recognition stage, use an API interface that supports recognizing multiple QR codes simultaneously to identify the QR code and obtain the antigen reagent kit number.
4. The automatic identification method for antigen reagent kits based on machine vision according to claim 1, characterized in that, In step 3), SQL statements are used to write all the antigen reagent kit numbers obtained in the previous step into the database.
5. The automatic identification method for antigen reagent kits based on machine vision according to claim 1, characterized in that, In step 6), the obtained antigen reagent kit number is queried using an SQL statement to see if it already exists in the database. If it does, the corresponding image path is exported.
6. The automatic identification method for antigen reagent kits based on machine vision according to claim 1, characterized in that, In step 8), the Python docx library is used to generate the recognition report.
7. An automated antigen reagent kit identification system based on machine vision, using the method described in any one of claims 1-6, characterized in that, include: The data collection module is used to collect past antigen kit image data to form a known dataset. ; Previously, the numbering module was used for... Each image in the process obtains the antigen kit number through QR code recognition and text recognition, and image enhancement technology is used in the process of obtaining the number. The number writing module is used to write all the antigen reagent kit numbers obtained in the previous step into the database, forming a known number set I; The current image acquisition module is used to acquire the image data of the antigen reagent kit that needs to be identified, forming the input dataset X; The current numbering module is used to obtain the antigen reagent kit number for each image in X through QR code recognition and text recognition, and to obtain the current number set K by using image enhancement technology during the numbering process. The query module is used to query whether there is an intersection between the current number set K and the known number set I. If there is, the corresponding image pairs in the intersection are marked and denoted as the overlapping dataset R. The result discrimination module is used to perform perspective transformation and image enhancement on each image in X, locate the result area and generate a region mask, and distinguish the yin and yang results, denoted as O; The identification report module is used to combine the overlapping dataset R and the positive / negative results O to generate an identification report.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the method as described in any one of claims 1-6.