415 results about "Person recognition" patented technology

The system described is an integrated parking management system which makes use of patented vehicle detectors to collect and transmit data, essentially in near real time, as to all events happening as to single or multiple parking spaces (e.g. current and historic use, length of time of occupancy of current occupant) to a central clearing device for which patent application has been made which serves as a logic core and repository, making use of proprietary software, analyzing, displaying and distributing the data so developed as to a parking plant and all of its components to allow all parties (including prospective users) who are concerned with the various aspects of a parking plant and its components (e.g. determination as to availability of spaces, maintenance and repair of meters, collection of revenues and enforcement of parking regulations) not only to access and make passive use of the information developed, in near real time, to permit them to identify what's happening to the plant and its components as to their own particular interest in such plant and so maximize the efficient use both of the resources of the plant and their own resources directed to the particular aspect of their interface with the plant and its components but also to access and make active use of such information for whatever purpose and in whatever fashion using whatever means of access they may wish. While others have made claim to certain of the individual functions described, e.g. vehicle detection, nobody has identified or patented

The present invention relates to a method of generating a multi-factor encryption key using a simple password in order to access control over information stored at a second entity from a first entity via at least one communication network. In one embodiment this is accomplished by, requesting to receive an application at the first entity from the second entity via the communication network, activating the first entity to generate a shared secret key, wherein the shared secret key is computed from a first entity specific ID and a random number generated at the first and second entity and allowing the user to register with the application of the second entity by the first entity, wherein the registration include entry of a personal PIN (personal identification number), a personal message etc.

The invention discloses a service robot control platform system and a multimode intelligent interaction and intelligent behavior realizing method thereof. The service robot control platform system comprises a voice control module, a binocular image acquisition module, an RFID (Radio Frequency Identification Device) receiving and transmitting module, a bottom wheel movement module, an obstacle avoidance module and a mechanical arm control module. The multimode intelligent interaction and intelligent behavior realizing method comprises the following steps of: 1, voice interaction; 2, independent navigation and location; 3, mechanical arm control; and face detection and recognition. According to the invention, a robot carries out intelligent interaction and intelligent behaviors, and the capacity of intelligent grabbing of the robot is enhanced. Except for special person recognition, distinguish of a picture face and an actual face is added, thus the influence to a program by the picture face is effectively eliminated. According to the invention, anthropomorphic mechanical arm grabbing is controlled in a specific anthropomorphic path grabbing manner, so that a service mode of the robot is more intelligent and humanized.

A system and method for increasing customer safety by directly involving customers and reminding and rewarding workers of hand decontamination compliance issues within a facility to include a plurality of positive-reinforcement hand-hygiene stations; stations that provide a conveniently-located choice of hand-hygiene products such as soap or lotion; personnel identification tags for workers in the facility; readers at the hand-hygiene stations capable of detecting the presence of worker identification tags; a controller for detecting whether a worker tag accessed a hand decontamination station; devices to visually and audibly prompt and / or educate a worker or customer in the use of the hand wash station; a device to give a visual and audible reward for using a station; a device to issue rewards; and a plurality of computers to manage the system.

When authentication data of a person O to be authenticated is registered as dictionary data, this authentication data of the person to be authenticated is acquired and collated with the registered dictionary data. In accordance with the collation result, the dictionary data is updated.

A smart electronic personal identification document, including a smart identification module and an automated anti-skimming element. The smart identification module includes a contactless chip module and an antenna. The smart identification module is operative to store and exchange personal identification information contactlessly with an external reader. The automated anti-skimming element is configured for preventing unauthorized theft of the information.

A first face detecting section detects the face of a passerby based on an image obtained from a first camera set to be easily recognized by the passerby. A second face detecting section detects the face of the passerby based on an image obtained from a second camera set so that the camera will be difficult to be recognized by the passerby. A classifying section classifies the passerby based on the detection results of the faces by the first and second face detecting sections and adjusts a threshold value for authentication based on the classification result. The face collating section calculates the similarity between the face of the passerby and each of faces of registrants and determines whether the passerby is a registrant or not according to whether the degree of calculated similarity is not lower than the adjusted threshold value for authentication.

