A method and system for facial comparison based on adenoid features

Abstract

The present invention belongs to the field of image processing technology, and discloses a facial comparison method and system based on adenoid features; the method and system comprise: collecting data related to OSA disease of a child group to obtain corresponding facial information; performing data preprocessing on the collected facial information to obtain a corresponding initial facial image set and adenoid evaluation index data; performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; and at the same time, performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoid evaluation data to obtain a corresponding facial representation vector set; constructing a corresponding feature recognition model based on the obtained facial feature vector set and the facial representation vector set, and performing facial comparison on the children to be compared based on the feature recognition model to obtain a corresponding facial comparison result; the present invention contributes to improving the quality of medical services.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more particularly to a face comparison method and system based on adenoid features. Background Art

[0002] With the development of biometric technology, facial recognition technology has been widely used in security, finance, medical and other fields.

[0003] However, existing facial recognition technologies mainly rely on the overall features of the face, such as the position and shape of the eyes, nose, and mouth, while ignoring the features of the adenoids (such as earlobes, nostrils, etc.); and most facial recognition technologies are based on external facial features, such as eyes, nose, and mouth; these methods ignore the internal structure of the face, especially the characteristics of the adenoids, which may lead to limited recognition accuracy; and there are many limitations in the field of facial auxiliary diagnosis of OSA patients; in view of this, the present invention proposes a facial comparison method and system based on adenoid features to solve the above problems. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions:

[0005] A face comparison system based on adenoid features, comprising:

[0006] A data collection module is used to collect OSA disease-related information of a group of children and obtain corresponding facial information, wherein the facial information includes a facial image set and facial medical data;

[0007] A data processing module is used to perform data preprocessing on the collected facial information to obtain a corresponding initial facial image set and adenoids evaluation index data;

[0008] a feature extraction module for performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; and also for performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set;

[0009] The facial comparison module is used to construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results.

[0010] Furthermore, the process of collecting data related to OSA disease in children and obtaining corresponding facial information includes:

[0011] The data acquisition module is provided with a plurality of acquisition nodes; facial images of a group of children aged 3-14 years who have been diagnosed with OSA disease by standard polysomnography and a group of children aged 3-14 years who have not been diagnosed with OSA disease are respectively acquired based on the acquisition nodes to obtain corresponding facial image sets, wherein the facial image sets are composed of facial images corresponding to the plurality of child groups;

[0012] At the same time, the collection node is also used to collect medical data corresponding to the group of children diagnosed with OSA disease to obtain corresponding facial medical data; summarize the obtained facial medical data and facial image collection to obtain corresponding facial information and store the data.

[0013] Furthermore, the process of performing data preprocessing on the collected facial information to obtain a corresponding initial facial image set and adenoids evaluation index data includes:

[0014] The data preprocessing module includes an image preprocessing unit and a medical preprocessing unit; the image preprocessing unit is used to perform image preprocessing on a facial image set in facial information, and the process of obtaining a corresponding initial facial image set includes:

[0015] Arbitrarily read a facial image and perform grayscale conversion on it to obtain a corresponding facial grayscale image, and obtain the grayscale value corresponding to each pixel in the corresponding facial grayscale image;

[0016] Decomposing the corresponding facial grayscale image by pixels to obtain high-frequency components and low-frequency components of the corresponding facial image in different decomposition directions;

[0017] Obtaining a high-frequency component corresponding to the last decomposition of the corresponding facial image, obtaining the grayscale value corresponding to each pixel in the corresponding high-frequency component and calculating an average value, replacing the original pixel value in each pixel in the corresponding high-frequency component based on the calculated average value to obtain a corresponding decomposed image; and recombining the high-frequency component and the low-frequency component in the pixel decomposition process and the decomposed image to obtain a corresponding enhanced grayscale image, and converting the enhanced grayscale image into a color space to obtain a corresponding first facial image;

[0018] Identifying the eye area in the corresponding first facial image based on a face detection algorithm, and marking the pixel points corresponding to the center of the left eye area and the right eye area as a left pixel point and a right pixel point, respectively;

[0019] Obtaining pixel coordinates of a corresponding left point of a pixel and a pixel point within the first facial image, constructing an image transformation matrix based on the coordinates, performing image multiplication on the image transformation matrix and the corresponding first facial image, and marking the first facial image after the image multiplication as an enhanced facial image;

[0020] Performing facial region recognition on the corresponding enhanced facial image, and performing region interception on the recognized facial region to obtain the corresponding initial facial image;

[0021] performing image preprocessing on other facial images in the corresponding facial image set based on the acquisition process of the initial facial image to obtain the corresponding initial facial image and aggregating the images to obtain the corresponding initial facial image set;

[0022] The medical pre-processing unit is used to pre-process the collected facial medical data to obtain the corresponding adenoids evaluation index, including:

[0023] Based on the collected medical facial data, the corresponding age groups of children are obtained. The diagnostic indicators corresponding to the disease are used to construct corresponding adenoids evaluation indicators based on the disease; the adenoids evaluation indicators include the lip-face angle, the distance between the nasal floor and the maxillary sinus floor, Corner and Angle and other related indicators; Among them, due to the corresponding The adenoid characteristics of the disease are different in different stages of illness, so the characteristics of adenoids in children of different age groups are different. There are some differences in the adenoids assessment indicators corresponding to different diseases.

