Abstract: Examples disclosed herein relate to selection of machine-readable link type. Examples include acquisition of an electronic document, selection of a machine-readable link type for evaluation, and a decision of whether at least one characteristic of the document satisfies at least one evaluation metric for use of the selected type of machine-readable link.

Abstract: The present disclosure describes methods and systems for storing virtual personal identifiable information. In some implementations, the information is collected during the authentication of identification (ID) documents. The system includes a one-way hashing function that converts unique personal identifiable information into a unique digest. The system can store the digest without having to store the personal identifiable information. Because the hashing function generates the same digest when given the same input, the digests can be used as anonymized identifiers in place of the personal identifiable information.

Abstract: Methods, systems, and media for processing queries relating to presented media content are provided. In some implementations, a method comprises: receiving a request to associate with a media playback device that is presenting media content to a user of the mobile device; activating a microphone associated with the mobile device; converting received ambient sounds to text inputs; determining whether the text inputs include a trigger term and the query; determining media playback information from the media application that includes timing information corresponding to when during the presentation of the media content the query was received and media content identification information; causing a search to be performed that includes the query, the timing information, and the media content identification information; obtaining a search result that is responsive to the query; and presenting the search result on a display associated with the mobile device.

Abstract: An apparatus for identifying plant varieties from leaf or flower samples taken while in the field comprises a scanning device having a backlight so as to enable a detailed image of a sample to be recorded digitally, a computer for uploading the image for analysis, a computer program which allocates user prescribed parameters such as leaf venation, leaf shape, base position and shape and leaf curvature to the image, and utilizing the data produced by the computer program and applying an algorithm to it for matching the data against a database of plant varieties to determine the highest match probability.

Abstract: One embodiment of the invention provides a system for mapping a neural network onto a neurosynaptic substrate. The system comprises a reordering unit for reordering at least one dimension of an adjacency matrix representation of the neural network. The system further comprises a mapping unit for selecting a mapping method suitable for mapping at least one portion of the matrix representation onto the substrate, and mapping the at least one portion of the matrix representation onto the substrate utilizing the mapping method selected. The system further comprises a refinement unit for receiving user input regarding at least one criterion relating to accuracy or resource utilization of the substrate. The system further comprises an evaluating unit for evaluating each mapped portion against each criterion. Each mapped portion that fails to satisfy a criterion may be remapped to allow trades offs between accuracy and resource utilization of the substrate.

Abstract: Systems and methods for graphical data presentation during a sporting event broadcast are disclosed. A server platform is constructed and configured in network communication with at least one input device and at least one display device. The at least one input device transmits input data with time code related to the sporting event to the server platform in real time or near real time. The server platform processes the input data according to a production sequencing of the sporting event, thereby creating processed data. The server platform creates and integrates the processed data with a video presentation of the sporting event based on the production sequencing of the sporting event. The at least one display device displays a customized graphical presentation of the processed data with the video presentation.

Abstract: Some implementations may include a computer-implemented method for applying at least two digital watermarks to a digital document, the method including: receiving a digital document comprising visual contents; generating a first digital watermark to be visually presented at a first time point; generating a second digital watermark to be visually presented at a second time point, the second digital watermark being different from the first digital watermark and the second time point being different from the first time point; and applying both the first digital watermark and second digital watermark to the digital document t.

Abstract: Disclosed herein are methods and systems for determining a location of an object within an environment. An example method may include determining a three-dimensional (3D) location of a plurality of reference points in an environment, receiving a two-dimensional (2D) image of a portion of the environment that contains an object, selecting certain reference points from the plurality of reference points that form a polygon when projected into the 2D image that contains at least a portion of the object, determining an intersection point of a ray directed toward the object and a 3D polygon formed by the selected reference points, and based on the intersection point of the ray directed toward the object and the 3D polygon formed by the selected reference points, determining a 3D location of the object in the environment.

Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.

Abstract: System and techniques for preventing face-based authentication spoofing are described herein. A visible light emitter may be controlled to project a pattern into a camera's field of view during an authentication attempt. An image may be obtained from the camera for the authentication attempt. A potential spoofing region on image may be identified by finding the pattern. An authentication attempt based on a face found in the potential spoofing region may be prevented.

Abstract: Systems, devices, media, and methods are presented for segmenting an image of a video stream with a client device, identifying an area of interest, generating a modified area of interest within one or more image, identifying a first set of pixels and a second set of pixels, and modifying a color value for the first set of pixels.

Abstract: Various image processing arrangements are detailed for detecting mis-marking of product packaging artwork with two conflicting steganographically-encoded product identifiers. Some embodiments concern detection in a pre-press or test-print quality assurance stage. Others concern detection post-press. All help serve to assure accurate product identification by point of sale scanners. A great number of other features and arrangements are also detailed.

