A portable fluorescence immunochromatographic test strip imaging system

Abstract

This invention relates to the field of chromatography detection technology, specifically a portable fluorescence immunochromatographic test strip imaging testing system. The system includes an edge detection module, a region segmentation module, a decoding and verification module, a timeliness determination module, a standard request module, a concentration analysis module, and an encrypted upload module. The system segments the test strip image into regions, obtaining a QR code sub-image and a detection line image; decodes the QR code image to obtain card-specific information; determines the status of the target chromatography test strip to obtain a timeliness identifier; makes an encrypted remote standard request to the cloud for the target chromatography test strip to obtain a dedicated detection standard; quantitatively analyzes the fluorescence intensity of the detection line image to obtain the detection result; and encrypts and encapsulates the card-specific information, the analyte concentration, and the detection result, then uploads the encrypted data to the cloud. This invention improves the efficiency of reference information generation in a portable fluorescence immunochromatographic test strip imaging testing system.

Description

Technical Field

[0001] This invention relates to the field of chromatography detection technology, and in particular to a portable fluorescence immunochromatographic test strip imaging system. Background Technology

[0002] In existing technologies related to imaging testing of portable fluorescence immunochromatographic test strips, there is a lack of adaptive edge detection methods for processing the original fluorescence image of the test strip, which cannot effectively compensate for the problem of uneven illumination. The extraction accuracy of the test strip area is insufficient. At the same time, in the image segmentation stage of the test strip area, there is a lack of accurate identification methods based on gray-scale distribution and fluorescence signal characteristics. The separation effect between the QR code and the detection line area is poor, resulting in poor quality of the basic image data for subsequent data interpretation and fluorescence intensity analysis, which directly reduces the efficiency of the pre-processing of imaging testing.

[0003] Existing technologies have numerous technical deficiencies in the detection, analysis, and data interaction stages of chromatographic test strips. The decoding of the QR code information on the test strip lacks an effective anti-tampering and legitimacy verification process, making it prone to information distortion during decoding. Furthermore, the lack of timeliness assessment based on test strip-specific information makes it susceptible to deviations in test results due to the use of expired test strips. Additionally, the quantitative analysis of fluorescence intensity does not effectively remove background grayscale interference, resulting in insufficient concentration calculation accuracy. Moreover, there is a lack of encrypted remote detection standard requests and data upload methods, leading to low adaptability of detection standards and low data transmission security. The overall technical integration of the detection process is poor, resulting in overall imaging testing efficiency and test result reliability that fail to meet practical application requirements. Therefore, improving the testing efficiency of portable fluorescence immunochromatographic test strip imaging has become an urgent problem to be solved. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a portable fluorescence immunochromatographic test strip imaging system, characterized in that the system includes an edge detection module, a region segmentation module, a decoding and verification module, a timeliness determination module, a standard request module, a concentration analysis module, and an encrypted upload module, wherein:

[0005] The edge detection module is used to perform adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image;

[0006] The region division module is used to divide the test strip region image into regions to obtain the QR code sub-image and detection line sub-image of the test strip region image;

[0007] The decoding and verification module is used to decode the data of the QR code sub-image and perform anti-tampering legality verification on the decoded QR code information to obtain the card-specific information of the QR code sub-image.

[0008] The timeliness determination module is used to determine the status of the detection date of the target chromatography test strip based on the card-specific information, and obtain the timeliness identifier of the target chromatography test strip;

[0009] The standard request module is used to make an encrypted remote standard request to the cloud of the target chromatography test strip based on the timeliness identifier, so as to obtain the dedicated detection standard of the target chromatography test strip.

[0010] The concentration analysis module is used to perform quantitative analysis of fluorescence intensity on the detection line image based on the detection standard, obtain the concentration of the analyte in the detection line image, and perform threshold comparison on the concentration of the analyte to obtain the detection result of the detection line image.

[0011] The encrypted upload module is used to encrypt and encapsulate the card-specific information, the concentration of the analyte, and the detection result, and then upload the encrypted data to the cloud.

[0012] In a preferred embodiment, when the edge detection module performs adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image, it is specifically used for:

[0013] The original fluorescence image of the target chromatography strip is compensated for by illumination non-uniformity to obtain a brightness-equalized image of the original fluorescence image;

[0014] The brightness equalization image is subjected to edge response enhancement processing to obtain the enhanced edge image of the brightness equalization image;

[0015] Closed boundary tracking is performed on the abruptly changed pixels of the enhanced edge image to obtain the test strip outline of the enhanced edge image;

[0016] Based on the test strip outline, the brightness equalization image is cropped to obtain the test strip region image of the original fluorescence image.

[0017] In a preferred embodiment, when the region segmentation module performs region segmentation on the test strip region image to obtain the QR code sub-image and detection line sub-image of the test strip region image, it is specifically used for:

[0018] Image brightness analysis is performed on the test strip area image to obtain the grayscale distribution spectrum of the test strip area image;

[0019] Based on the abrupt change locations of texture density in the grayscale distribution map, structural texture recognition is performed on the test strip region image to obtain the QR code candidate region of the test strip region image;

[0020] The fluorescence signal is geometrically located in the test strip area image to obtain the candidate region of the detection line in the test strip area image;

[0021] The boundaries of the QR code candidate region are refined to obtain the QR code sub-image of the test strip region image;

[0022] Morphological separation is performed on the candidate regions of the detection line to obtain the detection line sub-image of the test strip region image.

[0023] In a preferred embodiment, when the decoding and verification module performs data decoding on the QR code sub-image and verifies the tamper-proof legitimacy of the decoded QR code information to obtain the card-specific information of the QR code sub-image, it is specifically used for:

[0024] The code bit space is mapped to the QR code sub-image to obtain the code bit position map of the QR code sub-image;

[0025] Based on the coded bit position map, the check bit of the QR code sub-image is extracted, and the pixel response of the check bit is read to obtain the grayscale sampling sequence of the check bit.

[0026] The fluorescence background statistical value of the test strip area image is obtained by performing blank area light intensity analysis on the test strip area image;

[0027] The grayscale sampling sequence is numerically compared with the fluorescence background statistics, and the deviation of the comparison result is evaluated with a preset reference interpolation sequence to obtain the consistency score of the grayscale sampling sequence.

[0028] Based on the consistency score, the decoded data of the QR code sub-image is subjected to a credibility weighting correction to obtain the credibility decoding identifier of the QR code sub-image.

[0029] Based on the trusted decoding identifier, the decoded data is reconstructed to obtain the card-specific information of the QR code sub-image.

[0030] In a preferred embodiment, when the decoding and verification module performs a numerical comparison between the grayscale sampling sequence and the fluorescence background statistics, and evaluates the deviation between the comparison result and a preset reference interpolation sequence to obtain a consistency score for the grayscale sampling sequence, it is specifically used for:

[0031] Spatial coordinate positioning is performed on the verification bit to obtain the pixel coordinate set of the verification bit;

[0032] Based on the fluorescence background statistics, the background deviation of the grayscale sampling sequence is subtracted to obtain the correction deviation vector of the grayscale sampling sequence;

[0033] Based on the correction deviation vector and the preset reference interpolation sequence, spatial trend fitting is performed on the pixel coordinate set to obtain the spatial correction coefficients of the pixel coordinate set.

