Abstract: A document generation system creates a secure document by: receiving document content to be printed onto a substrate; creating a stencil mask comprising an image of at least a portion of the document content; receiving an image of a watermark to be printed on the substrate; modifying the watermark to remove portions of the watermark that will correspond to locations of the stencil mask; causing a print device to print the document content on the substrate; and causing the print device to print the modified watermark through the stencil mask on the substrate.
Type:
Grant
Filed:
May 26, 2015
Date of Patent:
May 1, 2018
Assignee:
Xerox Corporation
Inventors:
Reiner Eschbach, Phillip J. Emmett, Edward N. Chapman
Abstract: An ultrasound system and method that can include: a receive beamformer configured to receive signals from a transducer; a processor coupled to the receive beamformer, the processor configured to: analyze echo data reflected from a region of interest, the echo data elicited by a transmitted pulse sequence; using the echo data, determine a central tendency of a signal magnitude from regions of adherent microbubbles over time within the region of interest; determine a time series of the signal magnitude; using the time series, determine an initial signal magnitude parameter; obtain a saturated signal parameter and a residual signal parameter using the time series; and determine a relative indication of information indicative of the residual signal magnitude versus the saturated signal magnitude.
Type:
Grant
Filed:
December 3, 2014
Date of Patent:
April 24, 2018
Assignee:
University of Virginia Patent Foundation
Inventors:
F. William Mauldin, Jr., Shiying Wang, John A. Hossack, Alexander L. Klibanov
Abstract: A computer system may generate a lineage graph for a data processing system. The lineage graph may contain one or more nodes, and it may identify the flow of data through the data processing system. The computer system may determine that a first node in the lineage graph defunct. The computer system may then generate a report for the data processing system and provide the report to a user. The report may include an explanation of why the first node is defunct. The computer system may insert an indication that the first node is defunct into metadata for the first node. The indication may also include the explanation of why the first node is defunct.
Type:
Grant
Filed:
August 15, 2017
Date of Patent:
April 24, 2018
Assignee:
International Business Machines Corporation
Inventors:
Marc N. Haber, Boris Melamed, Gideon Sireling, Gidi Weber
Abstract: The invention provides for a system and method for the simultaneous capturing and storage of digital audio data in association with still image data. The captured audio clip is instantaneously associated and embedded with the photographic image, and allows for the user to digitally play back, view, and share the still image embedded with the audio clip.
Abstract: Systems and methods for generating a crop yield estimate for an area as small as an individual field from images captured by a satellite are disclosed. The system generates simulations of crop yields in a region that includes the area by applying combinations of different parameters to a crop yield models. Observable quantities for simulated yields are determined from the simulations. The simulations and the observable properties are used to train a statistic model for the region that has two or more variables. Images captured by a satellite that include at least a portion of the area are obtained. Crop information is then determined from the images and weather information associated with the dates that the images where captured is obtained. The statistical model is then applied to the crop information and the weather information to determine a crop yield estimate.
Type:
Grant
Filed:
December 16, 2015
Date of Patent:
April 24, 2018
Assignee:
The Board of Trustees of the Leland Stanford Junior University
Abstract: A movement of an object is recognized as a predetermined movement, by transmitting signals between transmitter-receiver pairs, which are reflected from the object. A first event is recorded for one of the transmitter-receiver pairs if a reflected signal meets a predetermined proximity criterion, and a second event is recorded for a second transmitter-receiver pair if, after the first event, a subsequent reflected signal meets a predetermined proximity criterion. The first and second events are used to identify the movement.
Abstract: An information processing apparatus acquires input brightness information of input image data. A setting unit sets, based on a user's operation, a display range for displaying within a range of brightness possibly taken by the input image data, and reference brightness that is an upper limit of brightness of a display unit. A generation unit generates display image data by converting gradation characteristics of the input image data based on the display. The brightness of the display unit is controlled based on the reference brightness. A notification unit performs first notification processing when the display unit is able to display an image based on the display image data with brightness of the input image data, and second notification processing when the display unit is not able to so display the image, based on the display range, the reference brightness, and the input brightness information.
