177 results about "Face verification" patented technology

The invention relates to the technical field of face verification, and discloses a face identity verification data processing method based on dynamic feature extraction, which comprises the following steps: acquiring a continuous face video frame sequence and calculating a full-pixel instantaneous velocity vector to generate an original dense optical flow field, selecting rigid region anchor points to calculate a rigid affine transformation matrix and construct a theoretical rigid motion field, performing differential stripping on the theoretical rigid motion field from the original dense optical flow field, and extracting a non-rigid micro-motion residual field; mapping the non-rigid micro-motion residual field to a facial muscle topological grid to generate a time sequence feature tensor, and calculating a geodesic line distance between a covariance matrix of the time sequence feature tensor and a reference dynamic feature in a Riemannian manifold space; when the geodesic distance is smaller than a threshold value, verification is passed, through a rigid-non-rigid orthogonal decomposition mechanism, the special viscoelastic micro-motion and cooperation law of biological soft tissue is captured by utilizing a residual field, and the high-simulation mask is effectively defended.

The invention relates to the technical field of intelligent construction site management, and particularly discloses a labor service management system for a construction site, and the system comprises a real-name management module which is used for inputting real-name data of labor service personnel; the attendance checking module is used for acquiring entry registration and exit registration information of the labor service personnel every day and generating an attendance checking record according to the entry registration and exit registration information, and the salary management module is used for automatically calculating basic salary according to an attendance checking report; the server is also used for analyzing whether the basic salary in the labor service salary table is consistent with the basic salary calculated by the attendance report, and if not, generating a salary making and issuing error early warning; and the registration verification module is used for acquiring the personnel photo of the work site, identifying the personnel identity according to the personnel photo and the input face verification information, judging whether the real-name labor service personnel have the corresponding entry registration of the day or not, and generating an unregistered prompt if the real-name labor service personnel do not have the corresponding entry registration of the day. According to the technical scheme, the construction site labor service management efficiency can be effectively improved, and labor service disputes are avoided.

Method of 3D face verification, includes verifying that user is positioned in standard orientation so that head rotation angles are small; capturing image of user's head at first position; generating PIN and transmitting it to a user device; upon receipt of the PIN, instructing the user to rotate his head to a first position indicated by the PIN and a corresponding graphic; repeating instructions to the user to rotate his head for all remaining values of the PIN, and capturing images of the head at positions corresponding to the remaining values of the PIN; transforming yaw and pitch angles of the user's head in the captured images into a polar coordinates graph; transforming the graph into a phase map; sending the phase map into machine learning classifier; securely sending and storing personal information to the server; determining, using the machine learning classifier, whether the head is a live 3D face.

The invention relates to the technical field of identity verification, in particular to a user login monitoring method, device and equipment and a medium, and the method comprises the steps: sending login information of a website of a server management chip of a user login server to the server, so that the server verifies the login information; after the information that the server login information passes verification is received, the user first image collected by the camera device is further obtained so as to be conveniently sent to the server for face verification, a second-layer verification mechanism is added, non-inductive second-layer verification can be achieved through face verification, and the user experience is improved. According to the method and the device, the access authority to the server management chip can be obtained only after the user passes two layers of verification, namely login information verification and face verification, so that the safety of the system is improved, and the user experience is improved.

Embodiments of a system and method enable secure connectivity between the computer systems of a financial institution and software for Brand On Banking. Embodiments of the system include an Identity Platform, Know Your Customer (KYC) processes including ID card verification, face verification, document verification such as utility bills as proof of address, and biometric verification, and bank servicing features such as checking, savings, debit, payments, loans, and bill-pay. The secure connectivity is established in various embodiments through private or public Application Programming Interfaces (APIs) over a network service provider, thus eliminating third-party risk for the financial institution. Additionally, the system allows for displaying alternate brands and identifying customers associated with a specific product brand other than the financial institution. The mobile interface is user-friendly and consolidates all financial accounts in one location, reducing customer friction.