Abstract: Some implementations may provide a computer-implemented method for validating a digital document, the method including: receiving, at a computing device, the digital document comprising at least two digital watermarks, the digital document issued by a central entity; retrieving a first digital watermark from the digital document, the first digital watermark visually presented at a first time point; retrieving a second digital watermark from the digital document, the second digital watermark visually presented at a second time point, the second digital watermark being different from the first digital watermark and the second time point being different from the first time point; and reading the digital document based on the retrieved first and second digital watermarks.

Abstract: An augmented reality system comprises one or more databases storing a passable world model data comprising a set of points pertaining to real objects of the physical world, and one or more object recognizers configured for running on the passable world model data. Each of the object recognizer(s) is programmed to recognize a predetermined object of the real world based on a known geometry of a corresponding set of points. The augmented reality system further comprises a head-worn augmented reality display system configured for displaying virtual content to a user based at least in part on the recognized object.

Abstract: A computed tomography (CT)-based clinical decision support system provides fractional flow reserve (FFR) decision support. The available data, such as the coronary CT data, is used to determine whether to dedicate resources to CT-FFR for a specific patient. A machine-learnt predictor or other model, with access to determinative patient information, is used to assist in a clinical decision regarding CT-FFR. This determination may be made prior to review by a radiologist and/or treating physician to assist decision making.

Abstract: A system and method validates user supplied photographs and/or characteristics using a video, audio or series of images of the user responding to instructions, and uses such validation in searching and/or matching.

Abstract: A facility for annotating portions of a document shown in a visual representation of the document with annotations reflecting aggregated document activities performed with respect to the portions is described. The facility specifies a visual representation of at least part of the document. For each of at least two portions of the document that are not identical and that are represented in the specified visual representation, the facility attaches to locations in the document's visual representation corresponding to the portion a visual annotation reflecting an aggregation operation against document activities performed with respect to the portion.

Abstract: Differential modulation schemes encode a data channel within host signal or noisy environment in a manner that is robust, flexible to achieve perceptual quality constraints, and provides improved data capacity. Differential arrangements enable a decoder to suppress host signal or other background signal interference when detecting, synchronizing and extracting an encoded data channel. They also enable the incorporation of implicit or explicit synchronization components, which are either formed from the data signal or are complementary to it.

Abstract: Imagery captured by a point-of-sale scanner (e.g., in a supermarket) for purposes of barcode decoding, is contrast-enhanced preparatory to use for watermark decoding—despite the fact that such operation may sometimes result in contrast between certain pixels being diminished. A great variety of other features and arrangements are also detailed.

Abstract: A media content sharing method is provided which includes receiving a query message including query information associated with a media content from a client device, determining whether a storage unit contains a target description file including at least a segment information including characteristics corresponding to the query information, whereby the storage unit stores a plurality of description files uploaded from a plurality of content providing devices, and transmitting a request message to a first content providing device which uploads the target description file, for requesting the first content providing device to provide a target media segment.

Abstract: Methods, systems and devices enable enhanced delivery of metadata, as well as auxiliary programs and services associated with a primary content. In one method, a primary content with pre-existing watermarks is received at a content distributor device. The pre-existing watermark include specific fields that allow retrieval of a first metadata. The values and boundary locations of the symbols of the pre-existing watermark messages are determined, and symbols of a new watermark message are embedded in the primary content to render the pre-existing watermarks undetectable. The new watermark message includes symbol values that different from those in the pre-existing watermark messages and enable retrieval of a second metadata. Upon transmission of the primary content to a client device, detection of the new watermark message, and initiation of a request by the client device, access to the first or the metadata, as well as associated programs or services, are enabled.

Abstract: The present invention relates to a video analysis system for an energy-consuming building equipment. The video analysis system includes a camera and an image processing unit to monitor people who appear in a target region, and in an actual space where the camera coexists with the energy-consuming building equipment, a height from the camera to a bottom surface of the actual space ranges from 2 to 10 meters. The present invention further relates to an intelligent building management system provided with the video analysis system for the energy-consuming building equipment. With the video analysis system of the present invention, a security system of a building is combined with the energy-consuming building equipment by means of an optimal camera design/arrangement, which can improve the operation efficiency of the whole building significantly and achieve a desirable energy-saving effect.

