Patents Examined by Stephen P. Coleman
  • Patent number: 10292483
    Abstract: An eyebrow shaping apparatus, including: a camera, for capturing one image of each of two eyebrows of a user at an initial state; an image processor, for horizontally flipping one of the two images, and for searching for differences between the horizontally flipped image and the other image, and for suggesting corrections in at least one of the captured images for obtaining a requested state having two equal mirrored images; CNC (Computer Numerical Control), for producing a program including physical steps for modifying the eyebrows from the initial state to the requested state; and a painting tip, a hair removing tip, and a robotic arm, for executing the program.
    Type: Grant
    Filed: March 21, 2017
    Date of Patent: May 21, 2019
    Inventor: Nisan Shlomov
  • Patent number: 10296790
    Abstract: Systems and methods for coded visual markers in a surveillance system. An exemplary system includes a camera to capture images of a secure area, memory to store identifiers for persons that are authorized to be in the secure area, and a processor communicatively coupled with the camera and the memory. The processor analyzes the images to detect a person in the secure area and detects a pattern of a light source at the person. The processor then decodes the pattern of the light source and authorizes the person in the secure area based on a match between the decoded pattern of the light source and an identifier stored in the memory of one of the persons authorized to be in the secure area.
    Type: Grant
    Filed: July 27, 2017
    Date of Patent: May 21, 2019
    Assignee: THE BOEING COMPANY
    Inventors: David K. Mefford, Aaron Y. Mosher
  • Patent number: 10296781
    Abstract: A method for detecting events in a signal received on a detection sensor linked to a processor comprises: given events of nature {Ee}e=1 . . . Ne, a domain of votes D composed of I sub-domains Di={[di, di+1[} with i=1 . . . I and a dictionary of micro-events {mi}i=1 . . . M, initialize to an identical value an array S containing values of scores, S[e][p], where p is a spatial or temporal position index (p?D), detect micro-events mn (n=1 . . . N), located at tn (n=1 . . . N), corresponding to a quantization of a local observation On in the signal, for each micro-event mn located at tn, for each type of event “e”, for each sub-domain Di update the array S[e][tn+p] by adding a constant value for all locations p?Di, determine a set of events associated with an observation in the signal on the basis of array S, and detect the most probable event.
    Type: Grant
    Filed: September 24, 2015
    Date of Patent: May 21, 2019
    Assignee: COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
    Inventors: Adrien Chan-Hon-Tong, Laurent Lucat
  • Patent number: 10289938
    Abstract: Systems and methods are described for generating an image-based prediction model, where a computing device may obtain a set 3D images from a 3D image data source. Each of the 3D images can have 3D point cloud data and a Distification technique can be applied to the 3D point cloud data of each 3D image to generate output feature vector(s). The output feature vector(s) may then be used to train and generate the image-based prediction model.
    Type: Grant
    Filed: May 16, 2017
    Date of Patent: May 14, 2019
    Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
    Inventors: Elizabeth Flowers, Puneit Dua, Eric Balota, Shanna L. Phillips
  • Patent number: 10283221
    Abstract: A method for risk assessment comprises receiving one or more images of a plurality of lesions captured from a body of a target person, generating one or more digital signatures based on the one or more images from the body of the target person, comparing the generated one or more digital signatures to digital signatures of respective reference persons, wherein the comparing comprises measuring similarities between the generated one or more digital signatures and the digital signatures of the respective reference persons, and determining a risk factor for the target person of developing a disease based on the measured similarities and predetermined risk factors of developing the disease for the reference persons.
    Type: Grant
    Filed: October 27, 2016
    Date of Patent: May 7, 2019
    Assignee: International Business Machines Corporation
    Inventors: Mani Abedini, Seyedbehzad Bozorgtabar, Rajib Chakravorty, Rahil Garnavi
  • Patent number: 10282618
    Abstract: Multi-blend fingerprinting may be detected. First, a video sample may be received. Next, frames of the received video sample may be step iteratively through until a probability value corresponding to a current frame indicates a match. Deciding that the probability value indicates the match may comprise creating an augmented frame, determining the probability value corresponding to the created augmented frame, and determining that the probability value indicates the match. Then a fingerprint from the created augmented frame may be extracted.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: May 7, 2019
    Assignee: Cisco Technology, Inc.
