170 results about "Age estimation" patented technology

To improve a safety of a driving by a person of advanced age without imposing a burden on the driver.

An age estimation device, based on a facial image photographed by a photographing device, estimates an age of a driver. An inattentiveness detection device sets conditions of detecting an inattentiveness to be laxer in order that it becomes easier to detect the inattentiveness as the driver's age rises. In the event that the driver's age is of an advanced age group, an obstacle detection warning unit accelerates a timing of warning of an approximation to an obstacle, an other vehicle detection warning unit accelerates a timing of warning of an approximation to another vehicle, a cornering control unit, when the vehicle itself turns right, controls a cornering in such a way that the vehicle itself passes through a trajectory outside a normal one, and a left and right check warning unit gives a warning when the driver does not make a left and right check at an intersection. The invention can be applied to a driving support apparatus.

The present invention discloses a multi-task learning convolutional neural network (CNN)-based face attribute analysis method. According to the method, based on a convolutional neural network, a multi-task learning method is adopted to carry out age estimation, gender identification and race classification on a face image simultaneously. In a traditional processing method, when face multi-attribute analysis is carried out, a plurality of times of calculation are required, and as a result, time can be wasted, and the generalization ability of a model is decreased. According to the method of the invention, three single-task networks are trained separately; the weight of a network with the lowest convergence speed is adopted to initialize the shared part of a multi-task network, and the independent parts of the multi-task network are initialized randomly; and the multi-task network is trained, so that a multi-task convolutional neural network (CNN) model can be obtained; and the trained multi-task convolutional neural network (CNN) model is adopted to carry out age, gender and race analysis on an inputted face image simultaneously, and therefore, time can be saved, and accuracy is high.

The invention relates to an intelligent individuation video advertisement pushing method which comprises the steps that advertisement putting site image information is collected and stored; the advertisement putting site image information is subjected to face detecting; face detecting comprises the steps that various human faces are recognized in the advertisement putting site image information, and face images of various human faces and the human face number in image information in a certain time period are obtained; the advertisement putting site image information is subjected to face tracking; face tracking comprises the steps that the process that a certain human face watches an advertisement in the advertisement putting site image information is tracked, so that the time interval of advertisement watching of the human face in the advertisement putting site image information is obtained; according to face tracking results, human faces of different people are subjected to gender identification and age estimation, the gender and age information of each person is obtained, and according to the gender and age information, the advertisement audience is sorted; and a recommending decision algorithm is used for generating divided-period advertisement recommending lists for various advertisement terminals.

The invention discloses a deeper layer network constructing method used for gender identification or age estimation based on human face. The method includes a step (101) dividing all training pictures into a plurality of groups; (102) extracting high layer features of a group of pictures based on a convolution neural network and thereby obtaining a first matrix composed of the high layer feature vectors, and extracting low layer and global features of the same group of the training images based on an artificial neural network and thereby obtaining a second matrix composed of the low layer feature vectors, obtaining a group of gender identification or age estimation results based on the extract first matrix, the second matrix and the defined judgment formula, wherein the values of a first weight matrix W1, a second weight matrix w2, an offset matrix b and an adjusting weight beta in the defined judgment formula are updated by utilizing an error back propagation algorithm and the final values of the parameters are obtained and the network construction is completed. Judgment of age and gender of a human face is performed based on the judgment formula determined according to the values of the parameters when the network construction is completed.

Age-estimation of a face of an individual is represented in image data. In one embodiment, age-estimation techniques involves combining a Contourlet Appearance Model (CAM) for facial-age feature extraction and Support Vector Regression (SVR) for learning aging rules in order to improve the accuracy of age-estimation over the current techniques. In a particular example, characteristics of input facial images are converted to feature vectors by CAM, then these feature vectors are analyzed by an aging-mechanism-based classifier to estimate whether the images represent faces of younger or older people prior to age-estimation, the aging-mechanism-based classifier being generated in one embodiment by running Support Vector Machines (SVM) on training images. In an exemplary binary youth/adult classifier, faces classified as adults are passed to an adult age-estimation function and the others are passed to a youth age-estimation function.

