29 results about "Face analysis" patented technology

The invention discloses a counterfeited face video detection method based on a regionalized space-time Transform. The method comprises the following steps: constructing a counterfeited face video data set containing real and counterfeited samples; the method comprises the following steps: constructing a fake face video detection network comprising a face analysis and region division module, a region adaptive feature extraction module, a regionalization space-time Transform module, an intra-region feature fusion module and an inter-region feature fusion module; training the detection network using a data set; and utilizing the trained network model to predict true and false labels of the input video sequence. According to the method, spatial-temporal feature differences generated in different areas of a face in a counterfeiting process are utilized, and key links such as feature extraction (adopting area adaptive convolution), spatial-temporal modeling (adopting spatial-temporal Transform with intra-area / inter-area attention) and feature fusion (adopting an intra-area / inter-area fusion mechanism) are penetrated through a regionalized processing strategy; the method aims to overcome the limitation of global analysis, and can detect the fake face video more accurately and robustly.

The present application relates to a kind of face analysis method and system based on self-supervised representation learning, the method includes: 1) obtaining face image from data set, and the face image is preprocessed;2) construct self-supervised local-to-global mask distillation network model to extract general face representation;Wherein, extract visible local feature Token sequence by online local encoder, extract target global feature Token sequence by target global encoder, and predict global feature Token sequence by local-to-global decoder;During model training, the weighted sum of mask loss and distillation loss is calculated, and the parameters of online local encoder are optimized by gradient back propagation, to realize the iterative training of model;3) the trained online local encoder is applied to face analysis, face key point detection, face attribute recognition or face expression recognition task by transfer learning.The method and system are beneficial to more robust, accurate, generalization to obtain the result of face analysis task.

The invention belongs to the technical field of face recognition, and particularly relates to a batch face analysis and comparison method and system. The method comprises the following steps: extracting key features in face data, namely a two-eye pupil distance, and performing batch calculation by utilizing a Hamming distance algorithm according to the two-eye pupil distance in the face data to obtain a plurality of pieces of face data with the highest similarity, and then, on the basis of a plurality of pieces of acquired face data with the highest similarity, performing similarity comparison on all features in the face data by adopting a cosine algorithm, and acquiring the same face data according to a similarity comparison result. The system comprises a face data snapshot module, a key feature extraction module, a face similarity extraction module and a face confirmation module which are connected in sequence. Compared with original batch comparison, the method and the system are faster, more efficient and more intensive.

The invention discloses an image processing method, electronic equipment and a computer readable storage medium, and belongs to the technical field of image processing. The method comprises the steps that a first face analysis graph of a to-be-enhanced image and a second face analysis graph of a reference image are acquired, the definition of the reference image meets a preset image definition condition, and the to-be-enhanced image and the reference image both comprise a first shooting object; determining a first affine transformation matrix for converting the second face analysis graph into the first face analysis graph; acquiring a first contour feature of the reference image; performing affine transformation on the first contour feature according to the first affine transformation matrix to obtain a second contour feature; and obtaining an enhanced image according to the second contour feature, the to-be-enhanced image and the face enhancement model, the definition of the face region in the enhanced image being greater than the definition of the to-be-enhanced image. The second contour feature carries the feature of the image with high definition in the reference image, so that the trueness and definition of the enhanced image can be improved, and the quality of the image is improved.

The present application relates to the technical field of advanced geological prediction, in particular to a kind of advanced geological prediction system based on information fusion of multiple detection methods, comprising comprehensive analysis subsystem, advanced prediction module and notification and statistics module.The comprehensive analysis subsystem includes face analysis module, advanced drilling analysis module and geological radar analysis module.The present application combines stress-strain monitoring, geological radar detection, advanced drilling and other detection methods, improves the adaptability to complex construction environment, improves the intelligent level, realizes the rapid transmission and sharing of geological information;Through logical judgment program, data centralized analysis is carried out, geological abnormal conditions such as rock burst, discontinuous geological structure are found in time during drilling process, so as to output corresponding early warning signal, which provides more definite decision basis for construction personnel.

The present invention discloses an Internet-based face recognition police information tracking platform, which includes a face analysis module, an identity formulation module, a police officer center module and a real-time monitoring module; the face analysis module includes a face information extraction unit, which is used to identify facial feature information of a face and extract and analyze the facial feature information; the identity formulation module is used to formulate an individual's identity based on the facial feature information of the face analysis module; the police officer center module includes an alarm information receiving unit and a police officer dispatch plan formulation unit, which is used for the police officer to predict the processing method and the police force to be dispatched after receiving the alarm information; the real-time monitoring module includes a real-time monitoring unit for movement trajectory and a real-time monitoring unit for the scene of the alarm, and the real-time monitoring module is used to monitor the movement trajectory of the person after face recognition and the scene picture when the alarm occurs.

