An image-based scleral icter analysis method

Abstract

This invention discloses an image-based method for analyzing scleral jaundice, relating to the field of image recognition technology. The method includes the following steps: S1, image data acquisition; S2, scleral region segmentation; S3, color feature extraction of the scleral region; S4, jaundice severity assessment based on color features; S5, health assessment of the jaundice level; and S6, long-term health monitoring based on the health assessment. By combining datasets from a cloud computing platform with image feature extraction technology, more multi-dimensional information is incorporated into the model training process. Using a multi-feature support vector machine (SVM) model based on image features and historical disease data, this method not only considers the features of a single image but also incorporates the patient's historical data, enabling the model to more comprehensively reflect the patient's jaundice trends. This effectively improves the prediction accuracy of jaundice severity and avoids the problem of poor performance of traditional SVM methods under complex data conditions.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, specifically to an image-based method for analyzing scleral jaundice. Background Technology

[0002] Jaundice is a pathological phenomenon caused by abnormal bilirubin metabolism, typically manifesting as yellowing of the sclera, skin, and other tissues. The detection of scleral jaundice has long been an important research direction in the medical field. Currently, visual analysis-based diagnostic methods for scleral jaundice largely rely on the subjective experience of physicians. However, due to individual differences in the severity of jaundice and variations in the image acquisition environment, traditional methods often have certain limitations. Therefore, image-based scleral jaundice analysis methods have become a research hotspot for improving diagnostic accuracy and automation.

[0003] Existing image analysis technologies mainly rely on image feature extraction and machine learning algorithms, such as support vector machines (SVM) and deep learning, for the automated assessment of jaundice levels. By extracting features such as color and texture from scleral images through image processing techniques and combining them with machine learning models, quantitative analysis of jaundice can be achieved. However, existing technologies still have certain shortcomings in some aspects, especially in terms of the accuracy and real-time performance of jaundice analysis models.

[0004] While Support Vector Machines (SVMs) have achieved some success in image classification, they still face challenges in predicting jaundice severity, particularly in terms of classification accuracy and generalization ability. Existing SVM models often rely on manually extracted image features and are typically limited to relatively simple linear classification problems. As the complexity of jaundice image features increases, SVM models struggle to provide accurate classification results when dealing with nonlinear features. Furthermore, SVMs are highly sensitive to hyperparameter selection; different kernel functions and regularization parameters can affect model performance, leading to inconsistencies in performance across different patients and imaging conditions. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an image-based method for analyzing scleral jaundice, thereby resolving the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide an image-based method for analyzing scleral jaundice, comprising the following steps:

[0008] S1. Image data acquisition: Using a high-definition camera, image data of the eye is acquired to obtain an image of the eye;

[0009] S2. Segmenting the scleral region: Analyze the eye image and segment the scleral region based on the shape, color, and brightness information of the eye;

[0010] S3. Extract color features from the scleral region: Convert the image of the scleral region into the HSV color space to intuitively represent the hue, saturation, and brightness of the image, thereby obtaining the color features of the scleral region.

[0011] S4. Assess jaundice severity using color features: Based on color features, a support vector machine model is set up to quantitatively assess the jaundice level of the sclera and output the jaundice grade.

[0012] S5. Conduct a health assessment based on the jaundice level: Based on the jaundice level and combined with the patient's historical disease history data, conduct a health assessment and generate a health assessment result;

[0013] S6. Long-term health monitoring based on health assessment: Based on the health assessment results, a real-time monitoring system is established to use the color characteristics of the patient's sclera images and the health assessment results for long-term tracking and dynamic monitoring to obtain monitoring data.

[0014] To further optimize this technical solution, the support vector machine model in step S4 is specifically a support vector machine model based on color space transformation and multi-feature fusion, wherein the formula is:

[0015] ;

[0016] in, : The predicted degree of jaundice, indicating the jaundice classification label;

[0017] The weight vector of a support vector machine represents the weighting coefficients of the model for each input feature;

[0018] Input feature vector, containing the patient's current position at the current time. Image data features;

[0019] Bias terms in the SVM model control the offset of the decision plane;

[0020] : Symbolic function, used to represent linear combinations Convert to discrete category labels.

[0021] To further optimize this technical solution, the feature vector input in step S4 represents the features of the current patient's scleral jaundice image, including color features, texture features, and edge features.