[0024] Furthermore, the formula for pixel decomposition of the corresponding facial grayscale image is: Where, Represents the normalization factor, which is a fixed constant and is used to adjust the output value of the corresponding decomposition process to ensure that the grayscale value of the decomposed pixel maintains an appropriate dynamic range; represents the pre-selected filter, and Represents the application of the filter in the horizontal and vertical directions respectively; Represents the pixel points in the original facial grayscale image In the The image information corresponding to the second decomposition; Indicates that after After decomposition, the pixel The pixel component corresponding to the location (i.e. grayscale value); Indicates the total number of decomposition times; 1 indicates the corresponding facial image;

[0025] The image transformation matrix ;

[0026] Where, ; ;in, Represents a scale factor, which is used in the image transformation process to determine the scale of the corresponding first facial image; represents the pixel coordinates of the corresponding pixel point in the first facial image; ; represents a first facial image;

[0027] Where, Indicates the rotation angle; and Respectively represent the pixel coordinates of the corresponding pixel left point and pixel point in the first face image.

[0028] Furthermore, the process of performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set includes:

[0029] Constructing a wavelet filter bank, and performing image decomposition on each initial facial image in the corresponding initial facial image set based on the constructed wavelet filter bank to obtain response images at different scales and directions; and constructing a corresponding image energy matrix based on the response images;

[0030] Flatten the obtained pixel energy matrix to obtain the corresponding first eigenvector;

[0031] At the same time, feature points of the corresponding initial facial image are extracted to obtain facial feature points corresponding to the corresponding initial facial image;

[0032] Obtain pixel coordinates of corresponding pixels of the facial feature points in the corresponding initial facial image, and based on the pixel coordinates, obtain Euclidean distances between different facial feature points, and based on the pixel coordinates, obtain multidimensional geometric features of the corresponding initial facial image;

[0033] Obtaining all first eigenvectors and multidimensional geometric features corresponding to the corresponding initial facial image respectively; and performing data classification on the corresponding first eigenvectors and multidimensional geometric features based on a pre-built data classifier, and obtaining weight parameters assigned by the data classifier to the corresponding first eigenvectors and multidimensional geometric features during the classification process;

[0034] Based on the weight parameters, the top ranked The first eigenvector and multidimensional set feature in the ranking are marked as weighted eigenvector and weighted geometric feature respectively; is a fixed constant;

[0035] Normalizing the corresponding weighted feature vectors and weighted geometric features, constructing corresponding row vector features based on the normalized weighted feature vectors and weighted geometric features, and performing feature fusion to obtain the corresponding facial feature vector;

[0036] The facial feature vectors corresponding to all the initial facial images are counted to obtain a corresponding facial feature vector set.

[0037] Furthermore, the process of constructing a wavelet filter bank includes:

[0038] Select the Gaussian function as the window function and define the kernel function of the corresponding filter based on it Where represents the standard deviation of the Gaussian factor corresponding to the Gaussian function; a and b represent the horizontal and vertical coordinates of the pixel point in the response image respectively;

[0039] Then, the scale and direction of the corresponding kernel function are changed to obtain filters of different scales and directions;

[0040] Kernel function of the corresponding filter after scale change Where, represents the translation parameter; Represents the scale parameter, which controls the width of the Gaussian function

[0041] The kernel function of the corresponding filter after the direction change ; and represents the spatial frequency parameter;

[0042] Obtain the filters corresponding to different scales and directions, and obtain the corresponding wavelet filter banks based on them;

[0043] The formula for image decomposition is: Where, Indicated on scale and direction Corresponding pixel position in the response image Pixel value of pixel at location; z=(a,b); Where, Represents the corresponding scale and direction The wave vector of the corresponding plane; Indicates the maximum frequency of the corresponding filter; Indicated on scale The spatial factor in the spatial domain; Refers to the scale factor of the window function.

[0044] Furthermore, the process of extracting local features from the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain the corresponding facial representation vector set includes:

[0045] Reading the obtained adenoids evaluation index; and obtaining facial feature points related to the adenoids face of the target child based on the obtained adenoids evaluation index;

[0046] Based on the multi-dimensional geometric features and the acquisition process of the first feature vector, a local feature vector and a local geometric feature corresponding to the corresponding local facial image are acquired;

[0047] Performing feature fusion on the local feature vector and the local geometric feature to obtain a corresponding facial representation vector; the facial representation vector is used to represent the image features of the corresponding local facial image;

[0048] All the obtained facial representation vectors are counted to obtain a corresponding facial representation vector set.

[0049] Furthermore, the process of constructing a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set includes:

[0050] Obtaining facial feature vectors and facial representation vectors corresponding to the corresponding initial facial images, and constructing corresponding feature triples based thereon, and then obtaining feature triplets corresponding to all initial facial images, and constructing corresponding training data sets based thereon;

[0051] The basic architecture of the feature recognition model is defined as an improved convolutional neural network, wherein the basic structure of the improved convolutional neural network is an input layer, a convolution layer, a pooling layer, and an output layer;

[0052] The input layer is used to receive the initial facial image in the training data and perform image scaling processing on the corresponding initial facial image so that it meets the requirements of the improved convolutional neural network;

[0053] The convolution layer is used to perform convolution processing on the initial facial image after image scaling processing based on the deployed convolution kernel; the pooling layer is used to perform pooling processing on the output feature map corresponding to the convolution layer; the output layer is used to synthesize the extracted features after the pooling processing of a fully connected layer and output them effectively;

[0054] The loss function of the feature recognition model is defined as: Where, Represents the total number of training samples in the training data set input into the feature recognition model; is the index variable of the training sample; Indicates the The feature recognition model output results of training samples; Indicates the training labels for training samples;

[0055] The formula for the convolution process is: Where, Represents the number of layers; and Respectively represent Layer and Layer and The output feature map corresponding to the channels; represents the pre-selected activation function; Indicates the and The connection weights between channels;

[0056] The formula for the pooling process is: Where, and Respectively represent the first floor The output feature map corresponding to the channels; represents the bias within the corresponding layer; Represents the downsampling function operation;

[0057] The corresponding feature recognition model is iteratively trained based on the training data set until the loss function of the corresponding feature recognition model tends to converge, and the model parameters are saved, thus completing the training of the feature recognition model.