The present invention is a system and method for estimating the age of people based on their facial images. It addresses the difficulty of annotating the age of a person from facial image by utilizing relative age (such as older than, or younger than) and face-based class similarity (gender, ethnicity or appearance-based cluster) of sampled pair-wise facial images. It involves a unique method for the pair-wise face training and a learning machine (or multiple learning machines) which output the relative age along with the face-based class similarity, of the pairwise facial images. At the testing stage, the given input face image is paired with some number of reference images to be fed to the trained machines. The age of the input face is determined by comparing the estimated relative ages of the pairwise facial images to the ages of reference face images. Because age comparison is more meaningful when the pair belongs to the same demographics category (such as gender and ethnicity) or when the pair has similar appearance, the estimated relative ages are weighted according to the face-based class similarity score between the reference face and the input face.

An age assessment method based on face recognition technology is a method capable of considering affects on age estimation caused by race, sex, latitude (region), rural-urban difference. The method of using face recognition technology to estimate age has vast applicability and improves accuracy of age estimation observably. The method is based on an effective hypothesis, that is people with similar appearance has similar facial features at different ages, when estimating ages, just comparing the face image to be estimated with face image of different ages with higher appearance similarity, finding numbers of face images at different ages has highest appearance similarity with the object being estimated, proceeding weighted average to infer age of the object being estimated.

The invention provides a method for automatically portioning a hair area, relating to the technical field of a hair partitioning method and belonging to the field of computer vision. The method comprises the following steps of: step 1, detecting the face: using a face detection module for detecting the face position from one input face picture by using a trained cascade classifier; step 2, marking target background marks: using a target background marking module to line out the interested area, and finding out the most possible target mark and the background mark according to position and color characteristics; and step 3, image partitioning: according to the target background marks, using an image partitioning module to partition the hair area and output the hair area. The method provided by the invention uses the image processing technology to perform face detection, target background marking, image partitioning and the like to an input image, and output the hear area in the image. The method can accurately detect the hair area under complicated background conditions, which provides good basis to the research and application of identity recognition, gender and age estimation, image retrieval and the like.

The invention provides a face automatic aging mechanism based on a conditional generative adversarial network. A conditional generative adversarial network consisting of four parts is obtained by training a large number of images of different age groups marked with ages, and the conditional generative adversarial network comprises an image generator G, an image discriminator D, an age estimation network AEN and an identity recognition network FRN. Wherein G is trained to generate an aged image, and the aged image is automatically and effectively generated by inputting the young image and a preset age condition. And D, identifying whether the generated old image is a real image or not, and ensuring that the generated old image has deception. Wherein the AEN is used for reducing the difference between the age of the generated image and a preset value, and the FRN is used for ensuring the consistency of portrait identities in the generation process. Through the design of the network structure, end-to-end training of the whole network is achieved, face aging is well shown, and high-quality face aging images with the advantages of identity consistency, high cheating performance, high resolution and the like can be generated.

The invention provides a face attribute recognition method based on a combined depth neural network. The method comprises the following steps: S1, performing area extraction on an inputted face image;S2, carrying out positioning on a facial important part and extracting a related area based on the area extraction result to obtain facial area features and facial key part features; S3, marking a real age and a gender of each face by using the area extraction result as a training sample, carrying out training based on a deep neural network, and outputting an age estimation value and a gender recognition result; and S4, on the basis of the facial area features outputted by the S2 and local area features of eyes and mouths, outputting expression and wearing prediction probabilities respectively according to a random forest algorithm, adding probabilities of corresponding attributes for different attributes, and outputting facial expression and wearing attribute results. In addition, the invention also provides a face attribute recognition apparatus based on a combined depth neural network.

The invention discloses a face age estimation method performing measurement learning based on a convolutional neural network. The method comprises the overall steps that a dataset is constructed; thedataset is divided into a training set and a verification set; paired construction is performed on mini-batches on a network input layer, and then the mini-batches are sent into two twin networks fortraining; a VGG-16 network is constructed; network training is performed; softmax loss and revised contrastive loss are jointly used as supervisory signals to perform network adjustment; network evaluation is performed; and the finally estimated age is a maximum probability corresponding category obtained on a softmax layer. According to the method, deep learning and measurement learning are combined; by introducing measurement learning, the distinction degree of a feature space is higher, and therefore the robustness of an age estimation algorithm is higher; and deep learning is utilized to combine a feature extraction task and an objective function optimization task, end-to-end training is realized for the whole task, and good performance can be obtained when the method is applied to a public dataset.