The invention discloses an intelligent switching method and system for face component structured mask learning, and the method comprises the steps: extracting a portrait mask with an edge perception capability, and reconstructing a high-fidelity background region with spatial continuity through combining a background reconstruction network; generating a standardized face image with geometric consistency by adopting a face detection and posture correction network; generating an optical head portrait with vision and texture consistency; performing structured mask learning on the standardized face image and the optical head image by using a semantic segmentation network to realize pixel-level face analysis; obtaining a multi-component region mask through mask calculation based on morphological operation; generating an optical head portrait with a natural transition effect by using an optical head portrait synthesis module based on Poisson fusion; and generating a hair changing portrait with physical authenticity by using a hair changing portrait synthesis module. According to the method, the visual fidelity, the detail consistency and the identity retentivity of the face image after hair changing are remarkably improved.

A face image local area restoration method based on priori knowledge distillation comprises the following steps: extracting a corresponding face analysis graph from a public data set as priori information, preprocessing the face analysis graph, generating a free occlusion training set, and training a constructed teacher network containing a double-gating convolution coordination attention module, freezing parameters of the trained teacher network, and performing instructive training on the constructed student network; and finally, performing restoration processing on the face image received in real time through the trained student network. According to the method, on the basis of the face prior information, the error accumulation dilemma caused by prediction prior information deviation is ingeniously avoided, the repair accuracy is improved from the source, the long-distance dependency relationship between effective pixels is deeply mined and fully utilized, and under the condition of free shielding, the repair accuracy is improved. The repaired face image is more excellent in structural integrity and semantic coherence, and the gap between the repaired image and the original real image is remarkably reduced.

The present application relates to the technical field of intelligent control of light-emitting mirrors, and discloses a control system of a rotating light-emitting mirror with face recognition, comprising an induction recognition module, a data analysis module, a mirror surface control module and a light-emitting mirror. The system collects data sets through the induction recognition module, and a face analysis unit calculates and generates a rotating data set Xzsj. The system automatically matches by default with the image center point of the nose as the target height, a brightness analysis unit calculates and generates a brightness data set Ldsj, and the system automatically adjusts by default with the standard value as the final light intensity. The system intelligently matches the user's line of sight focus, an instruction analysis unit generates an execution data set Zxsj according to the corresponding voice data set, the mirror surface control module controls the opening of the rotating motor and the light adjustment module, and generates corresponding voice prompts. The voice control is more intelligent, has a wide range of flexible applications, and provides a better user experience.

The invention belongs to the technical field of face recognition and verification, and particularly relates to a park and meeting room entrance and exit face recognition and verification system, which comprises an image acquisition module, a face recognition module, a face recognition module, a face recognition module and a face recognition module, the image adjusting module is used for adjusting the face image acquired by the image acquisition module so as to ensure the definition of the acquired face image; and the face analysis module is used for analyzing the face of the person according to the image adjusted by the image adjustment module so as to verify the face of the person and grading verification results. According to the invention, by arranging the face analysis module and the expression analysis module, when the face recognition is carried out on the personnel participating in the conference, the grade of the face image can be firstly determined, and then the expression analysis module is executed according to the judgment grade, so that when the face of the personnel participating in the conference changes, dual verification can be carried out, and the face recognition efficiency is improved. And the accuracy of face recognition is further ensured.

Embodiments of the present disclosure provide a face image repairing method and device, electronic equipment and storage medium. The method comprises: obtaining a face image to be repaired; cropping a first face image from the face image to be repaired by a face detection algorithm; analyzing the first face image by a face analysis model to generate a binary face mask image; performing face repairing processing on the first face image by a face repairing model to obtain a second face image; synthesizing a third face image according to the first face image, the second face image and the binary face mask image; and replacing the first face image in the face image to be repaired with the third face image to form a repaired face image. The method analyzes and performs face repairing processing on the face image by the face analysis model and the face repairing model respectively to obtain the binary face mask image and the second face image. Different regions of the face image are selectively repaired according to the binary face mask image, so that the repaired face image is more natural.