[0058] Furthermore, the process of performing facial comparison on the child to be compared based on the feature recognition model and obtaining corresponding facial comparison results includes:

[0059] Based on the collected facial information, the age of the corresponding child is obtained; and the facial representation vector and facial feature vector corresponding to the corresponding child are obtained by combining the facial representation vector set and the facial feature vector set; based on the age of the corresponding child, the facial representation vector and the facial feature vector are arranged in time series.

[0060] Based on the facial representation vector and the facial feature vector arranged after the time series features, a corresponding tree bifurcation map is constructed, wherein the tree bifurcation map includes a first-level bifurcation point, a second-level bifurcation point, and a third-level bifurcation point; the first-level bifurcation point is used to store the time series information of the corresponding child; the second-level bifurcation point is used to store the facial representation vector; and the third-level bifurcation point is used to store the facial feature vector;

[0061] Then, a facial image of the child to be compared is obtained and image preprocessed to obtain an initial facial image of the corresponding child to be compared; and the initial facial image of the child to be compared is input into the constructed feature recognition model to obtain a corresponding feature recognition result, wherein the feature recognition result includes a facial representation vector and a facial feature vector corresponding to the corresponding child to be compared;

[0062] At the same time, the age of the corresponding child to be compared is obtained, and based on it, the corresponding feature recognition result is input into the first-level bifurcation point corresponding to the corresponding age and the adjacent age. Then, the facial representation vector and facial feature vector in the corresponding feature recognition result are similar to the facial representation vector and facial feature vector stored in all the second-level bifurcation points and third-level bifurcation points connected to the corresponding first-level bifurcation point, and the similarity is calculated and sorted. The second-level bifurcation point and third-level bifurcation point corresponding to the facial representation vector and facial feature vector with the highest similarity are selected as the quasi-output node; whether the facial representation vector and facial feature vector in the corresponding quasi-output node are disease facial representation vectors and disease facial feature vectors is obtained; if not, it indicates that the corresponding child to be compared does not have If the disease is abnormal, the output comparison result is normal; if it is, it indicates that the corresponding child to be compared has abnormal characteristics. If the disease-related disease has abnormal characteristics, the output comparison result will be abnormal;

[0063] At the same time, the facial representation vector and facial feature vector stored in the corresponding quasi-output node are fed back as data.

[0064] Furthermore, a facial comparison method based on adenoid features includes:

[0065] Step 1: Children's Collecting disease-related information to obtain corresponding facial information, including facial image sets and facial medical data;

[0066] Step 2: Preprocess the collected facial information to obtain the corresponding initial facial image set and adenoids evaluation index data;

[0067] Step 3: performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; at the same time, performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set;

[0068] Step 4: Construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results.

[0069] The technical effects and advantages of the face comparison method and system based on adenoid features of the present invention are as follows:

[0070] 1. It can arrange the facial representation vector and facial feature vector of the child according to their age, and then construct a tree-like bifurcation map; It provides strong support for early detection and intervention of diseases;

[0071] 2. Through the comprehensive processing of facial information and adenoids assessment data, key features related to adenoids can be extracted and a feature recognition model can be constructed for facial comparison; compared with traditional diagnostic methods, this method can more accurately identify patients with It can help children with abnormal features related to the disease to reduce misdiagnosis and missed diagnosis, thereby improving the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 Schematic diagram of a facial comparison system based on adenoid features of the present invention;

[0073] Figure 2 Schematic diagram of a facial comparison method based on adenoid features of the present invention. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0075] Example 1

[0076] See also Figure 1 As shown, this embodiment provides a face comparison system based on adenoid features, including:

[0077] A data collection module is used to collect OSA disease-related information of the children group and obtain corresponding facial information, which includes facial image collection and facial medical data;

[0078] A data processing module is used to perform data preprocessing on the collected facial information to obtain a corresponding initial facial image set and adenoids evaluation index data;

[0079] a feature extraction module for performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; and also for performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set;

[0080] A facial comparison module is used to construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results;

[0081] The modules are connected via wired and / or wireless means to achieve data transmission between modules.

[0082] It should be further explained that, in the specific implementation process, the process of collecting data related to OSA disease in children and obtaining corresponding facial information includes:

[0083] The data collection module is equipped with several collection nodes, which are connected to the medical databases of multiple medical institutions based on network ports;

[0084] The collection node is based on the network port to collect data from the corresponding medical institutions for patients diagnosed with Children aged 3-14 years and those not confirmed as The facial images of the diseased children aged 3-14 years old are collected to obtain a corresponding facial image set, which is composed of facial images corresponding to several groups of children, including diseased facial images and normal facial images; among them, the patients diagnosed as The disease facial images of children aged 3-14 years old with the disease; The group of children aged 3-14 years with the disease corresponds to the normal face image;

[0085] At the same time, the collection node is used to The medical data corresponding to the diseased child group is collected to obtain the corresponding facial medical data; the obtained facial medical data and facial image collection are aggregated to obtain the corresponding facial information and store the data.

