6033 results about "Feature data" patented technology

A vibrational analysis system diagnosis the health of a mechanical system by reference to vibration signature data from multiple domains. Features are extracted from signature data by reference to pointer locations. The features provide an indication of signature deviation from a baseline signature in the observed domain. Several features applicable to a desired fault are aggregated to provide an indication of the likelihood that the fault has manifested in the observed mechanical system. The system may also be used for trend analysis of the health of the mechanical system.

A robotic system includes a humanoid robot with robotic joints each moveable using an actuator(s), and a distributed controller for controlling the movement of each of the robotic joints. The controller includes a visual perception module (VPM) for visually identifying and tracking an object in the field of view of the robot under threshold lighting conditions. The VPM includes optical devices for collecting an image of the object, a positional extraction device, and a host machine having an algorithm for processing the image and positional information. The algorithm visually identifies and tracks the object, and automatically adapts an exposure time of the optical devices to prevent feature data loss of the image under the threshold lighting conditions. A method of identifying and tracking the object includes collecting the image, extracting positional information of the object, and automatically adapting the exposure time to thereby prevent feature data loss of the image.

The present invention provides a system and method for dynamic object-driven database manipulation and mapping system which relates in general to correlating or translating one type of database to another type of database or to an object programming application. Correlating or translating involves relational to object translation, object to object translation, relational to relational, or a combination of the above. Thus, the present invention is directed to dynamic mapping of databases to selected objects. Also provided are systems and methods that optionally include caching components, security features, data migration facilities, and components for reading, writing, interpreting and manipulating XML and XMI data files.

Provided herein are systems and methods that improve the redemption integrity of portable gaming instruments such as tickets and magnetic cards. The systems and methods encrypt biometric data for a recipient of a portable gaming instrument and store the encrypted biometric data on the portable gaming instrument. When a person tries to redeem value on the portable gaming instrument, a comparison is made between: a) biometric data for the person trying to redeem the value, and b) the biometric data encrypted and stored on the portable gaming instrument.

In a method of switching a locked state of an electronic device with a user-verifying function, a biologic feature data from a user is captured while receiving an input from the user for an operation when the electronic device is in a locked state. Whether the biologic feature data conforms to a reference biologic feature data is then determined. If it is determined that the biologic feature data conforms to the reference biologic feature data, the electronic device is switched from the locked state into a non-locked state and directly controls the electronic device to perform the operation according to the input when the biologic feature data is determined conforming to the reference biologic feature data.

A method and program product for providing paperless receipts for conducting business transactions. Biometric data and product specific identification information is collected with each purchase and included with an electronic receipt generated for each purchase. The collected product specific information may include product serial numbers for some products, all products or product valued above a minimum threshold cost. The biometric data may include a digital image of each purchaser. The electronic receipt may be passed directly to the customer.

A system generates a model based on feature data relating to different features of a link from a linking document to a linked document and user behavior data relating to navigational actions associated with the link. The system also assigns a rank to a document based on the model.

A computerized method that provides a Web page having control structures for gathering behavioral biometrics. The method can receive behavioral biometric data in accordance with the control structures and in accordance with interactions of a user with the Web page. Additionally, the method can compare the received behavioral biometric data with at least one set of previously established values. The user can be profiled based upon comparison results. This profiling can affect the manner in which Web pages are provided to the user as well as the content contained therein.

A gaming system is provided with biometric facilities for identifying or verifying the identity of a player or perspective player. In one aspect reference biometric data is stored in a portable biometric data storage device such as a smart card, PCMCIA card or the like and is preferably left in the possession or control of the individual or individuals to whom the biometric data relates. The reference biometric data is read in individual gaming terminals and compared, in individual gaming terminals to measured biometric data of a player or perspective player. In one aspect, gaming terminals use biometric verification or indication to implement a practical and feasible cashless gaming terminal.

