43 results about "Face registration" patented technology

A face registration controller includes a face image obtaining unit, an adverse condition determination unit, a notification control unit, and a registration unit. The face image obtaining unit obtains a face image of an occupant. The adverse condition determination unit determines whether the face image falls within one of adverse conditions for a face authentication and identify a type of the one of the adverse conditions. The notification control unit notifies, when the face image falls within the one of the adverse conditions, at least one of the type of the one of the adverse conditions and a solution devised in accordance with the type. The registration unit resisters the face image as an authentication image when the face image does not fall within the adverse conditions and refrains from registering the face image when the face image falls within the adverse conditions.

The invention discloses a face quality label generation method based on cooperation of a multi-modal large model and a computer vision algorithm, and relates to the technical field of artificial intelligence and computer vision crossing, in particular to a face quality label generation method based on collaborative decision making of the multi-modal large model and the computer vision algorithm. The method is especially suitable for a high-security-level identity verification system, an automatic identification photo auditing platform, a large-scale face registration pre-screening process, a living body detection front level and other scenes, and is used for carrying out fine-grained, interpretable and high-robustness quality evaluation and defect positioning on an input face image. The core problems of weak semantic understanding ability, unstable discrimination precision, rigid fusion strategy, poor scene adaptability and the like in the prior art are solved by constructing a four-level technical architecture of dimension decoupling, double-channel parallelism, dynamic confidence fusion and scene adaptive evaluation.

The invention provides a face data encryption method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises: in response to a face registration operation, generating a first derived parameter associated with an identity identifier of a target user account, the target user account being a user account currently logged in by a terminal; generating a first key based on an initial key, the identity identifier and the first derived parameter, the initial key being a symmetric key associated with a device identifier of the terminal, and the first key being a symmetric key associated with the identity identifier; and through the first key, encrypting first face data authorized to be collected by the target user account to obtain first face encrypted data of the target user account. According to the scheme, the face data under different user accounts can be encrypted by using different keys, the risk that the face encrypted data is leaked is reduced, and the data security is improved.

The invention discloses a delivery signing method based on face recognition, and relates to the technical field of image recognition. Comprising the following steps: performing face registration, and establishing a face data pre-processing a front face image uploaded by a retailer, generating a feature vector by adopting a deep learning algorithm according to the pre-processed face image, encrypting the feature vector, binding the encrypted feature vector with corresponding identity information, and storing the encrypted feature vector in the face database, a retailer face image is shot according to an order corresponding to a deliveryman, the shot retailer face image is preprocessed, a feature vector is extracted, an ArcFace face recognition algorithm is adopted to compare whether the similarity between the feature vector obtained by the shot retailer face image and the feature vector in a face database is larger than a threshold value or not, and if yes, delivery signing is carried out; if yes, the two feature vectors belong to the same face image, signature verification succeeds, otherwise, the two feature vectors do not belong to the same face image, and shooting verification is conducted again or a standby verification mode is adopted.

The invention provides a point cloud registration method and apparatus, and an electronic device. The point cloud registration method comprises the steps of obtaining target point cloud data of the head of a patient; acquiring registration point cloud data of the face of the patient; respectively extracting a first feature description set of the target point cloud data and a second feature description set of the registration point cloud data; determining an initial transformation matrix between the target point cloud data and the registration point cloud data according to the first feature description set and the second feature description set; and according to the initial transformation matrix, the target point cloud data and the registration point cloud data, determining a registration matrix between the target point cloud data of the registration point cloud data. By adopting the above technical scheme, high precision can be ensured, and fast and robust face registration can be realized at the same time.

To provide a face authentication system that does not require management by a management company or the like and allows residents alone to safely start using the system or change users. [Solution] The system comprises a face registration means for registering a user's face image or face data that is processed data thereof, a photographing device installed near the front door of a dwelling unit in an apartment building, a resident registration means for registering the user as a resident of the dwelling unit, an authentication means for comparing the face photographed by the photographing device with the resident's face data, and a resident tool that is a user interface for the face registration means and the resident registration means, and the user account for the resident tool is handed over to the resident of the dwelling unit along with the front door key, and the user account for the resident tool is provided by a face authentication system that is pre-registered for each dwelling unit in the apartment building.