[0034] Based on the spatial correction coefficients and the reference interpolation sequence, the consistency score of the grayscale sampling sequence is calculated, wherein the formula for calculating the consistency score is:

[0035] ;

[0036] In the formula, For the consistency score, It is an exponential function. The sequence number of the verification bearer bit. The total number of the verification bits. The first of the correction deviation vectors One element, The spatial correction coefficient is... The x-coordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The x-coordinate value of each check bit. The ordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The ordinate value of each check bit. For the first reference interpolation sequence One element, This is the preset allowable deviation benchmark.

[0037] In a preferred embodiment, when the timeliness determination module performs a status determination on the detection date of the target chromatography test strip based on the card-specific information to obtain the timeliness identifier of the target chromatography test strip, it is specifically used for:

[0038] The card-specific information is analyzed for field separators to obtain the validity period code field of the card-specific information;

[0039] Perform a number system mapping on the validity period code field to obtain the validity period time value of the validity period code field;

[0040] Read the current time count of the target chromatographic test strip and reconstruct the current time count by year, month, and day to obtain the current date value of the target chromatographic test strip;

[0041] The validity period value is compared digit by digit with the current date value to obtain the determination result of the current date value;

[0042] Based on the determination result, the validity level of the card-specific information is defined to obtain the timeliness identifier of the target chromatography test strip.

[0043] In a preferred embodiment, when the standard request module performs an encrypted remote standard request to the cloud based on the timeliness identifier to obtain the dedicated detection standard for the target chromatographic test strip, it is specifically used for:

[0044] Based on the timeliness identifier, the background perturbation of the target chromatographic test strip is quantified to obtain the noise amplitude sequence of the target chromatographic test strip;

[0045] The noise amplitude sequence is obfuscated and spliced ​​with the timeliness identifier to obtain the noise obfuscation request data of the target chromatographic test strip;

[0046] The noise obfuscation request data is sent to the cloud of the target chromatography test strip three times consecutively, and the cloud response latency of the noise obfuscation request data is recorded.

[0047] Based on the cloud response latency, the transmission time of the noise obfuscation request data is determined to obtain the valid request data of the noise obfuscation request data.

[0048] The cloud response data of the valid request data is parsed to obtain the encrypted data packet of the valid request data.

[0049] The encrypted data packet is XORed bit by bit with the noise amplitude sequence to obtain the dedicated detection standard for the target chromatography test strip.

[0050] In a preferred embodiment, when the standard request module performs a transmission time determination on the noise-obfuscated request data based on the cloud response latency to obtain valid request data for the noise-obfuscated request data, it is specifically used for:

[0051] The variance of the noise amplitude sequence is estimated by performing volatility statistics on the noise amplitude sequence.

[0052] Based on the preset scaling parameters, the variance estimate is adaptively adjusted to obtain the attenuation coefficient of the cloud response latency;

[0053] Based on the attenuation coefficient, the matching energy value of the cloud response latency is calculated, wherein the formula for calculating the matching energy value is:

[0054] ;

[0055] In the formula, For the first Matching energy value of the noise-obfuscated request data. The index number of the noise amplitude sequence. The order in which the noise obfuscation request data is sent. The length of the noise amplitude sequence. The noise amplitude sequence is the first... Each noise amplitude, The attenuation coefficient is... For the first Cloud response latency for noise-obfuscated data requests The noise amplitude sequence is the first... Reference time offset for each noise amplitude;

[0056] The matching energy values ​​are numerically compared to obtain the maximum value of the matching energy values, and the noise-obfuscated request data of the maximum value is taken as the valid request data.

[0057] In a preferred embodiment, when the concentration analysis module performs quantitative fluorescence intensity analysis on the detection line image based on the detection standard to obtain the analyte concentration in the detection line image, and performs threshold comparison on the analyte concentration to obtain the detection result of the detection line image, it is specifically used for:

[0058] The detection line light intensity of the detection line image is obtained by performing longitudinal grayscale projection analysis on the detection line image.

[0059] Perform grayscale analysis on the blank area of ​​the detection line image to obtain the average grayscale value of the background of the detection line image;

[0060] Based on the mean gray value of the background, the background contribution of the detection line light intensity is removed to obtain the net light intensity of the detection line sub-image;

[0061] Based on the detection standard, the net light intensity is subjected to concentration interpolation mapping to obtain the concentration of the analyte in the detection line image, and the concentration of the analyte is compared with the judgment threshold in the detection standard to obtain the detection result of the detection line image.

[0062] In a preferred embodiment, when the encrypted upload module encrypts and encapsulates the card-specific information, the concentration of the analyte, and the detection result, and uploads the encrypted data to the cloud, it is specifically used for:

[0063] The serial number in the card-specific information is compressed to obtain the fingerprint summary of the target chromatographic test strip;

[0064] The card-specific information, the concentration of the analyte, and the detection result are fused together, and based on the fingerprint digest, the fused data is replaced byte by byte to obtain the encrypted data block of the target chromatography test strip;

[0065] A header timing appender is added to the encrypted data block to obtain the encrypted data frame of the encrypted data block;

[0066] The encrypted data frame is transmitted to the cloud, and an acknowledgment signal is received from the cloud.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. This invention significantly improves the efficiency of pre-processing data and the accuracy of information analysis in fluorescence immunochromatographic test strip imaging tests through refined multi-module collaborative processing. The system employs adaptive edge detection to accurately extract the test strip area, and combines grayscale distribution and fluorescence signal characteristics to accurately delineate the QR code and detection line areas. Coupled with a tamper-proof QR code decoding and verification process, the authenticity and validity of the card's unique information are guaranteed. Simultaneously, based on this unique information, the timeliness of the test strip is accurately determined. The optimization of technical means in each stage makes image and information processing in the pre-test stage more efficient, laying a reliable technical foundation for subsequent testing.

[0069] 2. This invention effectively improves the accuracy of test strip results and the security and compatibility of data interaction, achieving standardization and efficiency in the testing process. The concentration analysis stage obtains net light intensity by eliminating background grayscale interference, and combines this with cloud-adapted dedicated testing standards to accurately quantify the concentration of the analyte, improving the reliability of the test results. The use of encrypted remote request to obtain dedicated testing standards, coupled with encrypted upload methods of fingerprint digests and byte-by-byte replacement, ensures both the compatibility of the testing standards and the secure encapsulation and upload of test data. The technical integration of each module is significantly improved, resulting in an overall increase in the detection efficiency and data management standardization of the imaging testing system. Attached Figure Description

[0070] Figure 1 This is a system architecture diagram of a portable fluorescence immunochromatographic test strip imaging system provided in an embodiment of the present invention;

[0071] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0074] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0075] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0076] In practice, the server-side equipment deployed in a portable fluorescence immunochromatographic assay strip imaging test system may consist of one or more devices. This portable fluorescence immunochromatographic assay strip imaging test system can be implemented as a business instance, a virtual machine, or hardware devices. For example, this portable fluorescence immunochromatographic assay strip imaging test system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this portable fluorescence immunochromatographic assay strip imaging test system can be understood as software deployed on a cloud node, used to provide a portable fluorescence immunochromatographic assay strip imaging test system to various user terminals. Alternatively, this portable fluorescence immunochromatographic assay strip imaging test system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, this portable fluorescence immunochromatographic assay strip imaging test system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide a portable fluorescence immunochromatographic assay strip imaging test system to various user terminals.