The invention discloses a face image age evaluation method based on the convolutional neural network (CNN). According to the traditional age identification technology, a training sample only corresponds to one age label, so relationships among adjacent ages are neglected. According to the method based on the convolutional neural network, each sample corresponds to multiple age labels, so an age estimation model acquired through training can be more precise. The method comprises steps that firstly, face detection, face key point detection, face alignment and image cutting for inputted images are carried out; secondly, modeling for an age aging process is carried out, and probability of each apparent age is calculated and is stored to form an age distribution table; thirdly, the aligned face images are utilized in combination with the age distribution table and a target function to train the CNN network; lastly, the trained CNN network can be utilized to carry out age estimation on the inputted face images.

The invention is a method for searching new positions of human face feature points by 2D outline in the field of image processing technique, comprising the steps of: (1) making human face detection on the given image and obtaining position coordinates of a human face region; (2) locating two eyes in the found human face region to find their positions; (3) calculating the coordinates of the midpoint of the two eyes, the distance between them, and the angle of the connection line of them; (5) making affine transformation on initial position of ASM model to obtain an initial model; (6) using the initial model as an initial position of ASM search and using 2D outline to make feature point location. It can be further applied to human face recognition, sex recognition, expression recognition, age estimation and other aspects and has higher accuracy.

The present invention is directed to a context-based image retrieval (CBIR) system for disease estimation based on the multi-atlas framework, in which the demographic and diagnostic information of multiple atlases are weighted and fused to generate an estimated diagnosis, on a structure-by-structure basis. The present invention demonstrates high accuracy in age estimation, as well as diagnostic estimation in Alzheimer's disease. The system and the pathology-based multi atlases can be used to estimate various types of disease and pathology with the choice of patient attributes. The present invention is also directed to a method of context-based image retrieval.

The invention belongs to the technical field of convolutional neural networks, and provides a face image age estimation method, device and terminal equipment. The method includes building a convolutional neural network model including a potential factorization layer; initializing the convolutional neural network model; inputting preprocessed images to the initialized convolutional neural network model, and training the initialized convolutional neural network model through a counterpropagation method based on an age loss function according to the preprocessed images; and inputting a face image to be detected to the trained convolutional neural network model, and outputting the age of the face in the face image to be detected. The potential factorization layer decomposes features of the image into components related with age which need to be obtained and related components unrelated with age, so training and detection can be performed based on the components related with age, so that the convolutional neural network model has relatively good robustness.

The invention discloses an age estimation method based on a multi-output convolution neural network and ordered regression. The method comprises the following steps of 1, establishing an Asian face age data set (AFAD); 2, establishing training data used for a dichotomy; 3, training a depth convolution neural network; 4, inputting a test sample into a trained convolution neural network; and 5, acquiring age estimation of the test sample. The invention provides a method of sorting the ages. The ordered regression and a deep learning method are combined so that accuracy of age prediction performance is greatly increased. In an existing age estimation method, characteristic extraction and regression modeling are performed independently and optimization is insufficient. By using the method of the invention, the above problems are solved; a sequence relation of age labels can be fully used to carry out ordered regression of age estimation; age estimation accuracy is increased; a large scale database is established for the age estimation of the Asian faces and a database basis is provided for face age estimation research. The method can be widely used for age estimation of face images.

The invention discloses a soft double-layer age estimation method based on facial image fusion features. The method includes the first step of obtaining a facial image to be estimated, the second step of preprocessing the facial image, the third step of extracting fusion features x, the fourth step of judging whether the soft double-layer age estimation method exists, if yes, going to the sixth step, and if not, going to the fifth step, the fifth step of learning the soft double-layer age estimation method, extracting fusion features of training images, dividing the training images into two stages, conducting learning to obtain a binary classifier F(x), setting an overlapping area at the age boundary, expanding the age range in each stage and conducting learning to obtain regression models Y(x) and A(x), the sixth step of inputting the fusion features x into the soft double-layer age estimation method, using the binary classifier F(x) to conduct classification first, and then selecting to apply the regression model Y(x) or A(x) according to a classification result to obtain an estimated age value y, and the seventh step of conducting correction processing on the estimated age value.

