Abstract: Methods, systems, and apparatus for deriving a relationship between minimum ground clearance (MGC) and inertial sensor data. A regression model may be generated by collecting tri-axial angular velocity and acceleration data from inertial sensors and MGC data from optical motion capture systems during a walking trial. A linear, quadratic, interaction, stepwise interaction, or another regression model may be generated. The regression model may estimate the MGC as a function of one or more parameters measured by or derived from the inertial sensor data. The regression model may be used to calculate an estimate of the MGC based on inertial sensor data collected from one or more individuals.

Abstract: A gesture recognition device configured to recognize a gesture of a hand from a captured image of a user, having a fingertip candidate detector that detects a fingertip candidate from the image, a finger detector that detects a skin area as a finger, the skin area extending by a predetermined length in a certain direction from the fingertip candidate detected by the fingertip candidate detector, and a gesture type specifying unit that specifies a type of the gesture based on the number of fingers detected by the finger detector.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and detect the presence of a human from at least one of the plurality of image frames using pattern matching performed on an input image. The input image to the pattern matching is a sliding window portion of the image frame that is aligned with a rectified coordinate system such that a vertical axis in the workspace area is aligned with a vertical axis of the input image.

Abstract: There is provided an image processing apparatus including: a communication unit receiving first feature amounts, which include coordinates of feature points in an image acquired by another image processing apparatus, and position data showing a position in the image of a pointer that points at a location in a real space; an input image acquisition unit acquiring an input image by image pickup of the real space; a feature amount generating unit generating second feature amounts including coordinates of feature points set in the acquired input image; a specifying unit comparing the first feature amounts and the second feature amounts and specifying, based on a comparison result and the position data, a position in the input image of the location in the real space being pointed at by the pointer; and an output image generating unit generating an output image displaying an indicator indicating the specified position.

Abstract: An embodiment provides a method, including: detecting, at a surface of a device accepting handwriting input, a location of the display surface associated with initiation of a handwriting input; determining, using a processor, a location of an entry field in a document rendered on a display surface, the location of the entry field being associated with a display surface location; determining, using a processor, a distance between the location of the surface associated with initiation of the handwriting input and the location of the entry field; and automatically inserting input, based on the handwriting input, into the entry field after determining the distance is less than a threshold value. Other aspects are described and claimed.

Abstract: Technologies are described herein for interpreting character arrangements. An image including an arrangement of characters may be received or captured by a computing device. Techniques described herein generate data representative of the characters. Characteristics and other information interpreted from the image may be processed to determine a data type. The data representative of the characters may be arranged into a data structure based on the data type, an arrangement type and/or other information interpreted from the image. The data type may indicate one or more attributes of the arranged data such as a format, font, date, language, or currency. The data type may also indicate how data is used in a process, equation or calculation. In addition, the data type may identify an anchor that may be used to merge data generated from the image with other data generated from another image.

Abstract: A method for detecting texts included in an image is disclosed. The method includes steps of: (a) detecting at least one text candidate in an inputted image by referring to feature values of pixels in the inputted image; (b) classifying (i) the detected text candidate as a strong text or a non-strong text by referring to a comparison result between a first threshold value and a first feature value and (ii) the text candidate classified as the non-strong text as a weak text or a non-text by referring to a comparison result between a second threshold value and a second feature value; and (c) determining whether to classify the weak text as the strong text by referring to information on the strong text and information on the weak text.

Abstract: A method includes identifying a plurality of linear geographic dividers for a region, wherein the plurality of linear geographic dividers comprises one or more of streets, railways, electrical lines or rivers, determining a set of logical geometric blocks for the region, based on the identified plurality of linear geographic dividers and generating one or more tiles based at least on the plurality of linear geographic dividers and the determined logical geometric blocks.

Abstract: The subject technology provides embodiments for performing fast corner detection in a given image for augmented reality applications. Embodiments disclose a high-speed test that examines intensities of pairs of pixels around a candidate center pixel. In one example, the examined pairs are comprised of pixels that are diametrically opposite ends of a circle formed with the candidate center pixel. Further, a pyramid of images including four rings of surrounding pixels is generated. An orientation of the pixels from the four rings are determined and a vector of discrete values of the pixels are provided. Next, a forest of trees are generated for the vector of discrete values corresponding to a descriptor for a first image. For a second image including a set of descriptors, approximate nearest neighbors are determined from the forest of tree representing closest matching descriptors from the first image.