The invention discloses an image point cloud extraction method for face registration, which comprises the following steps: S1, acquiring an electronic computed tomography image of the head of a patient to obtain a skin surface model of the patient, and converting the skin surface model into a point cloud; s2, transforming the point cloud obtained in the step S1 to a standard coordinate system; s3, roughly extracting the point clouds, clustering the point clouds obtained in the step S2 to obtain four clustering centers, and filtering out the point clouds meeting a first preset condition according to the four clustering centers; and S4, finely extracting the point clouds, clustering the point clouds obtained in the step S3 to obtain three clustering centers, and filtering out the point clouds meeting a second preset condition according to the three clustering centers. Using a clustering method to reversely determine an area which needs to be extracted and has unobvious feature points from a plurality of clustering centers of the obtained point clouds through the plurality of clustering centers; clustering and extraction are carried out step by step, the number of clustering points each time is controlled, and the influence of noise features is eliminated.

The present invention belongs to the technical field of face recognition, and provides a face recognition data protection method and system. The method includes: generating quantum key K1 and quantum key K2; distributing quantum key K1 and quantum key K2; the face registration machine obtaining the first face feature value; the face recognition terminal collecting the second face feature value; the face registration machine encrypting the first face feature value through quantum key K1 and the national cryptography algorithm to generate the encrypted face feature value ciphertext B. The system includes: a quantum key management and service platform, a quantum key distribution network, a face registration machine, a face recognition terminal, a face recognition server, and a plaintext database. The face recognition data protection method and system of the present invention ensure the security of the key from the physical level, can resist the quantum threats suffered by traditional encryption algorithms; get rid of the dependence on foreign technologies and products, and build a network security environment for the industry.

The disclosed embodiment provides a method for face registration based on video data, comprising: receiving video data; obtaining a first image frame sequence from the video data, each image frame in the first image frame sequence each including a face detection frame containing complete facial features; determining whether the image frame reaches a preset clarity based on the relative position between the face detection frames in each image frame; if it is determined that the image frame reaches the preset clarity, extracting multiple groups of facial features based on image information of multiple face detection frames, and determining whether the faces represent the same object based on the multiple groups of facial features; and if it is determined that the faces represent the same object, registering the object based on the first image frame sequence. The disclosed embodiment also provides a device and an electronic whiteboard for face registration based on video data.

The present invention discloses a face authentication and recognition method, device, storage medium, and equipment. Among them, the method includes: when detecting that a user performs face registration, obtaining the face feature information of the above user and the 3D code style selected by the above user; determining an encryption key and an encryption algorithm corresponding to the above 3D code style; performing an encryption operation on the above face feature information by using the above encryption key and the above encryption algorithm to generate a face feature point ciphertext; generating a face authentication 3D code of the above user by using the above face feature point ciphertext and 3D code image information, wherein the above 3D code image information is determined according to the above 3D code style by using a 3D code generation algorithm. The present invention solves the technical problem that there is a risk of leakage of the user's face information in the prior art face authentication and recognition method.

The invention discloses a secure login method through face recognition. The secure login method comprises the following steps: S1, a face registration process: S101, binding a user account, a password and face features of an intelligent card; s2, a face recognition safe login process: S201, recognizing the face information of a current operation user by a camera, comparing through a built-in algorithm of the camera, acquiring a user account bound with the face information of the current operation user in the step S101 after the comparison succeeds, and if the comparison fails, stopping login and recording; and S202, after the comparison succeeds, matching the obtained user account with the user account of the smart card accessed by the current computer, if the matching succeeds, replacing the user to input a password, and if the matching fails, stopping login and recording.

The application discloses a logistics weighing safety control system based on face recognition and relates to the technical field of logistics transportation management.The system comprises a collection module, which is used for collecting the images of vehicles and drivers when the vehicles are weighed, and sends the processed images to a recognition module; the recognition module receives the images sent by the collection module, identifies the face images and vehicle images therefrom, extracts face feature information and vehicle information, and sends the face feature information and the vehicle information to a comparison module; and a storage module, which is used for storing vehicle and face registration information and receiving the vehicle information and the face feature information transmitted by the comparison module.The logistics weighing safety control system based on face recognition has significant technical advantages and practical value in improving the identity verification strength, safety prevention and control capability and management intelligent level of the logistics weighing link.