A system performing secondary verification using only existing apparatuses to accomplish a measure for relief in personal authentication without causing complexity or without increasing cost. The system has a registering apparatus for obtaining data for verification from information inputted using an inputting unit and registering the data. The registering apparatus has a first extracting unit for extracting biometrics characteristic data from the biometrics information obtained by the inputting unit, and registering the biometrics characteristic data as registry biometrics characteristic data for primary verification, and a second extracting unit for extracting data, which is different from the registry biometrics characteristic data, from information inputted using the inputting unit and registering the data as registry data for secondary verification. The system is used for personal authentication using biometrics information such as fingerprint, palm print, finger shape, palm shape, voice, retina, iris, face image, dynamic signature, blood vessel pattern, keystroke, or the like.

A method and system of providing user profiling for an electrical device is disclosed. Face representation data is captured with an imaging device. The imaging device focuses on the face of the user to capture the face representation data. A determination is made as to whether a facial feature database includes user facial feature data that matches the face representation data. User preference data is loaded on a memory module of the electrical device when the face representation data matches user facial feature data in the facial feature database. A new user profile is added to the user profile database when the face representation data does not match user facial feature data in the facial feature database.

The embodiment of the invention provides a human face similarity matching method which comprises the following steps of: obtaining a first human face image; extracting the feature data of a plurality of key points in the first human face image and a stored second human face image; searching a matched key point in the key points of the second human face image for each key point of the first human face image; calculating the score of the similarity between the key point of the first human face image and the key point of the second human face image matching with the key point of the first human face image; and inosculating each key point of the first human face image with the similarity score of the key point of the second human face image to judge whether the two are matched with each other.

Systems and methods are provided for processing a medical image to automatically identify the anatomy and view (or pose) from the medical image and automatically assess the diagnostic quality of the medical image. In one aspect a method for automated decision support for medical imaging includes obtaining image data, extracting feature data from the image data, and automatically performing anatomy identification, view identification and/or determining a diagnostic quality of the image data, using the extracted feature data.

A process monitoring and event capturing system, including at least one video detector for monitoring a process and outputting a video signal and at least one event signal representing an event condition of the process being monitored. A recorder records the video signal and the event signal in a digital video file of a digital storage device having a predetermined data structure. The video file is structured to include at least one event feature data structure at the end of the video file for storing the event signal representative of the captured event condition. The digital storage device includes a temporary data file for storing video segments for examination by the user. The file format structure stores event data from the end of the data file forward in reverse order, permitting additions of data without affecting the previous file structure.

A SLAM of a robot is provided. The position of a robot and the position of feature data may be estimated by acquiring an image of the robot's surroundings, extracting feature data from the image, and matching the extracted feature data with registered feature data. Furthermore, measurement update is performed in a camera coordinate system and an appropriate assumption is added upon coordinate conversion, thereby reducing non-linear components and thus improving the SLAM performance.

A computer in the form of a client comprises a graphical user interface and a memory, the memory including a first data object for storing the feature data in a first format, and a second data object for storing the image data in a second format. The client computer is configured to send at least one query; receive at least one of the feature data and the image data in response to the at least one query; and display the feature data in the first format and the image data in the second format in the graphical user interface.

The invention provides an object tracking method and device based on a neural network model. The neural network model comprises a feature extraction neural network, a first neural network and a second neural network. The object tracking method comprises that S120) a video to be processed is input to the feature extraction neural network to extract feature data of the video to be processed; S140) the feature data of the video to be processed is input to the first neural network to obtain a bounding box of at least one object in the video to be processed; and S160) the feature data and the bounding box of the video to be processed are input to the second neural network to obtain an identifier, which is used to indicate the at least one object, of the bounding box and further to track the at least one object in the video to be processed. According to the object tracking method and device, the object of the video can be detected and tracked more effectively, and the object tracking speed and accuracy are improved.