The present disclosure relates to a gait recognition method based on deep learning, which comprises recognizing an identity of a person in a video according to the gait thereof through dual-channel convolutional neural networks sharing weights by means of the strong learning capability of the deep learning convolutional neural network. Said method is quite robust to gait changes across a large view, which can effectively solve the problem of low precision in cross-view gait recognition existing with the prior art gait recognition technology. Said method can be widely used in scenarios having video monitors, such as security monitoring in airports and supermarkets, person recognition, criminal detection, etc.

The invention relates to a system for monitoring the person entering and exiting the presence area of a prison by recognizing the face of the person. The system comprises servers, personnel information collecting and registering equipment, an entering and exiting gate, face recognition equipment and real-time displaying equipment; the servers consist of a web server and a database server and is used for storing all the effective historical recordings and browsing and printing the historical recordings; the personnel information collecting and registering equipment comprises a registration machine, a computer for registering and a card reader connected with the computer, and is used for taking a picture for the visiting person, analyzing the face feature data of the visiting person, associating the identity information of the visiting person with the identity information of the visited person and sending the face feature data of the person to the server and the person-face recognizing equipment; the person-face recognizing equipment is used for recognizing the visiting person and controlling the gate to open and close according to the visiting person recognition result; the real-time displaying equipment is used for displaying the picture, the name and the certificate number of the visiting person, the name and the department information of the visited person and the comparisonresult when the person entering and exiting the presence area of the prison so that the operator on duty can monitor the person entering and exiting the presence area of the prison in real time. Due to the adoption of the system, the automatic recognition of the person entering and exiting the presence area of the prison in the prison industry is realized, the visiting person check accuracy and safety are improved effectively, and the visiting person entering and exiting the presence area of the prison can be monitored in real time and checked later.

A computer-implemented method for executing a search in a social networking application is disclosed. In one aspect, a social networking application facilitates the initiation of a search, based on user-provided search criteria. In addition, the social networking application generates a list of persons to recommend to the searcher, for forwarding the search criteria. For example, persons in the list are identified, according to various algorithms, as being likely to know a person satisfying said search criteria. Furthermore, the social networking application facilitates the selection of one or more persons from the list, thereby enabling the user to quickly forward the search to the selected persons.

A speech recognition method is provided. The speech recognition method includes the steps of (a) receiving a speech from a user; (b) recognizing the speech to generate a recognition result with a score; and (c) according to the score of the recognition result, performing one of the following steps, (c1) preventing from performing an adaptation for an acoustic model but using a utility rate of the speech to learn a new language and grammar probability model when the score is relatively high, (c2) performing a confirmation by the user when the score is relatively low, further comprising: (c21) when the recognition result is confirmed in the confirmation by the user, performing the adaptation in the acoustic model to increase an occurrence probability of the speech and using the utility rate of the speech to learn the new language and grammar probability model, (c22) when the recognition result is rejected in the confirmation by the user, performing the adaptation in the acoustic model to decrease the occurrence probability of the speech.

Some embodiments promote website credibility and the optimization of websites for people by automatedly quantifying various elements of a website into component credibility scores. In some embodiments, a set of encoded credibility scoring rules are used to compute each of the component credibility scores, wherein the credibility scoring rules are derived based on factors that have been identified by a grouping of people that preferably represent a primary demographic of users that consume the content of a particular classified type of website. In some such embodiments, the credibility scoring rules are derived from commonality that is identified from a sample set of known credible and / or non-credible websites of a particular classification. Once the credibility scoring rules are defined, the system applies the rules to other websites having the same classification as those from which the rules are derived to automatically generate credibility scores for the other websites.

The invention discloses a multi-background modeling method for speaker recognition, relating to a background modeling method in speaker recognition. The method is characterized by comprising the steps of: firstly, dividing training data according to a vocal tract length bending coefficient of voice, respectively training a UBM (Universal Background Model) in each group of data, then obtaining a target speaker GMM (Gaussian Mixture Model) by means of the self-adaption of each background model, obtaining multiple groups of GMM and UBM models, when recognizing a speaker, carrying out calculation on test data by each group of GMM and UBM models to obtain logarithm likelihood ratio fractions, and finally selecting a minimum logarithm likelihood ratio fraction from the logarithm likelihood ratio fractions to output. By adopting the invention, delicate depiction can be carried out on the background model, thereby improving the accuracy rate on speaker recognition.

