274 results about "Facial identity" patented technology

An automated elevator control system using facial recognition, comprising an elevator car, a facial image database comprising facial image data of authorized passengers and corresponding authorized floor destination data for each such passenger, a facial recognition program capable of comparing a facial image stored in the facial image database to video data output from an imaging device, and an imaging device capable of outputting video data. The system is capable of recognizing the elevator passenger's face in a field of view of the imaging device, capturing the elevator passenger's facial image using video data output from the imaging device, and comparing the captured facial image to pre-registered facial image data. Upon determining a match between the captured facial image and a stored facial image, the system is capable of sending a signal to the elevator control system to move the elevator car to the elevator passenger's authorized floor destination.

A system and method includes detecting motion in a space; capturing images of a scene in a direction of the motion within the space by peripheral image capturing devices and detecting a body of a person within the images of the scene; extracting an image of the body from the images of the scene; identifying a head of the body based on the extracted at least one image of the body and extracting an image of a head from the extracted the one image of the body; transmitting the one image of the body to a body tracking module; transmitting the extracted image of the head to a face detection module; in parallel, tracking the body within the space and performing by a facial recognition module facial recognition of the extracted image of the head of the body; and determining an identity of a user associated with the body.

The invention relates to a facial-recognition-based network teaching method and system. Facial feature identification can be carried out on a student in real time during the whole courseware learning period, so that the network teaching can realize the same effect as the face-to-face teaching. Meanwhile, a certain number of times of failure is allowed, so that a stable and smooth learning environment can be provided for the student in a real-time monitoring mode and the learning of the student can be prevented from being influenced due to the detection failure or other factors. In addition, the system also provides expression management, so that the teacher can know the reflection of the student conveniently during the courseware learning and thus the network teaching environment is close to the face-to-face teaching. On the basis of the off-line learning function provided by the system, the student can carry out learning on any occasion and an objective of real-time monitoring can be achieved. Besides, with the log management module provided by the system, no more network flow is increased because of real-time monitoring when the student uses a mobile terminal for learning, thereby lowering the learning cost.

A face illumination normalization method includes acquiring a digital image including a face that appears to be illuminated unevenly. One or more uneven illumination classifier programs are applied to the face data to determine the presence of the face within the digital image and / or the uneven illumination condition of the face. The uneven illumination condition may be corrected to thereby generate a corrected face image appearing to have more uniform illumination, for example, to enhance face recognition.

A method is provided for simultaneously recognizing facial attributes and identity to organize photo and / or video albums, based on modifying an efficient convolutional neural network (CNN) which extracts facial representations suitable for face identification and attribute (age, gender, ethnicity, emotion, etc.) recognition tasks. The method enables to process all the tasks simultaneously, without a need for additional CNNs. As a result, a very fast facial analytic system is provided, and the system can be installed onto mobile devices.

An automated screening system includes an access control reader with one or more computer devices for screening a pre-registered individual seeking admittance into a controlled area. The system has a facial recognition database that stores a facial record for the individual. A camera system captures a facial image of the individual and the one or more computer devices determine whether it matches the facial record that is stored in the facial recognition database. A skin temperature sensor is used for obtaining a skin temperature reading for the individual. The one or more computer devices are configured to generate an electronic signal to admit the individual into the controlled area if the captured facial image matches the facial record that is stored in the facial recognition database and if the skin temperature reading for the individual is within an acceptable pre-established skin temperature range.

A system may receive a primary image containing a first set of facial feature data. The primary image may be sent by a facial recognition device for association with a user account. The system may also retrieve a secondary image from a secondary image source. The secondary image may contain a second set of facial feature data. The secondary image may further depict a user associated with the user account. The system may then compare the first set of facial feature data to the second set of facial feature data to determine whether the primary image depicts the user associated with the user account.

A digital image processing apparatus for easily obtaining information regarding a face, a method of controlling the same, and a recording medium for storing a program for executing the method. The digital image processing apparatus includes a face recognition unit recognizing a face from an image, a face index assignment unit assigning a face index to the recognized face if the face recognized from the image is not a previously recognized face, and a relation index update unit that, if the image includes a second face, updates a relation index corresponding to the number of times the first face and second face appear together in a plurality of images.