The invention discloses a safe access judgment method and system for saas platform designated drivers. The invention relates to the technical field of SaaS online car-hailing platforms. Matching identity information submitted by the current driver from an identity library; and if the identity information does not exist in the identity library, carrying out OCR identification on the photo of the identity information. The identity information comprises an identity card and a driving license; wherein the OCR result is compared with the submitted identity information, and if the OCR result is consistent with the submitted identity information, automatic If not, manual reexamination is carried out; the effective identity document information database is used for verifying the authenticity of the identity of the driver; through strict face verification, certificate verification and certificate data authenticity verification, the authenticity and legality of the identity of the driver can be ensured, identity false use and fraudulent behaviors are effectively prevented, and thus the safety of designated driving service is improved. According to the method, the age, driving age, illegal behavior records and the like of the driver are comprehensively checked, the driver is ensured to meet platform requirements and laws and regulations, and the compliance of designated driving service is enhanced.

The present invention allows for the creation of a biometrically secure environment that allows viewing, editing and sharing of confidential documents, or the like, in public places, without worrying that someone will see the contents. The invention provides privacy, for example for the purposes of reading documents, in a public environment while having the confidence that you are the only one able to read the document. Privacy may be achieved through methods of identification using biometric features, such as: face, iris or voice recognition. Verification that a real person is viewing the document may also be achieved by pulse recognition. In one embodiment, the screen will shut down when more than one person looks directly at the screen. In different embodiments, the present invention may use voice recognition, print behavior, iris scan, finger print, face verification, etc. A control panel and dashboard may be used, and liveness check or activity audit may be performed. In further embodiments, a document may be securely shared with groups of recipients; a user may be authenticated while video chatting; voice commands may be used to upload, share, send, and open documents; commands may be provided to allow for documents to be read out loud; documents that are shared during screen sharing during a video conference session may be logged; and documents may be scanned and uploaded into the system.

The invention relates to the technical field of attendance management, in particular to an intelligent electronic work card and a data management system thereof, the system comprises a face verification module, a card punching scale block, a behavior evaluation module, an authority isolation module and a risk push module, and based on collected face key point images, key point boundaries and archive standard images are compared point by point. According to the invention, through multi-level fusion of face feature point comparison and attendance behavior data and time sequence cooperative verification of card punching records and identity verification data, dynamic identification of identity authenticity and behavior track association is realized, and through combination of equipment affiliation determination and a sensitive label triggering mechanism, hierarchical management of sensitive data access is enhanced. According to the invention, the method supports the active push of abnormal operation based on the man-hour and track comprehensive discrimination process, can reflect the types and risk levels of abnormal behaviors in multiple dimensions, enhances the timeliness and refinement degree of risk response, and improves the application capability of intelligent early warning in attendance management.

The invention relates to the technical field of laser cutting, and discloses a laser cutting platform control system based on image recognition, which comprises an equipment unlocking module, an equipment control module and a cutting control module, the equipment unlocking module comprises a face recognition module and an electrical equipment unlocking module; the equipment control module comprises an image acquisition module, a coordinate establishment module and a cutting control module; and the equipment unlocking module is used for carrying out limited unlocking on the equipment control module and the cutting control module by the electrical equipment unlocking module according to a face verification passing instruction of the face recognition module. The equipment control module is used for collecting information of the four positioning stickers on the plate, so that cutting coordinates can be established according to the position of the plate, the plate is cut according to the cutting coordinates, the plate can be placed on the cutting platform at any angle to be cut through the design, and the cutting efficiency is improved. And the laser cutting operation can be carried out without positioning the plate.