Abstract: A method for evaluating the placement of a prosthetic heart valve in a structure of interest. The method comprises acquiring one or more depictions of an anatomical region of interest that includes the structure of interest, wherein each depiction shows the structure of interest and/or the blood pool volume of the left ventricular outflow tract (LVOT) of the patient's heart. The method further comprises designating one or more positions in at least one of the one or more depictions wherein each position corresponds to a respective position in the structure of interest at which the prosthetic valve may be placed. The method still further comprises predicting, for each of the one or more designated positions, an amount of blood flow obstruction through the LVOT of the patient's heart that would occur if the prosthetic valve was to be placed at a corresponding position in the structure of interest.
Type:
Grant
Filed:
May 30, 2017
Date of Patent:
April 17, 2018
Assignee:
Henry Ford Health System
Inventors:
Dee Dee Wang, William O'Neill, Eric Myers, Michael Forbes
Abstract: The present disclosure relates to the measurement of vital signs such as a respiratory rate or a heart rate. In particular, a system (1) for determining a vital sign of a subject (100), comprising an imaging unit (2) for obtaining video data of the subject, a marker (10, 20, 60, 61) directly or indirectly attached to a body of the subject, wherein the marker comprises a graphical pattern (11, 21), an image processing unit (3) for detecting said marker in said video data, and an analysis unit (4) adapted to extract a vital sign parameter related to the vital sign of the subject from said video data and to determine the vital sign from said vital sign parameter. Further aspects of the disclosure relate to a device and a method for determining a vital sign of a subject and a computer program for carrying out said method.
Type:
Grant
Filed:
June 11, 2013
Date of Patent:
April 17, 2018
Assignee:
KONINKLIJKE PHILIPS N.V.
Inventors:
Erik Bresch, Jens Muehlsteff, Timo Tigges, Alexander Dubielczyk, Caifeng Shan
Abstract: The present disclosure relates to digital watermarking. One claim recites a method to detect two or more different digital watermarks in media. The method includes: receiving captured imagery of the media, the captured imagery comprising a plurality of image frames; for a first image frame applying a first watermark detector to search for a first digital watermark hidden within the first image frame, in which an electronic processor is programmed as the first watermark detector; and for a second image frame applying a second, different watermark detector to search for a second, different watermark hidden within the second image frame, in which an electronic processor is programmed as the second watermark detector. Other claims and combinations are provided too.
Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.
Abstract: A method and system for generating a color-textured three-dimensional dental model is specific to a patient is disclosed. According to one embodiment, a three-dimensional dental model that is deficient of volumetric data for a three-dimensional anatomical landmark is obtained. A two-dimensional anatomical landmark of a two-dimensional intra-oral photograph that corresponds to the three-dimensional anatomical landmark of the three-dimensional dental model is identified. The two-dimensional intra-oral photograph is projected onto the three-dimensional dental model. The three-dimensional anatomical landmark is calculated from the projection of the two-dimensional anatomical landmark of the two-dimensional intra-oral photograph.
Abstract: Embodiments of the present invention provide systems and methods to verify and/or obtain a registration of images obtained two image systems (such as a CT system and an MRI system) via the use of a third imaging modality (such as an ultrasound system).
Abstract: In one embodiment, a method includes accessing a social graph of a social-networking system, and determining, from the social graph, that a user “likes” a first page associated with a particular version of a media content. The social graph includes a plurality of nodes and edges connecting the nodes. The nodes include user nodes that are each associated with a particular user of the social-networking system. The method further includes determining that one or more other versions of the media content exist, determining that a main page is associated with the particular version and the one or more other versions of the media content, and aggregating the user's “like” of the first page to the main page. Each of the one or more other versions of the media content has one or more associated pages.
Abstract: The present invention relates to a system for detecting and tracking facial features in images and can be used in conjunction with a camera. Given a camera, the system will detect facial landmarks in images. The present invention includes software for real time, accurate facial feature detection and tracking in unconstrained images and videos. The present invention is better, more robust and faster than existing approaches and can be implemented very efficiently allowing real-time processing, even on low-power devices, such as mobile phones.
Abstract: A method and system may display real-time aerial images of insured properties in a neighborhood captured from an unmanned aerial vehicle (UAV), a manned aerial vehicle (MAV), or from a satellite device. For example, a neighborhood which has been affected by a catastrophe and has a large concentration of properties which are insured by a particular insurance provider may be identified. Aerial images of the entire neighborhood may then be received from the UAV, MAV, or the satellite device. As a result, the property owner may receive a notification that a catastrophe has impacted her neighborhood. The notification may also indicate that real-time images of the owner's property may be viewable by logging in to a customer account. Moreover, the real-time images may be transmitted via a web page to the property owner's web-enabled device after the property owner logs in to the customer account.
