824 results about "Facial recognition system" patented technology

Controls are provided for a web server to generate client side markups that include recognition and / or audible prompting. The controls comprise elements of a dialog such as a question, answer, confirmation, command or statement. A module forms a dialog by making use of the information carried in the controls. The dialog follows a selected order of prompting and receiving input from a user as related to the order of the controls, and departs from the selected order as a function of responses from the user. The speech controls are adapted such that elements of the speech controls can be combined or re-used.

Collecting images of a patron in an entertainment venue is performed by facial recognition of the patron's face within the images, simplifying the storage and distribution of the images for a patron. In order to enhance the reliability of the facial recognition system, information about the patron that is not directly related to most facial recognition systems, including clothes, height, other associated people, use of glasses and jewelry, disposition of facial hair, and more, can be used. Some of the characteristics used can be specific to a particular date or event, and which will not be more generally characteristic of the patron. The facial recognition system can also be used to identify the patron requesting images to be collected. The present invention also relates to the use of facial recognition in sorting and collecting images from an electronically-stored image collection, enabling the easy retrieval of images that are related to a particular person or set of people.

Collecting images of a patron in an entertainment venue is performed by facial recognition of the patron's face within the images, simplifying the storage and distribution of the images for a patron. In order to enhance the reliability of the facial recognition system, information about the patron that is not directly related to most facial recognition systems, including clothes, height, other associated people, use of glasses and jewelry, disposition of facial hair, and more, can be used. Some of the characteristics used can be specific to a particular date or event, and which will not be more generally characteristic of the patron. The facial recognition system can also be used to identify the patron requesting images to be collected. The present invention also relates to the use of facial recognition in sorting and collecting images from an electronically-stored image collection, enabling the easy retrieval of images that are related to a particular person or set of people.

An adaptive face recognition system and method. The system includes a database configured to store a plurality of face classes; an image capturing system for capturing images; a detection system, wherein the detection system detects face images by comparing captured images with a generic face image; a search engine for determining if a detected face image belongs to one of a plurality of known face class; and a system for generating a new face class for the detected face image if the search engine determines that the detected face image does not belong to one of the known face classes. In the event that the search engine determines that the detected face image belongs to one of the known face classes, an adaptive training system adds the detected face to the associated face class.

A facial recognition system that captures a plurality two-dimensional images of a target face, creates a three-dimensional facial model from the plurality of two-dimensional images of a target face, moves the three-dimensional facial model to a predetermined pose orientation to result in a normalized three-dimensional facial model, extracts measurements from the normalized three-dimensional facial model, and compares the extracted measurements to other facial measurements stored in a data base. Measurement extraction can be enhanced by modifying the data format of the normalized three-dimensional facial model into range and color image data.

A movable-vehicle security system includes a facial-recognition system including a scanner such as a television or infrared camera directed at the face of a person in the driver's seat, which system produces output control signals that are applied to enable or disable operation of the vehicle, with or without a key or other supplemental security system. In a particular embodiment, the system includes a camera mounted on the “third taillight” assembly (which is preferably mounted below the roof and inside the rear window), directed at the rear-view mirror, and coupled to a facial-recognition computer, which in turn is coupled (with appropriate security precautions) to an enabling element for the vehicle, such as a starter motor. In a further embodiment, the system can be coupled to various elements of the motive system to create an auto-starting car.

Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.

Embodiments of the invention perform assisted tagging of images, including tagging of people, locations, and activities depicted in those images. A batch of images is received comprising images of faces, including at least some faces that have not yet been tagged. A facial recognition algorithm is applied to the faces to determine matching data comprising possible tags for each untagged face. A logic engine applies logic rules to reduce the likelihood that certain matches are correct. The most likely match from among the possible matches is selected for suggestion to the user for verification. Once verified, the metadata of the image indicating the recognized people within the image is updated.

A system detects the presence of a living being within a vehicle and triggers an alarm should the temperature rise above or fall below a predetermined threshold limit. The system uses a carbon dioxide monitor to determine for the living being's presence, which is backed up by one or more subsystems that include a motion sensor that senses motion, a sound sensor that senses sounds, especially those made by distressed living beings, and a camera that uses facial recognition software to detect a face within the vehicle. The alarm can be staged so that a lower level of alarm is triggered when the hazardous temperature is approaching, but has not yet reached critical levels, and one of the subsystems has detected a living being within the vehicle, but the others have not yet activated, and a higher level alarm once critical temperatures have been reached.