[0022] To further optimize this technical solution, in step S4, the support vector machine model is trained based on the training set data to determine the optimal weight vector. and bias terms To maximize the margin between categories during training, the following formula is used:

[0023] .

[0024] To further optimize this technical solution, in step S4, during the training process of the support vector machine model, the support vectors are the training samples closest to the decision boundary. These samples are crucial for the construction of the classification model, and the decision boundary of the model is represented by the following equation:

[0025] .

[0026] To further optimize this technical solution, the usage process of the support vector machine model in step S4 is as follows:

[0027] Feature extraction: Extracting multiple color features and the patient's historical disease course data from images of the scleral region;

[0028] Feature mapping and fusion: Multiple extracted features are mapped to a high-dimensional space through nonlinear mapping and then fused.

[0029] Training the Support Vector Machine: The SVM model is trained using high-dimensional features that have undergone feature fusion and mapping to determine the optimal classification hyperplane;

[0030] Jaundice grade prediction: By using a trained support vector machine model and inputting new image data and the patient's relevant historical data, the model will output the jaundice grade result, providing a basis for subsequent jaundice assessment and monitoring.

[0031] To further optimize this technical solution, the real-time monitoring system in step S6 is set up based on a cloud computing platform, specifically an adaptive adjustment model based on dynamic feature updates, wherein the parameters include:

[0032] The input feature vector contains information about the patient at the current time. Image data features;

[0033] Indicates time The degree of jaundice predicted by the SVM model at any given time, i.e., the degree calculated in step S4. ;

[0034] This indicates a status update based on real-time monitoring data, reflecting the current monitoring status of the system.

[0035] It is a decay factor used in the system to measure time intervals, reflecting the importance of new input data in the decision-making process;

[0036] It is a global patient dataset obtained based on a cloud computing platform, containing historical jaundice data and image data information;

[0037] This indicates the adjustment parameters based on real-time monitoring.

[0038] To further optimize this technical solution, the dynamic monitoring mechanism of the real-time monitoring system in step S6 relies on real-time updated predictive output. and image features The adjustment decision is calculated using the following formula:

[0039] ;

[0040] in:

[0041] Based on the feature vector at the current time Jaundice level and global patient dataset Calculated adjustment value;

[0042] These are the system adjustment parameters from the previous time step.

[0043] To further optimize this technical solution, in step S6... The calculation formula is:

[0044] ;

[0045] : Feature vector based on the current time step Jaundice level Calculated adjustment value;

[0046] Based on global patient dataset The calculated adjustment values ​​include historical jaundice data, image data from other patients, etc.

[0047] and : Weighting coefficient, representing the weight of the current data and global data on the final adjusted value.

[0048] To further optimize this technical solution, the calculation obtained in step S6 is... The usage process includes the following steps:

[0049] Obtain real-time data;

[0050] Calculate the current adjustment parameters;

[0051] Apply adjustment parameters ;

[0052] Feedback and dynamic adjustment;

[0053] Real-time dynamic response.

[0054] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of an image-based scleral jaundice analysis method as described in the first aspect of the present invention.

[0055] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of an image-based scleral jaundice analysis method as described in the first aspect of the present invention.

[0056] Compared with existing technologies, this invention provides an image-based method for analyzing scleral jaundice, which has the following advantages:

[0057] This image-based scleral jaundice analysis method incorporates more dimensional information into the model training process by combining datasets from a cloud computing platform with image feature extraction technology, thereby improving classification accuracy. By using a multi-feature support vector machine model based on image features and historical disease data, this method not only considers the features of a single image but also incorporates the patient's historical data, enabling the model to more comprehensively reflect the patient's jaundice change trend. This multi-feature fusion approach helps capture more complex nonlinear features, improving the model's robustness and generalization ability, thus effectively improving the prediction accuracy of jaundice severity and avoiding the problem of traditional SVM methods performing poorly under complex data conditions. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram of the structure of an image-based scleral jaundice analysis method proposed in this invention;

[0060] Figure 2This is a schematic diagram of the automatic exposure control technology process for an image-based scleral jaundice analysis method proposed in this invention;

[0061] Figure 3 This is a schematic diagram of the jaundice level output process of an image-based scleral jaundice analysis method proposed in this invention;

[0062] Figure 4 This is a schematic diagram illustrating the parameter adjustment process of an image-based scleral jaundice analysis method proposed in this invention. Detailed Implementation

[0063] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0064] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0066] Example 1:

[0067] Reference Figures 1-4 This is the first embodiment of the present invention, which provides an image-based method for analyzing scleral jaundice, including the following steps:

[0068] S1. Image data acquisition: Using a high-definition camera, image data of the eye is acquired to obtain an image of the eye;

[0069] Automatic exposure control technology is used in the process of image acquisition using a high-definition camera to evaluate the brightness information of the current image in real time and dynamically adjust the exposure parameters according to the brightness changes, thereby minimizing the situation of overexposure or underexposure of the image and improving the image acquisition quality.