The invention discloses a face analysis method based on multi-task learning and transformer, and the method comprises the following steps: dividing an input image into a plurality of non-overlapping windows, and carrying out the feature transformation through a multi-layer perceptron; tasks are classified according to output types, each prediction head has an independent and unique feature fusion module and a decoding module and can learn a plurality of sub-tasks at the same time, finally, corresponding losses are calculated, and a gradient normalization strategy is adopted to ensure that a model does not tend to each task. The invention provides a face analysis architecture based on multi-task learning and transformer, a plurality of related or unrelated tasks are allowed to be processed in a unified model at the same time, and feature representation is shared among different tasks, so that redundancy of feature extraction is reduced, and the resource utilization efficiency is improved. By dynamically calculating the learning weight for different tasks, the multi-task learning framework can synchronize the learning speed of each sub-task to the greatest extent, and an effective convergence effect is achieved.

This invention provides an intelligent interactive media display method and system. The method includes: offline construction of a visitor image library; capturing faces of people standing in front of the media wall using a camera installed on the media wall, and extracting qualified facial images using face detection technology; then, using face analysis technology to perform attribute analysis on the extracted qualified facial images to determine the gender, age, and identity attributes of the faces in front of the media wall; combining the constructed visitor image library with the results of face detection and analysis to intelligently display the media wall; and using gesture recognition technology to allow users to interact with the media wall without contact, including pausing, starting, scrolling forward, scrolling backward, and deleting. This invention innovatively applies face recognition and gesture recognition technologies to building walls, intelligently displaying media wall content and providing a contactless interactive method, giving users not only a sense of presence and surprise, but also a sense of interaction and friendliness.

The invention relates to the technical field of driving behavior safety recognition, in particular to a two-dimensional holder face positioning and fatigue driving detection device which comprises a data collection and storage module, an image information recognition and processing module, a face analysis and fatigue driving evaluation module and an intelligent alarm module. A two-dimensional image lossless storage mechanism is established in the data collection and storage module, the face image information is compressed and stored, and a two-dimensional image storage information base is obtained; a two-dimensional image feature recognition model and a two-dimensional image processing model are arranged in the image information recognition and processing module, a two-dimensional image information base is recognized and processed based on the models, and face monitoring information is obtained; a face analysis model and a fatigue driving evaluation system are established in the face analysis and fatigue driving evaluation module, and the module receives and processes the face monitoring information and outputs a fatigue driving evaluation result; and the intelligent alarm module sends a warning signal according to the evaluation result, so that the fatigue driving state is monitored and alarmed.

The invention is suitable for the technical field of man-machine interaction, and provides an auxiliary makeup method and system based on a user face analysis algorithm, and the method comprises the steps: firstly obtaining the intentional makeup information and multiple pieces of makeup feature information of a target user, and then obtaining the basic face information and real-time face information of the target user, and generating target makeup information based on the basic face information and the makeup feature information, generating expected makeup information based on the real-time face information and the makeup feature information, and finally sending the target makeup information and the expected makeup information to a display screen. According to the method, the user can conveniently know the final effect of the current makeup operation in real time, the user is assisted in forming a clearer expectation for the final makeup, the user can easily compare the current effect with the ideal target makeup, the user is helped to make more appropriate adjustment in the makeup process, the more satisfactory makeup effect is achieved, and the user experience is improved. And the user experience is obviously improved.

The invention relates to an unconditional face image generation method and system based on end-to-end self-distillation, and the method comprises the steps: obtaining a face image, inputting the face image into a variational auto-encoder and a face analysis network, and obtaining potential features and a face region analysis result; constructing an end-to-end self-distillation unconditional generation network, and adding current and previous time step noise to the potential features to obtain temporary strong and weak random Gaussian noise; constructing face region noise based on a face region analysis result, and combining the face region noise with the noise to obtain strong and weak noise; weak noise is input into a target SiT to extract deep representation, strong noise is input into online SiT to extract shallow representation, and loss optimization parameters are aligned through representation; performing face high-order structure clustering on the deep representation to obtain a hypergraph, and calculating a Laplacian matrix as attention structure bias of online SiT; and on-line SiT, strong noise is input to predict noise, and parameters are optimized through diffusion loss. According to the invention, diversified face images can be efficiently generated with high quality, and the structure consistency and detail expression are improved.

The invention relates to the field of face capture, in particular to a VR virtual character interaction system and method based on user-defined expression and mouth shape synchronization, and the system comprises a data collection unit which is used for collecting face data of a target user; the face analysis unit is used for determining a paragraph division mode according to the face analysis state; the paragraph division unit is used for executing a paragraph division The point location processing unit is used for judging whether the sub-region is a target sub-region or not according to the motion trend median value, determining a range setting mode according to the influence coefficient difference degree of the first key point and determining a second key point setting strategy according to the motion state of the first key point; according to the invention, the virtual character interaction effect is improved.