An apparatus, system and method for telepresence communications at a virtual location between two or more participants at multiple locations (100, 200). First perspective data descriptive of the perspective of the virtual location environment experienced by a first participant at a first location and feature data extracted from features of a second participant at a second location (210, 220) are processed to generate a first virtual representation of the second participant in the virtual environment from the perspective of the first participant (250). Likewise, second perspective data descriptive of the perspective of the virtual location environment experienced by the second participant and feature data extracted from features of the first participant (230, 240) are processed to generate a second virtual representation of the first participant in the virtual environment from the perspective of the second participant (260). The first and second virtual representations are rendered and then displayed to the first and second participants, respectively (260, 270). The first and second virtual representations are updated and redisplayed to the participants upon a change in one or more of the perspective data and extracted feature data from which they are generated (290, 295). The apparatus, system and method are scalable to two or more participants.

The invention provides a human behavior recognition method based on a depth neural network, comprising the following steps: acquiring original depth data stream of an actor; extracting human skeleton joint data from the original depth data stream of the actor; modeling the entire human body with three-dimensional coordinates corresponding to the extracted human skeleton joint data; extracting features by modeling the entire human body, sending feature data to a restricted Boltzmann machine network for preprocessing, training out a depth neural network model based on received weight initialization BP neural network parameters, and identifying a behavior from a feature extraction result; overlapping the extracted human skeleton joint data and the actual human body through multi-threaded parallel processing, and displaying the identified behavior in real time; and establishing an abnormal behavior template library and alarming for a detected abnormal behavior. The change of human behavior can be detected in real time, and alarm can be raised for abnormal behaviors (such as fall) of a human body.

RFID tags, methods and systems for total asset management, in-transit visibility and bio-metric verification and authorization. The system comprises an active, multi-modal, bi-directional RFID tag having a primary communication mode RF transceiver and a secondary mode IR/US transceiver. The tag includes sensors, such as bio-metric, and memory containing user bio-metric data. A reader and illuminator(s), preferably IR and/or US, are communicatively coupled with the tag and adapted to provide command and control signals to the tag and receive data/information from it. The user's bio-metric data is read by the sensor, compared to the data base and verification communicated to an access or point of sale device. The tag looks for illuminators and reports to the reader the IDs of those it sees. The detection history permits tracking and locating tagged objects or persons, such as theme park guests. If no illuminator signal is seen, the tag sends a special signal.

A flight deck display system for an aircraft or other vehicle includes a first data source of visual feature data that is indicative of visual features of a location of interest, a second data source of flight data for the aircraft, a processor architecture, and a display element. The processor architecture is operatively coupled to the first data source and to the second data source, and it is configured to process the visual feature data, process the flight data, and, based upon the visual feature data and the flight data, generate image rendering display commands. The display element receives the image rendering display commands and, in response thereto, renders a dynamic graphical representation of the location of interest using the visual feature data. The dynamic graphical representation of the location conveys an amount of visible detail that varies as a function of the flight data.

A secure embedded system that uses cryptographic and biometric signal processing acceleration is described. In one embodiment, the secure embedded system is configured as a wireless pay-point protocol for brick-and-mortar and e-commerce applications in which biometric information is localized and does not require transmission of biometric data for authentication. In one embodiment, a key-generation function uses a dynamic key generator and static biometric components. In one embodiment, an embedded system design methodology provides hardware and software acceleration transparency.

An organization can manage its compliance through a system and process for collecting characteristic data for regulated elements and applying a rule application system to identify those having an out-of-compliance status. A responsible representative is assigned and notified of the out-of-compliance status and compelled to perform corrective actions through repeated and successive notification of the assigned representative and a hierarchy of responsible representatives until compliance is achieved. Compliance is further compelled through assigning a default out-of-compliance status for an element until such time as its characteristics are collected such as through mandatory data collection. Preferably, the compliance management system is implemented in a client-server network utilizing remote data collection devices and server-based applications and databases of rules, a corrective action register of pending out-of-compliance elements and a compliance calendar interface for responsible representatives. A map interface provides compliance at a glance. The entities are displayed according to their geographical location and the compliance status is indicated by the color of the symbol representing the entity on the map. Symbols may flash to indicate urgent actions required.