[0070] The automatic exposure control model is constructed as follows:

[0071] Indicates the coordinates in the image are The pixel brightness value at that location;

[0072] This represents the ideal target brightness value, which is usually preset to a value within a standard brightness range and set according to the requirements of the scleral area;

[0073] This represents the exposure adjustment factor, which is the exposure value that is automatically adjusted through a feedback mechanism;

[0074] It is the sensitivity coefficient for exposure adjustment, which controls the response speed of exposure adjustment, and its value ranges from [0,1].

[0075] It is a weighting coefficient for image brightness changes, used to adjust the relative influence of brightness distribution;

[0076] ;

[0077] in:

[0078] This represents the average brightness of all pixels in the image, i.e., the average brightness of the current image. It is the number of pixels in the image;

[0079] This represents the difference between the average brightness of the current image and the target brightness, determining whether the exposure needs to be increased or decreased.

[0080] This measure indicates the uniformity of image brightness distribution. If the image brightness varies greatly (e.g., there is strong lighting contrast), this value will increase, reflecting the need for more exposure adjustments to adapt to the complex brightness changes in the image.

[0081] Its usage process is as follows:

[0082] Image brightness assessment: First, the brightness distribution of the currently captured image is acquired in real time by the camera, and the average brightness of the image is calculated. ;

[0083] Feedback adjustment: Based on the current average brightness of the image With target brightness The model calculates the exposure adjustment factor based on the difference between the two values. If the image brightness is too low, then A positive value indicates that the exposure needs to be increased; if the image brightness is too high, then... A negative value indicates that exposure needs to be reduced;

[0084] Brightness variation compensation: While adjusting the exposure, the model further compensates for areas with large brightness variations (such as highlights or shadows) by introducing a uniformity index of image brightness distribution, so as to avoid over- or under-exposure adjustment.

[0085] Exposure adjustment implementation: Ultimately, automatic exposure control is achieved by adjusting the camera's exposure settings (such as shutter speed, aperture size, or ISO sensitivity) to ensure that the image brightness reaches the target value. This ensures the clarity and color accuracy of the scleral area.

[0086] S2. Segmentation of the scleral region: The eye image is analyzed, and the scleral region is segmented based on the shape, color, and brightness information of the eye. The segmented image can be used for subsequent jaundice analysis to remove interference from other parts of the eyeball and ensure the accuracy of the analysis results.

[0087] S3. Extract color features from the scleral region: Convert the image of the scleral region into the HSV color space to intuitively represent the hue, saturation, and brightness of the image, thereby obtaining the color features of the scleral region.

[0088] S4. Assess jaundice severity using color features: Based on color features, a support vector machine model is set up to quantitatively assess the jaundice level of the sclera and output the jaundice grade.

[0089] The support vector machine model in step S4 is specifically a support vector machine model based on color space transformation and multi-feature fusion, wherein the formula is:

[0090] ;

[0091] in, : The predicted degree of jaundice, indicating the jaundice classification label;

[0092] The weight vector of a support vector machine represents the weighting coefficients of the model for each input feature;

[0093] Input feature vector, containing the patient's current position at the current time. Image data features;

[0094] Bias terms in the SVM model control the offset of the decision plane;

[0095] : Symbolic function, used to represent linear combinations Convert to discrete category labels;

[0096] The input feature vector in step S4 represents the features of the current patient's scleral jaundice image, including:

[0097] Color characteristics: The color value of the sclera portion in the image;

[0098] Texture features: Texture features extracted through the gray-level co-occurrence matrix reflect detailed information about jaundice;

[0099] Edge features: Scleral contour information obtained by edge detection methods (such as Canny edge detection);

[0100] In step S4, the support vector machine model is trained based on the training set data to determine the optimal weight vector. and bias terms To maximize the margin between categories during training, the following formula is used:

[0101] ;

[0102] In step S4, during the training of the support vector machine model, the support vectors are the training samples closest to the decision boundary. These samples are crucial for the construction of the classification model, and the decision boundary of the model is represented by the following equation:

[0103] ;

[0104] Using this decision boundary, SVM can categorize data into different classes.