The application provides an occlusion face recognition method based on an occlusion-feature mapping relationship, and the method comprises the following steps: establishing a face analysis and face key point detection module, obtaining a face semantic region division picture through the face analysis module; performing sub-region division on the face semantic region through the face key point detection module; inputting a pair of original face images and sub-region occlusion face images into a differential twin network to learn the mapping relationship between the occlusion and the deep feature, thereby establishing a mask dictionary of different sub-regions of the face; segmenting a binary image of the occlusion region through a segmentation network FCN-8s; merging the corresponding occlusion sub-region mask dictionary through the binary image query; multiplying the face picture to be recognized with the corresponding mask dictionary in the face recognition network to eliminate the damaged feature elements caused by the occlusion, so that the recognition rate of the occlusion face is improved; and the feasibility of the method is verified through experiments on a public data set.

The application discloses a method and device for tracing a fake face based on region classification, a medium and equipment. The method comprises the following steps: acquiring a face picture, wherein the face picture comprises a regionally fake picture, a globally fake picture and a real picture; performing face analysis on the face picture to obtain a face region picture, a background region picture and a connection region picture; performing trace feature extraction on the face picture to obtain a global feature and a global feature decision vector, and performing trace feature extraction on the face region picture, the background region picture and the connection region picture to obtain a face region feature, a background region feature, a connection region feature, a face region feature decision vector, a background region feature decision vector and a connection region feature decision vector; performing feature-level fusion and decision-level fusion on the features and the feature decision vectors to obtain a coarse-grained trace decision vector; and inputting the coarse-grained trace decision vector into a classifier to predict a trace result. The application can improve the accuracy of face tracing.

The invention relates to a face analysis method and system based on self-supervised representation learning, and the method comprises the steps: 1) obtaining a face image from a data set, and carrying out the preprocessing of the face image; 2) constructing a self-supervised local-to-global mask distillation network model to extract universal face representation; wherein a visible local feature Token sequence is extracted through an online local encoder, a target global feature Token sequence is extracted through a target global encoder, and a global feature Token sequence is predicted through a local-to-global decoder; in the model training process, the weighted sum of mask loss and distillation loss is calculated, and parameters of an online local encoder are optimized through gradient back propagation, so that iterative training of the model is realized; and 3) applying the trained online local encoder to face analysis, face key point detection, face attribute recognition or face expression recognition tasks through transfer learning. The method and the system are beneficial to obtaining the result of the face analysis task more robustly, accurately and generalizedly.

An object of a system according to an embodiment is to propose optimal makeup to a user and explain a procedure thereof.SOLUTION: A system according to an embodiment includes a face analysis unit, a makeup suggestion unit, a makeup simulation unit, and a makeup procedure explanation unit. The face analysis unit analyzes features of the face of the user. The makeup suggestion unit suggests optimal makeup based on the feature analyzed by the face analysis unit. The makeup simulator applies the makeup proposed by the makeup proposal unit to the face of the user. The makeup procedure explanation unit explains a makeup procedure applied by the makeup simulation unit.SELECTED DRAWING: Figure 1

A face analysis method based on multi-expert features and task prompts comprises the following steps: extracting aggregated multi-expert features from an input image by adopting a unified student network under the supervision of a multi-expert teacher network, generating task features according to task prompts and the aggregated multi-expert features through a feature fusion network, and analyzing the task features according to the task prompts and the aggregated multi-expert features. And finally, a face analysis result is obtained by the task head according to task feature classification. According to the invention, task features are aggregated from a plurality of teachers which are not limited to specific face downstream tasks by using a unified network, and expert features required by each downstream specific task are adaptively selected by using a unified feature fusion network with task prompts. Therefore, face recognition (metric learning), face attribute recognition (classification task) and age estimation (regression task) can be carried out at the same time, and complex and heavy specific task sub-network design is not needed.

The application discloses a portrait LAB color correction method based on a convolutional neural network, and comprises the following steps: constructing a face analysis network, wherein the face analysis network adopts a BiseNet (Bilateral Segmentation Network), and a channel fusion down-sampling structure is added to each pyramid sampling layer of a context path component of the BiseNet; training the face analysis network by using a training sample set to obtain a face analysis model; performing face analysis on a face image by using the face analysis model to obtain face subdivision parts and part identification information; performing LAB color cast detection on preselected face subdivision parts to obtain LAB color casts of each preselected face subdivision part; obtaining a color cast part according to the LAB color casts, and correcting the color cast part; and merging each face subdivision part according to the part identification information to obtain a corrected face image. The application solves the problems of low precision, color correction and low shooting quality of a certificate photo in the prior art.