A system for, method of and computer program product captures performance-characteristic data from the execution of a program and models system performance based on that data. Performance-characterization data based on easily captured reuse distance metrics is targeted, defined as the total number of memory references between two accesses to the same piece of data. Methods for efficiently capturing this kind of metrics are described. These data can be refined into easily interpreted performance metrics, such as performance data related to caches with LRU replacement and random replacement strategies in combination with fully associative as well as limited associativity cache organizations. Methods for assessing cache utilization as well as parallel execution are covered.

A personal identification device of the present invention is provided with a registered data storage unit for storing registered data containing facial feature data for a registered user, a recognition parameter storage unit for storing recognition parameters, a image determination unit for determining whether or not the image quality of a user facial image input from an imaging device is appropriate, an adjustment unit for adjusting the settings of the imaging device or modifying the recognition parameters, in accordance with the result of determination carried out in the image determination unit, a feature extraction unit for extracting user facial feature data from a facial image, and a face recognition unit for comparing the extracted feature data with the registered data to determine whether or not the user is a registered user based on the result of comparison and the recognition parameters.

The present invention is directed to an automated vehicle identification and tracking system. The system includes at least one area monitoring system that has a plurality of imaging units disposed in an area. Each imaging unit is configured to capture an image of a monitored vehicle disposed in the area. A control system is remotely coupled to the at least one area monitoring system. The control system is configured to classify and track the monitored vehicle based on anonymous vehicle feature data extracted from the captured image. The system can assimilate eyewitness input concerning a vehicle based on anonymous vehicle feature data, including time and location of the sighting of the target vehicle, wherein the system can effectively identify the current location of candidate target vehicles within the monitored area.

A method for predictive maintenance of a machine includes collecting feature data for the machine which includes a plurality of feature vectors. At least some of the feature vectors are standardized to facilitate compatibility between different vectors. At least some of the standardized feature vectors are transformed into corresponding two-dimensional feature vectors. At least some of the two-dimensional feature vectors are clustered together based on operating modes of the machine. Similar steps are performed on additional feature data collected from the machine. Recently gathered two-dimensional feature vectors are compared to previously clustered feature vectors to provide predictive maintenance information for the machine.

A wireless mobile terminal works with an identification server to automatically identify a broadcast program/movie and then identify and connect to a networked media server to receive the identified program/movie therefrom. The terminal generates data that characterizes content of a broadcast program/movie that is send by the terminal and is playing external thereto. The terminal transmits a message that includes the characterization data and a request for identification of a media server from which the broadcast program/movie can be received. The identification server identifies the broadcast program/movie, and identifies a user viewed location within the identified program/movie that corresponds to what was sensed by the terminal. The identification server identifies an Internet address of a media server from which the terminal can receive transmission of the identified program/movie. The identification server transmits a message to the terminal that identifies the identified program/movie, the user viewed location therein, and the Internet address of the media server. The terminal responds to the message by establishing a communication connection to the identified media server and requesting transmission therefrom of the identified program/movie starting from a location corresponding to the user viewed location.

The storage system includes a first auxiliary storage device, a second auxiliary storage device, and a main storage device, and also includes a data management unit which stores and keeps, in the main storage device, index data based on feature data by referring to the feature data of storage target data stored in the first auxiliary storage device, and if the index data stored and kept in the main storage device reaches a preset amount, stores and keeps, in the second auxiliary storage device, the index data stored and kept in the main storage device, and deletes the index data stored and kept in the second auxiliary storage device from the main storage device.

A system for verifying, authenticating, and processing membership information to generate a selectively approved searchable membership database, viewable through a computer information network, such as the internet. membership verification includes a first processing unit (200) for transmitting data native biometric data to a second processing unit (204) for artificial rendering by a lab processing module (300) stores settings in a database (301). Artificially rendered biometric data is used for reference physical configuration of a first processor biometric capture device (301) Artificially rendered biometric data is used to reference the identity of a native capture device source (301) Artificial rendered biometric data is used in a pass code configuration to activate a biometric capture device (301). A custom user biometric data reference module is used for member users to create a custom biometric data reference database (303). A controlled biometric capture device by second processor is used with the custom biometric data reference database to provide multiple security encryption form identification and verification of a member user.