Abstract: In accordance with one embodiment, an information processing apparatus comprises an image capturing module configured to photograph a commodity to capture the image of the commodity, an acquisition module configured to acquire the image captured by the image capturing module, a recognition module configured to recognize a commodity as a candidate of the commodity from standard commodities based on the image of the commodity captured by the image capturing module, a clock module configured to count an elapsed time until the recognition module recognizes the commodity, and a notification module configured to give a notification if the elapsed time reaches a given time.

Abstract: A computer-implemented method of tracking a target object in an object recognition system includes acquiring a plurality of images with a camera. The method further includes simultaneously tracking the target object and dynamically building environment map data from the plurality of images. The tracking of the target object includes attempting to estimate a target pose of the target object with respect to the camera based on at least one of the plurality of images and based on target map data. Next, the method determines whether the tracking of the target object with respect to the camera is successful. If not, then the method includes inferring the target pose with respect to the camera based on the dynamically built environment map data. In one aspect the method includes fusing the inferred target pose with the actual target pose even if tracking is successful to improve robustness.

Abstract: A system and computer implemented method for detecting the location of a mobile device using semantic indicators is provided. The method includes receiving, using one or more processors, a plurality of images captured by a mobile device at an area. The area is associated with a set of candidate locations. Using the one or more processors, one or more feature indicators associated with the plurality of images are detected. These feature indicators include semantic features related to the area. The semantic features are compared with a plurality of stored location features for the set of candidate locations. In accordance with the comparison, a location from the set of candidate locations is selected to identify an estimated position of the mobile device.

Abstract: A system and method executable by a computing device of an augmented reality system for registering a camera in a physical space is provided. The method may include identifying an origin marker in a series of images of a physical space captured by a camera of an augmented reality system, and defining a marker graph having an origin marker node. The method may further include analyzing in real-time the series of images to identify a plurality of expansion markers with locations defined relative to previously imaged markers, and defining corresponding expansion marker nodes in the marker graph. The method may further include calculating a current position of the camera of the augmented reality system in the physical space based on a location of a node in the marker graph corresponding to a most recently imaged marker, relative to the origin marker and any intermediate markers.

Abstract: The automatic generation (702) of one or more secondary video streams based on an input primary video stream (701) may use analytics performed on the video to provide information on targets, events, and/or areas of interest to permit the one or more secondary video streams (703) to concentrate on one or more targets, events, and/or areas of interest.

Abstract: The invention relates to a vehicle (10) with at least one camera (16), by means of which at least one image area of a surrounding of the vehicle (10) is capturable, the image area comprising a plurality of pixels and being arranged obliquely above a vehicle front as viewed in the direction of travel of the vehicle (10), and with a tunnel detection device (44) designed for determining an average brightness of the at least one image area. The tunnel detection device (44) comprises a device (46) for feature or edge detection, by means of which differences in the brightness of pixels differing from each other are capturable and thus features characterized by abrupt changes in brightness are detectable in the at least one image area. Moreover, the invention relates to a method for operating a camera arrangement for a vehicle (10).

Abstract: A monitoring unit for the exterior in the direction of travel of a motor vehicle includes at least one camera system with an image recording sensor. The sensor has color encoding in some regions and, otherwise, monochrome encoding. An assist system is also provided with such a monitoring unit, in particular a traffic sign and/or lane recognition assist system.

Abstract: A system and method that is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. It can also process cursive handwriting. Further, the method and system can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of segmentation, character recognition, and language modeling. These three processes occur concurrently through the use of dynamic programming.

Abstract: The present disclosure relates to a method for identity authentication based on face recognition. The method comprises: initiating an interaction authentication request, which includes requested interaction tracks, and sending the interaction authentication request to an authentication client; receiving face interaction information sent by the authentication client; extracting face action tracks from the face interaction information; determining whether the face action tracks are consistent with the requested interaction tracks; if the face action tracks are consistent with the requested interaction tracks, determining that the authentication is passed, otherwise determining that the authentication fails. The above solution could prevent the authentication server from being cheated by face pictures or videos taken previously and could ensure that the face pictures or videos passing the authentication is taken in real time from a real person.