[0077] In terms of implementation, the portable fluorescence immunochromatographic test strip imaging system and the user terminal are mutually compatible. That is, if the portable fluorescence immunochromatographic test strip imaging system is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the portable fluorescence immunochromatographic test strip imaging system is implemented as a website, then the user terminal is implemented as a webpage; or if the portable fluorescence immunochromatographic test strip imaging system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0078] like Figure 1 The diagram shown is a system architecture diagram of a portable fluorescence immunochromatographic test strip imaging system provided in an embodiment of the present invention.

[0079] The portable fluorescence immunochromatographic test strip imaging system 10 described in this invention can be located on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the portable fluorescence immunochromatographic test strip imaging system 10 may include an edge detection module 11, a region segmentation module 12, a decoding and verification module 13, a timeliness determination module 14, a standard request module 15, a concentration analysis module 16, and an encrypted upload module 17. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0080] In this embodiment of the invention, in a portable fluorescence immunochromatographic strip imaging testing system, each of the above-mentioned modules can be implemented independently and can be called upon with other modules. Here, "calling upon" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. The portable fluorescence immunochromatographic strip imaging testing system provided by this embodiment of the invention allows for adjustment of the applicable scope of the system architecture without modifying the program code, through adding modules and directly calling them. This enables cluster-based horizontal expansion, achieving the goal of quickly and flexibly expanding the portable fluorescence immunochromatographic strip imaging testing system. In practical applications, the above modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0081] The following describes the various components and specific workflow of a portable fluorescence immunochromatographic test strip imaging system, using specific embodiments as examples:

[0082] The edge detection module 11 is used to perform adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image;

[0083] In this embodiment of the invention, when the edge detection module performs adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image, it is specifically used for:

[0084] The original fluorescence image of the target chromatography strip is compensated for by illumination non-uniformity to obtain a brightness-equalized image of the original fluorescence image;

[0085] The brightness equalization image is subjected to edge response enhancement processing to obtain the enhanced edge image of the brightness equalization image;

[0086] Closed boundary tracking is performed on the abruptly changed pixels of the enhanced edge image to obtain the test strip outline of the enhanced edge image;

[0087] Based on the test strip outline, the brightness equalization image is cropped to obtain the test strip region image of the original fluorescence image.

[0088] The brightness values ​​of each pixel in the original fluorescence image of the target chromatography test strip are extracted, and the overall brightness distribution of the image is smoothed. The brightness values ​​of the corresponding pixels in the image with high brightness are reduced, and the brightness values ​​of the corresponding pixels in the image with low brightness are increased, so that the brightness of each region in the image is at a uniform adaptation level. This completes the compensation for the illumination non-uniformity of the original fluorescence image, and finally obtains the brightness equalization image corresponding to the original fluorescence image.

[0089] The brightness difference between adjacent pixels in the brightness equalization image is extracted, and the effective information of the pixel brightness difference in the image is completely preserved. For the pixel area corresponding to the edge of the test strip in the image, the contrast effect of the brightness difference between adjacent pixels in the area is improved, so that the pixel features of the test strip edge are clearly distinguished from the surrounding pixels. This completes the edge response enhancement processing of the brightness equalization image, and finally obtains the enhanced edge image corresponding to the brightness equalization image.

[0090] Identify abrupt changes in pixel brightness in the enhanced edge image, connect the abrupt pixels distributed along the edge of the test strip according to their spatial position in the image, and supplement any missing abrupt pixels at the edge of the test strip in the image during the connection process, so that all connected abrupt pixels form a complete closed line, thus completing the closed boundary tracking of the abrupt pixels in the enhanced edge image, and finally obtaining the test strip outline corresponding to the enhanced edge image.

[0091] Using the obtained test strip outline as the boundary, the area enclosed by the test strip outline in the image is defined as the target cropping area. All pixel areas outside the test strip outline in the brightness equalization image are removed, and only the complete pixel areas inside the test strip outline are retained. This completes the cropping of the brightness equalization image, and finally the test strip area image corresponding to the original fluorescence image is obtained.

[0092] Beneficial effects include: compensating for uneven illumination in the original fluorescence image, resulting in a brightness-equalized image that eliminates brightness deviations caused by illumination, providing a high-quality base image for subsequent processing; enhanced edge response that highlights the pixel features at the test strip edges, providing a clear basis for identifying abrupt pixel changes; closed boundary tracking that forms a complete test strip outline, providing a precise reference for region cropping; and precise region cropping that extracts the effective area of ​​the test strip and removes irrelevant areas, ensuring the quality of edge detection processing and laying a solid foundation for subsequent image processing stages.

[0093] The region division module 12 is used to divide the test strip region image into regions to obtain the QR code sub-image and the detection line sub-image of the test strip region image;

[0094] In this embodiment of the invention, when the region segmentation module performs region segmentation on the test strip region image to obtain the QR code sub-image and detection line sub-image of the test strip region image, it is specifically used for:

[0095] Image brightness analysis is performed on the test strip area image to obtain the grayscale distribution spectrum of the test strip area image;

[0096] Based on the abrupt change locations of texture density in the grayscale distribution map, structural texture recognition is performed on the test strip region image to obtain the QR code candidate region of the test strip region image;

[0097] The fluorescence signal is geometrically located in the test strip area image to obtain the candidate region of the detection line in the test strip area image;

[0098] The boundaries of the QR code candidate region are refined to obtain the QR code sub-image of the test strip region image;

[0099] Morphological separation is performed on the candidate regions of the detection line to obtain the detection line sub-image of the test strip region image.

[0100] The brightness value of each pixel in the test strip area image is extracted, and the brightness values ​​of all pixels are arranged in an orderly manner according to the spatial coordinate position of the image to form an image distribution form with the horizontal and vertical coordinates of the pixels as coordinate axes and the pixel brightness value as the characterization parameter. This completes the image brightness analysis of the test strip area image and finally obtains the grayscale distribution spectrum corresponding to the test strip area image.

[0101] The texture density of each region in the grayscale distribution map is analyzed. The frequency of pixel brightness changes within a fixed range around each pixel in the map is counted and used as the texture density value of that pixel location. The texture density values ​​of all pixels are arranged as a whole according to their spatial coordinates. The pixel locations in the map where the texture density value changes abruptly are identified and determined as abrupt changes in texture density. All consecutive abrupt changes in texture density are connected sequentially to form a closed boundary. The dense texture density region enclosed by this boundary is the QR code candidate region of the identified test strip area image.

[0102] Extract the fluorescence signal intensity values ​​of all pixels in the test strip area image, summarize and statistically analyze the fluorescence signal intensity values ​​at different horizontal coordinates according to the vertical spatial position of the image, identify the vertical pixel areas in the image where the fluorescence signal intensity values ​​are distributed in a continuous strip shape, accurately determine the horizontal and vertical boundary ranges of the strip-shaped area, and the area formed by the boundary ranges together is the candidate area for the detection line of the test strip area image obtained after completing the geometric localization of the fluorescence signal.