Type:
Grant
Filed:
October 9, 2014
Date of Patent:
March 27, 2018
Assignee:
STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Inventors:
Brian N. Harvey, Nathan L. Tofte, Roger D. Schmidgall, Michael Jeffrey Aviles, Kyle Pott, Rosemarie Geier Grant, Eric Haefli, Michael Shawn Jacob
Abstract: The present invention relates to a video analysis method, including: requesting a plurality of chunks from different locations within a video from a server; receiving the plurality of chunks of the video streamed from the server; extracting one or more frames from each chunk; analysing each frame in accordance with a static image analysis engine to generate a pornographic content rating for the frame; and combining the ratings of the frames from the plurality of chunks to generate a pornographic content rating for the video, wherein the plurality of chunks received are non-contiguous. A system and software for analysing video also described.
Abstract: A dynamic object monitoring method including, setting types of monitored zones of a monitored region in a video frame captured by a network camera and setting device parameters and sensitivity values corresponding to each of the monitored zones. Analyzing the predicted macro blocks of a current shooting frame retrieved by the network camera according to the prediction mode of the MPEG-4 encoding algorithm. Counting a number of the predicted macro blocks of each of the monitored zones. Determining whether a number of predicted macro blocks of a monitored zone is equal to or greater than a corresponding preset value. A monitored zone is determined where a dynamic object is located. The device parameters of the network camera as device parameters of the monitored zone are adjusted where the dynamic object is located for recording.
Type:
Grant
Filed:
October 19, 2015
Date of Patent:
March 27, 2018
Assignees:
HONG FU JIN PRECISION INDUSTRY (ShenZhen) CO., LTD., HON HAI PRECISION INDUSTRY CO., LTD.
Abstract: A sign language message may be derived from user movements detected proximate to an electronic device by comparing the movements to a database that includes data regarding one or more sign languages. A control function may then be identified which the electronic device may be caused to perform. Output related to the user's detected movements may be provided to the user. In some implementations, output specifying identified control functions may be transmitted to a presentation device. Further, in some implementations, if a sign language message and/or a control function cannot be unambiguously derived and/or identified, output promoting the user to provide additional information may be transmitted to a presentation device. Detected movements may be compared to data regarding multiple different sign languages and/or a subset of available multiple different sign languages.
Abstract: Methods and systems are disclosed for sending information in an observation platform. A determination is made, at an observation platform, that a first communication device associated with a first user is located in an environment. A determination is made, at the observation platform, that the first communication device is located in proximity to a second communication device associated with a second user. Speech information is sent to the first communication device for the first user to use in communicating with the second user.
Type:
Grant
Filed:
December 12, 2016
Date of Patent:
March 27, 2018
Assignee:
TheatroLabs, Inc.
Inventors:
Steven Paul Russell, Guy R. VanBuskirk, Ravi Shankar Kumar, Kranthimanoj Nagothu
Abstract: The invention concerns a 3D circuit design method implemented by a processing device involving partitioning a 2D circuit representation into two or more tiers, the 2D circuit representation defining circuit elements interconnected by interconnecting wire each weighted based on at least one of: its length; its propagation delay; and its priority level, the 2D circuit representation initially forming a first tier, the partitioning involving: a) selecting a first highest ranking wire, interconnecting at least first and second circuit elements in the first tier; b) moving one of the first and second circuit elements connected by the selected wire to a further tier of the 3D circuit representation and replacing the interconnecting wire with a connecting via between the first and further tiers; and c) repeating a) and b) for one or more further interconnecting wires of the first tier.
Type:
Grant
Filed:
November 13, 2015
Date of Patent:
March 20, 2018
Assignee:
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
Abstract: A method of producing an authenticatable article. An overt feature is produced in the article using a fabricating technique which is selected based on a material of the article so as to produce the overt feature having predetermined, reproducible macroscopic characteristics as well as random, non-reproducible microscopic characteristics rendering the article physically unique. The overt feature including the microscopic characteristics are imageable using a predetermined imaging technology to produce an overt feature image. An authentication signature is generated based on the overt feature image and stored in a central database. The overt feature may alternatively be produced in an apparatus or means used to manufacture authenticatable articles such that the overt feature including the random, microscopic characteristics is reproduced in the articles. The overt feature and generated authentication code therefore corresponds to articles manufactured using that apparatus or means.
