16 results about "Age classification" patented technology

The invention relates to a lightweight millimeter-wave radar children age classification method based on feature engineering. The method comprises the following steps: acquiring a millimeter-wave radar vital sign data set containing a plurality of children of different ages; extracting a respiratory signal; calculating a plurality of candidate features from the respiratory signal, constructing a candidate feature set, and screening out a key feature subset for children age classification from the candidate feature set; training the lightweight machine learning model to obtain a child age classification model; and processing the input millimeter wave radar signal, and outputting a child age classification result. The method has the beneficial effects that the calculation complexity and the storage overhead of the model are remarkably reduced, so that the high-precision child age classification model can efficiently run on a resource-limited embedded platform.

The invention provides a portrait beautifying real-time processing method based on a deep neural network, and the method comprises the steps: carrying out the age classification processing of a face region in a feature map through an initialized age recognition neural network module, analyzing the face age indication features of the face of a user, judging the age group of the user, and outputting an age classification label; performing differentiation analysis on each face age indication feature according to the age classification label, taking a differentiation analysis result as a weight distribution basis, distributing weight coefficients to different face age indication features according to importance degrees, and obtaining face feature vectors for different age groups; and according to an eye processing strategy in the personalized beautification processing scheme, performing refined processing on the eye region, and adjusting eye contour enhancement strength and color saturation parameters according to the age group of the user to obtain image data subjected to eye beautification processing.

The invention discloses a child neural development evaluation system and method based on a questionnaire of a sentior, and the system comprises a data collection module which is configured to obtain a child neural development behavior feature data set through a multi-source clinical database; a multi-dimensional evaluation module; the standardized evaluation module is configured to call a corresponding evaluation unit according to an age grading rule and perform standardized score conversion based on a norm database; and the result generation module is configured to output a comprehensive diagnosis report containing the three-dimensional evaluation result. Through the data acquisition module, the system can efficiently acquire a child neurodevelopment behavior characteristic data set from a multi-source clinical database, and the comprehensiveness and accuracy of data are ensured. And the standardized evaluation module can call a corresponding evaluation unit according to the age of the child, and performs standardized score conversion by using a norm database. This ensures the objectivity and comparability of the evaluation results, enabling the evaluation results to be effectively compared and analyzed between different children.

The invention discloses an intelligent tea age grading method and device based on deep learning, and relates to the technical field of tea grading, and the method comprises the steps: S1, obtaining a tea image; s2, constructing a lightweight tea classification network; wherein the tea texture sensing module performs parallel extraction by using a parallel multi-scale convolution kernel; the channel attention module performs feature enhancement by using a channel attention mechanism; the multi-dimensional feature extraction module performs feature extraction by using four parallel branches to obtain color features, texture features, morphological features and time sequence features, and fuses the color features, the texture features, the morphological features and the time sequence features; the classification output module outputs the tea age group category of the tea image; s3, training the lightweight tea classification network; and S4, performing age classification evaluation on the tea image by using the trained lightweight tea classification network. According to the method, the tea texture sensing module and the channel attention module are introduced, and time sequence analysis is introduced, so that the method has better recognition precision and adaptability in a tea recognition task.

The application discloses an age classification model generation method, an age classification method and system, and a training method. i Input into a face feature extraction network to obtain a face feature map f i ; the face feature map f i is input into a feature discrimination module D f for first optimization processing; the face feature map corresponding feature vector is input into a first full connection layer for second optimization processing; and iterative training is performed to obtain an age classification model. In terms of training data, the weight setting of data sampling is performed on face images of different age stages, and the data proportion of different age stages is balanced; in model optimization, a feature discrimination module and a ViT module are introduced to reduce the ambiguity information of face images of different age stages, and accurate and stable prediction is realized.

The invention relates to the technical field of artificial intelligence, and discloses an age prediction method and system based on an oral anterior panoramic X-ray film, and the method comprises the steps: obtaining the development stage data of each permanent tooth through the relative fixed space coordinate information of the oral anterior panoramic X-ray film and each permanent tooth through optimized YoloV8; the development stage data of all the permanent teeth are numeralized and then added to obtain the development stage sum Sum of all the permanent teeth, and then the oral cavity normal position panoramic X-ray film and the Sum are transmitted into a classification model TANet to obtain the inference result of the individual age. Compared with the existing age prediction technology, the method has the advantages that the age is classified and predicted by using the learning ability of deep learning, the serious dependence on the Demirjian judgment standard is avoided, the systematic error caused by the Demirjian judgment standard is reduced, and compared with the huge demand of the traditional model on the data quantity, the TANet model is more suitable for the age classification task of the oral orthotopic panoramic X-ray film, and the accuracy of the age classification task of the oral orthotopic panoramic X-ray film is improved. The problem is relieved by using a pre-training model vitb16 and introducing permanent tooth development stage auxiliary reasoning.