[0105] For example, when At that time, it was classified as mild jaundice;

[0106] when At that time, it was classified as severe jaundice;

[0107] when This means that when the patient is at the decision boundary, they are in a state of moderate jaundice. Depending on the changes in the medical context, this may indicate that the patient's jaundice is progressing to severe or is recovering to a mild state.

[0108] The process of using the support vector machine model in step S4 is as follows:

[0109] Feature extraction: Extracting multiple color features and the patient's historical disease course data from images of the scleral region;

[0110] Feature mapping and fusion: Multiple extracted features are mapped to a high-dimensional space through nonlinear mapping and then fused.

[0111] Training the Support Vector Machine: The SVM model is trained using high-dimensional features that have undergone feature fusion and mapping to determine the optimal classification hyperplane;

[0112] Jaundice grade prediction: By using a trained support vector machine model and inputting new image data and the patient's relevant historical data, the model will output the jaundice grade result, providing a basis for subsequent jaundice assessment and monitoring.

[0113] S5. Health assessment based on jaundice level: Based on the jaundice level and combined with the patient's historical disease data, a health assessment is conducted to obtain the health assessment results. By integrating multiple information, we can provide each patient with customized health advice, predict the potential impact of jaundice on their health, and provide corresponding early warning and intervention suggestions according to different jaundice levels.

[0114] S6. Long-term health monitoring based on health assessment: Based on the health assessment results, a real-time monitoring system is established, and the color characteristics of the patient's sclera images are used to conduct long-term tracking and dynamic monitoring with the health assessment results to obtain monitoring data.

[0115] The real-time monitoring system in step S6 is based on a cloud computing platform, specifically an adaptive adjustment model based on dynamic feature updates, wherein the parameters include:

[0116] The input feature vector contains information about the patient at the current time. Image data features;

[0117] Indicates time The degree of jaundice predicted by the SVM model at any given time, i.e., the degree calculated in step S4. ;

[0118] This indicates a status update based on real-time monitoring data, reflecting the current monitoring status of the system.

[0119] It is a decay factor used in the system to measure time intervals, reflecting the importance of new input data in the decision-making process;

[0120] It is a global patient dataset obtained based on a cloud computing platform, containing historical jaundice data and image data information;

[0121] This indicates the adjustment parameters based on real-time monitoring.

[0122] The dynamic monitoring mechanism of the real-time monitoring system in step S6 relies on real-time updated predictive output. and image features The adjustment decision is calculated using the following formula:

[0123] ;

[0124] in:

[0125] Based on the feature vector at the current time Jaundice level and global patient dataset Calculated adjustment value;

[0126] It is the attenuation factor, which controls the importance of new input data; a larger one... New data will have a greater impact on system adjustments, while historical data will be emphasized.

[0127] These are the system adjustment parameters from the previous time step;

[0128] In step S6 The calculation formula is:

[0129] ;

[0130] : Feature vector based on the current time step Jaundice level Calculated adjustment value;

[0131] Based on global patient dataset The calculated adjustment values ​​include historical jaundice data, image data from other patients, etc.

[0132] and Weighting coefficients represent the weights of the current data and global data on the final adjusted value;

[0133] The calculation obtained in step S6 The usage process includes the following steps:

[0134] Obtain real-time data: at every moment The system will acquire image data from the patient's scleral area. And the degree of jaundice was predicted using an SVM model. That is, steps S3 and S4;

[0135] Calculate the current adjustment parameters: obtained through formula. ;

[0136] Apply adjustment parameters ;

[0137] Feedback and dynamic adjustment: Over time, the system continuously updates and adjusts parameters based on image data and jaundice prediction results at each moment. New adjustment parameters This will affect the data acquisition and processing strategy for the next moment. Each new... After calculation, each of these factors will have a direct impact on the system's behavior, thereby ensuring that the monitoring system can adapt to changes in jaundice.

[0138] Real-time dynamic response: In this way, the system can continuously adapt to different changes in the patient's jaundice. Each time new data is acquired, the system... The system updates automatically adjusts image acquisition and processing strategies to ensure the accuracy and timeliness of monitoring.

