Abstract: Systems, methods, and non-transitory computer readable media decentralizes biometric enrollment. A server receives a request to enroll a user for biometric authentication in association with a unique ID, generates an activation code corresponding to the unique ID, and sends the activation code to the user. A user device receives and validates the activation code. If the activation code is valid, the user device is enabled to: capture at least one biometric image, and to send the biometric image to the server. The server receives at least one biometric image from the user device in response to the activation code and extracts features from at least one biometric image to generate a biometric template based upon the extracted features to enroll the user for biometric authentication without requiring the user to visit a central location to provide at least one biometric image.

Abstract: A system for detecting a person being interested in a target includes a camera configured to capture an image of a location in front of a target area, a memory configured to store instructions and position information with respect to the target area, and a processor that executes the instructions to perform operations including receiving the image from the camera, detecting a face of person within the image, detecting a face direction in accordance with the detected face, and determining whether the person looks at the target area in accordance with the detected face direction and the stored position information with respect to the target area.

Abstract: A system and method for selectively enrolling new pattern information in a way that reduces incorrect mapping or reduces overuse of previously mapped pattern information using a multi-match model. A method for dynamically enrolling a pattern-under-test into a pattern template, the pattern template including a set of template elements, may include a) determining a number N of template elements of the set of template elements matched by the pattern-under-test, wherein N is greater than one; b) establishing a multi-match mode for a dynamic enrollment of the pattern-under-test into the pattern template; and c) enrolling dynamically the pattern-under-test responsive to the multi-match mode.

Abstract: A virtual reality apparatus comprises an image generator to generate images representing a virtual environment, for display to a user by a head mountable display to be worn by that user. The virtual environment includes an avatar representation of the user positioned within the virtual environment so that the user's viewpoint of the virtual environment substantially corresponds to the viewpoint of the avatar corresponding to that user. One or more user controls are provided with which predetermined inputs may be selected by the user. The image generator is responsive to selection of a predetermined input by the user to correspondingly configure a face of the avatar representing that user. The image generator is arranged to generate respective facial configurations of the avatar for display to other users viewing the virtual environment.

Abstract: A method and an apparatus for controlling a running status of a wearable electronic device, where the method includes determining a posture of a wearable electronic device, where the posture includes a stationary posture and a moving posture, and controlling a running status of the wearable electronic device according to the posture. According to the method and the apparatus for controlling a running status of a wearable electronic device, the posture of the wearable electronic device is monitored using, for example, a gyroscope signal from a mobile phone, whether a user is using the wearable electronic device is determined, and the running status of the wearable electronic device is determined without using a light sensor, which reduces manufacturing costs of the wearable electronic device.

Abstract: An electronic device is provided. The electronic device includes an optical sensor, the optical sensor comprising a lighting device configured to emit light, a sensor layer including an array of sensors configured to detect first image information corresponding to an object from light reflected by the object, and a filter layer including openings configured to transmit the light reflected by the object, the filter layer disposed on the sensor layer, wherein the first image information is different from an image of the object identified with naked eyes. The electronic device may be diversified according to embodiments.

Abstract: A smart phone is used to accomplish measurement of a wound surface area, when at least one flat marker device, which is a predefined reference, is placed near the wound and photographed by a smart phone.

Abstract: The invention provides an optical fingerprint sensor including: an image sensing layer having an array composed of a plurality of sensing blocks; a collimating layer disposed on the image sensing layer and having a plurality of through holes penetrating from the top surface to the bottom surface of the collimating layer; a light guiding layer disposed in the collimating layer, and a glass cover layer disposed on the light guiding layer, the top surface of the glass cover layer receiving a finger touch, wherein the image resolution of the optical fingerprint sensor is defined by the number of sensing blocks, and there are a plurality of through holes directly above each of the sensing blocks.

Abstract: A wearable apparatus is provided for capturing and processing images from an environment of a user. In one implementation, the wearable apparatus is used for identifying a contextual situation related to a wearer. The wearable apparatus includes a wearable image sensor configured to capture a plurality of images from an environment of the wearer. The wearable apparatus further includes at least one processing device. The at least one processing device is programmed to analyze the plurality of images to identify the contextual situation related to the wearer; determine information associated with the contextual situation; and cause the transmitter to transmit the determined information to a device paired with the wearable apparatus to cause the paired device to provide at least one alert to the wearer based on the determined information associated with the contextual situation.

