1388 results about "Face detection" patented technology

The invention discloses a space-frequency domain graph learning-based adaptive deep fake face detection method and system, and the method comprises the steps: randomly extracting an image frame from a video, intercepting a face image, adjusting the feature dimension of the face image, and transmitting the face image to a depth adaptive wavelet module and a normalized residual homomorphic composition neural network module; a depth adaptive wavelet module extracts frequency features of the face image; a normalized residual homograph neural network module extracts spatial domain features of the face image; performing weighted fusion on the frequency domain features and the spatial domain features by using a self-adaptive feature fusion module based on gated convolution, realizing class attention guidance by using the gated convolution, dynamically adjusting the channel of a feature map and the weight of a spatial dimension, and finally obtaining fusion features; and performing classification according to the fusion features by using a classifier. According to the method, the extraction capability of forged detail clues is enhanced, and the detection precision and stability of the model are remarkably improved.

The invention discloses a domain generalization face anti-counterfeiting method for guiding CLIP through cross-modal fusion. The method comprises the steps of inputting an image sample into a preprocessing unit for preprocessing, including face detection and data enhancement of a detected face image; generating text features including category description and content description for each text sample based on the fine-grained prompt template unit, generating visual features for the preprocessed image samples based on the domain perception adapter unit, fusing the text features and the visual features to form cross-modal joint feature representation, and extracting the cross-modal joint feature representation. Training a face anti-counterfeiting prediction network by using joint feature representation; and inputting the real face image processed by the preprocessing unit into the trained face anti-counterfeiting prediction network, and performing reasoning prediction. According to the method, the visual features are dynamically adjusted by using the text features instead of directly editing the visual features, so that the understanding and association of the model on content and category semantics are enhanced, and the domain generalization ability of a face anti-counterfeiting technology is enhanced.

The invention relates to the technical field of face detection, and particularly discloses a face recognition system based on a face mask detection model, which is used for solving the problems of face recognition accuracy reduction and counterfeiting risk caused by mask shielding, counterfeiting attack and multi-source environment interference in high-security sensitive scenes such as a banking business window and the like. The system comprises a data acquisition and enhancement module, a feature extraction and multi-task neural network discrimination module, a counterfeit attack detection and risk blocking module, and a system deployment and model adaptive training module. According to the invention, through integration of multi-channel high-resolution visible light and infrared imaging, forgery attack sample enhancement based on the generative adversarial network, adaptive difficult sample sampling and multi-task deep discrimination network collaborative optimization, efficient recognition and real-time risk blocking of real and forgery mask faces are realized; and the security and robustness of a face recognition system in scenes such as banks are improved.

The invention discloses an automobile data recorder fatigue driving detection and reminding method based on multi-modal data fusion, and the method comprises the following steps: S1, collecting and preprocessing a face image through a vehicle-mounted camera, and carrying out the face detection and region positioning; s2, dynamically adjusting the size and the position of an image block by adopting a dynamic image blocking technology; s3, performing facial image feature extraction by using a visual converter; s4, acquiring vehicle multi-modal data and fusing the vehicle multi-modal data with the facial features; s5, optimizing a visual converter network structure and training hyper-parameters through a wolf pack optimization algorithm; s6, performing fatigue state analysis based on the optimized visual converter; and S7, when the fatigue state is detected, reminding the driver to have a rest through sound-light alarm. The fatigue driving detection and reminding method of the automobile data recorder is high in precision and high in real-time performance through a deep learning algorithm of multi-modal data fusion and optimization, and the recognition accuracy of fatigue driving and the robustness of the system are effectively improved.

The invention relates to the technical field of intelligent robots, and discloses a face recognition method of an intelligent robot, which comprises the following steps: step 1, lightweight face detection and feature extraction: performing face detection and feature extraction through a lightweight neural network structure, and combining model compression and edge calculation to reduce calculation complexity; and step 2, illumination and attitude adaptability is realized through multi-modal fusion, and face processing under different illumination and attitude conditions is carried out based on the extracted face features by utilizing fusion of an RGB image and an infrared image, adaptive illumination enhancement and 3D attitude correction. Through a multi-modal fusion technology, 3D attitude correction and self-adaptive illumination enhancement, different illumination conditions and attitude changes can be adapted, then the recognition stability of the system in a complex environment is remarkably improved, it is ensured that face recognition has high accuracy and robustness under the conditions of insufficient illumination, strong light or multi-angle offset, and the face recognition accuracy and robustness are improved. And the application requirements of the intelligent robot in multiple scenes are met.