Abstract: A crowdsourced search and locate platform has been developed and put into practice. A plurality of geospatial images of a geographical region of interest are presented to a plurality of participants in an internet mediated crowdsourcing campaign for the purpose of identifying and tagging specific features of interest to the campaign administrator. An algorithm of the invention, CrowdRank, monitors the identification accuracy of the participants both absolute and compared to other participants calculating a score used to weight each identification made by that user. CrowdRank also chooses images to maximize campaign efficiency and calculates the confidence level of each feature identification.

Abstract: Disclosed are blockchain-based methods and systems for watermarking digital content. In an exemplary aspect, a method for watermarking digital content is provided, by receiving, by a processor, a data stream comprising audio and/or video content; receiving watermark data, by a processor, from a computing node communicatively linked to a blockchain-based distributed ledger; and applying at least one watermark to the data stream based upon the watermark data, wherein the watermark comprises at least one hash based on one or more data blocks stored in the blockchain-based distributed ledger.

Abstract: A CT-based clinical decision support system provides coronary decision support. With or without CT-FFR, a machine learnt predictor predicts the clinical decision for the patient based on input from various sources. Using the machine learnt predictor provides more consistent and comprehensive consideration of the available information. The clinical decision support may be provided prior to review of coronary CT data by a radiologist and/or treating physician, providing a starting point or recommendation that may be used by the radiologist and/or treating physician.

Abstract: A method for emergency communication includes encoding a message for visual display including a message to field and a message from field. The visual display is revealed to a reading device in communication with a broadcast center, which stores the visual display. The messages are decoded and sorted from visual displays at the broadcast center. On an index channel, a time and channel number for when a message body of the message will be broadcast on a message channel is broadcasted. The message body is broadcasted on the message channel.

Abstract: An apparatus comprises an unit configured to obtain captured images captured at a plurality of positions/orientations; an unit configured to generate a guidance instruction for causing a captured image corresponding to a position/orientation substantially the same as a captured image of a stipulated state to be obtained; an unit configured to output the guidance instruction; an unit configured to determine whether or not one captured image obtained after output of the guidance instruction was captured at a position/orientation substantially the same as the captured image of the stipulated state; and an unit configured to, if the one captured image is determined to be captured at the position/orientation, generate or update a three-dimensional map from three-dimensional coordinates of a feature included in a captured image based on the plurality of captured images including the one captured image.

Abstract: A computer-implemented method obtains at least one image from which severity of a given pathological condition presented in the at least one image is to be classified. The method generates a hybrid image representation of the at least one obtained image. The hybrid image representation comprises a concatenation of a discriminative pathology histogram, a generative pathology histogram, and a fully connected representation of a trained baseline convolutional neural network. The hybrid image representation is used to train a classifier to classify the severity of the given pathological condition presented in the at least one image. One non-limiting example of a pathological condition whose severity can be classified with the above method is diabetic retinopathy.

Abstract: A capability determining method for a terminal device, a host, and a system is provided. The capability determining method includes acquiring, by the host, a capability supported by the terminal device. The method also includes determining, by the host according to the capability supported by the terminal device and a capability supported by the host, a capability supported by both the terminal device and the host, and using the capability supported by both the terminal device and the host as an overlapping capability, where the overlapping capability is used by the terminal device to perform capability configuration. The method also includes sending the overlapping capability to the terminal device.

Abstract: The present invention provides systems and methods for facilitating the integration of former inmates into society upon release from inmate facilities. A representative embodiment of the present invention allows participating inmates to utilize one or more pre-defined services during their period of incarceration. Utilization of these pre-defined services increases the participant's likelihood of rehabilitation, thus reducing recidivism. Examples of pre-defined services include identification, education, employment, financial, housing, and social connection services. A release package based upon information collected during use of these services also provides a personal dossier that facilitates criminal investigations, parole evaluations, probation determinations, and the like.

Abstract: An image management server including a receiver configured to receive an image file. The image file includes image data, copyright information, and tag information including route information for transmitting the image data. The image file is transmitted by an external device in accordance with the route information. The image management server further includes a processor configured to add digital watermark information to the image data to make the image file in a state in which the copyright information is protected or waived, and a transmitter configured to transmit the image file to an image display server in the state in which the copyright information in the image file is protected or waived.

Abstract: An embodiment of the invention provides a method for finding missing persons by learning features for person attribute classification based on deep learning. A first component of a neural network identifies geographic locations of training images; and, a second component of the neural network identifies weather information for each of the identified geographic locations. A third component of the neural network generates image pairs from the training images. For each image pair of the image pairs, the third component of the neural network determines whether images of the image pair include the same person. The neural network generates neural network parameters with the identified geographic locations, the weather information for each of the identified geographic locations, and the determination of whether the images of the image pairs include the same person.