A method is provided for validating an individual's identity by using a combination of a RFID card, signature captured by a touch screen computer, and a facial photo captured by a built-in camera of a touch screen computer. Using third party biometric signature recognition algorithms and facial recognition algorithms are preferred to differentiate the differences between a sample signature and facial photo referenced by a RFID card value.

The present invention relates to a method of verifying that (or determining whether) a live human face is present. More particularly, the present invention relates to a method of verifying that (or determining whether) a live human face is present for use as part of a facial recognition system and / or method. In particular, the invention relates to a method 100 of determining whether a live human face is present, comprising: generating 102 a stimulus 206; predicting, using a model 214, human face movement in response to said generated stimulus; presenting 104 the stimulus to a face of a person; tracking 106 a movement of the face in response to the stimulus using a camera; and determining 108 whether a live human face is present by comparing the movement of the face against said prediction.

The present invention relates to a system and method for efficiently generating images and videos as an array of objects of interest (e.g., faces and hands, plates, etc.) in a desired resolution to perform vision tasks, such as face recognition, facial expression analysis, detection of hand gestures, among others. The composition of such images and videos takes into account the similarity of objects in the same category to encode them more effectively, providing savings in terms of time transmission and storage. Transmission time is less advantage to such a system in terms of efficiency, while less low cost storage means for storing data.

A facial recognition authentication process operating on a device may capture an image of a user using a camera on the device. The facial recognition authentication process may include operating a full face facial recognition authentication process on the captured image or operating a partial face facial recognition authentication process on the captured image. The process may determine which process to operate (either full face or partial face) based on an assessment of an amount of occlusion in the captured image. The partial face facial recognition authentication process may be operated when there is at least some occlusion of selected features (e.g., nose and / or mouth) on the user's face in the captured image.

The present invention teaches a purchase enabling database consisting of customer records which each contain 1) sufficient commercial information about a customer to enable an electronic purchase and 2) a face key of electronic facial recognition identity data allowing electronic comparison to a submitted facial identity code candidate. If the facial recognition of the candidate face indicates a match, the individual is able to make a commercial transaction without further exchange of financial information, thus allowing the user / customer to make a purchase. A system embodiment allows a subscribing vendor to embed facekey enablement in their own vending website / software / hardware.

The invention discloses a facial expression recognition method based on joint learning identity information and emotion information, which comprises a face recognition image database and a facial expression image database, wherein the facial identity information network branch is independently trained by using the face recognition image database, the last full connection layer is removed after thetraining, and the identity feature vector of the input image can be extracted through the neural network; The facial expression information network branch is trained by facial expression image database. After the whole connection layer is removed, the affective feature vector of the input image can be extracted by neural network. Identity feature vector and affective feature vector are concatenated to get concatenated facial feature expression. The cascaded facial expression features fusing the identity information and the facial information are fed to the full connection layer, and the subsequent training only uses the facial expression image database for joint learning and optimization of the merged network. The present invention improves the robustness of the facial expression recognition method to self-differences between subjects.

The invention discloses a specific facial identity-based face identification access control system and an implementation method, belonging to the technical scope of safety management. The access control system comprises image acquisition equipment used for shooting a face picture or video of a person about to enter an access control position, an access control acquisition terminal used for inputting a facial feature code by the person about to enter the access control position, and a back-stage management end being a common PC (personal computer) or an industrial computer; the image acquisition equipment, the access control acquisition terminal and the back-stage management end realize communication by means of a transmission network or a wired transmission way. The implementation method is characterized in that personnel facial feature identities are adopted to mark face photos of managed objects, one face photo can be quickly retrieved by inputting the corresponding code and is compared with the face photo shot on site to be verified, a security and protection base front-line unit is helped to perform access control management, and the condition in the past that an unimaginable million-level huge-number photo library needs to be compared is changed into the reality that a feature identity (or code) is retrieved for one to one comparing on site.

A facial recognition system for customer relationship management (CRM) is provided. The system includes one or more cameras, point-of-sale (POS) terminals, and a backend server. The one or more cameras are disposed within a retail establishment, and are configured to capture one or more images of a patron within the establishment. The point-of-sale (POS) terminals are operably coupled to the one or more cameras, where one or more of the POS terminals receives the one or more images, and transmits a request over a network for recognition of the patron. The backend server is disposed other than where the POS terminals are disposed, and is operably coupled to the POS terminals via the network, and is configured to receive the request, to recognize the patron, to access loyalty program data corresponding to the patron, and to transmit the loyalty program data to the POS terminals.