Abstract: In the environment of executing an image processing for scenes by defining a parameter set for each scene, a configuration is needed capable of reflecting the change by smaller man-hour even when the content of the image processing has been changed. The image processing device includes an operating unit (that selectively executes a plurality of pieces of processing) and a storage that can be accessed from the operating unit. The storage holds: a common flow for executing processing selected out of the plurality of pieces of processing, in a predetermined order; user scene data in which a parameter set including one or a plurality of parameters are defined for each scene; and a command code concerning the parameter set included in the user scene data. The command code includes a first processing rule for causing a corresponding parameter set to reflect a result of a processing following the common flow.

Abstract: A method and system that allows healthcare providers, hospitals, skilled nursing facilities and other persons to monitor disabled, elderly or other high-risk individuals to prevent or reduce falls and/or mitigate the impact of a fall by delivering automated notification of “at risk” behavior and falls by such an individual being monitored where assistance is required. The monitored individual is virtually represented as a blob object of at least a specific size by a computerized monitoring system and such system detects and alerts when the blob object enters or crosses into a virtually defined or designated blob detection zone and remains in the zone for at least a predetermined period of time.

Abstract: A method of determining a contour segment for an object in an image captured by a camera is disclosed. A plurality of corner points located on a part of an object in the image is determined. Pairs of corner points are selected from the determined corner points. A path for at least one of the pairs of corner points is determined, the path connecting the corner points of the at least one pair of corner points along the boundary of the object. The contour segment is determined for the object using the determined path.

Abstract: Aspects of the present invention are related to systems, methods and apparatus for boundary detection, in an image, by suppression of contours resulting from background textures and text in the image.

Abstract: An image processing device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute: determining whether or not an eye region of a user being detected a line-of-sight in an image resulting from photographing an eye of the user is influenced by reflection light, the eye region being a region of the eye; and detecting, as a feature portion of the eye, a region that is included in the eye region and that includes a pixel having a feature that is the same as or similar to any of features of the feature portion, when it is determined that the eye region is influenced by the reflection light, the features being accumulated for respective strengths of influences of the reflection light that appear in images of the feature portion of the eye.

Abstract: A reference 2D data is provided. The reference 2D data comprises a first plurality of pixels defined in 2D coordinates. The reference 2D data is transformed into a reference 1D data having a first 1D size. The reference 1D data comprises the first plurality of pixels in a transformed 1D order. A plurality of input 2D data are also provided. An input 2D data comprises a second plurality of pixels defined in 2D coordinates. The plurality of input 2D data are transformed into a plurality of input 1D data, which comprises transforming the input 2D data into an input 1D data. Transforming the input 2D data into the input 1D data is the same as transforming the reference 2D data into the reference 1D data. Finally, a transformed input 1D data from the plurality of input 1D data that matches the transformed reference 1D data is searched.

Abstract: Disclosed herein are a method, system, and computer program product for determining a correspondence between a first object (713) tracked in a first field of view and a second object tracked (753) in a second field of view. The method determines a first area (711) in the first field of view, based on the location and size of the first object (713). The method utilizes a predetermined area relationship between the first area (711) in the first field of view and at least one area (751) in the second field of view to determine a second area (751) in the second field of view. In one embodiment, the method determines the second area (751) in the second field of view by comparing predetermined area relationships between the first area (711) and any areas (751) in the second field to determine a best match.

Abstract: Example systems and methods for classifying visual patterns into a plurality of classes are presented. Using reference visual patterns of known classification, at least one image or visual pattern classifier is generated, which is then employed to classify a plurality of candidate visual patterns of unknown classification. The classification scheme employed may be hierarchical or nonhierarchical. The types of visual patterns may be fonts, human faces, or any other type of visual patterns or images subject to classification.