[0086] It should be further explained that, in a specific implementation process, the process of preprocessing the collected facial information to obtain the corresponding initial facial image set and adenoids evaluation index data includes:

[0087] The data preprocessing module includes an image preprocessing unit and a medical preprocessing unit; the image preprocessing unit is used to perform image preprocessing on the facial image set in the facial information to obtain a corresponding initial facial image set; the medical preprocessing unit is used to perform data preprocessing on the collected facial medical data to obtain corresponding adenoids evaluation indicators;

[0088] It should be further explained that, in a specific implementation process, the image preprocessing unit is used to perform image preprocessing on the facial image set in the facial information to obtain the corresponding initial facial image set, including:

[0089] Taking any facial image in the facial image set as an example, grayscale conversion is performed on the corresponding facial image to obtain a corresponding facial grayscale image, and at the same time, the grayscale value corresponding to each pixel in the corresponding facial grayscale image is obtained;

[0090] Then, the corresponding facial grayscale image is pixel-decomposed to obtain the high-frequency component and low-frequency component of the corresponding facial image in different decomposition directions. The formula for pixel-decomposition of the corresponding facial grayscale image is: Where, Represents the normalization factor, which is a fixed constant and is used to adjust the output value of the corresponding decomposition process to ensure that the grayscale value of the decomposed pixel maintains an appropriate dynamic range; represents the pre-selected filter, and Represents the application of the filter in the horizontal and vertical directions respectively; Represents the pixel points in the original facial grayscale image In the The image information corresponding to the second decomposition; Indicates that after After decomposition, the pixel The pixel component (i.e. grayscale value) corresponding to the location; and There is a corresponding correlation between them, which is determined by the filter and downsampling operation of the wavelet transform; it is used to ensure that the information of the original facial grayscale image can be effectively transferred to the new image while maintaining important structural information; Indicates the total number of decomposition times; 1 indicates the corresponding facial image;

[0091] Obtain the high-frequency component corresponding to the last decomposition of the corresponding facial image, obtain the grayscale value corresponding to each pixel in the corresponding high-frequency component and calculate the average value, replace the original pixel value in each pixel in the corresponding high-frequency component based on the average value, and obtain the corresponding decomposed image; then, replace the previous Reconstructing the high-frequency component and the low-frequency component corresponding to the secondary decomposition and the decomposed image to obtain a corresponding enhanced grayscale image, and converting the image into a color space to obtain a corresponding first facial image;

[0092] Then, the eye parts in the corresponding first facial image are identified based on the face detection algorithm, and the pixel points corresponding to the center of the left eye part and the right eye part are marked as the left pixel point and the right pixel point respectively;

[0093] Obtaining pixel coordinates of the left point of the corresponding pixel and the pixel point within the first facial image respectively, constructing an image transformation matrix based thereon, performing image multiplication on the image transformation matrix and the corresponding first facial image, and marking the first facial image after the image multiplication as an enhanced facial image, wherein the image multiplication on the image transformation matrix and the corresponding first facial image serves to perform image correction on the facial region within the corresponding first facial image;

[0094] Performing facial region recognition on the corresponding enhanced facial image, and performing region interception on the recognized facial region to obtain the corresponding initial facial image;

[0095] Based on the acquisition process of the initial facial image, image preprocessing is performed on other facial images in the corresponding facial image set to obtain the corresponding initial facial image and summarize them to obtain the corresponding initial facial image set;

[0096] Among them, the image transformation matrix Where, ; ;in, Represents a scale factor, which is used in the image transformation process to determine the scale of the corresponding first facial image; represents the pixel coordinates of the corresponding pixel point in the first facial image; ; represents a first facial image; Where, Indicates the rotation angle; and Respectively represent the pixel coordinates of the corresponding pixel left point and pixel point in the first facial image;

[0097] It should be further explained that, in a specific implementation process, the medical pre-processing unit is used to pre-process the collected facial medical data to obtain the corresponding adenoids evaluation index, including the following steps:

[0098] Based on the collected medical facial data, the corresponding age groups of children are obtained. The corresponding diagnostic indicators are constructed based on them; the adenoids evaluation indicators include lip-face angle, nose bottom-maxillary sinus bottom distance, Corner and Angle and other related indicators; Among them, due to the corresponding The corresponding adenoid characteristics are different in different stages of the disease, so the characteristics of adenoids in children of different ages are different. There are some differences in the corresponding adenoids assessment indicators.

[0099] It should be further explained that, in a specific implementation process, the process of extracting image features from the obtained initial facial image set and obtaining the corresponding facial feature vector set includes:

[0100] Constructing a wavelet filter bank, and performing image decomposition on each initial facial image in the corresponding initial facial image set based on the constructed wavelet filter bank to obtain response images at different scales and directions; and constructing a corresponding image energy matrix based on the response images, where each matrix element of the image energy represents the pixel energy distribution of the corresponding response image at the corresponding scale and direction;

[0101] The obtained pixel energy matrix is subjected to matrix flattening to obtain a corresponding first eigenvector; wherein the first eigenvector is used to represent the texture features of the corresponding image at different scales and directions corresponding to the corresponding initial facial image; matrix flattening refers to converting a multidimensional matrix into a one-dimensional array, and each element in the corresponding one-dimensional array is the corresponding first eigenvector;

[0102] Get pre-built Library, The library is used to provide a pre-trained model, which is used to extract key points of facial features in the corresponding initial facial image; wherein, the construction process of the DLIB library is prior art and will not be elaborated in detail in the present invention;

[0103] Based on the pre-trained model provided by the DLIB library, feature points of the corresponding initial facial image are extracted to obtain the facial feature points corresponding to the corresponding initial facial image;