Disclosed herein is a system and method for iris recognition including stereoscopic face recognition, which can recognize irises using a stereoscopic face recognition system in order to recognize an authenticatee. The system includes two or more face recognition cameras for photographing two or more face images of an authenticatee; a recognition system for receiving the face images photographed by the face recognition cameras from the face recognition cameras and creating stereoscopic face information on the basis of the face images; and one or more iris recognition cameras controlled by the recognition system to photograph focused irises of the authenticatee using the created stereoscopic face information.

A system and method of recognizing human faces by converting a two-dimensional (2D) Facial image into three-dimensions (3D) and subsequently using a Facial Recognition System to identify the individual in the original 2D image. The 3D image may also be processed in a variety of ways so as to broaden the recognition of the individual in the original 2D image.

An electronic device may include a housing and at least one infrared (IR) proximity sensor carried by the housing. The at least one IR proximity sensor may include an IR emitter configured to emit IR illumination toward a user, and an IR sensor configured to sense reflected IR illumination from the user. The electronic device may also include a camera carried by the housing and configured to capture an image of the user's face based upon the reflected IR illumination. The electronic device may further include a controller configured to apply facial recognition to the captured image of the user's face based upon the reflected IR illumination.

The invention relates to a self-service automated transaction machine that permits an authorized user to perform transactions therewith based on facial recognition. Examples of transactions include withdrawing cash, depositing cash, and exchanging cash. The machine includes a plurality of cameras from which plural facial images are captured in determining whether to grant machine access to an individual adjacent the machine.

The invention relates to a method and an apparatus for improving the responsiveness and accuracy of speech recognition systems with tightly integrated Automatic Speech Recognition (ASR) and voice resources, more particularly to a system and method for providing an improved speech recognition enhanced user interface through a reduction in the effective talk-over period. The speech recognition system comprises a host server, managing and arbitrating between a voice resource and an ASR resource, among other resources, through the exchange of run-time controls. The novel method provides for a daisy chain architecture within the speech recognition system, whereby the voice data, or prompt, output by the voice resource is passed directly to the ASR resource, where it is output to the system user. Upon detection of speech from the user, the ASR resource stops transmitting the prompt to the system user, transparent to both the voice resource and the server, followed by a "speech detected" message sent to the server. The delay between the time at which the speech is detected and the time at which the voice resource stops playing the prompt, as a result of a "stop play" request received from the server, goes unnoticed by the system user due to the ASR resource intervention.

The invention discloses a bio-assay detection method. The method comprises the steps of 1, continuously acquiring frame pictures of a face through an image acquiring device; 2, detecting the acquired continuous frame pictures through a trained facial expression detecting unit, a face posture detecting unit and an expression change detecting unit; 3, determining that the face is a true human face if more than two groups of basic actions change according to the detection result in step 2, and otherwise, entering step 4; 4, randomly selecting a group of basic instructions from state element sets of the three detecting units, and prompting a user of finishing the group of basic instructions within the specified time; if that the user finishes the basic instructions is determined according to the detecting results of the three units, determining that the face is the true human face, and otherwise, determining that the face is a false face. With the adoption of the method, the effective deformation of the human face can be accurately caught and accurately detected, so that the true human face and the false face can be distinguished, and the invasion of a human face recognition system can be reduced.

Methods, systems and computer readable medium for improving the accuracy of voice processing are provided. Embodiments of the present invention generally provide methods, systems and articles of manufacture for adjusting a language model within a voice recognition system. In one embodiment, changes are made to the language model by identifying a word-usage pattern that qualifies as an anomaly. In one embodiment, an anomaly occurs when the use of a given word (or phrase) differs from an expected probability for the word (or phrase), as predicted by a language model. Additionally, observed anomalies may be shared and applied by different users of the voice processing system, depending on an affinity in word-usage frequency between different users.