The invention relates to a simulation digital human real-time intelligent voice interaction system and a simulation digital human real-time intelligent voice interaction method based on vision and a large model, and aims to solve the problems of inaccurate target speaker recognition, high response delay and the like in digital human voice interaction in a complex scene. The system circles an effective recognition range through a camera, triggers audio collection in combination with face detection, locks a target speaker and reduces noise by using lip movement recognition and sound image fusion technologies, converts the target speaker into a text through voice wake-up, generates an answer by means of a large language model (LLM) and knowledge retrieval enhancement (RAG) technologies, generates low-delay voice through a voice synthesis technology accelerated by the vLLM, and performs voice recognition on the target speaker. And driving the preloaded digital human image to synthesize a video stream and pushing the video stream to a front end for rendering in real time. Accurate pickup, low-delay interaction and rapid digital human image switching in a complex environment are realized, the accuracy and real-time performance of intelligent voice question answering are improved, and the method is suitable for government affair halls, exhibition halls and other scenes.

The invention discloses a classroom student attention assessment method and system based on multi-source feature fusion. According to the invention, face recognition is carried out through the face detection unit of the system, occurrence frequencies of different emotional states of students are obtained through a trained student expression recognition neural network model containing four expression discrimination blocks in the expression recognition unit, and fatigue times of the students are obtained through the fatigue detection unit. The number of times of abnormal head postures of the students is obtained through the head posture estimation unit, finally attention evaluation parameters of the students are obtained through an extreme learning machine model of the attention evaluation unit, and then the attention states of the students in the class are evaluated and displayed. According to the method, a more efficient dynamic student expression recognition method can be provided, real-time and accurate classroom feedback is provided for teachers, optimization and implementation of personalized teaching strategies are supported, longitudinal extension of teaching of the teachers and transverse extension of learning modes of the students are facilitated, and new talents are expanded to cultivate a new normal form.

The invention provides a face recognition method and device, electronic equipment and a medium, and the method comprises the steps: processing a scaled to-be-recognized face image through a face detection model, and determining the coordinates of a face region and a plurality of key points in the original to-be-recognized face image based on the recognition result of the face detection model; based on the coordinates of the plurality of key points in the to-be-recognized face image and the coordinates of the plurality of key points in a preset face template, aligning a face region in the to-be-recognized face image to the preset face template, and outputting an aligned face image of a preset size; processing the aligned face image through a face recognition model comprising a down-sampling module, and generating a target face feature of the face image to be recognized; the user information of the target user corresponding to the to-be-recognized face image is determined based on the similarity between the target face feature of the to-be-recognized face image and the feature vector of the user in the database, so that the calculation amount in the face recognition process is reduced, and the accuracy and precision are both considered.

The invention belongs to the technical field of chemical safety detection, and discloses a chemical storage tank corrosion safety detection device and method.The method comprises the steps that a route planning module plans routes of a side face detection mechanism and an end face detection assembly; the transverse driving mechanism drives the side face detection mechanism to move, and a detection unit on the side face detection mechanism detects the circumferential side face of the storage tank. The transverse moving assembly drives the end face detection assembly and the detection unit to detect the two end faces of the storage tank. The ultrasonic detection module, the infrared detection module and the image analysis module identify abnormal conditions of the storage tank; the comprehensive evaluation module comprehensively evaluates the corrosion safety of the storage tank and predicts potential risks. According to the invention, the circumferential side surface and the two end surfaces of the storage tank are rapidly and comprehensively detected, and corrosion safety detection is carried out on the storage tank by multiple means through ultrasonic detection, infrared detection and image analysis; and the detection results of the plurality of detection modules are fused with environmental data, the corrosion safety of the storage tank is comprehensively evaluated, and potential risks are predicted.