The embodiment of the invention discloses a face data entry method and device, equipment, a medium and a program product. A specific embodiment of the method comprises the following steps: in response to currently executed face data entry for a face registration object, obtaining an image of currently shooting the face registration object; determining facial feature information corresponding to the image according to the color information and the depth information; according to the facial feature information, generating a head posture and facial information corresponding to the image; and in response to determining that the head posture meets a posture condition set based on the visual angle of the robot, storing face data corresponding to the face registration object to a face database corresponding to the robot according to the face information so as to realize face information input under the head posture. The implementation mode is related to an intelligent robot, the face data under different head postures can be accurately and efficiently input into the robot, and efficient interaction between a subsequent object and the robot is facilitated.

To provide authentication technology that enables enhanced authentication accuracy while allowing users to enjoy the benefits of facial recognition-enabled gate devices.SOLUTION: An authentication device performs a predetermined subtraction operation on an authentication threshold to be compared with a score corresponding to the collation result between a face registration image linked to registration information and face image information of an entering person, allowing the collation result between the face registration image linked to the registration information and the face image information of the entering person to be prioritized over the collation result between the face registration image not linked to the registration information and the face image information of the entering person. The authentication device authenticates whether the person corresponding to the face registration image used to obtain the collation result with the highest difference between the score and the authentication threshold, among collation results favored because the face registration image is linked to the registration information and collation results not favored because the face registration image is not linked to the registration information, is the same person as the entering person.SELECTED DRAWING: Figure 1

To secure accuracy of information on a user while reducing load of the user on input operation for registration of face information on the user, with a simple configuration.SOLUTION: In a face information registration system 1, a face authentication server 2 stores identification information except face information of a user in a registration information database 29 and generates a two-dimensional code storing therein the identification information to transmit the two-dimensional code to a user terminal 6 used by the user or requests an external device 4 to generate the two-dimensional code and transmit the two-dimensional code to the user terminal 6, and a face registration terminal 3 acquires the two-dimensional code from the user terminal 6 and acquires the face information of the user to transmit the face information and the identification information included in the two-dimensional code to the face authentication server 2, and the face authentication server 2 stores information associating the received face information and identification information with each other in the registration information database 29 as registration information.SELECTED DRAWING: Figure 1

1. The name of this design product: Face Recognition Module (Smart Screen 3D). 2. Purpose of the product of this design: used for face collection, view analysis, data storage, face comparison, face recognition decision-making, face recognition management, application open interface and other requirements; performance requirements include modules for face detection, face registration, face recognition, response time and liveness detection. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention relates to an intelligent lock control system and method based on an embedded edge AI. The method comprises the following steps: firstly, building a system hardware platform by taking an edge intelligent computing K210 chip as a main component; secondly, face information acquisition is realized by adopting an OpenMV machine vision module; thirdly, training a face recognition model based on a YOLO deep learning network to realize face registration and recognition; then, an HC-08BLE4.0 Bluetooth communication module is adopted to realize data interaction between the WeChat applet and the intelligent lock, and transmission information is encrypted through an AES algorithm, so that the transmission efficiency is improved, and the communication security is ensured; finally, the system is externally connected with a matrix keyboard to achieve panel function operation of the intelligent lock, and meanwhile a motor drive circuit is externally expanded to achieve clutch control of the intelligent lock. The system has the functions of user management, face registration, face recognition unlocking, WeChat unlocking, record query and the like, and the intelligent lock WeChat applet improves the convenience of user operation. The intelligent lock control system designed by the invention has the characteristics of light weight, low cost and low power consumption, and better meets the design and market requirements of the intelligent lock.