[0139] Among them, the application adjustment parameters Includes: Image acquisition frequency: if jaundice prediction results In cases of severe jaundice, the system may increase the image acquisition frequency to obtain scleral images of the patient more frequently, ensuring timely capture of changes in jaundice.

[0140] The monitoring system will be based on Determine the interval between image acquisitions for the next acquisition time. Use the following relationship:

[0141] ;

[0142] in, This is the exposure interval adjustment factor;

[0143] Exposure settings: If the current jaundice prediction result shows mild or severe jaundice, the system may need to increase the exposure to ensure that the image quality is clear enough for subsequent analysis;

[0144] The relationship between exposure time and exposure time is as follows:

[0145] ;

[0146] This is the current exposure time. Exposure factor (empirical value). Adjust the exposure time factor;

[0147] Image processing precision: The system may need to adjust the image processing precision depending on the severity of jaundice. For severe jaundice, a more precise image processing algorithm may be required to improve the sensitivity and accuracy of jaundice detection.

[0148] Image processing accuracy at the next moment Depend on Direct impact:

[0149] ;

[0150] This is an adjustment factor for accuracy.

[0151] Example 2:

[0152] This embodiment also provides a computer device applicable to an image-based scleral jaundice analysis method, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the image-based scleral jaundice analysis method proposed in the above embodiment.

[0153] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements an image-based scleral jaundice analysis method as proposed in the above embodiments.