[0104] Obtain pixel coordinates of corresponding pixels of facial feature points in the corresponding initial facial image, and based on the pixel coordinates, obtain Euclidean distances between different facial feature points, and based on the pixel coordinates, obtain multidimensional geometric features of the corresponding initial facial image; the multidimensional geometric features refer to Euclidean distances and angles between different facial feature points;

[0105] All first eigenvectors and multidimensional geometric features corresponding to the corresponding initial facial image are obtained respectively; and data classification is performed on the corresponding first eigenvectors and multidimensional geometric features based on a pre-constructed data classifier, and at the same time, weight parameters assigned by the data classifier to the corresponding first eigenvectors and multidimensional geometric features during the corresponding classification process are obtained; wherein the data classifier refers to a classification model constructed based on the XGboost algorithm, and the corresponding construction process is prior art and will not be elaborated in detail in the present invention;

[0106] Based on the weight parameters, get the top ranking The first eigenvector and multidimensional set feature in the ranking are marked as weighted eigenvector and weighted geometric feature respectively; is a fixed constant;

[0107] Furthermore, the corresponding weighted feature vectors and weighted geometric features are normalized, and corresponding row vector features are constructed based on the normalized weighted feature vectors and weighted geometric features, and feature fusion is performed to obtain corresponding facial feature vectors for representing the corresponding initial facial image; wherein each initial facial image corresponds to multiple facial feature vectors;

[0108] Counting facial feature vectors corresponding to all initial facial images to obtain a corresponding facial feature vector set;

[0109] It should be further explained that, in the specific implementation process, the process of constructing the wavelet filter bank includes:

[0110] Select the Gaussian function as the window function and define the kernel function of the corresponding filter based on it Where represents the standard deviation of the Gaussian factor corresponding to the Gaussian function; a and b represent the horizontal and vertical coordinates of the pixel point in the response image respectively;

[0111] Then, the scale and direction of the corresponding filter kernel function are changed to obtain filters of different scales and directions;

[0112] Kernel function of the corresponding filter after scale change Where, represents the translation parameter; Represents the scale parameter, which controls the width of the Gaussian function;

[0113] The kernel function of the corresponding filter after the direction change ; and represents the spatial frequency parameter;

[0114] Obtain the filters corresponding to different scales and directions, and obtain the corresponding wavelet filter banks based on them;

[0115] It should be further explained that, in a specific implementation, the process of extracting local features from the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain the corresponding facial representation vector set includes:

[0116] The obtained adenoids evaluation index is read; and based on the obtained adenoids evaluation index, facial feature points related to characterizing the adenoid face of the target child are obtained. It should be further explained that, in the specific implementation process, since the adenoids themselves are not part of the face, but lymphatic tissue located in the nasopharynx, the facial features of the adenoids are usually characterized by the correlation between the jaw, nose, lips, and other facial parts of the corresponding child. For example: The angle is formed by the center of the sella turcica, the nasion, and the upper alveolar seat. This angle reflects the anterior-posterior position of the maxilla relative to the skull. Therefore, the facial feature points to be acquired are the center of the sella turcica, the nasion, and the upper alveolar seat.

[0117] Then, based on the facial feature points corresponding to the adenoids evaluation index, a partial facial image is captured from the corresponding initial facial image to obtain a corresponding partial facial image;

[0118] Based on the process of obtaining the multidimensional geometric features and the first feature vector, a local feature vector and a local geometric feature corresponding to the corresponding local facial image are obtained. It should be further explained that, in a specific implementation, the local geometric feature is determined by the adenoids evaluation index involved in the corresponding local facial image. For example, if the adenoids evaluation index corresponding to the local facial image is the SNA angle, the corresponding local geometric feature is determined by the Euclidean distance and the angle between the three facial feature points: the center of the sella turcica, the nasion point, and the superior alveolar seat point.

[0119] Then, the local feature vector and the local geometric feature are subjected to feature fusion to obtain a corresponding facial representation vector; the facial representation vector is used to represent the image features of the corresponding local facial image;

[0120] Counting all the obtained facial representation vectors to obtain a corresponding facial representation vector set;

[0121] It should be further explained that, in the specific implementation process, the facial representation vector includes a disease facial representation vector and a normal facial representation vector; the facial feature vector includes a disease facial feature vector and a normal facial feature vector.

[0122] It should be further explained that, in a specific implementation process, the process of constructing a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set includes:

[0123] Obtaining facial feature vectors and facial representation vectors corresponding to the corresponding initial facial images, and constructing corresponding feature triples based thereon, and then obtaining feature triplets corresponding to all initial facial images, and constructing corresponding training data sets based thereon;

[0124] The basic architecture of the feature recognition model is defined as an improved convolutional neural network. The basic structure of the improved convolutional neural network is the input layer, convolution layer, pooling layer and output layer.

[0125] The input layer is used to receive the initial facial image in the training data and perform image scaling processing on the corresponding initial facial image so that it meets the requirements of the improved convolutional neural network;

[0126] The convolution layer is used to perform convolution processing on the initial facial image after image scaling based on the deployed convolution kernel; the pooling layer is used to perform pooling processing on the output feature map corresponding to the convolution layer; the output layer is used to synthesize the extracted features after the pooling processing of a fully connected layer and output them effectively;

[0127] The loss function of the feature recognition model is defined as: ; Where N represents the total number of training samples in the training data set input into the feature recognition model; d is the index variable of the training sample; Indicates the The feature recognition model output results of training samples; Indicates the training labels for training samples;

[0128] The formula for convolution processing is: ; In the formula, cs represents the number of layers; and Respectively represent the cs layer and the cs-1 layer and The output feature map corresponding to each channel; f() represents the pre-selected activation function, which is used to transform the linear fit; Indicates the and The connection weights between channels;