[0103] The edge pixels of the QR code candidate region are verified point by point. Isolated pixels that deviate from the texture density change position on the boundary are removed. Missing boundary pixels at the texture density change position are added to make the corrected QR code candidate region boundary form a regular and closed complete outline. Using the corrected closed outline as the precise boundary, all pixel regions corresponding to the outline in the test strip region image are extracted, and finally the QR code sub-image corresponding to the test strip region image is obtained.

[0104] Neighborhood pixel correlation analysis is performed on all pixels within the candidate region of the detection line to remove stray pixels that have no continuous spatial correlation with the main pixels of the detection line. The main pixel region of the detection line, which is distributed in a continuous strip shape within the candidate region of the detection line, is completely preserved. The contour of the preserved main pixel region is then regularized to determine the precise boundary of the regularized main pixel region. All pixel regions within the boundary in the test strip region image are then extracted to finally obtain the detection line sub-image corresponding to the test strip region image.

[0105] The beneficial effects include: the grayscale distribution map obtained by brightness analysis of the test strip area image provides a clear basis for subsequent texture recognition; the location of abrupt changes in texture density can accurately locate the QR code candidate region; and the geometric positioning of the fluorescence signal can determine the detection line candidate region by matching the detection line features. Fine-grained boundary correction of the QR code candidate region yields a well-defined QR code sub-image; and morphological separation of the detection line candidate region can remove stray pixels and retain the effective area. Ultimately, this achieves accurate segmentation of the test strip area image, providing an accurate image region foundation for subsequent QR code decoding and fluorescence intensity analysis.

[0106] The decoding and verification module 13 is used to decode the data of the QR code sub-image and perform anti-tampering legality verification on the decoded QR code information to obtain the card-specific information of the QR code sub-image.

[0107] In this embodiment of the invention, when the decoding and verification module performs data decoding on the QR code sub-image and verifies the tamper-proof legality of the decoded QR code information to obtain the card-specific information of the QR code sub-image, it is specifically used for:

[0108] The code bit space is mapped to the QR code sub-image to obtain the code bit position map of the QR code sub-image;

[0109] Based on the coded bit position map, the check bit of the QR code sub-image is extracted, and the pixel response of the check bit is read to obtain the grayscale sampling sequence of the check bit.

[0110] The fluorescence background statistical value of the test strip area image is obtained by performing blank area light intensity analysis on the test strip area image;

[0111] The grayscale sampling sequence is numerically compared with the fluorescence background statistics, and the deviation of the comparison result is evaluated with a preset reference interpolation sequence to obtain the consistency score of the grayscale sampling sequence.

[0112] Based on the consistency score, the decoded data of the QR code sub-image is subjected to a credibility weighting correction to obtain the credibility decoding identifier of the QR code sub-image.

[0113] Based on the trusted decoding identifier, the decoded data is reconstructed to obtain the card-specific information of the QR code sub-image.

[0114] When the decoding and verification module performs a numerical comparison between the grayscale sampling sequence and the fluorescence background statistics, and evaluates the deviation between the comparison result and a preset reference interpolation sequence to obtain a consistency score for the grayscale sampling sequence, it is specifically used for:

[0115] Spatial coordinate positioning is performed on the verification bit to obtain the pixel coordinate set of the verification bit;

[0116] Based on the fluorescence background statistics, the background deviation of the grayscale sampling sequence is subtracted to obtain the correction deviation vector of the grayscale sampling sequence;

[0117] Based on the correction deviation vector and the preset reference interpolation sequence, spatial trend fitting is performed on the pixel coordinate set to obtain the spatial correction coefficients of the pixel coordinate set.

[0118] Based on the spatial correction coefficients and the reference interpolation sequence, the consistency score of the grayscale sampling sequence is calculated, wherein the formula for calculating the consistency score is:

[0119] ;

[0120] In the formula, For the consistency score, It is an exponential function. The sequence number of the verification bearer bit. The total number of the verification bits. The first of the correction deviation vectors One element, The spatial correction coefficient is... The x-coordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The x-coordinate value of each check bit. The ordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The ordinate value of each check bit. For the first reference interpolation sequence One element, This is the preset allowable deviation benchmark.

[0121] Identify the pixel positions of all coded bits in the QR code sub-image, sort and calibrate the spatial coordinates of each coded bit according to the QR code's encoding structure, visualize the position information of each coded bit according to the image's pixel coordinate system, form a map containing the spatial positions of all coded bits, complete the spatial mapping of the coded bits of the QR code sub-image, and finally obtain the coded bit position map of the QR code sub-image.

[0122] Based on the spatial positions of each coding bit marked in the coding bit location map, the coding bits used for verification, namely the verification bits, are identified and extracted from the map. The light intensity response of each pixel area of ​​the verification bit is read one by one, and the gray value corresponding to each verification bit is recorded. The gray values ​​of all verification bits are arranged in order according to their spatial positions, and finally the gray sampling sequence of the verification bit is obtained.

[0123] In the test strip area image, blank pixel areas without fluorescent signals and coded textures are identified. The light intensity values ​​of all pixels in the blank area are extracted and summarized point by point. All extracted light intensity values ​​are statistically processed to obtain values ​​that can characterize the background light intensity level of the test strip area image. Finally, the fluorescence background statistical value of the test strip area image is obtained.

[0124] Each gray value in the gray-scale sampling sequence is compared with the fluorescence background statistical value one by one to obtain the comparison results between the values. All comparison results are compared with the preset reference interpolation sequence bit by bit for deviation analysis and the overall deviation degree is evaluated. Based on the evaluation results, a value that can characterize the degree of fit between the gray-scale sampling sequence and the reference interpolation sequence is obtained, and finally the consistency score of the gray-scale sampling sequence is obtained.

[0125] In the pixel coordinate system of the QR code sub-image, the pixel region of each check bit is precisely calibrated one by one, and the horizontal and vertical coordinates of the pixel corresponding to each check bit are recorded. The coordinate information of all check bits is integrated in order of their spatial positions to form a complete coordinate set, and finally the pixel coordinate set of the check bit is obtained.

[0126] Using the fluorescence background statistical value as the reference value, the deviation subtraction operation is performed on each gray value in the gray-scale sampling sequence to eliminate the influence of the background light intensity deviation contained in each gray value. All the values ​​after the deviation subtraction are arranged in the original order to form a set of values ​​in vector form, and finally the correction deviation vector of the gray-scale sampling sequence is obtained.

[0127] By combining all the values ​​in the correction deviation vector with the corresponding values ​​in the preset reference interpolation sequence, an overall spatial trend analysis is performed on all coordinate information in the pixel coordinate set. The trend fitting adjustment is completed according to the spatial distribution law of the coordinates to obtain the correction values ​​that can adapt to the spatial trend of the pixel coordinate set, and finally the spatial correction coefficient of the pixel coordinate set is obtained.

[0128] Using the spatial correction coefficient as the adaptation benchmark, and combining the value of the correction deviation vector with the value of the preset reference interpolation sequence, a comprehensive review and evaluation of the overall fit of the grayscale sampling sequence is conducted to obtain a specific value that can characterize the fit, and finally obtain the consistency score of the grayscale sampling sequence.

[0129] Using consistency scores as the credibility criterion, targeted corrections and adjustments are made to the decoded data of the QR code sub-image. Based on the scoring results, the weights of each part of the decoded data are allocated and corrected and optimized to eliminate the deviations and distortions in the decoded data, thereby obtaining the identification information that can characterize the credibility of the decoded data. Finally, the credible decoding identifier of the QR code sub-image is obtained.