Abstract: An optical fingerprint sensor is provided. The optical fingerprint sensor includes a sensing module. The sensing module includes a light sensing layer and a light filter layer disposed above the light sensing layer. The light sensing layer includes a plurality of photo detectors arranged in a sensing array. The light filter layer includes a plurality of collimators. The collimators are divided into a plurality of collimator groups corresponding to the photo detectors, and the number of collimator groups is equal to the number of photo detectors. Each of the collimator groups comprises the same number of collimators arranged in a specific pattern and disposed above the corresponding photo detector. The photo detectors receive reflected light from a user's finger through the collimators of the corresponding collimator groups.

Abstract: Each user terminal apparatus is connected with a service business enterprise system by a connection business enterprise system in a state that a live image can mutually be transmitted through the service business enterprise system. An user beforehand sets its live image to be appropriately utilized as an advertisement medium, and chooses selling goods to be advertised. A live image transmitted from the user terminal apparatus of the user who performed the aforesaid setting receives a superposed image, for example, by the superposing the T shirt of the user or the like with the image signal of the selling goods as the advertisement object in the service business enterprise system, and then the processed live image signal is transmitted to the user terminal apparatus of a communication companion.

Abstract: An image of a pinna is captured. Based on the image of the pinna, a non-linear transfer function is determined which characterizes how sound is transformed at the pinna. A signal is output indicative of one or more audio cues to facilitate spatial localization of sound via the pinna, where the one or more audio cues is based on the non-linear transfer function.

Abstract: A device, system and a method extract physiological information indicative of at least one vital sign of a subject. To provide a high motion robustness, an input interface is configured to obtain at least two detection signals derived from detected electromagnetic radiation transmitted through or reflected from a skin region of a subject. Each detection signal includes wavelength-dependent reflection or transmission information in a different wavelength channel. At least two pulse signals are computed from said at least two detection signals using different signature vectors for the computation of each pulse signal. Quality indicator values are computed for the pulse signals indicating a characteristic of the respective pulse signal. Physiological information indicative of at least one vital sign is derived from the signature vector resulting in the pulse signal with the best quality indicator value and/or from the pulse signal.

Abstract: A medication confirmation method and apparatus for confirming administration of medication employing an inhalable medication administration apparatus. The method of an embodiment of the invention includes the steps of capturing one or more video sequences of a user administering medication employing the inhalable medication administration apparatus, storing the captured one or more video sequences, capturing one or more audio sequences of the user administering medication employing the inhalable medication administration apparatus and storing the captured one or more audio sequences. At least one of the stored video sequences and at least one of the stored audio sequences are then analyzed to confirm that the user has properly administered the medication.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning using goals and observations. One of the methods includes receiving an observation characterizing a current state of the environment; receiving a goal characterizing a target state from a set of target states of the environment; processing the observation using an observation neural network to generate a numeric representation of the observation; processing the goal using a goal neural network to generate a numeric representation of the goal; combining the numeric representation of the observation and the numeric representation of the goal to generate a combined representation; processing the combined representation using an action score neural network to generate a respective score for each action in the predetermined set of actions; and selecting the action to be performed using the respective scores for the actions in the predetermined set of actions.

Abstract: Disclosed are laryngoscopes and other devices that include both a visualization feature and a suction component, to eliminate debris and bodily fluids and secretions that may accumulate on the visualization component. The devices may include one or more of the fluid intake ports that may be sized and located proximate to the operational ends of the visual-aid components, e.g., the camera lens or LED, to maintain a clean field of view for operation of the component. The internal passageways of the device are configured, dimensioned and/or shaped to facilitate desired fluid flow characteristics, flow rate, and/or pressure rates and facilitate methods of manufacturing the device.

Abstract: A multi-level state detecting system includes an image capture device for capturing an image of a subject; a site detecting unit for detecting a person in the image; a face recognition unit for detecting a face in the image via a face recognition database; a multi-level state identification unit for determining corresponding state and probability of the subject; a neural network prediction model database storing trained neural network prediction model associated with state classifications, the multi-level state identification unit identifying corresponding state of the subject when the face recognition unit does not detect the face; and a multi-level state updating unit for generating a final state according to a current state and at least one previous state received from the multi-level state identification unit.