Abstract: Systems and methods are described for using data collected by unmanned aerial vehicles (UAVs) to generate insurance claim estimates that an insured individual may quickly review, approve, or modify. When an insurance-related event occurs, such as a vehicle collision, crash, or disaster, one or more UAVs are dispatched to the scene of the event to collect various data, including data related to vehicle or real property (insured asset) damage. With the insured's permission or consent, the data collected by the UAVs may then be analyzed to generate an estimated insurance claim for the insured. The estimated insurance claim may be sent to the insured individual, such as to their mobile device via wireless communication or data transmission, for subsequent review and approval. As a result, insurance claim handling and/or the online customer experience may be enhanced.

Abstract: Embodiments of the present invention provide methods, program products and systems to reduce mistakes in production and management of digital identification cards. Embodiments of the present invention can create a digital card template design using graphical icons in a user interface display and publish the created digital card template design to a server. Embodiments of the present invention can access the server to test the published digital card template design using sample data and deploy the published digital card template design to an issuing service. Embodiments of the present invention can, responsive to receiving an acquisition URL from the issuing service, build an instance of a digital identification card from information included in the acquisition URL.

Abstract: Methods and apparatus are provided for determining moisture content of corn. In one example, a method includes processing a captured image of an ear of corn using a threshold value to create a segmented binary image comprising a first plurality of blobs, determining at least one characteristic of a plurality of corn kernels represented by the first plurality of blobs, and estimating a moisture value for the ear of corn based on the at least one characteristic of the plurality of corn kernels. In some embodiments, the method includes generating a luminance intensity profile across a region of the captured image containing at least one corn kernel in the plurality of corn kernels, computing a derivative of the luminance intensity profile; an determining, with reference to the derivative of the luminance intensity profile, a location of a boundary of the at least one corn kernel.

Abstract: Systems, apparatuses and methods for triggering actions in response to capturing and characterizing image data. Real-time characterization techniques include object and shape recognition analytics to detect specifically designated content in captured image data. Actions are triggered based upon such detection. Global data access and distribution systems and methods are provided, particularly for use by law enforcement agencies and designated alert systems.

Abstract: There is provided systems and methods for embedding data into a video content. A system includes an encoder, a memory storing the encoder, and a hardware processor configured to execute the encoder from the memory. The hardware processor is configured to execute the encoder from the memory to obtain the data, determine a plurality of pixels in the video content, and embed the data into the video content by inverting the plurality of pixels in the video content according to the data. The system further includes a decoder for decoding the video content to obtain the data.

Abstract: Briefly, a method for verifying the visual perceptibility of a display is provided. An intended message is written to a bistable display. Pixels that comprise portions of the message are measured and evaluated to determine if the message actually displayed on the bistable display was perceptible by a human or a machine. In some cases, information regarding the message actually perceivable from the display may be stored for later use. Responsive to determining that a message is perceivable or not perceivable, alarms may be set, one or more third parties notified, or additional display features may be set.

Abstract: A seismic modeling system may include a seismic model data storage device, and a processor cooperating with the seismic model data storage device to transform a seismic model spatial domain data set associated with a given region into a seismic frequency domain data set, where the given region includes a suspect region, transform a seismic model spatial domain data subset associated with the suspect region into a seismic frequency domain data subset, and perform inpainting of the seismic frequency domain data subset based upon the seismic frequency domain data set. The processor may further convert the inpainted seismic frequency domain data subset into an inpainted spatial domain data subset, and substitute the inpainted spatial domain data subset for the seismic model spatial domain data subset associated with the suspect region in the seismic model spatial domain data set associated with the given region.

Abstract: An X-ray apparatus includes an image separator configured to separate an X-ray image of an object into material images representing materials in the object; a parameter determiner configured to determine a width of a material of interest (MOI) based on the material images, and determine an enhancement parameter configured to enhance contrast of the MOI according to the width of the MOI; and an image enhancer configured to separate the X-ray image into detailed images respectively including spatial frequencies of different frequency bands, enhance each of the detailed images according to the enhancement parameter, and synthesize the enhanced detailed images to generate an enhanced image.

Abstract: Unmanned aerial vehicles (UAVs) may facilitate the generation of a virtual reconstruction model of a vehicle collision. UAVs may collect data (including images) related to the vehicle collision, such as with the insured's permission, which may be received by an external computing device associated with the insurer and utilized to perform a photogrammetric analysis of the images to determine vehicle impact points, the road layout at the scene of the collision, the speeds and directions of vehicles, etc. This data may be used to generate a virtual reconstruction model of the vehicle collision. An insurer may use the virtual reconstruction model to perform various insurance-related tasks, such as allocating fault to drivers or autonomous vehicles involved in the vehicle collision, and adjustment of insurance pricing based upon the fault allocation. As a result, innocent drivers or vehicles may not be unfairly penalized for vehicle collisions not their fault.