Abstract: According to an example, a digital image may be processed by an ensemble of convolutional neural networks (CNNs) to classify objects in the digital image. For each CNN, a candidate architecture and candidate parameters may be selected to build a plurality of CNNs. Once it is determined that a predetermined number of CNNs, each having different values for the selected candidate parameters, meet a validation threshold, an ensemble of CNNs may be generated from the predetermined number of CNNs. The predictions from the ensemble of CNNs may then be aggregated to accurately classify the objects in the digital image.

Abstract: The disclosure discloses a non-transitory computer-readable recording medium storing print data editing program. The program executes steps including a background patter print data generating, a disposition setting, and a disposition adjusting. In the disposition adjusting, at least one spacing adjustment of column spacing adjustment and row spacing adjustment is performed. The column spacing adjusts the column spacing so that a length of the sides parallel with the angle of inclination in the disposition adjustment region becomes an integer multiple of a total length of a length of the background pattern print data along the row direction and the column spacing. The row spacing adjustment adjusts the row spacing so that a length of the sides orthogonal to the angle of inclination becomes an integer multiple of a total length of a length of the background pattern print data along the column direction and the row spacing.

Abstract: An image processing apparatus performs a density adjustment process for generating an image containing a copy-forgery-inhibited pattern image for warning against the use of copy products. To help users to easily adjust the density of a latent image portion and a background portion in the copy-forgery-inhibited pattern image, the image processing apparatus determines a density relationship of the latent image portion and the background portion by performing a plurality of adjustment operations, in combination, different in the amount of adjustment relating to the range of variable density in at least one of the latent image portion and the background portion, and sets, based on the density relationship, the density data of each of the latent image portion and the background portion in the data of the copy-forgery-inhibited pattern image.

Abstract: An image forming device comprises: a receiving unit that receives a request from an external device; an acquiring unit that acquires a port number indicated by the request received by the receiving unit and an information amount of the request; a first determining unit that determines whether or not the port number coincides with a specific port number; a second determining unit that determines whether or not the information amount is equal to or greater than a specific threshold; and a system control unit that switches an operation mode from a power-saving mode to a normal mode when the first determining unit determines that the port number coincides with the specific port number and the second determining unit determines that the information amount is equal to or greater than the specific threshold.

Abstract: A product surface including a first optoelectronically readable code formed by an arrangement of planar cells of a first and a second cell type. The code has a large detectable region and the readability thereof is robust in relation to demands during the production and/or the use of the surface. The cells, as integral components of the surface, have a surface profile. An intensity difference ?I=I2?I1 in the intensity I2 reflected by the surface profile of the second cell type and intensity I1 reflected by the surface profile of the first cell type results in the case of light incidence as a result of the configuration of the surface profiles. The surface has a second code. The maximum of the absolute intensity difference |?I1| of the first code lies in a different reflection direction than the maximum of the absolute intensity difference |?I2| of the second code.

Abstract: A protective stripe for a bank card includes several layers interconnected with one another, as the first of the layers is an adhesive layer, a protective stripe is fixed to the bank card, a second layer is protective and bearing layer made of at least one of paper, plastic and foil, and a third layer is the carrier of ex officio information necessary for the operation of ATMs.

Abstract: Methods for manufacturing a supply item for an imaging device having a helical physical unclonable function are disclosed. The helical physical unclonable function may be used to authenticate a supply item for an imaging device. Measurements of the magnetic field above a helical flight are stored in a non-volatile memory to be used by an imaging device to authenticate the supply item. Other systems and methods are disclosed.

Abstract: A preferred embodiment of the invention includes: an identification device (1) for receiving a first signal and transmitting a second signal, the device including: a receiving means (35) for receiving the first signal to generate a voltage; an integrated circuit (37) having a state selection means (41) for selecting whether the device (1) is in a. first state or a second state; a connection (39) between the receiving means (35) and the integrated circuit (37); a transmission means (45) for generating the second signal. The invention also includes a. system (50) that includes an interrogator (43) for interrogating a, plurality of the identification devices (1).