Abstract: An apparatus for identifying a fake fingerprint includes a housing, a prism, a first light source unit, a second light source unit, a sensor unit and a control unit. The prism is disposed in the internal space of the housing. The first light source unit irradiates light in the internal space to allow the light to pass through the prism. The second light source unit irradiates light to allow the light not to pass the prism. The sensor unit acquires a first image through the first light source unit and a second image through the second light source unit. The control unit identifies a fake fingerprint on the basis of a result acquired by comparing the first image and the second image. The housing includes a light irradiating unit that fixes and supports the second light source unit to form a predetermined angle with the fingerprint contact surface.

Abstract: A system includes a first scanner having an inflatable membrane configured to be inflated with a medium to conform an exterior surface of the inflatable membrane to an interior shape of a cavity. The medium attenuates, at first rate per unit length, light having a first optical wavelength, and attenuates, at a second rate per unit length, light having a second optical wavelength. An emitter is configured to generate light to illuminate the interior surface and a detector is configured to receive light from the interior surface. The scanner further includes a processor configured to generate a first electronic representation of the interior shape based on the light. A design computer is configured to modify the first electronic representation into a three-dimensional shape corresponding to at least a portion of the interior shape and a fabricator configured to fabricate, based at least on the modified first electronic representation, an earbud.

Abstract: An image forming apparatus of an embodiment includes a sensor unit, an operation identification unit, and an object detection unit. The sensor unit receives an electromagnetic wave and outputs information indicating a physical quantity of the received electromagnetic wave. The operation identification unit identifies an input operation to its own apparatus, based on the information indicating the physical quantity of the electromagnetic wave. The object detection unit detects the presence or absence of an object around its own apparatus, based on the information indicating the physical quantity of the electromagnetic wave.

Abstract: A blush guide device is provided to guide a user to draw a blush. The blush guide device includes an image capturing unit, a processing unit and a display unit. The image capturing unit captures a user face image. The processing unit receives the user face image, and obtains a plurality of face feature points according to the user face image. The processing unit performs calculation according to the face feature points to obtain at least one blush guide block. The display unit displays the user face image and the corresponding blush guide block, and guides the user to put on makeup to the blush guide block. The disclosure further provides a blush guide method adapted to the blush guide device.

Abstract: A system may include one or more sensors configured to acquire data associated with a driver of a vehicle and a processor. The processor may receive the data and determine whether the data is within a baseline data associated with expected behavior of the driver. The processor may then control one or more operations of the vehicle in response to the data being outside the baseline data.

Abstract: A system and a method are described for preventing pressure ulcers in a medical care environment by monitoring adherence to a pressure ulcer prevention protocol. The method also includes identifying a first subset of pixels from the plurality of potential locations as representing a bed and/or a seating platform. The method also includes identifying a second subset of pixels within the field of view of the camera as representing an object (e.g., a subject, such as a patient, medical personnel; bed; chair; patient tray; medical equipment; etc.) proximal to the bed and/or seating platform. The method also includes determining an orientation of the object with respect to the bed and/or seating platform, and determining changes in the orientation and/or position of the object over a period of time. In implementations, the method further includes issuing an electronic communication alert based upon the determined orientation and/or position of the object over the period of time.

Abstract: A biometric image capturing apparatus includes an irradiating unit configured to irradiate a subject with light, a camera configured to capture an image of the subject, a polarizing unit which is disposed on an optical path between the irradiating unit and the camera, and configured to allow passage of light in a first polarization direction and light in a second polarization direction, a processor configured to perform computation using a first image captured by the camera according to the light in the first polarization direction that has passed through the polarizing unit and a second image captured by the camera according to the light in the second polarization direction that has passed through the polarizing unit, and to determine whether the subject is a biological body according to a result of the computation performed by the computing unit.

Abstract: An information processing apparatus includes a depth image acquisition unit configured to acquire a depth image from a measurement apparatus that has measured a distance to an object, an image acquisition unit configured to acquire a captured image from an image capturing apparatus that has captured an image of the object, and an estimation unit configured to estimate a shape of the object based on the depth image and the captured image. The estimation unit acquires information about a contour of the object from the captured image, corrects the information about the contour based on the depth image, and estimates the shape of the object based on the corrected information about the contour.