In view of the foregoing, an embodiment herein discloses a system and method for facilitating cardless financial transaction in which the face of the user can itself be used as the credit card for financial transaction at the point of sale (POS) or online financial transaction. The method includes capturing a user's face using a 3-D facial recognition system, converting the facial image into digital data and converting the digital data is converted into the numeric template for that user's face and stored in the separate block within the server's database. One aspect discloses a method in which the multiple bank accounts can be managed as single accounts and at the time of cardless financial transaction user may choose which bank account to use which is differentiated by the three digit alphanumeric code assigned for each bank account.

Presented are improvements for speech recognition systems used to control devices. Features include two-stage confirmation, two-stage limited speech recognition mode, and two-stage wake-up for speech driven applications and systems. A headset computer device includes such staged confirmation operation.

A noise suppressor device for attaining perceptually preferable noise suppression is disclosed. The device minimizes reduction in quality even in the presence of increased noises. The device is adaptable for use in voice communications systems and speech recognition systems employed in a variety of kinds of noisy environments. The device includes a spectrum subtracter and a spectrum amplitude suppressor that operate on the basis of perceptual weights.

A multipass processing system includes a first grammar-based speech recognition system that compares a spoken utterance to a sub-grammar. The sub-grammar includes keywords or key phrases from active grammars that each uniquely identifies one of many application engines. The first grammar-based speech recognition system generates a first grammar-based speech recognition result and a first grammar-based confidence score. A demultiplexer receives the spoken utterance through an input. The demultiplexer transmits the spoken utterance to one of many other grammar-based speech recognition systems based on the first grammar-based speech recognition-result.

Systems, methods and apparatuses are provided for allowing a user to supervise personal exposure to a program exhibited by a consumer electronics device, such as, e.g., a television system. The consumer electronics device includes a facial recognition system and media rating enforcement circuitry that analyzes a program signal and either blocks or passes the program signal based on certain content and viewer based criteria and also, in the alternative, time based criteria. In this connection, a user can program the enforcement circuitry with the content and viewer based criteria in the form of one or more viewing profiles comprising viewer specifications and content-based specifications associated with the viewer specifications, and, which specify a rating and / or a subject matter category. The enforcement circuitry receives one or more viewer indicators from a facial recognition system that are indicative of the viewers present in a viewing area and one or more content-based indicators, which are indicative of a rating and / or a subject matter category of the program. The enforcement circuitry compares the viewer indicators with the viewer specifications and then the content-based indicators with the content-based specifications. Based on this comparison, the enforcement circuitry either passes the program signal to an output device for transformation of the program signal into the program or blocks the program signal from being sent to the output device.

Ultrasound image recognition systems and methods, and artificial intelligence training networks for such systems and methods, are provided. An ultrasound data information system includes an ultrasound image recognition training network that is configured to receive ultrasound training images and to develop ultrasound image knowledge based on the received ultrasound training images. An ultrasound imaging device acquires ultrasound images of a patient, and the device includes an ultrasound image recognition module. The ultrasound image recognition module is configured to receive the ultrasound image knowledge, receive the acquired ultrasound images from the ultrasound imaging device, and determine, based on the ultrasound image knowledge, whether the received ultrasound images represent a clinically desirable view of an organ or whether the clinically desirable views indicate normal function or a particular pathology. The received ultrasound images are transmitted to the ultrasound image recognition training network for further training and development of updated ultrasound image knowledge.

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.

A desktop is unlocked or locked using a mobile client device, such as a smart phone, tablet, smart watch, etc. The authentication mechanism of the mobile client device, such as fingerprint, facial recognition, voice recognition, username and password, is leveraged for faster, less-cumbersome user authentication on the desktop. In this vein, a client device is added to an authentication agent on the desktop, and the desktop recognizes successful attempts to access the mobile client device as a method of unlocking or locking the desktop.

A method for recognizing a face in an image is performed by a facial recognition system. The system retrieves an image and detects a face within the image. The system then determines a set of facial feature positions for a set of facial features. The set of facial feature positions are used to separate the face into a set of facial feature parts. For each part, the system extracts a set of image features. The extracted features are concatenated into a full feature. The system performs dimension reduction on the full feature to derive a final feature.