[0130] Based on the range of valid decoding information determined in the trusted decoding identifier, the decoding data of the QR code sub-image is filtered and organized, invalid and distorted information content in the decoding data is removed, and the filtered valid decoding information is reorganized and arranged according to the preset information structure to finally obtain the card-specific information of the QR code sub-image.

[0131] The consistency score is obtained by an exponential function, the input of which is obtained by the relevant numerical calculation of each check bit. The check bits are numbered sequentially according to their spatial position. The total number of check bits is determined by the number of check bits extracted from the coding bit position map. The elements of the correction deviation vector are obtained by subtracting the fluorescence background statistical value from the grayscale sampling sequence. The spatial correction coefficient and the corresponding abscissa and ordinate coefficients are obtained by fitting the spatial trend of the pixel coordinate set with the correction deviation vector and the reference interpolation sequence. The abscissa and ordinate values ​​of the check bits in the pixel coordinate set are obtained by spatially locating the check bits. The elements of the reference interpolation sequence are preset content, and the preset allowable deviation benchmark is preset content.

[0132] This operation is used to evaluate the degree of fit between the grayscale sampling sequence and the preset reference interpolation sequence. By integrating the correction deviation, spatial position and reference interpolation information of each check bit, a value that reflects the degree of matching between the grayscale sampling sequence and the reference interpolation sequence is obtained. This value is the consistency score, which is used to perform confidence-weighted correction on the decoding data of the QR code sub-image to obtain a reliable decoding identifier.

[0133] The consistency score improves when the sum of the squared differences between the correction deviation corresponding to each check bit and the spatially corrected reference interpolation sequence elements decreases, and decreases when the sum of the squared differences between the correction deviation corresponding to each check bit and the spatially corrected reference interpolation sequence elements increases.

[0134] The beneficial effect is that the encoded bit location map obtained by the encoded bit space mapping provides a clear location basis for the accurate extraction of the verification carrier bit and the acquisition of the grayscale sampling sequence. The fluorescence background statistics can eliminate the interference of background light intensity on grayscale values, and the consistency score obtained after a series of processing can effectively determine the fit of the grayscale sampling sequence. The score is used to correct the decoding data to obtain a reliable decoding identifier, and finally, the valid card-specific information is reconstructed, realizing the accurate interpretation of QR code information and the verification of its tamper-proof legality, ensuring the authenticity and validity of the obtained card-specific information.

[0135] The timeliness determination module 14 is used to determine the status of the detection date of the target chromatography test strip based on the card-specific information, and obtain the timeliness identifier of the target chromatography test strip.

[0136] In this embodiment of the invention, when the timeliness determination module performs a status determination on the detection date of the target chromatography test strip based on the card-specific information to obtain the timeliness identifier of the target chromatography test strip, it is specifically used for:

[0137] The card-specific information is analyzed for field separators to obtain the validity period code field of the card-specific information;

[0138] Perform a number system mapping on the validity period code field to obtain the validity period time value of the validity period code field;

[0139] Read the current time count of the target chromatographic test strip and reconstruct the current time count by year, month, and day to obtain the current date value of the target chromatographic test strip;

[0140] The validity period value is compared digit by digit with the current date value to obtain the determination result of the current date value;

[0141] Based on the determination result, the validity level of the card-specific information is defined to obtain the timeliness identifier of the target chromatography test strip.

[0142] Iterate through all the characters in the card's unique information, identify the preset field separator characters in the information, accurately determine the specific character position of each separator in the card's unique information, and use the field separator as the content boundary to extract the character segment in the card's unique information that represents the test strip's validity period. This character segment is the validity period code field of the card's unique information.

[0143] Identify the original number system type of the validity period code field, and convert the character-based encoding content in the validity period code field into decimal number-based time information according to the corresponding number system conversion rules. Then, arrange the converted number-based time information in an orderly manner according to the fixed number of digits for year, month, and day to form a regular number sequence, and finally obtain the validity period time value of the validity period code field.

[0144] The real-time time count during the detection operation of the target chromatography test strip is extracted. This time count is a continuous digital time information. According to the preset year, month and day division rules, the digital information of the real-time time count is accurately split. Then, the split numbers are arranged and combined in the order of year, month and day to form a regular number sequence, and finally the current date value of the target chromatography test strip is obtained.

[0145] Align the expiration date value and the current date value one by one according to the corresponding digits of the year, month and day. Starting from the year digit, compare the size of the two values ​​in each corresponding digit of the year, month and day. Record the specific result of the comparison of each digit. Then integrate the comparison results of all digits to form the overall result. This overall result is the determination result of the current date value.

[0146] The card-specific information validity level is preset to correspond one-to-one with various judgment results. The current date value judgment result is accurately matched with the preset validity level to determine the unique validity level corresponding to the judgment result. Then, the validity level is converted into fixed-format identification information according to the preset identification rules. This identification information is the timeliness identification of the target chromatography test strip.

[0147] The beneficial effects include: accurate extraction of the expiration date code field from the card's unique information through field separator recognition; conversion of the code into a standardized expiration date value through number system mapping; and reconstruction of the year, month, and day from the real-time time count to obtain a unified format for the current date value. A digit-by-digit comparison of the year, day, and month provides a precise determination result. Combined with preset level matching to define validity and convert it into a timeliness identifier, this achieves accurate determination of the test date on the chromatography strip, providing effective evidence of the test strip's validity for subsequent testing and ensuring the standardization of the testing process.

[0148] The standard request module 15 is used to make an encrypted remote standard request to the cloud of the target chromatography test strip based on the timeliness identifier, so as to obtain the dedicated detection standard of the target chromatography test strip.

[0149] In this embodiment of the invention, when the standard request module performs an encrypted remote standard request to the cloud of the target chromatographic test strip based on the timeliness identifier to obtain the dedicated detection standard for the target chromatographic test strip, it is specifically used for:

[0150] Based on the timeliness identifier, the background perturbation of the target chromatographic test strip is quantified to obtain the noise amplitude sequence of the target chromatographic test strip;

[0151] The noise amplitude sequence is obfuscated and spliced ​​with the timeliness identifier to obtain the noise obfuscation request data of the target chromatographic test strip;

[0152] The noise obfuscation request data is sent to the cloud of the target chromatography test strip three times consecutively, and the cloud response latency of the noise obfuscation request data is recorded.

[0153] Based on the cloud response latency, the transmission time of the noise obfuscation request data is determined to obtain the valid request data of the noise obfuscation request data.

[0154] The cloud response data of the valid request data is parsed to obtain the encrypted data packet of the valid request data.

[0155] The encrypted data packet is XORed bit by bit with the noise amplitude sequence to obtain the dedicated detection standard for the target chromatography test strip.

[0156] When the standard request module performs a transmission time determination on the noise-obfuscated request data based on the cloud response latency to obtain valid request data for the noise-obfuscated request data, it is specifically used for:

[0157] The variance of the noise amplitude sequence is estimated by performing volatility statistics on the noise amplitude sequence.

