1092 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 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 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 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 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 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.

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 relates to the field of information security, in particular to a space-frequency joint deep forgery detection method based on double-domain attention collaborative deformable convolution. The method comprises the steps that a training sample set and a test sample set are acquired, a deep learning network model is formed based on a space-frequency feature extraction structure, and the training sample set and the test sample set are composed of real faces and forged faces; the space-frequency feature extraction structure is composed of a space domain feature extraction structure, a frequency domain feature extraction structure and a bidirectional cross attention structure; transmitting the training sample set to the deep learning network model, and executing a model training action to obtain a deep forgery detection model; and transmitting the test sample set to the deep counterfeiting detection model, and executing a face authenticity classification action to obtain an authenticity face detection result. The purposes of improving the detection performance, effectively judging the real image and the forged image and improving the safety are achieved.

The invention discloses an intelligent campus student activity trajectory tracking method and system based on front and rear end fusion learning, and relates to the technical field of intelligent campus security. An embedded front end collects videos of a plurality of monitoring cameras of a campus, carries out target detection and extracts primary features of student targets; uploading the extracted primary features and the video to a back-end server; and the back-end server extracts advanced features of human body postures and gaits from the video by using a human body posture estimation algorithm and a gait recognition algorithm, fuses the advanced features and the primary features to obtain fused features, and clusters all detected student targets by using the fused features, thereby realizing cross-camera identity unification of the same student under different cameras, and improving the identification accuracy of the student. Face detection and recognition are carried out in each clustering group, a student information base is matched to determine student IDs, and the student IDs, video timestamps and monitoring camera position information are stored; and the client retrieves target information according to the input student ID or photo, and automatically clips and generates a time-space continuous complete cross-camera trajectory tracking video. According to the invention, efficient and intelligent analysis of campus monitoring data is realized, and targets can be accurately associated and tracked in a cross-camera scene.

A webcam includes a hardware microcontroller and a memory device. The hardware microcontroller executes program code of a hybrid face detection auto exposure module to detect a user's face within an image captured by the webcam and define a first image region of interest of the image that includes the user's face with the second image region of interest of the image including a background of the image, executes program code of a lighting detection module to detect brightness levels of the user's face within the first image region of interest and brightness levels in the second image region of interest, and executes program code of a hybrid face detection auto exposure module to determine if a background brightness change threshold level is exceeded and to automatically adjust an exposure setting for the first image region of interest of the image captured by the webcam when the threshold is exceeded.

The invention relates to the technical field of face recognition, and discloses a face recognition system and a detection method thereof, and the recognition system is composed of a face image acquisition module, an environment perception and preprocessing module, a face detection feature extraction module, a comprehensive analysis and comparison module and a data storage monitoring module. According to the method, environmental factors such as illumination intensity, light source type and color temperature are detected through a sensor, corresponding preprocessing is carried out on the image, the influence of the environmental factors on the recognition precision can be reduced by correcting illumination unevenness, denoising and enhancing contrast and sharpness, meanwhile, image compensation and denoising are carried out, illumination unevenness is compensated, and denoising processing is carried out, so that the recognition precision is improved. The beneficial effects of comprehensive analysis of age, health conditions and illumination condition environmental factors through face recognition and more stable recognition precision are achieved.

A computerized train driver behavioral analysis system for the automated analysis of behavioral characteristics of drivers of railway trains based on target and keypoint detection. A train operation status and position analysis portion monitors train position, speed, and acceleration. A standardized driver practice analysis portion compares actual driver behaviors and actions to standardized driver behaviors and actions. A driver mental state analysis portion automatically detects a driver's face with a human face detection model with automated target keypoint detection to detect predetermined keypoints to produce an electronic human face box and performs a computer analysis of eye and mouth statuses and makes an automated electronic determination whether the eyes and mouth are open or closed. The system thus produces a computerized judgment regarding behavioral characteristics of drivers based on the train operation status and position analysis, standardized driver practice analysis, and driver mental state analysis portions.

The invention discloses a campus intelligent alarm linkage method and system based on face recognition, and the method comprises the steps: collecting a video stream in real time, and extracting a face image in a video frame through a face detection algorithm; comparing the face image with a white list database pre-stored in a campus in real time, and generating an identity recognition result and a confidence score of the face; calculating the threat level of the current behavior scene through a dynamic early warning judgment model and generating a graded early warning signal based on the identity recognition result and the confidence score in combination with the real-time analysis of the personnel behavior scene; automatically triggering a corresponding equipment linkage instruction according to the graded early warning signal; and on the basis of the execution state of the equipment linkage instruction and a subsequent video analysis result, generating a complete security event disposal report containing an incident position, an incident-related personnel image and a disposal suggestion. According to the embodiment of the invention, the active early warning capability and the emergency response efficiency of the campus security system can be improved.