The present application relates to the technical field of image processing, in particular to a kind of recycling material quality automatic identification and classification method based on image processing, by detecting old household appliance panel lap joint boundary, extract the mean difference of yellow and blue channel of exposure side and shielding side, construct net yellowing amount difference signal, and take shielding side color as original color reference datum;Combined with the anisotropic characteristics of texture, ABS main body and PP ventilation structure area segmentation is realized, the net yellowing amount of each material and the partition confidence are obtained;Further calculate the cross-material chroma shift direction angle difference to construct degradation path characteristics, form two-dimensional feature vector with net yellowing amount and map to pre-built age characteristic space to complete manufacturing age classification;Through the sufficiency of data determined by coverage index, when the condition is met, output deterministic classification result, otherwise output interval age range and retake guide information.The method improves the accuracy and reliability of identification and classification in multi-material mixed scene.

The invention relates to the technical field of computer vision, in particular to an age identification method and device, computer equipment and a medium. According to the invention, age classification is carried out on the trajectory images in the time sequence trajectory through the human body age classification model, the age classification result of the detection target in each frame of trajectory image and the corresponding prediction confidence are obtained, and then the target result of which the prediction confidence is greater than the confidence threshold is screened out from the age classification results. According to the method, high-confidence aggregation of age classification results is realized, track consistency of track images in a time sequence track is evaluated by determining whether the result number of the target results is greater than a preset first threshold, and when the result number of the target results is greater than the first threshold, the target results are used as age identification results of the detection targets. Compared with an age identification method based on a single-frame image in the prior art, the method has the advantages that the influence of a low-quality track image in the time sequence track on the identification precision of the human body age classification model is reduced, and the purpose of improving the accuracy of an age identification result is achieved.

This invention discloses a method and system for assessing the insulation aging status of high-voltage equipment, relating to the field of high-voltage equipment insulation detection technology. The invention first extracts original image data of high-voltage equipment with different insulation states, aging types, and degrees from historical insulation aging records, constructs a standard sample library, and preprocesses it to obtain standard image features. Then, it collects image features of the equipment to be assessed, compares them with the standard samples to calculate the comprehensive similarity, determines the insulation state, and identifies the aging type. Next, it extracts operating and environmental parameters, analyzes their influence on the target aging type, and calculates a standard influence benchmark value. Then, it combines the similarity and the two benchmark values ​​to comprehensively assess the insulation aging degree, finally classifying the aging level and triggering the corresponding early warning mechanism. This invention, through the fusion assessment of image features and operating environmental parameters, can identify insulation aging types and calculate the aging degree, achieving high-voltage equipment insulation aging classification and accurate early warning.

The present invention belongs to the technical field of image classification, and specifically relates to a generative feature order regularization method for a deep ordered regression model. The present invention maps an input image into a low-dimensional feature representation through a deep convolutional neural network, and calculates the distances between the low-dimensional feature representations of all samples in a batch in the corresponding low-dimensional space; then calculates the distances between the ordered labels of all samples in the batch; normalizes the obtained feature representation distance vectors and label distance vectors between all samples in the batch and other samples respectively; calculates the divergence of the normalized feature vectors and label distance vectors to constrain the distribution of features to be consistent with the distribution of ordered labels in the embedding space, that is, to ensure the orderliness of features; the final loss function of the model includes an ordered regression loss and this KL divergence loss; the method of the present invention helps to improve the classification performance in various task scenarios (such as face age estimation, medical image classification, historical image age classification, etc.).

The embodiments of the present application relate to the technical field of face image recognition, and disclose a training method for an age recognition model, a face age recognition method, and related devices. The trained age recognition model includes an age classification model, an uncertainty model, and an age regression model. In the first stage, the uncertainty model is used to convert the influence of noise interference on the first predicted age value output by the trained age classification model into an uncertainty probability. In the second stage, the training set is used to train the recurrent neural network, and the uncertainty probability corresponding to each face image is introduced into the loss function to obtain an age regression model. The introduction of uncertainty probability is equivalent to telling the age regression model that the features extracted from each face image have a certain probability of uncertainty. Therefore, during the training process, image features with higher uncertainty probabilities need to be studied in depth, which can reduce the impact of the above-mentioned noise and improve the generalization ability and accuracy of the model.