The invention relates to the technical field of security and protection, and provides a face recognition security and protection attendance system which comprises a video acquiring end, a character identity information base, a character information training module, a character information matching base, a character face feature base, a character information recognition module and an automatic attendance module, wherein the video acquiring end is used for acquiring character face features; the character identity information base is used for recording character identity information comprising names and identities (IDs); the character information training module is used for analyzing face recognition marks corresponding to characters; the character information matching base is used for carrying out unique mapping matching between the character identity information and the face recognition marks analyzed by the character information training module to obtain individual face marks; the character face feature base is used for storing matching results of the character information matching base, namely, individual face recognition marks; the character information recognition module is used for matching the individual face marks extracted from the character face feature base with the character face features acquired by the video acquiring end in real time to obtain character identity information; and the automatic attendance module is used for generating a report generation base of an attendance report according to the character position information and the character identity information.

The embodiment of the invention discloses a virtual image model generation method, a device and a storage medium, belonging to the computer technical field. The method comprises: A plurality of face images and a feature point matrix thereof are obtained, in accordance with that characteristic point matrix, the feature point matrix of natural human face image and the feature point matrix of non-natural human face image, Average matrix, identity shift matrix and expression shift matrix are obtained, facial identity base and facial expression base are obtained by dimension reduction processing, and a virtual image model matching facial expression with facial expression in target facial image is generated according to target facial image, facial identity base, facial expression base and virtual image model base. As only fivesensing organs are used for calculation, that time consumption is short, long-time occupation of processing resources is avoided, the operation performance is improved,and the data amount of the face identity base and the face expression base can be reduced by dimension reduction processing. Moreover, the virtual image model of expression matching can be generatedaccording to the facial identity base and facial expression base, which improves the versatility.

A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and / or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and / or footprints of components.

The invention relates to an image processing method and device, a model training method and device, computer equipment and a storage medium. The image processing method comprises the steps: obtainingan initial face image and a template face image; respectively encoding the initial face image and the template face image to obtain a face identity feature of the initial face image and an attribute feature of the template face image; jointly encoding the initial face image and the template face image to obtain a common encoding feature jointly corresponding to the initial face image and the template face image; fusing the facial identity feature, the attribute feature and the common coding feature to obtain a target feature; decoding the target feature to obtain a target face image, wherein the target face image is matched with the face identity feature of the initial face image and is matched with the attribute feature of the template face image. The method can improve the image processing efficiency.

The invention discloses a student online class learning state evaluation method based on facial recognition. The method comprises the steps of obtaining a facial image of a student, a student questionanswering situation and student information; obtaining a question answering result of the student according to the comparison condition of the question answering condition of the student and a reference answer; standardizing the acquired face image into consistent picture information, and inputting the picture information into a trained micro-expression recognition convolutional neural network model to obtain an online lesson listening comprehension degree state of the student; obtaining the concentration degree of the student according to the comparison condition of the ratio of the face length and width of the student to a preset standard face length-width ratio and the comparison condition of the eye opening height of the student to a preset standard face eye opening height; and takingthe question answering result of the student, the online lesson listening comprehension degree state and the concentration degree as the online lesson learning state evaluation result of the student.According to the method, the recognition efficiency can be improved, and the evaluation effect is improved.

Disguised Face Identification (DFI) system and method for identifying multiple individuals with disguised faces in uncontrolled environments / scenarios is provided. The Disguised Face Identification (DFI) system and method includes detecting facial landmarks / facial key-points and performing face identification using the ScatterNet Hybrid Deep Learning (SHDL) Network. The system also can be evolved, after deployment, by the user as it provides one with an ability to add new faces to a known face database which are identified by the system thereafter. Further includes two facial disguise (FG) datasets, the datasets are simple facial disguise (FG) datasets and complex facial disguise (FG) datasets for training the deep convolutional networks.

The invention discloses an intelligent door and a control method thereof. The intelligent door mainly comprises a door body, a gate, a face recognition system, a key conversation unit, a voice broadcast unit, a controller and a management center. The face recognition system comprises a face recognition device and standard face information. The controller is connected with the gate, the face recognition system and the management center. The door body comprises a left side plate, a right side plate and a top plate connected with the side plates. A pedestrian path is formed among the top plate and the two side plates, the side plates are provided with the gate which is arranged at the tail end of the pedestrian path, and the face recognition device is arranged at the bottom of the top plate above the gate and directly faces the pedestrian path. When the intelligent door is in use, a user can enter a community only through face recognition and does not need to carry any recognition device, and use convenience and operation rapidness of the intelligent door are greatly improved.