Abstract: A method for enhancing user liveness detection is provided that includes calculating, by a computing device, parameters for each frame in a video of captured face biometric data. Each parameter results from movement of at least one of the computing device and the biometric data during capture of the biometric data. The method also includes creating a signal for each parameter and calculating a similarity score. The similarity score indicates the similarity between the signals. Moreover, the method includes determining the user is live when the similarity score is at least equal to a threshold score.

Abstract: Embodiments of the present disclosure provide a software program that displays both a volume as images and segmentation results as surface models in 3D. Multiple 2D slices are extracted from the 3D volume. The 2D slices may be interactively rotated by the user to best follow an oblique structure. The 2D slices can “cut” the surface models from the segmentation so that only half of the models are displayed. The border curves resulting from the cuts are displayed in the 2D slices. The user may click a point on the surface model to designate a landmark point. The corresponding location of the point is highlighted in the 2D slices. A 2D slice can be reoriented such that the line lies in the slice. The user can then further evaluate or refine the landmark points based on both surface and image information.

Abstract: An audio-video distribution system includes a base station 12 having inputs and outputs for connection of audio-video sources and display screens respectively. In most embodiments, any audio-video source will be selectable for viewing on any display screen. Infra-red transmitters 14a,b,c,d are provided for controlling connected source devices and connected display screens. An application running on a mobile computer 16 can cause the infra-red transmitters 14a,b,c,d to transmit infra-red commands in response to user input. This is achieved with very low latency by loading machine code instructions into a secondary computer, and causing the second computer to execute those instructions in response to user input on the mobile computer 16. The machine code instructions can be stored on the mobile computer.

Abstract: Various arrangements for handling a potential security situation using a home automation system are presented. During a defined active monitoring time period, a biometric measurement of a user may be received. The biometric measurement of the user may exceed a defined threshold value for the biometric measurement. A security alert from a home automation device in wireless communication with the home automation host system may be received. If the time period between the biometric measurement is within a threshold time period of the security alert being received a security response action may be performed.

Abstract: Techniques are described for analyzing communications sent during a service session to provide (e.g., customer) service on a social media channel, the analysis to determine a quality of service provided during the session. Natural language processing, lexical analysis, pattern matching, or other types of analysis may be used to determine an empathy factor and a conversational factor for communications between a service representative (SR) and a user during a session. The factors may be combined with other factors, such as a timely acknowledgement factor and a timely resolution factor, to generate a response quality index (RQI) for the session. Based on the RQI, feedback information may be generated and sent to the SR. In some implementations, the communications may be analyzed and feedback information sent to the SR in real time during the session, to dynamically improve service quality.

Abstract: A movement error detection apparatus includes a movable region inside mark made of a projected image arranged in a movable region of a movable conveyor of each of first and second substrate conveyance devices; and a pair of movable region outside marks respectively provided on both sides of the movable region inside mark and arranged at a position outside the movable region of the movable conveyor and outward of a substrate at a work position; an imaging device which moves together with a mounting head; and a control device that selects two marks, among the marks, which are positioned on both outer sides of the substrate and are closest to the substrate, and causes the first substrate recognition camera to image the marks, as well as obtaining a movement error of the first mounting head on the basis of the two mark images.

Abstract: A medical imaging apparatus includes a gantry with a tunnel-shaped opening, an examination region and a holder. In an embodiment, the holder includes a light source for illuminating the examination region and the holder is arranged on the gantry projecting above the tunnel-shaped opening.

Abstract: According to one aspect of the present disclosure, an apparatus for taking pictures or videos triggered by pre-selected changes in a user's biorhythms is provided. The apparatus includes at least one biosensor configured to detect at least one biorhythm of a user and to generate a biorhythm signal based on the detected at least one biorhythm of the user, a camera for taking one or more pictures and/or videos, and at least one processor configured to receive the biorhythm signal from the at least one biosensor, the processor configured to compare the biorhythm signal to a biorhythm threshold and, in response to the biorhythm signal exceeding the biorhythm threshold, to simultaneously trigger the camera to take one or more pictures or videos. Further aspects and methods are also disclosed.