Abstract: A method of watermarking includes determining a first substantially uniform color pixel space in a first frame of a video, determining a first offset color based on the first substantially uniform color pixel space, and compositing a first watermark trace of a watermark key having the first offset color into the substantially uniform color pixel space so that a modified video frame is creating having the first watermark trace of the watermark key having the first offset color.
Abstract: For ensuring the integrity of a physical document, an apparatus is disclosed. A system, method, and program product also perform the functions of the apparatus. The apparatus for ensuring the integrity of a physical document includes a processor, a memory that stores code executable by the processor. The processor identifies an integrity symbol within a physical document, the first integrity symbol representative of content of the physical document, and converts the integrity symbol into an integrity map having at least two values, the integrity symbol being a symbolic representation of the integrity map suitable for printing. The processor compares content of the physical document to the integrity map to verify integrity of the physical document.
Type:
Grant
Filed:
August 15, 2016
Date of Patent:
March 20, 2018
Assignee:
Lenovo (Singapore) PTE. LTD.
Inventors:
Robert James Kapinos, Timothy Winthrop Kingsbury, Scott Wentao Li, Russell Speight VanBlon
Abstract: Embodiments include methods for predicting one or more characteristics of an individual, such as a human or non-human animal, by applying computational methods to image(s) of the individual to generate one or more metrics indicative of the characteristics. Embodiments determine predictors of characteristics by creating a sample library of individuals, determining facial measurements for each individual, determining relationships between facial measurements and additional library data, and selecting predictors from these relationships. Embodiments include methods for predicting characteristics of individuals not in the library. Embodiments include methods for predicting characteristics of groups using predicted characteristics of individuals. Embodiments determine suitability of a pair of individuals (from the same or different species) for a particular purpose, task, or relationship based on characteristics of individuals.
Abstract: The present disclosure relates to a method and a device for processing an identification of a video file. The method includes detecting a video on a display of a device, wherein the video includes a plurality of frames; identifying a detection area in at least one frame of the plurality of frames of the video; detecting a video identification mark in the detection area of the at least one frame; and concealing the video identification mark based on pixel values of boundary pixels of the detection area.
Abstract: An information providing method of an electronic device is provided. The information providing method includes determining a selected area based on a user input, determining an extraction method based on types of one or more objects included in the selected area, extracting information from the selected area according to the determined extraction method, and performing a specific function based on the information.
Type:
Grant
Filed:
August 28, 2015
Date of Patent:
March 20, 2018
Assignee:
Samsung Electronics Co., Ltd.
Inventors:
Bang Hyun Kwon, Keun Soo Kim, Jae Ho Lee, Chong Hoon Lee, Hyun Woong Kwon, Soon Sang Park
Abstract: The embodiments herein provide a system and method for monitoring and detecting Television (TV) ads in real-time using content databases. The method comprises an ingest process and a lookup process. An audio stream of an ad is chopped into predetermined timeframe samples. The chopped samples are stored in an ingest database. A TV broadcast stream of predefined length is chopped into samples which are compared with the ingest database. When the threshold value of a candidate is more than an average value, the candidate is shortlisted for further filtrations. Then the TV broadcast stream is compared with contents of an additional database. The additional database stores the whole length of an ingested ad without any chopping. A shifted search is performed on short listed candidates to detect the version of the ad played in the TV channel.
Abstract: A method for preventing overlap during the application of a universal identifier (UID) to a signature document in an electronic signature service is disclosed. The method includes parsing an image file of the signature document to obtain a content vector. A set of addresses of the content vector uniquely correspond with a set of locations in the image. Each value in the content vector indicates content at a corresponding location in the image. The method also includes measuring an overlap quantity for a potential UID location using the content vector to measure the overlap quantity. The method also includes selecting a UID location in the signature document using the overlap quantity. The method also includes applying the UID to the signature document using the UID location.