A digital video camera system that provides a video summary using a method that includes: designating a reference image containing a particular person; capturing a video sequence of the scene using the image sensor, the video sequence including a time sequence of image frames; processing the captured video sequence using a video processing path to form a digital video file; during the capturing of the video sequence, analyzing the captured image frames using a person recognition algorithm to identify a subset of the image frames that contain the particular person; forming the video summary including fewer than all of the image frames in the captured video sequence, wherein the video summary includes at least part of the identified subset of image frames containing the particular person; storing the digital video file in the storage memory; and storing a representation of the video summary in the storage memory.

One or more input video sequences and a set of person-of-interest (“POI”) information are received. The set of POI information identifies at least one person-of-interest. A particular video sequence is identified that prominently or relatively prominently displays at least the person-of-interest. The particular video sequence is identified from (a) the input video sequence(s), or (b) a portion of the input video sequence, if only one was received, or a portion of one of the input video sequences, if more than one was received. Then, a customized output video is generated from at least a portion or portions of the input video sequence(s), the customized output video being generated based at least upon the set of POI information to include at least the particular video sequence.

The invention relates to an embedded type speech emotion recognition method and an embedded type speech emotion recognition device. The method comprises a feature extraction method, an emotion model training method, a Gaussian mixture model and an emotion recognition method. The method is as follows: parameters of a speech emotion recognition model can be adjusted in a self-adoption manner according to the recognition result of a speaker module, and an unspecific speaker speech emotion recognition question is transformed into a specific speaker speech emotion recognition problem. The device comprises a central processor, a power supply, a clock generator, a Nand Flash storage, a Nor Flash storage, an audio coding-decoding chip, a microphone, a loudspeaker, a keyboard, an LCD (Liquid Crystal Display) display and an USB (Universal Serial Bus) interface storage. According to the embedded type speech emotion recognition method and device, a speaker recognition model is added to the speech emotion recognition, and therefore, the problem that the speech emotion recognition is suddenly declined under an unspecific speaker condition is solved, and the identity recognition function is brought to the device.

An imaging apparatus is provided including an imaging unit configured to obtain image data, a display unit, and a communication unit configured to communicate with a plurality of external apparatuses. The imaging apparatus further includes a storing unit configured to store person identification information including at least face image data while associating the person recognition information with information relating to the external apparatuses, a collation unit configured to collate a target in the image data with the person identification information, a detection unit configured to detect an external apparatus that is communicating with the imaging apparatus, and a display control unit configured to display a plurality of pieces of face image data on the display unit each as a candidate of a transmission destination of the image data in an order based on a result of collation by the collation unit and a result of detection by the detection unit.

The invention discloses a smart community monitoring system, including an access control system for opening a door when the first human body feature information of a person trying to open a corresponding door is verified to be successful, an elevator control unit for unlocking the button for a target floor in an elevator for a first preset time when the second human body feature information of a passenger is verified to be successful, a video monitoring unit for acquiring real-time video images in a community, a security detection unit for detecting whether someone fall down according to the video images and alarming when a person falls down over a second preset time, a person recognition unit for detecting a facial image in the video images and comparing the facial image with a prestored target person image and alarming when detecting a facial image consistent with the target person image, a rubbish detection unit for alarming when detecting the rubbish quantity at a rubbish spot exceeds standards, and a smart home unit for performing indoor safety protection and environmental conditioning. According to the invention, real-time smart monitoring and safeguard of the community are achieved.

A monitoring device includes a range imaging sensor, a bed recognition unit, a person recognition unit, a movement determination unit and a notification unit. The range imaging sensor generates a range image wherein pixel values are distance values to an object, the entirety of a bed to be monitored being included in a field of vision thereof. The bed recognition unit extracts a location of the bed using the range image. The person recognition unit detects regions occupied by a person inside and outside of the range of the bed recognized by the bed recognition unit in the range image. The movement determination unit determines the movement of the person relative to the bed using a combination of the regions of the bed detected by the bed recognition unit and the person detected by the person recognition unit. The notification unit notifies a determination result of the movement determination unit.