Abstract: An image forming apparatus includes a sensor, an operation section, and a controller. The sensor detects a sensor target. The operation section receives an operation instruction. The controller executes a setting process for controlling the sensor. The setting process is a process to adjust a sensitivity of the sensor according to detection precision. The detection precision is a relationship in a first unit period between the number of times the sensor detects the sensor target and the number of times of the operation section receives the operation instruction.

Abstract: A system and method for providing a matching process that determines a conforming pattern match to a pattern-under-test from a set of matching patterns in a pattern storage. A matching process tests every template against the pattern-under-test and resolves a conforming match condition when multiple matches to the pattern-under-test are found. In some embodiments, a matcher engine using variable match thresholds may be used to differentiate among matching templates to identify a conforming-matching template with respect to the pattern-under-test.

Abstract: An acquiring unit acquires a face image. A display control unit displays the face image acquired by the acquisition unit on a display unit. A detection unit detects positions on the face image designated by a pointer 20. A drawing unit draws makeup objects 34 and 35 on the face image along the trajectory specified by sequentially connecting the positions detected by the detection unit. The overlap control unit increases a density of an overlapping portion 36 between the makeup object 34 and the makeup object 35. The correction unit corrects the density of the overlapping portion 36 at a position corresponding to a point P3 when the trajectory has the point P3 where a direction changes with a change amount equal to or greater than a threshold value.

Abstract: A dual sensor imaging system is described for visible and infrared light. One example includes a first image sensor to detect the luminance of a scene, a second image sensor to detect the visible light chrominance of the scene and to detect an infrared image of the scene, and an image processor to receive the luminance from the first image sensor and the chrominance from the second sensor to generate a visible light image of the scene, the image processor to further receive the infrared image from the second image sensor and to extract the infrared image from the visible light chrominance of the scene.

Abstract: A fluorescence imaging device detects fluorescence in parts of the visible and invisible spectrum, and projects the fluorescence image directly on the human body, as well as on a monitor, with improved sensitivity, video frame rate and depth of focus, and enhanced capabilities of detecting distribution and properties of multiple fluorophores. Direct projection of three-dimensional visible representations of florescence on three-dimensional body areas advantageously permits viewing of it during surgical procedures, including during cancer removal, reconstructive surgery and wound care, etc. A NIR laser and a human visible laser (HVL) are aligned coaxially and scanned over the operating field of view. When the NIR laser passes over the area where the florescent dye is present, it energizes the dye which emits at a shifted NIR frequency detected by a photo diode. The HVL is turned on when emission is detected, providing visual indication of those positions.

Abstract: Data is received that is derived from a plurality of geo-spatial sensors that respectively generate data characterizing a plurality of sources within a zone of interest. The data includes series time-stamped frames for each of the sensors and at least one of the sources has two or more associated sensors. The received data can be sorted and processed, for each sensor on a sensor-by-sensor basis, using a sliding window. The sorted and processed data can then be correlated and written into a data storage application. Related apparatus, systems, techniques and articles are also described.

Abstract: An apparatus for detecting when a subject has exited an item of furniture is provided. The apparatus comprises a camera adapted to be arranged, when in use, below the underside of an item of furniture having an upper side for supporting a subject, the underside being opposite to the upper side, and a processing unit. The camera captures sequential images that do not include the upper side of the item of furniture, the images having a foreground corresponding to a region below the underside of the item of furniture and a background corresponding to a region adjacent the item. The processing unit receives images from the camera; detects, for each image, an edge corresponding to an edge of the item; detects the appearance of a feature contiguous with the edge; monitors how a detected feature changes over a time period; determines whether a change to the detected feature satisfies at least one predefined criterion for a subject exit event; and outputs a signal based on the determining.

Abstract: A passenger information detection device includes: an acquisition unit that acquires an image imaged by an imaging device that is provided in an interior space of a vehicle to image a passenger seated on a seat and a detection value of a load sensor provided on the seat; a first calculation unit that calculates first information that is information on a face of the passenger from the image; and a second calculation unit that calculates second information that is information on a body size of the passenger based on the first information and the detection value.