The invention belongs to the field of block chains, and particularly relates to a cross-chain transaction batch processing method of a block chain. The method comprises the following three core processes: firstly, a grouping device groups cross-chain transactions to generate cross-chain transaction to-be-processed groups, and ensures that the quantity of each group of transactions conforms to the on-chain limitation through balance adjustment; secondly, the aggregator network eliminates a repeated calculation part of a Merkle verification path in the cross-chain transaction group to be processed, constructs an aggregation transaction (ATX) containing the cross-chain transaction group and aggregation proof, and reduces redundant hash calculation; and finally, the light client executes dual verification, firstly verifies the consistency of the ATX aggregation proof and the block header Merkle root submitted by the oracle machine, and then verifies the validity of the Merkle root set submitted by the aggregator network. The face verification time and cost of the cross-chain transaction can be greatly reduced, and the method is suitable for large-scale cross-chain scenes such as decentralized finance and cross-chain payment.

The invention discloses a door lock camera cooperative processing method and system, and the method comprises the steps: generating an identity verification request message according to a doorbell button signal detected by a door lock, and transmitting the identity verification request message to a corridor camera A covering the door lock; according to the identity checking request message, the camera A obtains a face feature vector of a person in front of the door lock, similarity matching is carried out on the face feature vector and a house owner feature vector, if the similarity exceeds a first threshold value, it is judged that verification is passed, and a face verification result is obtained; according to the face verification result, a robot calling instruction is sent to the platform, and the robot is triggered to move to the door lock position; according to a human face image collected after the robot reaches the position of the door lock, if the similarity between the human face image feature and the target human face feature exceeds a second threshold value, unlocking of the door lock is authorized, and the unlocking state is fed back to the platform. According to the embodiment of the invention, efficient, safe and intelligent access control can be realized.

The present application discloses a method, apparatus, device, and storage medium for obtaining the true value of a head pose. Images of a target object are collected by multiple image acquisition devices at the same time, and the two-dimensional face key points marked in the multiple collected images are used as the data basis for three-dimensionally reconstructing the face key points of the target object, and then the true value of the head pose of the target object corresponding to the images is obtained. Since this solution does not need to rely on a wearable device to obtain the true value of the head pose, it is not affected by the wearing angle. By using multiple image acquisition devices at the same time and three-dimensionally reconstructing the face key points, the accuracy of the obtained true value of the head pose is guaranteed. Furthermore, when the true value of the head pose is applied to fields such as driver fatigue degree analysis, virtual reality somatosensory games, commodity purchase desire analysis, and face verification, the analysis results of the data can be made more accurate.

Embodiments of the present application provide an image processing method, device, storage medium and program product. The method synchronously performs face verification and key point regression by using an end-to-end single model, and optimizes the multi-stage processing flow in the related art into integrated operation. The calculation delay and memory occupation are significantly reduced, the consumption of calculation resources is reduced, and the method can be deployed in a mobile device or an embedded system with limited calculation resources. Since the classification task and the regression task share the same feature representation, the model can improve the accuracy of face verification while keeping a small amount of parameters, and effectively reduce the probability of misjudging a non-face area as a face. This double protection mechanism ensures that the key point detection result is output only on the confirmed face image, thereby improving the reliability of subsequent applications.

The present invention relates to a face verification system based on a lensless camera. The system comprises a lensless mask, a camera sensor, and a controller. The lensless mask is used for lensless imaging of a face, and its parameters are optimizable. The camera sensor is used to capture a face image formed after passing through the lensless mask. The controller is used to directly perform face verification based on the face image captured by the camera sensor. The training process of the controller includes: establishing an imaging model for the lensless mask; inputting the face image into the imaging model to obtain a lensless imaging result; then inputting the result into a face verification model to be trained to obtain a face identity prediction result; calculating a loss function based on the face identity prediction result, thereby jointly optimizing and training the imaging model and the face verification model; and the face verification system optimizes the parameters of the lensless mask based on the trained imaging model. Compared with the existing technology, the present invention enhances the security of face data and improves prediction accuracy.