[0154] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0155] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0157] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0158] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0159] 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, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An image-based method for analyzing scleral jaundice, characterized in that, Includes the following steps: S1. Image data acquisition: Using a high-definition camera, image data of the eye is acquired to obtain an image of the eye; Automatic exposure control technology is used in the process of image acquisition using a high-definition camera to evaluate the brightness information of the current image in real time and dynamically adjust the exposure parameters according to the brightness changes, thereby minimizing the situation of overexposure or underexposure of the image and improving the image acquisition quality. The automatic exposure control model is constructed as follows: Indicates the coordinates in the image are The pixel brightness value at that location; This represents the ideal target brightness value, preset to a value within a standard brightness range, and set according to the requirements of the scleral area; This represents the exposure adjustment factor, which is the exposure value that is automatically adjusted through a feedback mechanism; It is the sensitivity coefficient for exposure adjustment, which controls the response speed of exposure adjustment, and its value ranges from [0,1]. It is a weighting coefficient for image brightness changes, used to adjust the relative influence of brightness distribution; ； in: This represents the average brightness of all pixels in the image, i.e., the average brightness of the current image. It is the number of pixels in the image; This represents the difference between the average brightness of the current image and the target brightness, determining whether the exposure needs to be increased or decreased; This measure indicates the uniformity of image brightness distribution. If the image brightness varies significantly, this value will increase, reflecting the need for more exposure adjustments to adapt to the complex brightness changes in the image. Its usage process is as follows: Image brightness assessment: First, the brightness distribution of the currently captured image is acquired in real time by the camera, and the average brightness of the image is calculated. ; Feedback adjustment: Based on the current average brightness of the image With target brightness The model calculates the exposure adjustment factor based on the difference between the two values. If the image brightness is too low, then A positive value indicates that the exposure needs to be increased; if the image brightness is too high, then... A negative value indicates that exposure needs to be reduced; Brightness variation compensation: While adjusting the exposure, the model further compensates for areas with large brightness variations by introducing a uniformity index of image brightness distribution, so as to avoid over- or under-exposure adjustment. Exposure adjustment implementation: Ultimately, automatic exposure control is achieved by adjusting the camera's exposure settings to ensure that the image brightness reaches the target value. This ensures clarity and color accuracy in the scleral area; S2. Segmenting the scleral region: Analyze the eye image and segment the scleral region based on the shape, color, and brightness information of the eye; S3. Extract color features from the scleral region: Convert the image of the scleral region into the HSV color space to intuitively represent the hue, saturation, and brightness of the image, thereby obtaining the color features of the scleral region. S4. Assess jaundice severity using color features: Based on color features, a support vector machine model is set up to quantitatively assess the jaundice level of the sclera and output the jaundice grade. The support vector machine model in step S4 is specifically a support vector machine model based on color space transformation and multi-feature fusion, wherein the formula is: ； in, : The predicted degree of jaundice, indicating the jaundice classification label; The weight vector of a support vector machine represents the weighting coefficients of the model for each input feature; Input feature vector, containing the patient's current position at the current time. Image data features; Bias terms in the SVM model control the offset of the decision plane; : Symbolic function, used to represent linear combinations Convert to discrete category labels; S5. Conduct a health assessment based on the jaundice level: Based on the jaundice level and combined with the patient's historical disease history data, conduct a health assessment and generate a health assessment result; S6. Long-term health monitoring based on health assessment: Based on the health assessment results, a real-time monitoring system is established, and the color characteristics of the patient's sclera images are used to conduct long-term tracking and dynamic monitoring with the health assessment results to obtain monitoring data. The real-time monitoring system in step S6 is based on a cloud computing platform, specifically an adaptive adjustment model based on dynamic feature updates, wherein the parameters include: Indicates time The degree of jaundice predicted by the SVM model at any given time, i.e., the degree calculated in step S4. ; This indicates a status update based on real-time monitoring data, reflecting the current monitoring status of the system. It is a decay factor used in the system to measure time intervals, reflecting the importance of new input data in the decision-making process; It is a global patient dataset obtained based on a cloud computing platform, containing historical jaundice data and image data information; This indicates the adjustment parameters based on real-time monitoring. The dynamic monitoring mechanism of the real-time monitoring system in step S6 relies on real-time updated predictive output. and image features The adjustment decision is calculated using the following formula: ； in: Based on the feature vector at the current time Jaundice level and global patient dataset Calculated adjustment value; It is the attenuation factor, which controls the importance of new input data; a larger one... New data will have a greater impact on system adjustments, while the opposite will emphasize the importance of historical data. These are the system adjustment parameters from the previous time step; In step S6 The calculation formula is: ； : Feature vector based on the current time step Jaundice level Calculated adjustment value; Based on global patient dataset The calculated adjustment values ​​included historical jaundice data and image data from other patients; and Weighting coefficients represent the weights of the current data and global data on the final adjusted value; The calculation obtained in step S6 The usage process includes the following steps: Obtain real-time data: at every moment The system will acquire image data from the patient's scleral area. And the degree of jaundice was predicted using an SVM model. That is, steps S3 and S4; Calculate the current adjustment parameters: obtained through formula. ; Apply adjustment parameters ; Feedback and dynamic adjustment: Over time, the system continuously updates and adjusts parameters based on image data and jaundice prediction results at each moment. New adjustment parameters This will affect the data acquisition and processing strategy in the next moment; each new... After calculation, each of these factors will have a direct impact on the system's behavior, thereby ensuring that the monitoring system can adapt to changes in jaundice. Real-time dynamic response: In this way, the system can continuously adapt to different changes in the patient's jaundice; each time new data is acquired, the system... The system updates automatically adjusts image acquisition and processing strategies to ensure the accuracy and timeliness of monitoring. Among them, the application adjustment parameters This includes: Exposure settings: If the current jaundice prediction result shows mild or severe jaundice, the system needs to increase the exposure to ensure that the image quality is clear enough for subsequent analysis; The relationship between exposure time and exposure time is as follows: ； This is the current exposure time. Exposure factor (empirical value). This is a coefficient used to adjust the exposure time.

2. The image-based scleral jaundice analysis method according to claim 1, characterized in that, The feature vector input in step S4 represents the features of the current patient's scleral jaundice image, including color features, texture features, and edge features.

3. The image-based scleral jaundice analysis method according to claim 1, characterized in that, In step S4, the support vector machine model is trained based on the training set data to determine the optimal weight vector and bias term. To maximize the margin between categories during training, the following formula is used: 。 4. The image-based scleral jaundice analysis method according to claim 1, characterized in that, In step S4, during the training process of the support vector machine model, the support vectors are the training samples closest to the decision boundary. The decision boundary of the model is represented by the following equation: 。 5. The image-based scleral jaundice analysis method according to claim 1, characterized in that, The process of using the support vector machine model in step S4 is as follows: Feature extraction: Extracting multiple color features and the patient's historical disease course data from images of the scleral region; Feature mapping and fusion: Multiple extracted features are mapped to a high-dimensional space through nonlinear mapping and then fused. Training the Support Vector Machine: The SVM model is trained using high-dimensional features that have undergone feature fusion and mapping to determine the optimal classification hyperplane; Jaundice grade prediction: By using a trained support vector machine model and inputting new image data and the patient's relevant historical data, the model will output the jaundice grade result, providing a basis for subsequent jaundice assessment and monitoring.

Images