The application relates to a ginseng age nondestructive classification model construction method and a ginseng age nondestructive classification system, in particular to a ginseng growth age classification method based on hyperspectral imaging technology and an improved swarm intelligence optimization algorithm. The method solves the problems of high-dimensional data redundancy, insufficient utilization of atlas features, insufficient model generalization ability and low precision of fine classification of adjacent cultivation ginseng ages in the prior art. The method comprises the following steps: 1. acquiring hyperspectral image data of different ginseng ages and performing pretreatment; 2. screening spectral features and texture features based on the hyperspectral image data; 3. performing feature-level fusion on the spectral features and the texture features to obtain fused features; and 4. inputting the fused features into an IHSO-RF model to perform training and testing. The classification model is embedded in the system to realize the classification of ginseng ages. The application is suitable for intelligent perception and analysis based on hyperspectral imaging and machine vision, nondestructive detection and grading of agricultural products / Chinese herbal medicine quality and the like.

The invention relates to the technical field of deep learning, and discloses an age classification method, an overload detection method and device, computer equipment and a storage medium, and the method comprises the steps: intercepting a whole body image and a half body image of a detection target from a detection image, inputting the whole body image into a whole body age classification model, and obtaining a whole body age classification result. And inputting the half-body image into a half-body age classification model to obtain a half-body age classification result, and fusing the whole-body age classification result and the half-body age classification result to obtain a target age classification result. Visibly, the whole-body age classification result output by the whole-body age classification model and the half-body age classification result output by the half-body age classification model are fused through the joint reasoning strategy to obtain the final target age classification result, so that diversified model input and output are realized; according to the invention, a more accurate age classification result can be obtained based on the detection image shot in a highly dynamic and uncertain environment, and the purpose of improving the age classification precision is achieved.

This application relates to the field of image recognition technology, and in particular to an age recognition model training method, recognition method, device, equipment, and medium. The method constructs a first age classification model and a second age classification model. The second age classification model has the same architecture as the first age classification model, and the parameters in the updated second age classification model are calculated based on the parameters of the updated first age classification model. The second age classification model is used to construct pseudo-labels for unlabeled data. The age classification model is trained using both unlabeled and labeled data, and the model parameters are updated using age labels and pseudo-labels identified by the model for unlabeled data, respectively. This effectively improves the model's age classification accuracy through self-supervised learning by accurately constructing pseudo-labels.

The invention relates to a nuclear power station card aging analysis and maintenance strategy establishment method and system. The method comprises the following steps: acquiring image information of a card; component identification is carried out based on the image information, and all components in the card and component information corresponding to all the components are obtained; determining aging information of the component according to the component information in combination with a maintenance manual of the component; determining the working environment of the card; analyzing and evaluating according to the aging information of the component and the working environment of the card to obtain the predicted life of the card; determining the grade of the card; and determining a maintenance strategy of the card according to the predicted service life of the card and the grade of the card. According to the invention, accurate aging grading and classification management of the card can be realized, key equipment influencing the availability of a unit is guaranteed to be preferentially and strictly managed, stable operation of the unit is realized, the cost of spare parts is saved, meanwhile, the service life of the aged component is analyzed, the service life of the card is evaluated, a maintenance strategy is given, and the reliability of the equipment is improved.

The present invention relates to the field of artificial intelligence technology, and discloses an age prediction method and system based on oral panoramic X-rays. The oral panoramic X-ray and the relatively fixed spatial coordinate information of each permanent tooth are used in an optimized YoloV8 to obtain the developmental stage data of each permanent tooth. The developmental stage data of all permanent teeth are digitized and added to obtain the sum of the developmental stages of all permanent teeth (Sum). The oral panoramic X-ray and Sum are then passed together to a classification model TANet to obtain an inference result of the individual's age. Compared to existing age prediction technologies, the use of deep learning's learning capabilities to classify and predict age avoids heavy reliance on Demirjian's judgment criteria and reduces the systematic errors caused by Demirjian's judgment criteria. Compared with the traditional model's huge demand for data volume, the TANet model is more suitable for the age classification task of oral panoramic X-rays. This problem is alleviated by using the pre-trained model vit_b16 and introducing permanent tooth development stage-assisted reasoning.