Abstract: Shielding is associated with RFID tags to achieve new systems and methods having various advantages. These systems include containers configured to store RFID enabled identity documents, the use of RFID tags to monitor the state of a container, and the inclusion of shielding in identity devices. Disclosed are shielded passports, driver's licenses, and the like. Some embodiments further including reading systems for reading identity devices comprising shielding and RFID tags. Further, various switchable RFID devices are disclosed. These switchable RFID devices may include one or more RFID tags and one or more switches. Some of these one or more switches are optionally wireless. In various embodiments, the switchable RFID devices include identity devices, financial devices, remote controls, and the like.

Abstract: A contact smart card has a smart card contact pad and an IC chip. The smart card contact pad includes a circuit substrate, a card-reader contact element on a first side of the circuit substrate, and a connection element on a second side of the circuit substrate. The card-reader contact element has a noble metal electrically conductive surface, and the connection element has a chip terminal connection surface which is not a noble metal. The IC chip is preferably flip-chip mounted at the second side of the circuit substrate and electrically connected to the chip terminal connection surface. Furthermore, the chip terminal connection surface is preferably an organometallic electrically conductive corrosion protection layer.

Abstract: Media rolls, support structures for the media rolls, and media processing systems are provided. A media roll may include an identification transponder having retrievable information regarding the media units and associated media unit transponders wound around a core of the media roll. A support structure may include a spindle for supporting a media roll and include an identification coupler for communicating with the identification transponder. In addition to the spindle having the identification coupler, the media processing systems may include a second coupler for encoding the media unit transponders and a printhead for printing indicia onto the media units. The information retrieved from the identification transponder may be used to adjust one or more encoding and/or printing settings of the systems.

Abstract: A cognitive architecture uses hierarchically arranged modules to associate the computation of many expected attributes with a single concept. A first value stored in a first module represents a concept state. A second value stored in the first module represents an expectation state. The first module receives a third value that represents an input state. The first module has a lower hierarchy than a second module and a higher hierarchy than a third module. The first module provides the first value to the second module and the second value to the third module. The first value is computed using the third value and concept information stored in the first module. The second value is computed using the first value, the third value and expectation information stored in the first module. An actuated mechanism receives a signal derived from the second value, which influences an operation of the actuated mechanism.

Abstract: Embodiments of the invention relate to canonical spiking neurons for spatiotemporal associative memory. An aspect of the invention provides a spatiotemporal associative memory including a plurality of electronic neurons having a layered neural net relationship with directional synaptic connectivity. The plurality of electronic neurons configured to detect the presence of a spatiotemporal pattern in a real-time data stream, and extract the spatiotemporal pattern. The plurality of electronic neurons are further configured to, based on learning rules, store the spatiotemporal pattern in the plurality of electronic neurons, and upon being presented with a version of the spatiotemporal pattern, retrieve the stored spatiotemporal pattern.

Abstract: Methods and systems for automating carbon footprinting are disclosed. In some embodiments, the methods include a plurality of steps. In some embodiments, related to predetermined resources associated with an item from predetermined data sources is obtained. Then, estimated emission factors are calculated for each of the resourced. Next, a contributory uncertainty of the data and of the emission factors is determined. Then, a user is guided based on a comparison of the respective contributory uncertainty of data related to the resources or emission factors Next, both data related to the resources and the estimated emission factors of the resources are utilized to determine a carbon footprint of the item.

Abstract: Computerized contextual analysis systems and methods suitable for monitoring situations, regions, and groups characterized by volatility and uncertainty are provided. Via use of exemplary systems and methods, decision makers, for example politicians, warfighters, and analysts can gain insight into the cultures, attitudes, events, and relationships that may impact their missions.

Abstract: A method for analyzing and prioritizing changes to configuration parameters of applications in an information technology system, including collecting configuration parameters of applications executed on computer stations in a network, storing the collected configuration parameters in a database, comparing the configuration parameters of an application from a specific station with configuration parameters of the application at different stations, determining differences in the configuration parameters by the comparing, analyzing the determined differences according to a set of analysis dimensions that represent rules for evaluating the differences, assigning a score representing the level of conformity of the differences to each of the analysis dimensions, defining a context for reviewing the differences, assigning a weight to each analysis dimension representing the importance of the analysis dimension, adjusting the weights assigned to the analysis dimension based on the context, calculating a total risk for

Abstract: A method, apparatus and product for automated multi-objective solution selection. The method comprises obtaining a set of solutions to a multi-objective problem, wherein each solution is a non-dominated solution. The method further comprises computing outranking weights for each pair of solutions and selecting a subset of the set of solutions based upon a defensive criteria in with respect to the outranking weights, wherein the defensive criteria relates to a number of solutions that outrank the subset. The method further comprises outputting the subset of the set of solutions.