The utility model discloses a multifunctional verification all-in-one machine which comprises a verification all-in-one machine host and a face verification camera arranged in the center of the front end of the top of the verification all-in-one machine host, a light supplementing lamp is further arranged on the left side of the face verification camera, and an RFID card reading panel is arranged on the right side of the face verification camera. The RFID card reading panel is used for sensing and reading RFID certificate information, a novel health protection device is additionally arranged on the upper side of the center of the rear end of a host of the verification all-in-one machine, the device is controlled by a host control terminal through an electric wire, a large amount of disinfectant can be injected into a liquid storage tank through a liquid adding opening, and when the all-in-one machine is used, the control terminal controls a small booster pump to pressurize the liquid storage tank, so that the liquid storage tank is protected from being damaged. Disinfectant flows to the atomizing nozzles through the plastic conveying pipe, the angles of the two forward atomizing nozzles are flexibly adjusted through the universal bent pipe, the sprayed atomized disinfectant accurately acts on a user, the surface of the body is disinfected and sterilized during identity verification of the user, and the risk of cross infection is reduced.

The invention discloses a natural face verification method for a military computer system, and the method comprises the steps: obtaining the image data of a face, which comprises a face image obtained based on a camera and a face thermal image obtained based on a thermal imager; image processing, wherein a target texture image is obtained through texture algorithm processing of the face image, and a target thermal image is obtained through thermal image texture algorithm processing of the face thermal image; fusing the target texture image and the target thermal image by adopting a feature weight fusion method to obtain a fused image; and performing model training based on the fused image to obtain a face verification model based on face image and face thermal image judgment, and verifying the face based on the face verification model. According to the method, the face image and the face thermal image are combined, so that the accuracy of the face verification model is higher, many problems caused by image recognition can be avoided, and the identity recognition efficiency of an army unit is improved.

To provide a system, a face authentication platform and an information processing method capable of improving convenience for a user.SOLUTION: The face authentication platform 10 includes the control unit 12 that functions as the token issuing means 13, the cooperation information updating means 14, and the like by executing a program, the token issuing means 13 issues a token for cooperation and transmits the token for cooperation to the user terminal 20 when receiving cooperation start information from the user terminal 20, and the cooperation information updating means 14 updates the cooperation information stored in the storage unit 18 so as to cooperate with the management server 30 when receiving a cooperation completion notification from the management server 30. The management server 30 includes a control unit 32 that functions as a cooperation completion notification means 34 that transmits a cooperation completion notification to the face authentication platform 10 when the cooperation token is received from the user terminal 20 by executing a program.SELECTED DRAWING: Figure 1

The application discloses a face anti-counterfeiting method and device and a storage medium. The face anti-counterfeiting method comprises the following steps: acquiring a to-be-detected image collected by a 2D monocular camera; acquiring a depth factor corresponding to each pixel coordinate point of the to-be-detected image through a preset face depth model; converting the to-be-detected image into a 3D space information image according to the depth factor and preset camera parameters; judging whether the converted 3D space information image is a plane false face; and if the 3D space information image is not a plane false face, judging whether the to-be-detected image is a three-dimensional false face through a preset three-dimensional anti-counterfeiting model. Thus, the face depth model and the three-dimensional anti-counterfeiting model are used to realize two-dimensional and three-dimensional anti-counterfeiting of the image through the 2D monocular camera. The hardware requirement for the camera is reduced without the action cooperation of the verifier, the face verification efficiency is improved, and the face anti-counterfeiting accuracy is improved.

The invention relates to the technical field of electronic equipment, and provides a notebook computer startup verification method and device, a notebook computer and a storage medium. According to the application, the startup signal of the notebook computer is detected and the ambient light brightness is acquired at the same time, so that the notebook computer can automatically adjust the acquisition brightness of the infrared camera according to the intensity of the ambient light brightness; the self-adaptive adjustment of the acquisition brightness of the infrared camera ensures that clear face images with appropriate contrast can be captured in different illumination environments. The collected face image is subjected to light reflection removal processing, so that the influence of factors such as ambient light and screen light reflection is eliminated or reduced, and the quality of the face image is further improved. According to the method, the notebook computer is subjected to startup verification based on the high-quality target image, so that identification errors caused by the image quality problem are reduced, and the safety of the notebook computer is enhanced. The technical problem of face verification failure caused by dynamic change of ambient light brightness is solved.