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for an unmanned aerial system inspection system. One of the methods is performed by a UAV and includes receiving, by the UAV, flight information describing a job to perform an inspection of a rooftop. A particular altitude is ascended to, and an inspection of the rooftop is performed including obtaining sensor information describing the rooftop. Location information identifying a damaged area of the rooftop is received. The damaged area of the rooftop is traveled to. An inspection of the damaged area of the rooftop is performed including obtaining detailed sensor information describing the damaged area. A safe landing location is traveled to.
Type:
Grant
Filed:
March 17, 2017
Date of Patent:
March 13, 2018
Assignee:
UNMANNED INNOVATION, INC.
Inventors:
Alan Jay Poole, Mark Patrick Bauer, Volkan Gurel, Bernard J. Michini, Justin Eugene Kuehn
Abstract: The present disclosure provides a method and system using software and associated equipment to automatically identify two or more preselected anatomical features by examining pixels within images, such as computerized tomography (CT) scanned images, determining appropriate measurements between such identified features based on dimensions and scaling available within the image file, comparing these measurements to normative data, and providing output of the results to a user, such as medical personnel. In at least one embodiment, the system can measure an interval between a first bone and a second bone that may be useful for medical analysis.
Type:
Grant
Filed:
June 3, 2015
Date of Patent:
March 6, 2018
Assignees:
Baylor University, Scott & White Healthcare
Inventors:
Brian A. Garner, Christopher Chaput, Jacob Hoffman
Abstract: A device for forming a random set of playing cards comprises a card in-feed area, a shuffling system, a card removal area, and a card reading system located within the device, the card reading system employing a complementary metal-oxide semiconductor (CMOS) sensor and a hardware component, the hardware component capable of converting signals from the CMOS sensor into vector sets and comparing the vector sets to known vectors to determine rank and suit.
Type:
Grant
Filed:
May 26, 2016
Date of Patent:
March 6, 2018
Assignee:
Bally Gaming, Inc.
Inventors:
Justin G. Downs, James D. Roberts, Vladislav Zvercov, Kapilkumar N. Kulakkunnath
Abstract: Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement power efficient detection of watermarks in media signals are disclosed. Example watermark detection methods disclosed herein include operating a watermark detector in a first operating mode to detect a first watermark in a media signal. Disclosed example watermark detection methods also include, in response to the first watermark being verified, operating the watermark detector in a second operating mode in which the watermark detector cycles between sleep intervals and active intervals to detect a second watermark at a second location in the media signal relative to a first location of the first watermark in the media signal.
Type:
Grant
Filed:
April 24, 2017
Date of Patent:
February 27, 2018
Assignee:
The Nielsen Company (US), LLC
Inventors:
David Gish, Sadhana Gupta, Vladimir Kuznetsov, Wendell D. Lynch, Alan R. Neuhauser
Abstract: A process for marking authorship of a digital asset in binary format can be done in the following manner. A first author adds a first binary code to the digital asset. Then, a record of a first ownership metadata in the digital asset is stored in a system of records. Next, an ownership of the first binary code is ascribed to the first author. After that, a first licensing metadata is embedding into the digital asset with a time-stamped and auditable record ascribing readability to a first user. Following that, the digital asset is secured by requiring a digital key to obtain the ability to write changes to the digital asset.
Abstract: A computer system may generate a lineage graph for a data processing system. The lineage graph may contain one or more nodes, and it may identify the flow of data through the data processing system. The computer system may determine that a first node in the lineage graph defunct. The computer system may then generate a report for the data processing system and provide the report to a user. The report may include an explanation of why the first node is defunct. The computer system may insert an indication that the first node is defunct into metadata for the first node. The indication may also include the explanation of why the first node is defunct.
Type:
Grant
Filed:
January 20, 2017
Date of Patent:
February 27, 2018
Assignee:
International Business Machines Corporation
Inventors:
Marc N. Haber, Boris Melamed, Gideon Sireling, Gidi Weber
Abstract: Methods and apparatuses for hiding and extracting data based on a pilot code sequence are provided. A data hiding method may include converting an input audio signal to a frequency domain, distorting phase information of the audio signal converted to the frequency domain based on a pilot code sequence representing data to be hidden, and converting the audio signal with the distorted phase information to a time domain and transmitting the audio signal converted to the time domain. The pilot code sequence may be a set of phase values corresponding to a bit value “0” or “1” of data.