Abstract: A biststream of encoded video data captured by a camera of a user device is received and decoded into a stream of decoded video frames. A light pattern representing a VLC signal captured by the camera is identified in at least one decoded video frame and decoded into a DRM identifier. Distribution of the bitstream is controlled based on a comparison of the DRM identifier and a defined DRM identifier. Hence, VCL is used to add watermarks to recorded video data and where such watermarks can be used to control distribution of copyright or digital rights protected video content.

Abstract: In order to provide an imaging apparatus which minimizes erroneous recognition of a moving body and prevent a braking operation from being erroneously performed, even if the moving body is likely to cross a road, the imaging apparatus includes a correlation value calculation unit that calculates a correlation value from two images captured by two imaging units, a three-dimensional object detection unit that detects a three-dimensional object from the two images, a region dividing unit that divides an image region including the three-dimensional object into multiple regions, a relative speed calculation unit that calculates relative speed for every region of the multiple regions, and a reliability calculation unit that calculates reliability of the three-dimensional object, based on the relative speed calculated for every region.

Abstract: A display device is provided. The display device includes a display configured to display a content, an input unit configured to obtain a photographed image of a user, a storage configured to store feature information of each pre-classified age stage and a processor configured to compare a feature part in the photographed image with the feature information of each age stage stored in the storage, and calculate an age matching probability the feature part with each age stage. The processor selects a plurality of age stages among all age stages by comparing the age matching probability with a preset threshold value, controls the display to display a combined content which includes a plurality of recommended contents corresponding to each of the selected plurality of age stages.

Abstract: A contextual zoom control method, system, and computer program product, includes detecting faces in an area of interest when a user is performing an image capturing action, extracting a facial image for each of a set of key individuals attending an event where the user is performing the image capturing action, creating a ranked list of the set of key individuals according to a predetermined parameter of each key individual, pairing each detected face with a matching extracted facial image to label an identity of each key individual in the area of interest, and in a single individual capturing mode, performing a camera function to assist the user in performing the image capturing action on the identity that is paired with a highest ranked individual on the ranked list within the area of interest.

Abstract: A method and system may assess the damage to insured properties in a neighborhood using aerial images captured from an unmanned aerial vehicle (UAV) or from a satellite device. The neighborhood may be selected by identifying a neighborhood affected by a catastrophe and having a large concentration of properties which are insured by a particular insurance provider. Aerial images of the entire neighborhood may then be captured and received from the UAV or the satellite device. For each insured property in the neighborhood, a condition and the extent and/or severity of the damage may be automatically determined based on the received aerial images. The aerial images along with indications of the extent of the damage may be displayed.

Abstract: A method is provided for controlling a device for reading machine-readable code. A processor, configured by a strike application program monitors for a strike against a surface of the device. The strike is caused by a user either striking the device against a non-device surface or striking the surface of the device without necessarily engaging a button, a capacitive surface, or a resistive surface of the device. The strike comprising a detected strike is detected. An identifying characteristic of the detected strike is determined and it is determined if the detected strike having the identifying characteristic correlates to a particular scan-related operation of the device. The particular scan-related operation correlating to the detected strike having the identifying characteristic is executed in response to determining that the detected strike having the identifying characteristic correlates to a particular scan-related operation.

Abstract: The present disclosure relate generally to digital watermarking and signal encoding. Various colors can be evaluated and modified to carry an encoded or auxiliary signal.

Abstract: The unique methodology and utility seeking patient protection in this application is using satellite imagery to quantify and derive harvest statistics of sun-drying crops. High resolution imagery can be used to geospatially define known coffee drying basins however it is impractical for continuous observation as it is costly and infrequent. The geospatially defined regions of interests of coffee drying basins can be matched with more frequent, lower resolution, multispectral satellite imagery (such as Sentinel-2). The signals can be tested against the known spectral signatures of washed and unwashed coffee to determine whether or not each pixel contains coffee. The result will yield a classified region of interest which can be used to determine the quantity of drying coffee and the washed to unwashed ratio of a harvest. With regular monitoring across multiple temporal scenes the harvest's seasonality and historical change can be derived.

Abstract: Detection of human hands within an environment is used for gesture recognition for input to a computing system. Detecting a hand is non-trivial, however, because the appearances of a hand vary widely with many independent digits and moving parts. A feature-based similarity measurement is used to detect two specific hand positions—an open hand and a closed hand.