The invention relates to a face authentication registration system, a face authentication apparatus, and a face authentication registration method. When face authentication is performed by accumulating face information of a user using a plurality of face authentication devices installed on a facility side, the occurrence of a different phenomenon that authentication can be performed in a certain device but cannot be performed in another device is prevented. A face authentication registration system (50) is provided with: a face registration server (30) that stores face information; and a plurality of face authentication devices (21-23) that register face information and use the face information in face authentication. When receiving a synchronization event of face information, the face registration server (30) performs a synchronization process of the face information on a plurality of face authentication devices (21-23) as a subject, and when one of the plurality of face authentication devices (21-23) fails to synchronize, the face registration server (30) performs a synchronization process of the face information on the plurality of face authentication devices (21-23). The face registration server (30) controls the plurality of face authentication devices (21-23) to return to a state before the synchronization process.

By utilizing facial recognition, visitors can enter a private space even when the owner is not present, while also enhancing security. [Solution] An authentication method using a system equipped with a facial recognition function and a visitor reception function, comprising: a visitor registration step in which a first user, who is the manager or owner of the occupied space, configures the system to allow a second user, who is a visitor to the occupied space, to enter the occupied space by facial recognition; and a facial registration step in which the second user registers their own face in the system using a second user terminal, which is an information terminal owned by the second user. The problem is solved by this authentication method and authentication system.

The invention relates to an account security operation processing method, which comprises the following steps: S1, establishing a face capacity shield and registering a background system, and applying data transmission of the background system for authentication; s2, acquiring face information of an account holder, performing face registration to generate registration information, and synchronizing a result to an application background system; and S3, the transaction is protected through the face capacity shield, the face capacity shield collects on-site face information of the operator to carry out living body recognition and verification, the face capacity shield generates transaction information and sends the transaction information to the application background system after the operator confirms the transaction information, and the application background system carries out verification and executes related operation and informs the client terminal of a transaction result. According to the invention, face information is not transmitted on line and is not stored in a terminal of a general operation system, so that the face information is strictly protected; the face acquisition process is carried out in a special customized safety device such as a face shield, and hackers cannot carry out attack and face video replacement like on a universal terminal; and the effect of confirming the practical operation of the person can be achieved.

The invention discloses a cross-modal non-inductive face processing method and device and electronic equipment, and belongs to the field of image processing. The method specifically comprises the following steps: extracting a first modal face image of a target face in a to-be-processed image; wherein the mode of the to-be-processed image is a first mode; extracting target face key point features and target face attributes corresponding to the first modal face image; obtaining a target average face set corresponding to the target face attribute; the target average face set comprises a second modal average face image corresponding to the target face attribute; generating a second modal target face image corresponding to the target face according to a second modal average face image corresponding to the target face attribute and the key point features of the target face; and performing non-inductive face registration and / or non-inductive face recognition of the target face according to the second modal target face image corresponding to the target face. According to the method, the data acquisition difficulty can be reduced, so that the cost of cross-modal non-inductive face processing is reduced.

To provide an authentication technique capable of enhancing authentication precision while having advantages of a gate device corresponding to face authentication.SOLUTION: An authentication device comprises: a processing unit which performs processing to link registration information showing a user of a portable terminal to one of a plurality of face registration images when the portable terminal of the intruder to the gate device is present nearby the gate device; and an authentication unit which extracts, as an authentication candidate, a face registration image whose score showing a collation result is equal to or larger than a predetermined authentication threshold in authentication processing to authenticate the intruder based upon collation results between face image information on the intruder and the plurality of face registration images, and performs the authentication processing while giving priority to a collation result between a face registration image linked to the registration information and face image information on the intruder when the face registration image linked to the registration information is included in the authentication candidate, or performs the authentication processing without giving priority to the collation result between the face registration image linked to the registration information and face image information on the intruder when the face registration image linked to the registration information is not included in the authentication candidate.SELECTED DRAWING: Figure 1

The invention provides a face recognition method and device, electronic equipment, a storage medium and a program product, and relates to the field of biological recognition. The method comprises the following steps: acquiring a to-be-recognized face image; outputting the face image to a pre-trained face recognition model, and obtaining a face recognition result output by the face recognition model; the face recognition model is obtained by training based on a face registration image set, a face image set, a face key point set and a face enhancement image set; face enhancement images in the face enhancement image set are provided with face masks generated according to the face key point set; and outputting the face recognition result. According to the method provided by the invention, the face recognition model is trained through the existing training data set and the face enhancement image set, so that the performance of the face recognition model is improved, and the accuracy of face recognition is improved.