[0129] The formula for pooling is: Where, and Respectively represent the first floor The output feature map corresponding to the channels; represents the bias of the channel in the corresponding layer; Represents the downsampling function operation;

[0130] The training data set is divided into P3 training data subsets, and the training data subsets are planned as sequence data according to the order of historical data collection time points; AdaGrad is defined as the optimizer to continuously optimize the parameters of the feature recognition model during the training process, and the sequence data is input into the feature recognition model in batches according to time, and the corresponding loss function value is recorded. When the continuous When the value of the batch loss function no longer decreases or changes, the parameters of the feature recognition model at this time are saved, and the training of the feature recognition model is completed. Among them, L and P3 are fixed constants;

[0131] It should be further explained that, in the specific implementation process, the process of performing facial comparison on the children to be compared based on the feature recognition model and obtaining the corresponding facial comparison results includes:

[0132] Based on the collected facial information, the age of the corresponding child and the corresponding facial image are obtained; the facial representation vector set and the facial feature vector set are combined to obtain the facial representation vector and facial feature vector corresponding to the corresponding child; and based on the age of the corresponding child, the corresponding facial representation vector and facial feature vector are arranged in time series.

[0133] It should be further explained that when the corresponding facial feature vectors and facial representation vectors are arranged in time series, the age of the corresponding child is used as the first constraint condition. The younger the age, the earlier the time series of the corresponding facial representation vector and facial feature vector. If different facial representation vectors are in the same time period, they are classified.

[0134] Based on the facial representation vector and facial feature vector arranged after the time series features, a corresponding tree bifurcation map is constructed, wherein the tree bifurcation map includes a first-level bifurcation point, a second-level bifurcation point, and a third-level bifurcation point; the first-level bifurcation point is used to store the time series information of the corresponding child (i.e., the child's age); the second-level bifurcation point is used to store the facial representation vector; and the third-level bifurcation point is used to store the facial feature vector;

[0135] Then, a facial image of the child to be compared is obtained and image preprocessed to obtain an initial facial image of the corresponding child to be compared; and the initial facial image of the child to be compared is input into the constructed feature recognition model to obtain a corresponding feature recognition result, which includes a facial representation vector and a facial feature vector corresponding to the corresponding child to be compared;

[0136] At the same time, the age of the corresponding child to be compared is obtained, and based on the age, the corresponding feature recognition result is input into the first-level bifurcation point corresponding to the corresponding age and the adjacent age, and then the facial representation vector and facial feature vector in the corresponding feature recognition result are similar to the facial representation vector and facial feature vector stored in all the second-level bifurcation points and third-level bifurcation points connected to the corresponding first-level bifurcation point. The facial representation vector and facial feature vector stored in the second-level bifurcation point and the third-level bifurcation point with the highest similarity are selected as the quasi-output node; whether the facial representation vector and facial feature vector in the corresponding quasi-output node are disease facial representation vectors and disease facial feature vectors is obtained; if not, it indicates that the corresponding child to be compared does not have abnormal disease characteristics related to OSA disease, and the output comparison result is normal; if so, it indicates that the corresponding child to be compared has abnormal disease characteristics related to OSA disease, and the output comparison result is abnormal;

[0137] At the same time, the facial representation vector and facial feature vector stored in the corresponding quasi-output node are fed back as data;

[0138] This invention integrates advanced data acquisition, processing, feature extraction, and comparison technologies to achieve efficient and accurate identification of childhood OSA. This not only helps improve the quality of medical services but also provides valuable data support for related research and clinical practice.

[0139] Example 2

[0140] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of Example 1. A face comparison method based on adenoid features is provided, comprising:

[0141] Step 1: Collect data related to OSA disease in children to obtain corresponding facial information, which includes facial image collection and facial medical data;

[0142] Step 2: Preprocess the collected facial information to obtain the corresponding initial facial image set and adenoids evaluation index data;

[0143] Step 3: performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; at the same time, performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set;

[0144] Step 4: Construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results.

[0145] Example 3

[0146] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned adenoid feature-based facial comparison method and system operation mode are implemented.

[0147] Since the electronic device described in this embodiment is an electronic device used to implement a facial comparison method and system based on adenoid features in the embodiments of this application, based on the facial comparison method and system based on adenoid features described in the embodiments of this application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiments of this application will not be described in detail here. As long as those skilled in the art implement the electronic device used by the facial comparison method and system based on adenoid features in the embodiments of this application, they are within the scope of protection of this application.

[0148] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0149] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that for users of ordinary skill in the art, various improvements and modifications that do not depart from the principles of the present invention are also within the scope of protection of the present invention.