A face recognition system of a residential environment identifies an individual present in the residential environment. The residential environment include a plurality of home devices and is associated with a group of different persons. The face recognition system identifies which person in the group is the individual and generate an operating instruction for a home device based on identity of the individual. For example, the face recognition system captures an image set of the individual's head and face and applies the image set to a machine learning model that is trained to distinguish between the different persons based on images of their heads and faces. The face recognition system can retrieve a personal profile of the identified individual, which includes settings of the home device for the identified individual. The face recognition system generates the operating instruction based on the personal profile.

A facial recognition process operating on a device may include one or more processes that determine if a camera and / or components associated with the camera are obstructed by an object (e.g., a user's hand or fingers). Obstruction of the device may be assessed using flood infrared illumination images when a user's face is not able to be detected by a face detection process operating on the device. Obstruction of the device may also be assessed using a pattern detection process that operates after the user's face is detected by the face detection process. When obstruction of the device is detected, the device may provide a notification to the user that the device (e.g., the camera and / or an illuminator) is obstructed and that the obstruction should be removed for the facial recognition process to operate correctly.

The disclosure relates to systems and methods for automating offender documentation with facial or other recognition technique. A method can include generating, by cameras situated about a correctional facility, pixel data including first pixels corresponding to a face of a first offender in the correctional facility and an environment around the first offender corresponding to a location within the field of view of the camera, and providing, to a server, the pixel data from the cameras through a network connection, and receiving, from the server, an alert that, based on facial recognition and location detection analysis performed on the pixel data by the server, indicates a monitoring rule associated with the first offender is violated, an offender identification associated with the first offender, a location of the first offender in the correctional facility, and an indication of the monitoring rule violated.

The invention provides a cross-aging face recognition method based on a unified generation model, which belongs to the technical field of computer vision and machine learning, and relates to the cross-aging recognition problem in face recognition. The method first assumes that the facial identity feature extracted from depth network can not completely eliminate the aging information on human face,and then the missing age pictures in the dictionary library are filled in by using the generation method, then the feature of each picture is extracted by face recognition network, and then the relevant image features are fused, and then the cosine similarity between the feature of each picture to be tested and each feature in the dictionary library is obtained. Finally, the object with the largest cosine similarity is taken as the correct matching object. The method of the invention can be used for cross-aging face recognition under various scenes.

The invention relates to the field of image recognition, and provides a vehicle payment method based on face recognition, related equipment and a storage medium, and the method comprises the steps: receiving a binding request of a user, and collecting face information of the user through employing 3D structured light technology; if detecting that the face information matches the driving license photo in the driving license information, whether the real-name authentication information is consistent with identity information in the driving license information or not is detected; if so, detectingwhether the license plate number is associated with the face information, and if so, determining that the authentication is passed; establishing a binding relationship between the license plate number and the payment account; calling a camera to collect and identify the license plate number of the to-be-paid vehicle, querying the payment account bound with the license plate number according to the binding relationship, and calculating the to-be-paid amount of the to-be-paid vehicle; generating and displaying first prompt information and a to-be-paid amount; and sending a first payment requestto a payment institution after facial identity verification of the facial information acquired by the camera is passed. By adopting the scheme, the payment efficiency can be improved.

The invention provides a neural-network-based facial feature extraction modeling method and a neural-network-based facial feature extraction modeling device. The method comprises the following steps: acquiring each block of a first picture, each block of a second picture, a first class of the first picture and a second class of the second picture from a training set of a preset application scenario; determining a global block damage cost function value corresponding to the blocks of the first picture; training a facial identity verification neural network on the training set; testing the facial identity verification neural network corresponding to the blocks of the first picture, and determining a target facial identity verification feature extraction model corresponding to the blocks of the first picture. According to the method and the device, the beneficial effect of improving face recognition accuracy when the facial identity verification feature extraction model obtained by modeling is applied to the preset application scenario for face recognition can be achieved. The invention also provides a face recognition method and a face recognition device applying the neural-network-based facial feature extraction modeling method and the neural-network-based facial feature extraction modeling device.