The present invention discloses a security management system for storing face image data, belonging to the technical field of face image data security management, which includes a stored data processing module, a user terminal, and a data verification and scheduling module; the stored data processing module is used to process the face image data stored in the access control database; the user terminal is for user use and includes a face data management module and a face verification module; the face data management module is used for the user to manage the corresponding face information; the data verification and scheduling module is used for data verification and scheduling during access control face recognition; the face verification module is used for face verification; through the mutual cooperation among the stored data processing module, the user terminal, and the data verification and scheduling module, the secure processing of the user face data stored in the community access control is realized, avoiding the leakage of the user face data stored in the existing access control system; and enhancing the confidence of users in using face recognition.

Method of 3D face verification, includes verifying that user is positioned in standard orientation so that head rotation angles are small; capturing image of user's head at first position; generating PIN and transmitting it to a user device; upon receipt of the PIN, instructing the user to rotate his head to a first position indicated by the PIN and a corresponding graphic; repeating instructions to the user to rotate his head for all remaining values of the PIN, and capturing images of the head at positions corresponding to the remaining values of the PIN; transforming yaw and pitch angles of the user's head in the captured images into a polar coordinates graph; transforming the graph into a phase map; sending the phase map into machine learning classifier; securely sending and storing personal information to the server; determining, using the machine learning classifier, whether the head is a live 3D face.

The invention discloses a self-service face verification method based on a configurable loan product process. The method comprises the following steps: face verification process information is configured; distributing a video room according to the loan customer identity information; playing a face-to-face question according to the face-to-face process information, and capturing and identifying an answer of the loan customer; confirming a loan willingness result according to the answer content of the loan customer; if the loan willingness result is loan confirmation, verifying the loan person, the loan information and the loan willingness result; if the information is verified to be correct, guiding the loan customer to contract a contract and submit a credit application; and recording and storing data in the kernel process. The method has the advantages of high efficiency, high safety, high matching degree and low cost.

The invention discloses a safety management system for face image storage data, which belongs to the technical field of face image data safety management and comprises a storage data processing module, a user side and a data verification scheduling module. The stored data processing module is used for processing the face image data stored in the access control database; the user side is used by a user and comprises a face data management module and a face verification module; the face data management module is used for a user to manage corresponding face information; the data verification scheduling module is used for performing data verification scheduling during access control face recognition; the face verification module is used for performing face verification; through mutual cooperation of the storage data processing module, the user side and the data verification scheduling module, safety processing of user face data stored in a community access control is realized, and leakage of user face data stored in an existing access control system is avoided; and the confidence of the user in using face recognition is improved.

The invention discloses an intelligent inspection method and system for a machine room and electronic equipment. The method is applied to a server, and comprises the following steps: receiving current position information and face verification data from a mobile terminal; if both the position verification and the identity authentication pass, pushing an inspection task list bound with the target machine room to the mobile terminal; receiving inspection data of the mobile terminal; in response to a patrol check-out request initiated by the mobile terminal, calculating the duration time of the patrol, and executing check-out confirmation after confirming that the duration time meets a preset minimum patrol duration constraint, so as to generate a closed-loop patrol record; accumulating closed-loop inspection records to form a historical inspection data set; extracting associated features according to the historical inspection data set; an inspection scheduling table is generated through a machine learning algorithm; and issuing the inspection scheduling table to a mobile terminal of a corresponding inspector, dynamically updating the associated features, and iteratively optimizing the scheduling model. According to the invention, the authenticity, normalization and result credibility of machine room inspection work can be ensured.

The invention provides a human face living body detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining to-be-detected human face data; inputting the to-be-detected face data into a face living body detection model to obtain a living body detection result; wherein the human face in-vivo detection model is obtained by training based on a training sample, the training sample at least comprises human face sample data and a correspondingly labeled human face expression category label, and the human face expression category comprises an unconventional human face expression. According to the invention, the human face sample data of the unconventional human face expression is added to the training sample to train the human face living body detection model, and the human face living body detection model can learn various human face expression features of the user, so that the robustness of the human face living body detection model to the unconventional human face expression of the user is enhanced; the accuracy and reliability of identity verification based on face living body detection are improved, and the face verification anti-counterfeiting recognition intensity is improved.