Abstract: A system and method for medical spatial orientation is disclosed including a robotic arm; an image sensor coupled to the robotic arm; a visualization headset; and a computing subsystem coupled to the robotic arm and the visualization headset. The computing subsystem includes a processor; a non-transitory machine-readable medium communicatively coupled to the processor; and instructions stored on the non-transitory machine-readable medium that, when loaded and executed by the processor, cause the processor to create a first image of a first portion of a surgical field at an image sensor coupled to the robotic arm; detect a movement of a visualization headset indicating a second portion of the surgical field; determine a movement of the robotic arm to position the image sensor at the second portion of the surgical field; move, based on the determination, the robotic arm; and create a second image of the second portion of the surgical field.

Abstract: A virtual reality (VR) or augmented reality (AR) head mounted display (HMD) includes multiple image capture devices positioned within and on the HMD to capture portions of a face of a user wearing the HMD. Multiple image capture devices are included within the HMD to capture different portions of the face of the user within the HMD, and one or more other image capture devices are positioned to capture portions of the face of the user external to the HMD. Captured images from various image capture devices may be communicated to a console or a controller that generates a graphical representation of the user's face based on the captured images.

Abstract: Proactively identifying and interdicting transport of commodities associated with illicit nuclear materials and nuclear weapons shielded by high Z-number materials, such as lead, can help ensure effective nuclear nonproliferation. In an embodiment, a method for imaging an object on a surface includes exciting a surface with ultrasonic excitation from an ultrasonic transmitter having an ultrasonic transducer in contact with the surface. The method further includes imaging, at a processor, a two-dimensional representation of the object acoustically coupled to the surface based on the ultrasonic reflections received at an ultrasonic receiver via a receiving transducer in contact with the surface. This method can complement existing x-ray screening systems to increase the odds of detecting radiological materials.

Abstract: Embodiments for facilitating communication between users sharing a visual cue. A gaze location of a first user is determined as an approximation in three dimensional space. The gaze location is transmitted to a second user. A gaze focus of the first user based on the determined gaze location is displayed to the second user.

Abstract: A lip gloss guide device including an image capturing unit, a processing unit and a display unit is provide to guide a user to draw a lip gloss. The image capturing unit captures a face image of the user, where the face image includes a lip of the user. The processing unit receives the face image, and obtains a plurality of lip feature points according to the face image. The processing unit performs calculation according to the lip feature points and a predetermined ratio between an upper lip and a lower lip to obtain an upper lip gloss guide block and a lower lip gloss guide block. The display unit displays a lip image and the corresponding upper lip gloss guide block and lower lip gloss guide block, and guides the user to put on makeup to the upper lip gloss guide block and the lower lip gloss guide block.

Abstract: An image of a pinna is captured. Based on the image of the pinna, a non-linear transfer function is determined which characterizes how sound is transformed at the pinna. A signal is output indicative of one or more audio cues to facilitate spatial localization of sound via the pinna, where the one or more audio cues is based on the non-linear transfer function.

Abstract: A method for identifying contamination upon a lens of a stereoscopic camera is disclosed. The stereoscopic camera is arranged such that it has the same capturing area over time, and is provided with a first camera providing first images of said capturing area and a second camera providing second images of said capturing area. The first and second images are divided into at least one evaluation area correspondently located in respective image. A traffic surveillance system is also disclosed where contamination upon a lens of a stereoscopic camera is identified according to said method.

Abstract: A computing system performs a method of determining cumulative exposure to a gas. The computing system receives data that correspond to local concentrations of a gas from a plurality of stationary gas sensors in a home. Respective stationary gas sensors are located at respective fixed locations in respective rooms in the home. The computing system also receives data that correspond to occupancy of the home, including occupancy by a first occupant. The computing system determines a cumulative exposure of the first occupant to the gas in the home, based at least in part on the received data that correspond to local concentrations of the gas and the received data that correspond to occupancy of the home. The computing system performs and/or sends instructions to perform one or more predefined operations in accordance with the determined cumulative exposure of the first occupant.

Abstract: Provided is a method of measuring a heart rate in an electronic device. The method includes obtaining a face image of a subject by using the electronic device; determining a target region within the obtained face image; analyzing color information within the determined target region; and determining a heart rate of the subject on the basis of the analyzed color information. The analyzing of color information is performed on the basis of a differential arithmetic operation between a first color component and a second color component within the target region.