The invention discloses a facial image age estimation method based on a three-level residual error network, belongs to the field of data processing technology and aims to increase the facial image age estimation level under a non-limited condition. According to the technical scheme, the method comprises the steps that first, the three-level residual error network is established on the basis of a basic residual error network framework; second, the three-level residual error network is adopted to perform pre-training on an ImageNet dataset to obtain an ImageNet residual error network model; third, fine-tuning training is performed on the obtained ImageNet residual error network model on a facial age dataset under the non-limited condition; and last, the three-level residual error network obtained after fine-tuning training is utilized to perform facial image age estimation. According to the method, the three-level residual error network is adopted to realize facial image age estimation, the learning ability of a DCNN network model is greatly improved, the problems of over-fitting and gradient disappearance in the training process are well solved, and therefore the accuracy of facial image age estimation under the non-limited condition is improved.

The invention discloses a people stream analysis method based on binocular vision. The analysis method comprises steps of stereo image obtaining; image preprocessing; face detection; human body positioning; counting of visitors and visit time, gender identification and age estimation; finishing people stream analysis in a set visit region around an exhibition stand. The analysis method can be applied to all kinds of public exhibition places like museums and related information of visitors in front of all exhibition products in a public exhibition place is acquired and analyzed, so an objective of people stream counting and analysis is achieved; the analysis method is characterized by high real-time performance, high precision and high implementation efficiency; and the method facilitates actually knowing of action characteristics of visitors, and provides a reliable data basis for all kinds of analysis, thereby facilitating improvement of self service quality and level of the public exhibition place.

The invention discloses a human age estimation method based on self-adaptation sign distribution. According to the method, through a self-adaptation training method combined with the application of an age sign distribution model algorithm, the obtained facial image feature vectors and initial age sign distribution are used as inputs, the KL divergence between the input initial age sign distribution and model prediction sign distribution is minimized by applying the age sign distribution model algorithm, and therefore the prediction age sign distribution can be obtained. Then, the prediction age sign distribution of the same age can be used for studying the age sign distribution of the corresponding age, circulation is carried out until training convergence is achieved or the set largest number of times is reached, and then the final prediction model can be obtained. Facial image features to be estimated are input into the final prediction model, and then the prediction age can be output. The age estimation accuracy of the system can reach the level similar to that of the human.

The invention provides a brain disease detection system based on brain pathological age estimation. The brain disease detection system comprises image acquisition equipment, actual age input equipment, a storer, a preprocessing module, a feature extraction module, a feature selection module, a brain pathological age estimation module, a parameter optimization module, a classified recognition module and a result output module; the storer is provided with a VCI sample database, a CTL sample database and a database to be measured. The brain disease detection system has the advantages that the system fully utilizes brain magnetic resonance image characteristics, in combination with the actual age information of samples, simulation training is conducted through a great number of samples, and the obtained brain pathological age estimation module can effectively estimate the brain pathological age of a measured object; meanwhile, deviation between the brain pathological age estimation value and the actual age serves as supplementary information, whether a patient suffers from brain disease or not is effectively diagnosed through infusion with brain image information, the whole system is definite in principle, convenient to implement, more scientific basis is achieved for brain disease detection, reliability is high, and feasibility is high.

The embodiments of the invention disclose a training method and device of a voiceprint model, a storage medium and electronic equipment, and belong to the technical field of computers. The method includes the following steps that an age estimation result is obtained from age estimation of user voice data, according to a voiceprint general model corresponding to the age estimation result, the model is trained to obtain a voiceprint personal model of a user, and voiceprint wake-up is realized by using different voiceprint personal models for users of different ages. According to the training method of the voiceprint model, the obtained voiceprint personal model is related to the user age, and according to the voiceprint personal model for voiceprint wake-up, wake-up accuracy can be improved.

The embodiment of the invention provides an establishing method and an establishing device for an artery blood vessel age estimation model, relating to the technical field of cardiovascular disease monitoring. The method comprises the following steps: collecting the reference artery blood vessel age, physiological signals and individual information of sample users; for each sample user, carrying out weighted feature acquiring operation according to the gender, namely, carrying out feature extraction according to the physiological signals and the individual information, carrying out normalization processing on the features, thus obtaining normalization features, calculating the weight coefficient of each feature according to the correlation coefficient of each feature and the reference artery blood vessel age, calculating the weighted feature of each feature according to the normalization feature and the weight coefficient; and by adopting the weighted features and the reference arteryblood vessel age of each sample user as sample data, training a neural network, thus obtaining the artery blood vessel age estimation model. The embodiment of the invention is accurate in estimation and suitable for family medical treatment, and can provide useful physiological parameters for family health.