Abstract: A method for configuring a device for detecting a situation from a set of situations where a physical system comprises the following steps: reception of a learning sequence corresponding to a given situation of the physical system; determination of parameters of a hidden-state Markov statistical model recorded in the detection device and relating to the given situation, on the basis of a prior initialization of these parameters.

Abstract: Embodiments include processing a data structure representing a dependency matrix having columns representing respective first components and rows representing respective second components. Aspects include assigning each cell of the matrix a value indicative of the level of dependency or indicative of an unknown dependency of a pair of first and second components forming the cell and assigning each component of the first and second components an affiliation vector indicative of the strength of affiliation of the component to N predefined initial clusters of cells of the matrix. Aspects also include determining a probability model using the affiliations vectors parameters and estimating the parameters of the probability model for a plurality of different numbers of clusters starting from the initial number N of clusters. Aspects further include computing a score for the parameters of the probability model estimated and selecting the parameters of the probability model with the highest computed score.

Abstract: An individual having a plurality of first features and a second characteristic is identified. A plurality of second features associated with a second characteristic is determined. For each first feature among the plurality of first features, a respective probability distribution indicating, for each respective second feature, a probability that a person having the respective second feature has the first feature, is determined, thereby generating a plurality of probability distributions. A probabilistic classifier is used to combine the plurality of probability distributions, thereby generating a merged probability distribution. A Monte Carlo method is used to generate a prediction set based on the merged probability distribution, the prediction set including a plurality of prediction values for the second characteristic of the individual, each respective prediction value being associated with one of the plurality of second features. The prediction set is stored in a memory.

Abstract: A technique relates to an assembly for a quantum computing device. A quantum bus plane includes a first set of recesses. A readout plane includes a second set of recesses. A block is positioned to hold the readout plane opposite the quantum bus plane, such that the first set of recesses opposes the second set of recesses. A plurality of qubit chips are included where each has a first end positioned in the first set of recesses and has a second end positioned in the second set of recesses.

Abstract: Systems and methods for conflict resolution and stabilizing cut generation in a mixed integer linear program (MILP) solver are disclosed. One disclosed method includes receiving a mixed integer linear problem (MILP), the MILP having a root node and one or more global bounds; pre-processing the MILP, the MILP being associated with nodes; establishing a first threshold for a learning phase branch-and-cut process; performing, by one or more processors, the learning phase branch-and-cut process for nodes associated with the MILP, wherein performing the learning phase branch-and-cut process includes: evaluating the nodes associated with the MILP, collecting conflict information about the MILP, and determining whether the first threshold has been reached; responsive to reaching the first threshold, removing all of the nodes and restoring a root node of the MILP; and solving, with the one or more processors, the MILP using the restored root node and the collected conflict information.

Abstract: In one embodiment, first weight information indicating a first set of delta values is obtained, where the first set of delta values includes a first delta value for each weight in a set of weights, the set of weights including a weight for each of a set of one or more parameters of a model. In addition, second weight information indicating a second set of delta values is obtained, where the second set of delta values includes a second delta value for each weight in the set of weights. Combined weight information including a combined set of delta values or a combined set of weights is generated based, at least in part, upon the first weight information and the second weight information.

Abstract: Various systems and methods provide an intuitive user interface that enables automatic specification of queries and constraints for analysis by ML component. Various implementations provide methodologies for automatically formulating machine learning (“ML”) and optimization queries. The automatic generation of ML and/or optimization queries can be configured to use examples to facilitate formulation of ML and optimization queries. One example method includes accepting input data specifying variables and data values associated with the variables. Within the input data any unspecified data records are identified, and a relationship between the variables specified in the input data and a variable associated with the at least one unspecified data record is automatically determined. The relationship can be automatically determined based on training data contained within the input data. Once a relationship is established a ML problem can be automatically generated.