The invention relates to the technical field of sound source localization, and provides a sound source localization method and system based on fusion confidence. The method comprises the following steps: when a preset wake-up word is detected, starting sound source positioning processing, calculating a horizontal azimuth angle according to a detected current voice signal, and determining a sound source positioning area; calculating a matched existing user voiceprint, and confirming a current user corresponding to the current voice signal; calculating a user preference fusion coefficient corresponding to the current voice signal, calculating a fusion confidence coefficient of the current voice signal, dynamically adjusting a scanning range of a holder camera, capturing an image frame of a current user at a fixed interval in a scanning process, executing face detection, obtaining a to-be-processed face image, performing face feature extraction, and obtaining a to-be-processed face image; and carrying out visual identity collaborative confirmation, stopping rotation of the holder camera when an identity consistency condition is satisfied, and locking the current direction as a sound source positioning position. According to the invention, the hardware complexity is reduced, and the positioning precision is effectively improved.

A computer-implemented method is provided for generating a digital image. The method includes inputting a prompt that provides a textual description of the image into a trained machine learning model to generate the image based on the prompt, and processing the image. Processing the image includes determining presence of one or more humans in the image by detecting one or more human faces using a face detection algorithm, if at least one human face is detected, which is indicative of at least one human present in the image, determining whether there is at least one anatomical deformity associated with the at least one human, and if at least one anatomical deformity is detected, performing correction of the at least one anatomical deformity. The method further includes grading, by the computing device, the image to generate a final score to evaluate image quality.

The invention provides a degradable packaging box outer surface defect detection device, and relates to the field of packaging box defect detection.The degradable packaging box outer surface defect detection device comprises a conveying device, a supporting frame is fixedly connected to a rack of the conveying device, four peripheral face detection cameras are installed on the periphery of the inner side of the supporting frame, and an upper surface detection camera is installed at the top of the inner side of the supporting frame; a receding mechanism is arranged at the bottom of a rack of the conveying equipment, and a trapezoidal conveying mechanism is installed on the upper portion of the receding mechanism. Through the design of the trapezoidal conveying mechanism, the lower side face of the degradable packaging box can be separated from the upper surface of the conveying belt of the conveying equipment, manual turnover is not needed in the process, manpower is effectively saved, and the detection efficiency is remarkably improved; the problems that when an existing degradable packaging box is detected, only four side faces, the upper surface and the lower surface of the outer periphery of the packaging box are blocked by a conveying belt, and manual turn-over detection is needed, manpower is consumed, and efficiency is low are solved.

The invention provides an image processing method and device, electronic equipment and a storage medium. Relates to the technical field of image processing. The method comprises the following steps: acquiring continuous K frames of images, wherein K is a positive integer greater than 1; performing block processing on the K frames of images to obtain a plurality of first block images corresponding to the previous K-1 frames of images and a plurality of second block images corresponding to the Kth frame of image; for each second block image in the plurality of second block images, performing super-resolution reconstruction processing on the second block images according to the plurality of first block images corresponding to the previous K-1 frame images to obtain a plurality of reconstructed images corresponding to the second block images, the resolutions of the plurality of reconstructed images being different; and performing face detection on the Kth frame of image according to the plurality of reconstructed images corresponding to the plurality of second block images to obtain a face detection result of the Kth frame of image. According to the scheme, the accuracy of face detection on the Kth frame of image is improved.

The present application relates to a facial recognition method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring real-time video data, and performing face detection processing on the real-time video data, in order to obtain a facial image and an environmental image; performing facial illumination extraction processing and facial recognition processing on the facial image, in order to obtain a facial illumination feature distribution vector and a facial feature vector; performing environmental illumination extraction processing on the environmental image, in order to obtain an environmental illumination feature distribution vector; performing fusion processing on the facial illumination feature distribution vector, the facial feature vector and the environmental illumination feature distribution vector, in order to obtain a fused vector; inputting the fused vector into an auto-encoder model for reconstruction processing, in order to obtain a multi-modal feature vector; and performing retrieval and matching processing on the multi-modal feature vector, in order to obtain a facial recognition result.

The invention relates to a human body state detection method, system and device based on facial actions and a medium, and the method comprises the steps: obtaining an image sequence of a human face, carrying out the human face detection and mark point positioning of the image sequence, and obtaining the coordinates of a face mark point; performing micro-expression action extraction on the image sequence based on the facial mark point coordinates to obtain facial micro-expression action features; performing time sequence analysis on the facial action features to obtain time sequence facial action features; performing multi-scale illumination adjustment on the time sequence facial action features to obtain illumination facial action features; performing multi-modal analysis on the illumination facial action features through a pre-trained long-short term memory network to obtain comprehensive human body state features; and performing real-time state analysis based on the comprehensive human body state characteristics to obtain a human body state detection result. According to the method, different types of facial action features can be comprehensively processed, and the reliability of a detection result is enhanced.