The invention discloses a human body detection and face recognition system and method, and belongs to the technical field of video stream real-time monitoring and face recognition, and the method comprises the steps: 1, carrying out the motion detection of an obtained video stream transmitted by a camera; 2, executing human body detection according to a motion area obtained by motion detection; step 3, executing face feature extraction in a local face database; step 4, executing multi-image fusion in the video stream; step 5, performing face detection on the detected human body area; step 6, performing face recognition after face detection is performed; the face feature extraction and recognition method is further optimized, so that the detection and recognition precision and the real-time performance of the system in practical application and the adaptive capacity in a complex scene are remarkably improved, and the robustness is good.

The embodiment of the invention provides a fatigue detection method and device based on time sequence self-attention and auxiliary supervision. Multi-dimensional features such as the eyelid aspect ratio, the mouth opening degree and the head turning angle of the face of a driver are extracted through face detection and key point positioning. A multi-layer self-attention coding network is innovatively constructed, two branches of trunk feature extraction and auxiliary supervision are included, and a dynamic change rule of a face state is captured by using a time sequence self-attention mechanism. An auxiliary supervision branch is introduced to predict each face parameter state, and a feature learning process is optimized through a multi-task loss function. According to the method, the limitation of traditional single feature analysis is broken through, accurate recognition of the fatigue state of the driver is achieved, and reliable technical support is provided for improving road traffic safety.

The invention relates to the technical field of speech recognition, and particularly provides a multi-mode speech processing method and device, a medium and a computer program product. The multi-mode voice processing method comprises the following steps: acquiring to-be-processed audio and video data, and performing data separation processing on the to-be-processed audio and video data to obtain original audio data and original video data; performing face detection processing on the original video data to obtain initial video data; performing audio detection processing on the original audio data to obtain initial audio data; and performing consistency detection processing on the initial video data and the initial audio data, and outputting target audio data and target video data under the condition that a consistency verification condition is met. The face in the video is recognized through face detection, noise and sound of the target speaker are recognized and separated through audio detection, and synchronization and matching of audio and video data in time and content are ensured through consistency detection, so that development of a multi-mode voice separation task is supported.

The invention relates to the technical field of diffusion counterfeit face detection methods, in particular to a diffusion counterfeit face detection method based on multi-modal fine-grained CLIP, and the method specifically comprises the following steps: constructing a layered fine-grained face data set, and carrying out the preprocessing of a face image in the data set and a corresponding layered fine-grained label; a layered fine-grained label tensor obtained after preprocessing is input into a fine-grained text generator to obtain a fine-grained text # imgabs0 #, and the fine-grained text # imgabs0 # and a face image tensor # imgabs1 # form a face image text pair # imgabs2 #; respectively processing the face image text pair # imgabs3 # to obtain a predicted language feature # imgabs4 # and a predicted image category feature # imgabs5 #; parameters in all the modules are optimized and trained through a loss function and an Adam optimizer, and a CLIP multi-mode fine-grained model after optimization training is obtained; and inputting a to-be-detected image into the trained and optimized CLIP multi-mode fine-grained model to obtain a final true and false discrimination result. According to the invention, the efficiency and the cross-modal detection capability of the diffusion counterfeit face detection model can be improved.

The invention relates to a high-definition monitoring camera tracking method and system for multi-angle face detection. The method comprises the following steps: preprocessing an original image collected by a high-definition monitoring camera to obtain a first preprocessed image and a second preprocessed image; performing feature extraction and feature fusion on the first preprocessed image and the second preprocessed image to obtain a multi-scale fusion feature map; face positioning and posture analysis are carried out through a position sensitive convolutional network, and a face detection result is obtained; performing face region subdivision and angle characteristic analysis on the face detection result to obtain enhanced face representation; and calculating a cross-camera matching cost matrix based on the enhanced face representation, and performing trajectory prediction and updating processing to obtain a face tracking result in the multi-camera environment. According to the method, the capability of capturing facial micro-expressions and fine features is improved, high-precision face association and smooth trajectory handover among different cameras are realized, and the problem of trajectory fragmentation in view crossing areas of the cameras is solved.