Claims

1. A facial comparison system based on adenoid features, comprising: Data collection module for children Collecting disease-related information to obtain corresponding facial information, including facial image sets and facial medical data; A data processing module is used to perform data preprocessing on the collected facial information to obtain a corresponding initial facial image set and adenoids evaluation index data; a feature extraction module for performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; and also for performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set; A facial comparison module is configured to construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results; The process of obtaining facial comparison results includes: Based on the collected facial information, the age and facial image of the corresponding child are obtained; and the facial representation vector and facial feature vector corresponding to the corresponding child are obtained by combining the facial representation vector set and the facial feature vector set; and based on the age of the corresponding child, the facial representation vector and the facial feature vector are arranged in time series. Based on the facial representation vector and the facial feature vector arranged after the time series features, a corresponding tree bifurcation map is constructed, wherein the tree bifurcation map includes a first-level bifurcation point, a second-level bifurcation point, and a third-level bifurcation point; the first-level bifurcation point is used to store the time series information of the corresponding child; the second-level bifurcation point is used to store the facial representation vector; and the third-level bifurcation point is used to store the facial feature vector; Obtaining a facial image of the child to be compared and performing image preprocessing on the image to obtain an initial facial image of the corresponding child to be compared; inputting the initial facial image into the constructed feature recognition model to obtain a corresponding feature recognition result, wherein the feature recognition result includes a facial representation vector and a facial feature vector corresponding to the corresponding child to be compared; At the same time, the age of the corresponding child to be compared is obtained, and based on it, the corresponding feature recognition result is input into the first-level bifurcation point corresponding to the corresponding age and the adjacent age, and the facial representation vector and facial feature vector in the corresponding feature recognition result are similar to the facial representation vector and facial feature vector stored in all the second-level bifurcation points and third-level bifurcation points connected to the corresponding first-level bifurcation point. The facial representation vector and facial feature vector stored in the second-level bifurcation point and the third-level bifurcation point with the highest similarity are selected as the quasi-output node; whether the facial representation vector and facial feature vector in the corresponding quasi-output node are disease facial representation vectors and disease facial feature vectors is obtained; if not, it indicates that the corresponding child to be compared does not have If the disease is abnormal, the output comparison result is normal; if it is, it indicates that the corresponding child to be compared has abnormal characteristics. If the disease-related disease has abnormal characteristics, the output comparison result will be abnormal; At the same time, the facial representation vector and facial feature vector stored in the corresponding quasi-output node are fed back as data.

2. The face comparison system based on adenoid features according to claim 1, characterized in that: For children The process of collecting disease-related information and obtaining corresponding facial information includes: The data acquisition module is provided with a plurality of acquisition nodes; based on the acquisition nodes, the patient is diagnosed as Children aged 3-14 years and those not confirmed as Collecting facial images of a group of children aged 3-14 years with a disease to obtain a corresponding facial image set, wherein the facial image set is composed of facial images corresponding to a plurality of child groups; At the same time, the collection node is also used to The medical data corresponding to the diseased child group is collected to obtain the corresponding facial medical data; the obtained facial medical data and facial image collection are aggregated to obtain the corresponding facial information and store the data.

3. The face comparison system based on adenoid features according to claim 2, characterized in that: The process of preprocessing the collected facial information to obtain the corresponding initial facial image set and adenoids evaluation index data includes: The data preprocessing module includes an image preprocessing unit and a medical preprocessing unit; the image preprocessing unit is used to perform image preprocessing on a facial image set in facial information, and the process of obtaining a corresponding initial facial image set includes: Arbitrarily read a facial image and perform grayscale conversion on it to obtain a corresponding facial grayscale image, and obtain the grayscale value corresponding to each pixel in the corresponding facial grayscale image; Decomposing the corresponding facial grayscale image by pixels to obtain high-frequency components and low-frequency components of the corresponding facial image in different decomposition directions; Obtaining a high-frequency component corresponding to the last decomposition of the corresponding facial image, obtaining the grayscale value corresponding to each pixel in the corresponding high-frequency component and calculating an average value, replacing the original pixel value in each pixel in the corresponding high-frequency component based on the calculated average value to obtain a corresponding decomposed image; and recombining the high-frequency component and the low-frequency component in the pixel decomposition process and the decomposed image to obtain a corresponding enhanced grayscale image, and converting the enhanced grayscale image into a color space to obtain a corresponding first facial image; Identifying the eye area in the corresponding first facial image based on a face detection algorithm, and marking the pixel points corresponding to the center of the left eye area and the right eye area as a left pixel point and a right pixel point, respectively; Obtaining pixel coordinates of a corresponding left point of a pixel and a pixel point within the first facial image, constructing an image transformation matrix based on the coordinates, performing image multiplication on the image transformation matrix and the corresponding first facial image, and marking the first facial image after the image multiplication as an enhanced facial image; Performing facial region recognition on the corresponding enhanced facial image, and performing region interception on the recognized facial region to obtain the corresponding initial facial image; performing image preprocessing on other facial images in the corresponding facial image set based on the acquisition process of the initial facial image to obtain the corresponding initial facial image and aggregating the images to obtain the corresponding initial facial image set; The medical pre-processing unit is used to pre-process the collected facial medical data to obtain the corresponding adenoids evaluation index, including: Based on the collected medical facial data, the corresponding age groups of children are obtained. The diagnostic indicators corresponding to the disease are constructed, and the corresponding adenoids evaluation indicators are constructed based on them.

4. The face comparison system based on adenoid features according to claim 3, characterized in that: The formula for pixel decomposition of the corresponding facial grayscale image is: Where, represents the normalization factor; represents the pre-selected filter, and Represents the application of the filter in the horizontal and vertical directions respectively; Represents the pixel points in the original facial grayscale image In the The image information corresponding to the second decomposition; Indicates that after After decomposition, the pixel The pixel component corresponding to the location; Indicates the total number of decomposition times; 1 indicates the corresponding facial image; The image transformation matrix ; Where, ; ;in, represents the scale factor; represents the pixel coordinates of the corresponding pixel point in the first facial image; ; represents a first facial image; Where, Indicates the rotation angle; and Respectively represent the pixel coordinates of the corresponding pixel left point and pixel point in the first face image.