Type:
Grant
Filed:
February 23, 2016
Date of Patent:
February 27, 2018
Assignee:
Electronics and Telecommunications Resarch Institute
Inventors:
Seung Kwon Baeck, Tae Jin Park, Jong Mo Sung, Yong Ju Lee, Tae Jin Lee, Jin Soo Choi
Abstract: There is described a new coding approach for printed document authentication, one objective of which is to increase the difficulty of copying. In addition, this new coding approach provides better performance compared to other 2D coding technologies under certain constraints. The new coding technique requires less print space in comparison to other coding techniques. This is achieved by optimizing some of the features which are used in standard 2D-codes for stabilization and which are necessary for e.g. mobile applications. Furthermore, the code can be decomposed in elementary units, or “byte-units” which can be widely spread over a text document. Such “byte-units” can in particular be used for integration in text symbols. If a document protected with such a coding is copied, at least some of these symbols will be extensively degraded by the copying process. Therefore, copy detection is intrinsically achieved thanks to the new coding technique.
Abstract: A method of obtaining identification information, and based on the obtained identification, wirelessly transmitting content between apparatuses, and a content transmission apparatus are provided. The method obtains the identification information on a content reception apparatus or a content backup apparatus by using an affordance function of a content transmission apparatus or a content providing apparatus. The method and the content transmission apparatus include obtaining identification information on a second apparatus by using a first apparatus; outputting confirmation information on the second apparatus from the first apparatus, based on the obtained identification information on the second apparatus; and wirelessly transmitting the content from the first apparatus to the second apparatus, so as to enable the content to be conveniently transmitted between the apparatuses and to provide easy accessibility to a content reception apparatus.
Type:
Grant
Filed:
November 8, 2007
Date of Patent:
February 20, 2018
Assignee:
SAMSUNG ELECTRONICS CO., LTD.
Inventors:
Young-sun Kim, Hyun-cheol Park, Chang-seog Ko, Yoo-jin Choi
Abstract: Techniques for restricting access to certain members of an online service are provided. Member accounts include one or more images. Attributes of member accounts that share the same image are analyzed to determine whether to label the image “bad.” In one technique, a model is created and trained to learn the attributes or features (and their corresponding weights) that are associated with “bad” user accounts that share the same image. As a result, member accounts that are associated with a “bad” image may be restricted in one or more ways.
Type:
Grant
Filed:
September 30, 2015
Date of Patent:
February 13, 2018
Assignee:
Microsoft Technology Licensing, LLC
Inventors:
Prashant V. Ullegaddi, David S. M. Freeman
Abstract: Audio signals are processed in a distributed reader and metadata routing system to provide metadata responses to mobile application programs. A routing system registers identifiers for different content ID schema. These identifiers are encoded in audio signals. Mobile device application programs are equipped with reader programs to extract identifiers from audio sensed by the microphone of a mobile device. Metadata responses are identified by the ID provider of the content ID schema and extracted identifiers. The metadata routing system routes metadata responses to a requesting mobile device, supporting a variety of different ID providers and mobile device applications.
Abstract: Systems and methods for streaming video and/or audio from multiple devices are provided. A camera may include an optical sensor, a wireless communication device, and a processor configured to establish a first connection with a remote location, establish a second connection with one or more other cameras, and stream video from the cameras to the remote location. The remote location may be, for example, a remote website, a remote server, or a remote client device. The camera may be further configured to provide control signals to the other cameras, such as for controlling applications running on the other cameras.
Type:
Grant
Filed:
August 6, 2013
Date of Patent:
February 6, 2018
Assignee:
Logitech Europe S.A.
Inventors:
John Bateman, Oleg Ostap, Oliver Hoheisel, David Kim, Vijay Karnataki
Abstract: By grading preview images of original images for the purpose of filtering eye blink patterns off and/or introducing face smile patterns, a result image can be generated with least eye blink patterns and most face smile patterns for satisfying image quality.
Type:
Grant
Filed:
January 31, 2013
Date of Patent:
February 6, 2018
Assignee:
HTC Corporation
Inventors:
Peter Chou, Drew Bamford, John C. Wang, Sung-Hao Lin, Jr-Ben Tian, Hao-Wei Miao
Abstract: This disclosure relates generally to image processing, and more particularly to system and method for image inpainting. In one embodiment, a method for image inpainting includes aligning a plurality of multi-view images of a scene with respect to a reference image to obtain a plurality of aligned multi-view images. A region of interest (ROI) representing a region to be removed from the reference image for image inpainting is selected. A dictionary is created by selecting image-patches from the reference image and the plurality of aligned multi-view images, and 3D rotations thereof. A priority value of each of a plurality of pixels of the ROI is created. The ROI is systematically reconstructed in the reference image based at least on the priority values of the plurality of pixels and the dictionary by computing a linear combination of two or more image-patches selected from the plurality of image-patches of the dictionary.