The present invention discloses a method and device for ensuring the consistency between the actual online car-hailing driver and the registered driver when driving. This method forms a comprehensive identity verification strategy for face recognition of the driver to be verified by judging whether the number of identity verification failures exceeds the failure threshold, querying the first identity verification request of the day, querying whether the previous identity authentication failed, detecting whether the driver to be verified has changed the mobile terminal, and executing the random recognition process in the selection order from top to bottom. It eliminates the traditional single face recognition identity verification for business, is effective and feasible, and improves the accuracy and efficiency of driver identity verification; it also avoids overly frequent face verification, reduces the impact on driving safety, and improves the user experience.

The invention relates to a building entrance guard linkage processing system, which comprises an electronic control part connected with a face verification part of a resident building entrance guard and used for starting linkage of face verification of the face verification part and entrance guard opening in a current time segment when receiving a visitor excessive signal, and otherwise, closing the linkage in the current time segment; and the signal conversion mechanism is used for sending a signal of excessive visitors when the number of visitors in the current time segment of the resident building obtained through intelligent analysis is greater than or equal to a set number threshold value. According to the invention, an intelligent analysis mode can be adopted to predict the number of visitors at the entrance guard of the resident building in the current time segment, and when the predicted number of visitors is too large, linkage of face verification and entrance guard opening of the face verification component is started in the current time segment, otherwise, linkage is closed, so that the access control of the resident building is realized. Therefore, the working efficiency and the mute requirement are both considered.

The utility model relates to a real-name authentication gate machine, which is applied to stations in public transportation operation of intercity railways, and is used for checking the identity of passengers when the passengers enter the stations. The public transportation riding voucher identification equipment comprises a code scanning head for identifying a paper two-dimensional code one-way ticket and an electronic riding code and an antenna for reading and writing a transportation card, a face verification tool; when the antenna or the code scanning head reads the unique code of the riding voucher, the industrial personal computer obtains the face id correspondingly bound with the riding voucher with the unique code from the server, the industrial personal computer transmits the face id to the face verification machine tool, and a screen of the face verification machine tool starts face information collection; the face verification machine tool compares the face id with the portrait information, if the face id and the portrait information are consistent, the industrial personal computer opens the gate, and if the face id and the portrait information are not consistent, the gate is kept in a closed state. According to the utility model, three-in-one ticket checking, authentication and verification of tickets, certificates and persons are realized, and the railway operation safety is ensured.

The present invention discloses a face verification privacy protection method and device. By loading the model parameters optimized by the present invention into the perturbation migration network T, corresponding privacy-protected image adversarial samples can be generated according to different facial images to be protected of different users. By uploading the privacy-protected image adversarial samples to the social platform, even after the platform's image compression processing, it cannot perform effective information processing activities after being captured by unauthorized malicious third parties, thereby ensuring the privacy security of users in the image sharing service process. The privacy-protected adversarial samples generated by the method of the present invention are real and natural. Through the two-stage collaborative generation framework of the user end and the server end, it is ensured that the server end does not need to obtain the user's original image in the process of constructing the adversarial sample, effectively avoiding the problem of information leakage of the user image on the server end, and enhancing the security of the privacy protection process itself.

The invention relates to the technical field of machine learning, can be applied to the fields of finance and medical treatment, and particularly discloses a model score mapping method and device based on piecewise linear interpolation, equipment and a medium. The score mapping formula is dynamically adjusted to adapt to the mapping requirements among different score models, the mapping accuracy is improved, the evaluation accuracy is further improved, the model score mapping method is applied to tasks such as face verification and medical image diagnosis when a financial account logs in, and the evaluation accuracy is improved. The scores of a plurality of scoring models actually used by the task can be accurately mapped, effective and accurate consistency scores are obtained, and then the evaluation accuracy is improved.