The invention discloses a face recognition method and system based on dynamic weighted wavelet attention, and the method comprises the steps: inputting a face image into a backbone network; extracting multi-scale feature vectors and adjusting feature intensity by using a spatial depth conversion convolution layer, a feature extraction enhancement module and a spatial pyramid pooling fast layer in the backbone network; a detail feature enhancement module is introduced into a feature extraction enhancement module, high-frequency information of an image is extracted through wavelet transform, and then detail features are enhanced through channel attention and space attention, so that the expression ability of textures, edges and other details is enhanced while space structure information of middle features is reserved. Multi-scale feature vectors extracted by a backbone network are input into a neck network, feature vectors after feature fusion are output and enter a detection layer, face recognition is performed by using detection heads of different sizes, and the small target face detection precision is improved.

Methods and systems are provided for facial detection techniques for image processing neural networks. In one example, a method may include collecting multi-channel outputs of a set of context modules, providing them to both a face detection head and a landmark localization head of the neural network. The face detection head may then generate bounding boxes which are also provided to the landmark localization head. Based on the output of the context modules and the bounding boxes, the landmark localization head may provide an output including a set of landmark indicators.

Provided is a system for authenticating a remote driver in real time using an image and artificial intelligence. The system for authenticating a remote driver in real time according to an embodiment of the present invention includes: a face detection unit mounted on construction equipment to detect a face of a driver on board; a remote control station configured to transmit facial data of the driver on board detected through the face detection unit to an authentication unit, receive a driver information search result and an authentication determination result from the authentication unit, and start the construction equipment; and the authentication unit configured to search for the facial data of the driver on board received from the remote control station from driver information data stored in a database and transmit the driver information search result and the authentication determination result to the remote control station.

The invention provides a method and device for evaluating real emotion and a video consultation system, and the method comprises the steps: obtaining audio and video data of a testee, and separating the audio and video data into an audio stream and a video stream; respectively carrying out framing processing on the audio stream and the video stream to obtain a plurality of voice frames and a plurality of video frames; performing face detection preprocessing on the video frame to obtain a face image, inputting the face image into an expression recognition model to obtain expression confidence, processing through an expression analysis method to obtain expression comprehensive confidence, inputting an audio frame into an emotion recognition model to obtain emotion confidence, and processing through an emotion analysis method to obtain expression comprehensive confidence; the emotion comprehensive confidence is obtained; according to the emotion analysis method, based on emotion abrupt change, an audio and video frame rate FPS and the emotion confidence coefficient, similarity calculation is carried out on the expression comprehensive confidence coefficient and a first standard confidence coefficient, and similarity calculation is carried out on the emotion comprehensive confidence coefficient and a second standard confidence coefficient. Through the expression recognition model and the emotion analysis method, the accuracy of evaluating the real emotion of the testee is improved.

The invention discloses a student state real-time analysis method and device based on deep learning, and the method comprises the steps: obtaining and preprocessing image data of students in a classroom, and carrying out the multi-scale face detection and facial feature extraction of the preprocessed image data; expression features are extracted based on standardized facial feature data, fusion is carried out in combination with attention indexes and attitude features, a time sequence feature sequence is constructed, a heavy-tailed recurrent neural network is applied to carry out time sequence modeling, an evaluation standard is established, evaluation parameters are adjusted through a self-adaptive threshold value, and finally a student state evaluation result is obtained. Through the heavy-tailed recurrent neural network and a slow transition mechanism to low-dimensional chaos, subtle changes and long-term trends of student states can be accurately captured, and the technical problems that a traditional student state monitoring method is poor in real-time performance, limited in coverage and insufficient in individuation are solved.