5. The face matching system based on adenoid features according to claim 3, characterized in that: The process of extracting image features from the obtained initial facial image set to obtain a corresponding facial feature vector set includes: Constructing a wavelet filter bank, and performing image decomposition on each initial facial image in the corresponding initial facial image set based on the constructed wavelet filter bank to obtain response images at different scales and directions; and constructing a corresponding image energy matrix based on the response images; Flatten the obtained pixel energy matrix to obtain the corresponding first eigenvector; At the same time, feature points of the corresponding initial facial image are extracted to obtain facial feature points corresponding to the corresponding initial facial image; Obtain pixel coordinates of corresponding pixels of the facial feature points in the corresponding initial facial image, and based on the pixel coordinates, obtain Euclidean distances between different facial feature points, and based on the pixel coordinates, obtain multidimensional geometric features of the corresponding initial facial image; Obtaining all first eigenvectors and multidimensional geometric features corresponding to the corresponding initial facial image respectively; and performing data classification on the corresponding first eigenvectors and multidimensional geometric features based on a pre-built data classifier, and obtaining weight parameters assigned by the data classifier to the corresponding first eigenvectors and multidimensional geometric features during the classification process; Based on the weight parameters, the top ranked The first eigenvector and multidimensional set feature in the ranking are marked as weighted eigenvector and weighted geometric feature respectively; is a fixed constant; Normalizing the corresponding weighted feature vectors and weighted geometric features, constructing corresponding row vector features based on the normalized weighted feature vectors and weighted geometric features, and performing feature fusion to obtain the corresponding facial feature vector; The facial feature vectors corresponding to all the initial facial images are counted to obtain a corresponding facial feature vector set.

6. The face comparison system based on adenoid features according to claim 5, characterized in that: The process of constructing a wavelet filter bank includes: Select the Gaussian function as the window function and define the kernel function of the corresponding filter based on it Where Indicates the standard deviation of the Gaussian factor corresponding to the Gaussian function; and Respectively represent the horizontal and vertical coordinates of the pixel points in the response image; Change the scale and direction of the corresponding kernel function to obtain filters of different scales and directions; Kernel function of the corresponding filter after scale change Where, represents the translation parameter; represents the scale parameter; The kernel function of the corresponding filter after the direction change is ; and represents the spatial frequency parameter; Obtain the filters corresponding to different scales and directions, and obtain the corresponding wavelet filter banks based on them; The formula for image decomposition is: Where, Indicated on scale and direction Corresponding pixel position in the response image The pixel value of the pixel at ; Where, Represents the corresponding scale and direction The wave vector of the corresponding plane; Indicates the maximum frequency of the corresponding filter; Indicated on scale The spatial factor in the spatial domain; Refers to the scale factor of the window function; and Refers to the scale and direction corresponding to the corresponding filter.

7. The face matching system based on adenoid features according to claim 3, characterized in that: The process of extracting local features from the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain the corresponding facial representation vector set includes: Reading the obtained adenoids evaluation index; and obtaining facial feature points related to the adenoids face of the target child based on the obtained adenoids evaluation index; Based on the multi-dimensional geometric features and the acquisition process of the first feature vector, a local feature vector and a local geometric feature corresponding to the corresponding local facial image are acquired; Performing feature fusion on the local feature vector and the local geometric feature to obtain a corresponding facial representation vector; the facial representation vector is used to represent the image features of the corresponding local facial image; All the obtained facial representation vectors are counted to obtain a corresponding facial representation vector set.

8. The face matching system based on adenoid features according to claim 3, characterized in that: The process of constructing a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set includes: Obtaining facial feature vectors and facial representation vectors corresponding to the corresponding initial facial images, and constructing corresponding feature triples based thereon; obtaining feature triplets corresponding to all initial facial images, and constructing corresponding training data sets based thereon; The basic architecture of the feature recognition model is defined as an improved convolutional neural network, wherein the basic structure of the improved convolutional neural network is an input layer, a convolution layer, a pooling layer, and an output layer; The input layer is used to receive the initial facial image in the training data and perform image scaling processing on the corresponding initial facial image; The convolution layer is used to perform convolution processing on the initial facial image after image scaling processing based on the deployed convolution kernel; the pooling layer is used to perform pooling processing on the output feature map corresponding to the convolution layer; the output layer is used to synthesize the extracted features after the pooling processing of a fully connected layer and output them effectively; The loss function of the feature recognition model is defined as: Where, Represents the total number of training samples in the training data set input into the feature recognition model; is the index variable of the training sample; Indicates the The feature recognition model output results of training samples; Indicates the training labels for training samples; The formula for the convolution process is: Where, Represents the number of layers; and Respectively represent Layer and Layer and The output feature map corresponding to the channels; represents the pre-selected activation function; Indicates the and The connection weights between channels; The formula for the pooling process is: Where, and Respectively represent the first floor The output feature map corresponding to the channels; represents the bias within the corresponding layer; Represents the downsampling function operation; The corresponding feature recognition model is iteratively trained based on the training data set until the loss function of the corresponding feature recognition model tends to converge, and the model parameters are saved, thus completing the training of the feature recognition model.

9. A facial comparison method based on adenoid features, which is implemented based on the facial comparison system based on adenoid features according to any one of claims 1 to 8, characterized in that: include: Step 1: Children's Collecting disease-related information to obtain corresponding facial information, including facial image sets and facial medical data; Step 2: Preprocess the collected facial information to obtain the corresponding initial facial image set and adenoids evaluation index data; Step 3: performing image feature extraction on the obtained initial facial image set to obtain a corresponding facial feature vector set; at the same time, performing local feature extraction on the corresponding initial facial image set in combination with the obtained adenoids assessment data to obtain a corresponding facial representation vector set; Step 4: Construct a corresponding feature recognition model based on the obtained facial feature vector set and facial representation vector set, and perform facial comparison on the children to be compared based on the feature recognition model to obtain corresponding facial comparison results.

Images