Abstract: Systems and methods for watermarking content and authenticating watermarked content are provided. Content is rendered on a display while watermarking information embedded in portions of the content are obtained. The watermarking information is verified to authenticate the content. If the content is not authentic, or is not authenticated within a period of time, the content can be terminated or otherwise blocked from rendering on the display.
Abstract: A digital watermark embedding device includes a synthesized voice generating unit that outputs a synthesized voice according to an input text and outputs phoneme-based alignment regarding phonemes included in the synthesized voice; an estimating unit that estimates whether or not a potentially risky expression is included in the input text, and outputs a potentially risky segment in which the potentially risky expression is estimated to be included; an embedding control unit that associates the potentially risky segment with the phoneme-based alignment, and decides and outputs an embedding time for embedding a watermark in the synthesized voice; and an embedding unit that embeds a digital watermark in the synthesized voice at a time specified as the embedding time for the synthesized voice.
Abstract: Systems and methods that enable the synchronized display of both “as-built” and “as-designed” representations and automated data updates of a target object of interest (e.g., specific line number aircraft). More specifically, the process allows users to display a panoramic image captured for a reference environment, and then display a visualization of the corresponding 3-D model at the same viewpoint. Interprocess communication between a panoramic image viewer application and a 3-D model visualization application provides the ability to synchronize viewpoints, fields-of-view and other display features.
Type:
Grant
Filed:
September 9, 2016
Date of Patent:
January 30, 2018
Assignee:
The Boeing Company
Inventors:
Jeremiah K. Scott, James J. Troy, Katherine I. Meza
Abstract: In one embodiment, a watermark is embedded in a sequence of video frames, for each one of the video frames, a set of N rectangular patches, two palettes of pixel values in a selected color space, such that the two palettes are denoted as P0 and P1, and P0?P1, and in each one of the N patches a processor which chooses one of P0 and P1 according to a value of a payload bit to be encoded, a calculator which calculates one of a variance of pixel values in the frame, and edginess for the pixel values in the frame, thereby determining a calculated value, and a processor which determines if the calculated value is beneath a given threshold value, if the calculated value is beneath the given threshold value the processor is operative to calculate a function of the pixel values, the closest value to a result of the calculation of the function in the chosen palette is chosen, and a replacer which replaces the pixel values within the patch with the chosen closest value.
Abstract: A gaze detection system includes a head mounted display and a gaze detection device detecting the gaze of the user. The head mounted display illuminate users eyes with infrared light, displays three-dimensional image comprising a plurality of layers in the depth direction and captures an image of user's eye illuminated by the infrared light. The gaze detection device detects the user's right eye's gaze direction (vector) and left eye's gaze direction (vector) with use of the captured images. The gaze detection device identifies the layer that the user is gazing at by selecting the layer having the shortest distance between the intersection points of the right eye gaze vector and the left eye gaze vector with each layer as a gaze point in the depth direction.
Abstract: A method and device generates a trajectory. The method includes receiving a plurality of tracklets indicative of movement of a plurality of targets over a predetermined temporal interval. The method includes determining a plurality of context data for a pair of tracklets based upon at least one additional tracklet. The method includes computing a probability that the pair of tracklets relate to a first one of the targets. The method includes generating a trajectory for the first target based upon a concatenation of select ones of the tracklets. The concatenation maximizes the probability that the pair of tracklets correspond to the first target based upon the context data associated with the pair of the tracklets.
Abstract: A method and system may determine the condition of 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 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 level of risk may be automatically determined based on the received aerial images, and the aerial images along with indications of the level of risk may be displayed.
Type:
Grant
Filed:
October 9, 2014
Date of Patent:
January 23, 2018
Assignee:
STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Inventors:
Brian N. Harvey, Nathan L. Tofte, Roger D. Schmidgall, Michael Jeffrey Aviles, Kyle Pott, Rosemarie Geier Grant, Michael Shawn Jacob