The invention relates to the technical field of face recognition, and discloses a face recognition method and system suitable for an outdoor electronic instrument to solve the problem of low recognition precision under complex illumination, posture change and shielding conditions in the prior art, and the method comprises the steps: S1, collecting image data, and carrying out the preprocessing; s2, performing face region detection and face key point positioning on the illumination enhanced image; s3, performing affine transformation based on the face detection result set to perform face alignment; s4, extracting a face feature vector based on a ResNet100 structure; s5, performing attitude-guided feature reconstruction processing on the face feature vector to obtain an attitude-enhanced face feature vector; s6, performing feature normalization and identity classification on the posture-enhanced face feature vector, and outputting a face recognition result; and S7, outputting a final identity recognition result and confidence. According to the method, an efficient and scientific optimization scheme can be provided in outdoor face recognition, and remarkable technical values and economic benefits are brought to practical application.

This invention belongs to the field of facial expression recognition and provides a micro-expression recognition method based on convolutional neural networks and optical flow features, which is used to improve the adaptability and accuracy of micro-expression recognition. The method first constructs a face detection module to perform face detection on each image frame in a video segment, outputs facial key point information, and extracts facial regions of interest (ROIs) based on the facial key point information: nose, mouth, left eye and eyebrow, right eye and eyebrow. Then, optical flow information and optical strain information are introduced to characterize the spatiotemporal information of facial movement and the intensity information of facial deformation. The optical flow eigenvalue of each image frame is calculated, and a binary search algorithm is used to search for the image frame with the maximum optical flow eigenvalue, which is used as the vertex frame for micro-expression recognition. Finally, a micro-expression recognition model based on a convolutional neural network is constructed, which uses the horizontal and vertical components of the optical flow and optical strain of the vertex frame as input. The micro-expression recognition model outputs a micro-expression category prediction result.

An information processing apparatus performs face detection processing to detect a face area and the orientation of a face from an image captured by an imaging unit, brightness reduction processing in which, when the orientation of the face detected by the face detection processing changes from a first orientation to a second orientation while the screen brightness of a display unit is controlled to a first screen brightness, the screen brightness is reduced from the first screen brightness to a second screen brightness after first time has elapsed, and imaging state determination processing to determine whether an imaging state is a first imaging state where the imaging unit can capture an image in an image brightness capable of detecting the face area or a second imaging state where the imaging unit cannot capture any image in the image brightness capable of detecting the face area.

A method of maintaining the security of an authentication session comprises operating a camera device to continuously capture a view of an environment of a computing device, performing face detection to detect all faces in the environment, performing comparisons between faces detected in the environment and faces of a set of authorized users, at a first time, detecting a first face of an authorized user of the set in the view of the environment and, in response, allowing the authorized user to operate the computing device, and at a second time after the first time, one of failing to detect the first face or detecting a second face that is not of an authorized user of the set in the view of the environment, and, in response, at least partially blocking operator access to input and output devices including blocking a display of the computing device.

An electronic device and method for face detection based on facial key-points is provided. The electronic device receives an image of an object of interest. The image may include a face of the object of interest. The electronic device detects a plurality of key-points associated with the face of the object of interest based on the received image and determines a first coordinate value in the received image based on the detected plurality of key-points. Thereafter, the electronic device determines a region in the received image that includes the face of the object of interest based on the determined first coordinate value and controls the display device to overlay a marker onto the determined region of the face. The marker indicates a location of the determined region in the image.

The invention discloses a living body face detection method based on a near-infrared and visible light binocular camera, and belongs to the technical field of face recognition, and the method comprises the steps: collecting binocular visible light and near-infrared images, and carrying out the cross-modal alignment; subcutaneous microvascular pulsation time sequence signals in the near-infrared image are extracted, texture boundary features in the visible light image sequence are enhanced in combination with the near-infrared image sequence, and an enhanced texture feature map is obtained; analyzing 3D deformation continuity and physiological motion consistency in the expressions and actions based on the enhanced texture feature map; and in combination with time-frequency domain disturbance detection, carrying out living body determination. According to the method, a multi-modal time sequence synchronous material reflection gradient analysis and microvascular pulsation time sequence tracking technology is adopted, and in combination with facial dynamic 3D deformation biomechanical model constraint and time-frequency combined anti-interference verification, the accuracy and robustness of in-vivo detection can be effectively improved, and a powerful guarantee is provided for the safety of a face recognition technology.