The invention discloses a low-resolution traffic video face super-resolution reconstruction and recognition method, and relates to the technical field of face recognition. Performing space-time semantic fusion preprocessing on the low-resolution video frame containing the human face and structured data such as a license plate and a vehicle; extracting local, global and context features of the face by adopting a dynamic attention mechanism; carrying out super-resolution reconstruction by utilizing a generative adversarial network in combination with various constraints; the reconstructed face features are fused with the structured data, and a graph convolutional network and a twin neural network are used for recognition; and the recognition threshold is dynamically adjusted according to the scene complexity, and adaptive decision is realized. According to the method, multi-modal data are fused, dynamic attention and multi-constraint reconstruction are utilized, and image convolution recognition and self-adaptive decision are combined, so that the quality and recognition accuracy of a low-resolution traffic video face image are improved, the system robustness is enhanced, and efficient and reliable traffic scene face analysis is realized.

The application discloses a multi-task real-time face analysis method and system based on OpenCV and light DNN, and relates to the technical field of computer vision. Input data in the form of static images or real-time video streams is preprocessed through OpenCV; face detection is completed based on a light MobileNet-SSD network optimized through channel pruning and dynamic weight distillation, and effective face images are screened; the face images are input into a multi-task light DNN model, synchronous inference of expression recognition, age prediction and gender classification is realized through a cross-task feature interaction mechanism; real-time video streams are processed through multi-thread parallel computing and optional CUDA GPU acceleration, analysis results are stored in a database in association and visual display and query are supported. The system corresponds to data input, preprocessing, face detection, multi-task analysis, parallel acceleration, data storage and result display and interaction modules. The application balances model precision and computing efficiency, improves complex scene adaptability and real-time response capability, and is suitable for various intelligent interaction scenes.

The application discloses a face restoration method based on a multi-scale face analysis graph, and belongs to the technical field of computer vision, machine learning and the like. First, the application uses an encoder-decoder structure to build a basic network, and adds a skip connection with a channel attention module to the basic network, so that the decoder can fully utilize the effective information contained in the extracted feature map to restore the face. Meanwhile, the face analysis graph is taken as a style image to be fused into the generated face image. Finally, the application adds a loss function that is beneficial to saving identity information during training, and uses the feature layer extracted by the face recognition network to constrain the identity of the restored face, and adds an adversarial loss and a multi-scale discriminator, so that the network can further generate a face image with more real details.

The application discloses a face cross-domain translation method based on multi-view knowledge integration and frequency consistency, which introduces face knowledge in large single-domain data into limited cross-domain data. Specifically, after the input photo is extracted by a face analysis network, the photo is cascaded into a translation network based on a multi-view knowledge integration model. On the other hand, the input photo is extracted by a face recognition network to obtain face identity features, and the cascaded features and the face identity features are used to calculate KL loss, thereby identity consistency supervision is achieved to enhance the high and low frequency consistency between the generated image and the real image. The frequency consistency loss is a general reconstruction loss, which can be flexibly applied to other generation models to improve the robustness of the model to noise.

The invention provides an image processing method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining a to-be-processed head portrait picture which comprises a head portrait of a target object; performing edge detection on the to-be-processed head portrait picture to obtain initial edge information of the to-be-processed head portrait picture; performing face analysis on the to-be-processed head portrait picture to obtain region images corresponding to each of M target regions in the to-be-processed head portrait picture; and respectively determining region edge information of the region image corresponding to each target region, and determining target edge information of the head portrait picture to be processed based on the region edge information of the region image corresponding to each target region and the initial edge information. The embodiment of the invention can effectively improve the accuracy of the edge information.

The invention relates to the technical field of industrial safety management, in particular to a workshop personnel safety management system and method, and the system comprises an AI terminal, a network camera, a video switch, a private cloud server, an environment monitoring unit and an alarm unit. The AI terminal carries safety helmet recognition, smoking detection, border crossing early warning, work clothes recognition and face analysis algorithms, supports edge calculation and processes video stream data in real time; the network camera is deployed in a key area of a workshop, collects a high-definition video stream and transmits the high-definition video stream to the AI terminal through the video switch; the video switch is connected with the plurality of network cameras and the AI terminal; the private cloud server communicates with the AI terminal through an MQTT protocol, stores historical data and supports mobile terminal interaction; the environment monitoring unit comprises a temperature and humidity sensor, a gas detector and the like, and is linked with the AI terminal to monitor environment abnormity; the alarm unit is used for receiving a signal of the AI terminal and sending out an alarm sound; the real-time performance and the accuracy of safety management are improved.