Provided is a face recognition system that does not require management by a management company or the like and can be safely started or the user can be changed only by the residents. 【Solution means】A face registration means for registering face data which is a face image of a user or its processed data, a photographing device installed in an apartment house, a resident registration means for registering the user as a resident of the apartment house, an authentication means for collating the face photographed by the photographing device with the face data of the resident, and a security token which is a physical object delivered to a resident of the apartment house and is a device, instrument, or electronic medium for proving that the user is a resident of the apartment house. The face recognition system solves this problem by requiring that the user performing the registration operation holds the security token at the time of resident registration.

The present disclosure relates to a moving object, a control apparatus, and a control method capable of performing intuitive face registration. A gesture control section controls a gesture driving that expresses a movement of a face of a user by a gesture at the time of a streaming capture in subsequent processing of a tutorial of face registration processing that registers the face of the user in advance, and a guidance sound control section controls an output of a gesture guidance sound in accordance with a gesture of the gesture driving. The present technology is applicable to an agent-type robot apparatus capable of performing autonomous traveling.

1. The name of this design product: Handheld entry detector. 2. Purpose of the product with this appearance design: A detector used for taking photos of people entering the venue for face registration and detecting whether they are carrying metal objects. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The present application provides a processing circuit applied to a face recognition system, which includes a feature value calculation module, a judgment circuit and a threshold value calculation module. The feature value calculation module is used to receive an image and process the image to generate a specific feature value; when the face recognition system operates in a face recognition stage, the judgment circuit calculates a plurality of differences between the specific feature value and a plurality of reference feature values respectively, and judges whether at least one difference is lower than a threshold value in the plurality of differences to generate a judgment result; and when the face recognition system operates in a face registration stage, the threshold value calculation module determines a new threshold value according to the differences between the specific feature value and the plurality of reference values to update the threshold value used by the judgment circuit.

To prevent generation of a case in which the face of a user can be authenticated in one system and cannot be authenticated in another system when the face information of the user is stored by a plurality of face authentication machines set in a facility so that the face is authenticated.SOLUTION: A face authentication registration system 50 includes: a face registration server 30 for storing face information; and a plurality of authentication devices 21 to 23 for registering face information and using the face information for face authentication. The face registration server 30 receives a synchronization event of the face information and executes synchronization processing of the face information on the plurality of face authentication devices 21 to 23 as targets, and performs control so that the face authentication devices 21 to 23 are returned to the state before synchronization even if one of the face authentication devices 21 to 23 fails to be synchronized.SELECTED DRAWING: Figure 8

The application provides a bearing double-end-face image registration and difference comparison defect detection method and system, relates to the technical field of machine vision detection, and the method comprises the following steps: extracting bearing outer circle contours and inner hole edges in a first end face standard image and a second end face standard image, and constructing an annular feature band; determining first and second microtexture anchor points on the annular feature band; establishing a local rectangular coordinate system with the first microtexture anchor point as the origin; and when it is detected that the vector azimuth angle of the second microtexture anchor point relative to the first microtexture anchor point is offset, a rotation compensation matrix is calculated. The application gradually completes image preprocessing, global coarse registration, accurate fine registration and defect identification, effectively improves the bearing double-end-face registration accuracy, accurately filters out interference and extracts defect features, realizes the determination of bearing end face defect types and positions, and improves the detection efficiency and accuracy.

A face registration method and device based on a 3D structured light camera, the method captures video stream data of a user's face through the 3D structured light camera; pushes the captured video stream data of the user's face into a server of an industrial computer system through an RTMP service; the host computer system acquires the video stream data of the user's face through the server of the industrial computer system, and according to the video stream data of the user's face, performs scanning and recognition processing on the user's face to complete user face registration; the industrial computer system performs live detection and picture quality detection on the registered user's face, and performs screenshot processing on the user's face picture that has passed the detection; the host computer system performs preliminary processing on the received screenshot and sends it to a cloud server; the cloud server registers the user's face according to the screenshot to complete user face registration and cloud backup. The application can adapt the 3D structured light camera to the Kirin system and realize fast and accurate face registration.