The invention discloses a living person identity authentication method based on voice pattern and image features. A self-recognition database and an intelligent living person recognition database are arranged, video information and audio information are acquired when an operator reads random content, and if the operator is himself and the intelligent living person and emotion are normal and face recognition, lip language recognition, voiceprint recognition, voice recognition, expression variance recognition and emotional state recognition are passed, identity authentication is successful. Compared with the methods in the prior art, multiple biological features are fused to simultaneously verify the person himself and intelligent living person identity and the normal emotional state without being directly contacted with the operator so that the method is easy to accept and convenient for popularization and application.

A method for testing a person's vision is disclosed. The method includes providing, for display to the person, one or more sequences of test images, each test image including one or more test symbols. For each test image, a target symbol is identified to the person. The person then views each test image in the sequence and activates a control in response to recognising a test symbol that replicates the shape of the target symbol. At the completion of the sequence, a parameter value associated with the activations is processed and correlated with a vision metric. A system for testing a person's vision is also disclosed.

A digital camera system that implements a method for providing image processing customized according to an identified person. The method includes: capturing an input digital image of a scene; analyzing the input digital image using a person recognition algorithm to identify at least one particular person in the input digital image; retrieving image processing preferences associated with one of the identified particular persons; processing the input digital image to form a modified digital image according to the retrieved image processing preferences; and storing the modified digital image in a storage memory.

Person identification information is extracted from digital data with a high accuracy and additional tag is recommended by adopting a decision fusion. In other words, the person identification information is acquired by using various additional information to tag the same to the digital data automatically as a person tag, in a digital data management system in which the person identification information is extracted from the digital data by referring to its attributes and contents; and specific digital data having specific tags which are same as those attached to newly created digital data are found out and then candidate tags which are attached to the specific digital data except the specific tags are provided to a monitor in order for a user to choose one or more proper tags from the candidate tags, which are desired to be attached to the newly created digital data additionally, by using the decision fusion.

A communication draw-in system that enables robot-human communication to start smoothly is provided. The communication draw-in system is a communication draw-in system provided in a robot that communicates with a target human, and includes: a human specifying unit 200 for specifying a position of the target human; a light source control unit 201 for moving light toward the specified position of the target human; a draw-in control unit 203 for instructing the robot to perform a draw-in operation for making the target human recognize a direction of the robot; and a human recognition specifying unit 204 for determining whether or not the target human has recognized the robot, wherein the robot is instructed to start communicating with the target human, in the case where the target human is determined to have recognized the robot.

A communication device (1, 1′, 1″) with at least one wireless communication channel is configured to receive digital pictures and / or video streams from at least one remote source. The communication device (1, 1′, 1″) is configured to test whether at least one person who is / are associated with said communication device by pre-stored person identification data is identifiable in the digital pictures and / or video streams of the remote source, and to process the digital pictures and / or video streams of the remote source only if the result of the person identification test is positive.

A hand-held personal identification analysis device is provided. The hand-held personal identification analysis device includes a scanning system for gathering biometric information from individuals, a profiler system for developing profiles of individuals based on biometric information gathered from the scanning system, and a personal data assistant or similar computing device with a screen for providing a user interface and overall system control A scanning system interface couples the scanning system to said computer module.

The invention discloses a dish recommendation method and device for healthy diet of an intelligent restaurant and a storage medium, and the method comprises the steps: collecting the basic informationof a pre-dining customer, obtaining the basic information of the customer body type, gender and age through a person recognition algorithm, and building a person database based on the face information of a user; constructing a dish nutrition database, recording nutrition parameters of all dishes wherein the nutrition parameters comprise calorie, sugar content, salt content, mineral substances andvitamin values of the dishes; for new customers, enabling a server randomly to generate a recommendation menu conforming to the intake standard through the national standard reference intake standardbased on the basic information of the dining customers, classifying and sorting the dishes according to different dish tastes, and recording the ordering content of the customers after the customersplace orders; for old customers, enabling the server to generate a recommendation menu conforming to the nutrition intake standard of the customers based on the basic information of the dining customers in combination with a dish preference prediction model generated by the historical ordering records of the customers.