[0158] Based on the preset scaling parameters, the variance estimate is adaptively adjusted to obtain the attenuation coefficient of the cloud response latency;

[0159] Based on the attenuation coefficient, the matching energy value of the cloud response latency is calculated, wherein the formula for calculating the matching energy value is:

[0160] ;

[0161] In the formula, For the first Matching energy value of the noise-obfuscated request data. The index number of the noise amplitude sequence. The order in which the noise obfuscation request data is sent. The length of the noise amplitude sequence. The noise amplitude sequence is the first... Each noise amplitude, The attenuation coefficient is... For the first Cloud response latency for noise-obfuscated data requests The noise amplitude sequence is the first... Reference time offset for each noise amplitude;

[0162] The matching energy values ​​are numerically compared to obtain the maximum value of the matching energy values, and the noise-obfuscated request data of the maximum value is taken as the valid request data.

[0163] Based on the status information of the target chromatographic test strip corresponding to the timeliness identifier, various disturbance signals generated in the background area during the test strip detection process are extracted. The amplitude of all disturbance signals is extracted and recorded sequentially. All extracted amplitudes are arranged in order according to the time sequence of signal acquisition to form a continuous amplitude sequence. The background disturbance of the target chromatographic test strip is quantified, and finally the noise amplitude sequence of the target chromatographic test strip is obtained.

[0164] All data in the noise amplitude sequence are preserved in their original order and interleaved with the original information of the timeliness identifier. During the interleaving process, the original data content of both is not changed, only the data format is fused and combined, so that the two types of data form a whole request data carrier, and finally the noise confusion request data of the target chromatography test strip is obtained.

[0165] According to a preset fixed time interval, the noise confusion request data is sent to the cloud of the target chromatography test strip three times in sequence. After each data transmission is completed, the time interval from the moment the data is sent to the moment the first feedback signal is received from the cloud is accurately recorded. This time interval is the cloud response delay corresponding to a single transmission. The cloud response delays corresponding to the three transmissions are recorded in full.

[0166] The overall fluctuation characteristics of all amplitude data in the noise amplitude sequence are statistically analyzed, the discrete distribution of data around the central value in the sequence is sorted out, and the numerical value that can characterize the fluctuation of the sequence is obtained based on the distribution characteristics of the data. Finally, the variance estimate of the noise amplitude sequence is obtained.

[0167] The preset scaling parameter and variance estimate are numerically fused and corrected. According to the preset adjustment rules, the scaling parameter is used to make targeted numerical adjustments to the variance estimate so that the adjusted value can adapt to the determination requirements of cloud response latency, and finally the cloud response latency attenuation coefficient is obtained.

[0168] Based on the attenuation coefficient, the cloud response delays corresponding to the three transmissions are numerically adapted. Combining the data characteristics of the noise amplitude sequence, the corresponding energy value is calculated for each cloud response delay. The matching energy value for each of the three transmissions is calculated, and finally the matching energy value corresponding to each noise obfuscation request data is obtained.

[0169] The three matching energy values ​​obtained from the three transmissions are compared comprehensively to accurately determine the matching energy value with the largest value. The noise obfuscation request data corresponding to the transmission operation with the largest value is determined as the valid request data, and the transmission time of the noise obfuscation request data is determined.

[0170] Extract the cloud response data corresponding to the valid request data, disassemble and analyze the overall message structure of the response data layer by layer, remove non-core data parts such as protocol headers and check bits from the message, accurately extract the core encrypted data content in the message, and finally obtain the encrypted data packet of the valid request data.

[0171] Each bit of data in the encrypted data packet is XORed with the corresponding bit of data in the noise amplitude sequence in turn. The operation is completed for all corresponding bits. The original detection standard data content is restored through the operation, and finally the special detection standard of the target chromatography test strip is obtained.

[0172] Matching energy value corresponding to the first The noise obfuscation request data is indexed sequentially according to the time sequence of the sequence acquisition. The sending order of the noise obfuscation request data is determined by the order in which the three data transmissions are performed. The length of the noise amplitude sequence is determined by the total number of amplitudes contained in the noise amplitude sequence obtained from the background disturbance quantization. The noise amplitude is obtained by successively extracting and completely recording the background disturbance quantization operation. The attenuation coefficient is obtained by adaptively adjusting the variance estimate of the noise amplitude sequence and the preset scaling parameter. The cloud response latency for each noise-obfuscated request data is precisely recorded by the time interval between the data transmission time and the first cloud response time. The noise amplitude sequence is the [number of requests]. The reference time offset for each noise amplitude is a preset fixed time offset corresponding to each noise amplitude.

[0173] This operation is used to calculate the matching energy value corresponding to each noise obfuscation request data. By integrating the amplitude information of the noise amplitude sequence, the attenuation coefficient, the cloud response latency, and the reference time offset, a value is obtained that can characterize the degree of matching between each noise obfuscation request data and the noise amplitude sequence. This value is used to filter out valid request data and provide a basis for judgment for subsequent extraction of encrypted data packets and restoration of dedicated detection standards.

[0174] When the difference between the cloud response latency and the corresponding reference time offset decreases, the denominator of the corresponding term decreases, the value of the term increases, and the overall matching energy value increases. When the difference between the cloud response latency and the corresponding reference time offset increases, the denominator of the corresponding term increases, the value of the term decreases, and the overall matching energy value decreases. The change in the value of the attenuation coefficient will directly affect the change in the denominator, thereby changing the degree of influence of the difference on the matching energy value.

[0175] The beneficial effect is that the noise amplitude sequence obtained by quantifying background disturbances based on the timeliness identifier, and the request data formed by concatenating and mixing it with the timeliness identifier, gives the remote request an encrypted foundation. By sending the request three times and recording the response delay, and then calculating the matching energy value through fluctuation statistics and coefficient adjustment, valid request data can be accurately filtered out. The encrypted data packet is extracted from the response data message and restored using XOR to obtain a dedicated detection standard, which not only ensures the security of request transmission but also makes the obtained detection standard compatible with the timeliness status of the chromatography test strip.

[0176] The concentration analysis module 16 is used to perform quantitative analysis of fluorescence intensity on the detection line image based on the detection standard, obtain the concentration of the analyte in the detection line image, and perform threshold comparison on the concentration of the analyte to obtain the detection result of the detection line image.

[0177] In this embodiment of the invention, when the concentration analysis module performs quantitative analysis of fluorescence intensity on the detection line image based on the detection standard to obtain the concentration of the analyte in the detection line image, and performs threshold comparison on the concentration of the analyte to obtain the detection result of the detection line image, it is specifically used for:

[0178] The detection line light intensity of the detection line image is obtained by performing longitudinal grayscale projection analysis on the detection line image.

[0179] Perform grayscale analysis on the blank area of ​​the detection line image to obtain the average grayscale value of the background of the detection line image;

[0180] Based on the mean gray value of the background, the background contribution of the detection line light intensity is removed to obtain the net light intensity of the detection line sub-image;

[0181] Based on the detection standard, the net light intensity is subjected to concentration interpolation mapping to obtain the concentration of the analyte in the detection line image, and the concentration of the analyte is compared with the judgment threshold in the detection standard to obtain the detection result of the detection line image.

[0182] The grayscale values ​​of all pixels in each column of the detection line sub-image are extracted sequentially according to the pixel distribution of the vertical columns. The grayscale values ​​of each column are summarized and statistically analyzed to determine the vertical pixel region corresponding to the detection line in the detection line sub-image. The grayscale statistical results of all columns in this region are extracted and integrated to form a value that can characterize the overall light intensity level of the detection line. The vertical grayscale projection analysis of the detection line sub-image is completed, and finally the light intensity of the detection line in the detection line image is obtained.