The invention relates to an occluded face recognition method based on FaceNet and an attention mechanism. The method comprises the steps of data set preprocessing, face recognition network construction, network training and testing. According to the method, an MTCNN backbone network is adopted to carry out face region detection and face key point detection, an attention mechanism is used to focus the network on an unshielded part, a CNN neural network is adopted to map a face image to a 128-dimensional Euclidean space, and the similarity degree of two persons is judged according to the Euclidean distance between two portraits. The invention aims to solve the problem of how to obtain the face features of the non-shielding face part, so that the performance and robustness of a face recognition task are improved, and the face detection effect in a complex shielding scene is improved.

SYSTEMS AND METHODS IN THE FIELD OF SELF-SUPERVISED DETECTION OF FACIAL BOUNDARIES. Systems and methods for self-supervised learning (SSL) in facial detection networks are proposed. In one embodiment, a facial detection network comprises encoder components configured to encode facial features, the encoder components including trained components of a masked image modeling (MIM) network configured to process non-overlapping patches determined from the input image, the MIM network trained with an SSL objective; and decoder components configured by training to determine local matches between features to determine estimates for facial landmarks. In one embodiment, the MIM network is an MAE network.In one embodiment, the decoder components are derived from those of a second trained network comprising the encoder components as trained but fixed, wherein the decoder components of the second network are trained using locality constraint repulsion loss (LCR). Methods are proposed for SSL training of the encoder and decoder components. Figure for abstract: none.

The invention provides a non-contact heart rate monitoring method and system based on adaptive feature fusion and key region division. The method comprises the steps that firstly, a face detection data set is obtained, a multi-scale feature extraction network is constructed, input face video frames are processed in parallel through convolution layers with different convolution kernel sizes, and multi-scale feature extraction is completed; designing an AFFM adaptive feature fusion module, using a SE-Net channel attention mechanism to obtain channel and space attention weights, fusing feature maps with different scales, and enhancing feature expression to obtain a feature map for face detection; then selecting a face key region, delimiting a region boundary by means of a deep learning semantic segmentation model, extracting light intensity information of each region at different moments, and integrating through a linear weighted fusion model to obtain a comprehensive heart rate signal source; and finally, denoising by using a filter technology, and detecting a light intensity peak value in combination with a sliding window so as to obtain a heartbeat cycle and a heart rate value.

The invention discloses a complex scene face detection method based on multi-domain feature dynamic fusion and CIOU optimization, and belongs to the technical field of face detection in complex scenes. The method comprises the following steps: acquiring a face detection data set; constructing a complex scene face detection network; training a complex scene face detection network by adopting the face detection training set to obtain a complex scene face detection model; and inputting a to-be-detected face detection image into the complex scene face detection model, and outputting a target detection position and a detection result. According to the invention, the detection precision of the small target face by the network is obviously improved; differences between prediction frames can be distinguished more accurately, so that a model training process is optimized, and a more accurate detection result is obtained; meanwhile, Varifocal Loss is introduced, the weight of a difficult sample is dynamically adjusted through a difficult sample balance mechanism, the learning direction of the model is guided, and the detection precision and adaptability of the model in a complex scene are enhanced.

The invention provides a method for tracking a speaker based on a panoramic camera and a close-up camera. The method comprises the steps that the panoramic camera shoots all people into a panoramic picture; based on a sound source of a speaker and / or analyzing facial actions of all people in the panoramic picture, positioning face position information of the speaker in the panoramic picture; based on the position relation between the panoramic camera and the close-up camera and the face position information of the speaker, the angle and the focal length of the close-up camera are determined, and close-up shooting is carried out on the speaker; the face position of the speaker in the close-up picture is analyzed, and the close-up camera is finely adjusted, so that the speaker is centered in the close-up picture. The position of the speaker is positioned by combining face detection and voice recognition technologies, and the close-up camera picture is triggered to track the close-up picture of the speaker, so that the conference control operation is avoided, and the intelligence of the conference terminal is remarkably improved.