[0183] In the detection line image, blank pixel regions without fluorescence signal distribution are identified. These regions are pixel regions around the detection line that do not participate in the detection reaction. The gray values ​​of all pixels in the blank region are extracted point by point. The extracted gray values ​​are averaged to obtain a value that can characterize the background light intensity level of the detection line image. This completes the gray value analysis of the blank region of the detection line image and finally obtains the average background gray value of the detection line image.

[0184] The average grayscale value of the background is used as the background light intensity contribution value contained in the light intensity of the detection line. The background light intensity contribution value is subtracted from the overall value of the light intensity of the detection line to eliminate the light intensity interference caused by the background grayscale in the light intensity of the detection line, so as to obtain the light intensity value generated only by the detection reaction. This completes the background contribution removal of the light intensity of the detection line and finally obtains the net light intensity of the detection line sub-image.

[0185] The system retrieves a dedicated detection standard from the cloud, which contains a correlation between light intensity values ​​and the concentration of the analyte. The net light intensity value is then compared with this correlation to perform interpolation matching, and the concentration value that matches the net light intensity value is found. This concentration value is the concentration of the analyte in the detection line image. The concentration value of the analyte is then matched with the preset judgment threshold in the detection standard to determine the range to which the concentration of the analyte belongs. The detection result of the detection line image is determined according to the result corresponding to the range.

[0186] The beneficial effects include: longitudinal grayscale projection analysis can accurately extract the light intensity of the detection line; grayscale analysis of the blank area can obtain an objective background grayscale mean; background contribution removal can eliminate background light intensity interference to obtain pure net light intensity, thus improving the accuracy of light intensity data. Interpolation mapping based on dedicated detection standards can accurately convert net light intensity into analyte concentration; threshold comparison can directly obtain reliable detection results, ensuring the accuracy of quantitative analysis of fluorescence intensity and the reliability of detection results.

[0187] The encrypted upload module 17 is used to encrypt and encapsulate the card-specific information, the concentration of the analyte, and the detection result, and upload the encrypted data to the cloud.

[0188] In this embodiment of the invention, when the encrypted upload module encrypts and encapsulates the card-specific information, the concentration of the analyte, and the detection result, and uploads the encrypted data to the cloud, it is specifically used for:

[0189] The serial number in the card-specific information is compressed to obtain the fingerprint summary of the target chromatographic test strip;

[0190] The card-specific information, the concentration of the analyte, and the detection result are fused together, and based on the fingerprint digest, the fused data is replaced byte by byte to obtain the encrypted data block of the target chromatography test strip;

[0191] A header timing appender is added to the encrypted data block to obtain the encrypted data frame of the encrypted data block;

[0192] The encrypted data frame is transmitted to the cloud, and an acknowledgment signal is received from the cloud.

[0193] Extract all characters of the serial number from the card's unique information, analyze the character arrangement features and core character identifiers in fixed positions, extract and integrate all the analyzed features, remove redundant content, retain only the core features that characterize the uniqueness of the serial number, compress the core features to a fixed length, and finally obtain the fingerprint summary of the target chromatography test strip.

[0194] All data, including card-specific information, analyte concentration, and test results, are integrated according to a pre-defined unified data format. During the integration process, the original information of each part of the data is preserved and the data is arranged in an orderly manner. The fusion processing of the three types of data is completed. Then, based on the core features in the fingerprint summary, the specific order and rules for data byte replacement are determined. Each byte of the fused data is adjusted according to the rules, changing only the byte arrangement position without modifying the original byte content, and finally obtaining the encrypted data block of the target chromatography test strip.

[0195] Extract the real-time time information of the encrypted data block's transmission time, organize the real-time time information into standardized time-series data according to the preset time-series data format, and add the complete time-series data to the header of the encrypted data block, so that the time-series data and the encrypted data block form a complete frame structure, and finally obtain the encrypted data frame of the encrypted data block.

[0196] The encrypted data frame is converted according to the communication transmission format preset in the cloud. After conversion, the encrypted data frame is transmitted to the cloud corresponding to the target chromatography test strip through a dedicated remote communication link. The cloud continuously receives feedback data information. When the cloud completes the reception and verification of the encrypted data frame, it will send back the corresponding reception verification information, which is the cloud's confirmation signal.

[0197] The beneficial effects include providing a unique and exclusive basis for data encryption by compressing the fingerprint digest obtained from the serial number features, ensuring the uniqueness of the encryption. After fusing multiple types of data, byte-by-byte permutation based on the fingerprint digest is performed, effectively encrypting the data while preserving its original information; the encrypted data blocks enhance data confidentiality. Adding a time sequence to the encrypted data blocks results in encrypted data frames, giving the data a time-series identifier and improving data traceability. Transmitting according to specifications and obtaining a cloud confirmation signal ensures the validity and integrity of the data upload, achieving secure encrypted upload of detection-related data.

[0198] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0199] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence 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 that knowledge to obtain optimal results.

[0200] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A portable fluorescence immunochromatographic test strip imaging system, characterized in that, The system includes an edge detection module, a region segmentation module, a decoding and verification module, a timeliness determination module, a standard request module, a concentration parsing module, and an encrypted upload module, wherein: The edge detection module is used to perform adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image; The region division module is used to divide the test strip region image into regions to obtain the QR code sub-image and the detection line sub-image of the test strip region image; The decoding and verification module is used to decode the data of the QR code sub-image and perform anti-tampering legality verification on the decoded QR code information to obtain the card-specific information of the QR code sub-image. The timeliness determination module is used to determine the status of the detection date of the target chromatography test strip based on the card-specific information, and obtain the timeliness identifier of the target chromatography test strip; The standard request module is used to make an encrypted remote standard request to the cloud of the target chromatography test strip based on the timeliness identifier, so as to obtain the dedicated detection standard of the target chromatography test strip. The concentration analysis module is used to perform quantitative analysis of fluorescence intensity on the detection line image based on the detection standard, obtain the concentration of the analyte in the detection line image, and perform threshold comparison on the concentration of the analyte to obtain the detection result of the detection line image. The encrypted upload module is used to encrypt and encapsulate the card-specific information, the concentration of the analyte, and the detection result, and then upload the encrypted data to the cloud.

2. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the edge detection module performs adaptive edge detection on the original fluorescence image of the target chromatographic test strip to obtain the test strip region image of the original fluorescence image, it is specifically used for: The original fluorescence image of the target chromatography strip is compensated for by illumination non-uniformity to obtain a brightness-equalized image of the original fluorescence image; The brightness equalization image is subjected to edge response enhancement processing to obtain the enhanced edge image of the brightness equalization image; Closed boundary tracking is performed on the abruptly changed pixels of the enhanced edge image to obtain the test strip outline of the enhanced edge image; Based on the test strip outline, the brightness equalization image is cropped to obtain the test strip region image of the original fluorescence image.

3. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the region segmentation module performs region segmentation on the test strip region image to obtain the QR code sub-image and detection line sub-image of the test strip region image, it is specifically used for: Image brightness analysis is performed on the test strip area image to obtain the grayscale distribution spectrum of the test strip area image; Based on the abrupt change locations of texture density in the grayscale distribution map, structural texture recognition is performed on the test strip region image to obtain the QR code candidate region of the test strip region image; The fluorescence signal is geometrically located in the test strip area image to obtain the candidate region of the detection line in the test strip area image; The boundaries of the QR code candidate region are refined to obtain the QR code sub-image of the test strip region image; Morphological separation is performed on the candidate regions of the detection line to obtain the detection line sub-image of the test strip region image.

4. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the decoding and verification module performs data decoding on the QR code sub-image and verifies the tamper-proof legitimacy of the decoded QR code information to obtain the card-specific information of the QR code sub-image, it is specifically used for: The code bit space is mapped to the QR code sub-image to obtain the code bit position map of the QR code sub-image; Based on the coded bit position map, the check bit of the QR code sub-image is extracted, and the pixel response of the check bit is read to obtain the grayscale sampling sequence of the check bit. The fluorescence background statistical value of the test strip area image is obtained by performing blank area light intensity analysis on the test strip area image; The grayscale sampling sequence is numerically compared with the fluorescence background statistics, and the deviation of the comparison result is evaluated with a preset reference interpolation sequence to obtain the consistency score of the grayscale sampling sequence. Based on the consistency score, the decoded data of the QR code sub-image is subjected to a credibility weighting correction to obtain the credibility decoding identifier of the QR code sub-image. Based on the trusted decoding identifier, the decoded data is reconstructed to obtain the card-specific information of the QR code sub-image.

5. The portable fluorescence immunochromatographic test strip imaging system as described in claim 4, characterized in that, When the decoding and verification module performs a numerical comparison between the grayscale sampling sequence and the fluorescence background statistics, and evaluates the deviation between the comparison result and a preset reference interpolation sequence to obtain a consistency score for the grayscale sampling sequence, it is specifically used for: Spatial coordinate positioning is performed on the verification bit to obtain the pixel coordinate set of the verification bit; Based on the fluorescence background statistics, the background deviation of the grayscale sampling sequence is subtracted to obtain the correction deviation vector of the grayscale sampling sequence; Based on the correction deviation vector and the preset reference interpolation sequence, spatial trend fitting is performed on the pixel coordinate set to obtain the spatial correction coefficients of the pixel coordinate set. Based on the spatial correction coefficients and the reference interpolation sequence, the consistency score of the grayscale sampling sequence is calculated, wherein the formula for calculating the consistency score is: ； In the formula, For the consistency score, It is an exponential function. The sequence number of the verification bearer bit. The total number of the verification bits. The first of the correction deviation vectors One element, The spatial correction coefficient is... The x-coordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The x-coordinate value of each check bit. The ordinate coefficient of the spatial correction coefficient in the pixel coordinate set. For the pixel coordinate set, the first The ordinate value of each check bit. For the first reference interpolation sequence One element, This is the preset allowable deviation benchmark.

6. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the timeliness determination module performs a status determination on the detection date of the target chromatographic test strip based on the card-specific information to obtain the timeliness identifier of the target chromatographic test strip, it is specifically used for: The card-specific information is analyzed for field separators to obtain the validity period code field of the card-specific information; Perform a number system mapping on the validity period code field to obtain the validity period time value of the validity period code field; Read the current time count of the target chromatographic test strip and reconstruct the current time count by year, month and day to obtain the current date value of the target chromatographic test strip; The validity period value is compared digit by digit with the current date value to obtain the determination result of the current date value; Based on the determination result, the validity level of the card-specific information is defined to obtain the timeliness identifier of the target chromatography test strip.

7. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the standard request module executes an encrypted remote standard request to the cloud of the target chromatographic test strip based on the timeliness identifier to obtain the dedicated detection standard for the target chromatographic test strip, it is specifically used for: Based on the timeliness identifier, the background perturbation of the target chromatographic test strip is quantified to obtain the noise amplitude sequence of the target chromatographic test strip; The noise amplitude sequence is obfuscated and spliced ​​with the timeliness identifier to obtain the noise obfuscation request data of the target chromatographic test strip; The noise obfuscation request data is sent to the cloud of the target chromatography test strip three times consecutively, and the cloud response latency of the noise obfuscation request data is recorded. Based on the cloud response latency, the transmission time of the noise obfuscation request data is determined to obtain the valid request data of the noise obfuscation request data. The cloud response data of the valid request data is parsed to obtain the encrypted data packet of the valid request data. The encrypted data packet is XORed bit by bit with the noise amplitude sequence to obtain the dedicated detection standard for the target chromatography test strip.

8. The portable fluorescence immunochromatographic test strip imaging system as described in claim 7, characterized in that, When the standard request module performs a transmission time determination on the noise-obfuscated request data based on the cloud response latency to obtain valid request data for the noise-obfuscated request data, it is specifically used for: The variance of the noise amplitude sequence is estimated by performing volatility statistics on the noise amplitude sequence. Based on the preset scaling parameters, the variance estimate is adaptively adjusted to obtain the attenuation coefficient of the cloud response latency; Based on the attenuation coefficient, the matching energy value of the cloud response latency is calculated, wherein the formula for calculating the matching energy value is: ； In the formula, For the first Matching energy value of the noise-obfuscated request data. The index number of the noise amplitude sequence. The order in which the noise obfuscation request data is sent. The length of the noise amplitude sequence. The noise amplitude sequence is the first... Each noise amplitude, The attenuation coefficient is... For the first Cloud response latency for noise-obfuscated data requests. The noise amplitude sequence is the first... Reference time offset for each noise amplitude; The matching energy values ​​are numerically compared to obtain the maximum value of the matching energy values, and the noise-obfuscated request data of the maximum value is taken as the valid request data.

9. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, The concentration analysis module, when performing quantitative fluorescence intensity analysis on the detection line image based on the detection standard to obtain the analyte concentration in the detection line image, and performing threshold comparison on the analyte concentration to obtain the detection result of the detection line image, is specifically used for: The detection line light intensity of the detection line image is obtained by performing longitudinal grayscale projection analysis on the detection line image. Perform grayscale analysis on the blank area of ​​the detection line image to obtain the average grayscale value of the background of the detection line image; Based on the mean gray value of the background, the background contribution of the detection line light intensity is removed to obtain the net light intensity of the detection line sub-image; Based on the detection standard, the net light intensity is subjected to concentration interpolation mapping to obtain the concentration of the analyte in the detection line image, and the concentration of the analyte is compared with the judgment threshold in the detection standard to obtain the detection result of the detection line image.

10. The portable fluorescence immunochromatographic test strip imaging system as described in claim 1, characterized in that, When the encrypted upload module encrypts and encapsulates the card-specific information, the concentration of the analyte, and the detection result, and uploads the encrypted data to the cloud, it is specifically used for: The serial number in the card-specific information is compressed to obtain the fingerprint summary of the target chromatographic test strip; The card-specific information, the concentration of the analyte, and the detection result are fused together, and based on the fingerprint digest, the fused data is replaced byte by byte to obtain the encrypted data block of the target chromatography test strip; A header timing appender is added to the encrypted data block to obtain the encrypted data frame of the encrypted data block; The encrypted data frame is transmitted to the cloud, and an acknowledgment signal is received from the cloud.

Images