    Inventors: Michael Costello-Jones, Tony Leigh, James Charles Wilson
  • Patent number: 10274623
    Abstract: A method for determining a displacement seismic image between two seismic images may begin with receiving a first seismic image and a second seismic image. The method may then include generating a first scaled image based on the first seismic image and a second scaled image based on the second seismic image and determining a scaled displacement volume between the two scaled images using an optical flow algorithm. The method may then involve calculating a displacement volume based on the scaled displacement volume and a scaling function used to generate the scaled images. The method may then generate a third seismic image by applying the displacement volume to the second seismic image. The method may then involve determining the difference volume between the first seismic image and the third seismic image.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: April 30, 2019
    Assignee: BP Corporation North America Inc.
    Inventors: Qie Zhang, Bosen Du
  • Patent number: 10275871
    Abstract: The present invention is directed to systems and methods for processing multi-dimensional image data to isolate specific features within the image data. One exemplary application is non-destructive testing to detect deformation of structures from image data. The methods for isolating salient features includes generating a “baseline” approximation of the surface image by subdividing the image into a network of triangle planes, approximating the measured value for each plane and subtracting the baseline from the original image data to generate a processed image. The process for defining the triangle-plane network, approximating each plane and performing baseline subtraction can yield a final processed image that includes changes in feature value occurring within a particular triangular plane, which can indicate deformation, while changes in feature value occurring over larger areas, which can be a product of environmental and inspection variables, are at least partially removed from the resulting data set.
    Type: Grant
    Filed: July 27, 2017
    Date of Patent: April 30, 2019
    Assignee: SAUDI ARABIAN OIL COMPANY
    Inventor: Enrico Bovero
  • Patent number: 10270946
    Abstract: There is provided a solid state imaging device. A rib is arranged on a frame part to be joined to a board on which an image sensor is mounted, the rib abutting on the board at an abutting position next to a periphery of the image sensor.
    Type: Grant
    Filed: March 12, 2014
    Date of Patent: April 23, 2019
    Assignee: Sony Corporation
    Inventor: Eiichiro Dobashi
  • Patent number: 10268897
    Abstract: In determining a representative still image of a video, a first set of parameters for each frame in a video is derived, and a second set of parameters for a specific user is derived. A frame with first set of parameters that best matches the second set of parameters is identified and selected as the representative still image of the video for the specific user. Different parameters may be derived for different specific users, and different frames are identified as best matches for different specific users. Different parameters may be derived for the specific user at different times, and different frames are identified as best matching at the different times. Different values for the parameters for the same specific user may be calculated at different times, and different frames may be identified as best matching the parameters at the different time.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: April 23, 2019
    Assignee: International Business Machines Corporation
    Inventors: Hernan A. Cunico, Jonathan Dunne, Jeremiah O'Connor, Asima Silva
  • Patent number: 10262423
    Abstract: An apparatus, system and process for tracking and analyzing target person movements, captured while the target person is performing ordinary tasks outside of a medical context, for medical diagnosis and treatment review are described. The method may include constructing a model of a target person from three-dimensional (3D) image data of the target person performing an activity over a period of time. The method may also include tracking movement of the model of the target person in the 3D image data over the period of time, and detecting one or more motion features in the movement of the model of the target person that are relevant to diagnosis, treatment, care, or a combination thereof, of a potential chronic neurodegenerative or musculoskeletal medical condition. The method may also include computing a risk score associated with likelihood of the target person having the medical condition based on the detected motion features.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: April 16, 2019
    Assignee: Verily Life Sciences LLC
    Inventors: Anupam J. Pathak, Emre Demiralp
  • Patent number: 10262226
    Abstract: Systems and methods are described for generating an enhanced prediction from a 2D and 3D image-based ensemble model. In various embodiments, a computing device can be configured to obtain one or more sets of 2D and 3D images and to standardize each of the 2D and 3D images to allow for comparison and interoperability. Corresponding 2D3D image pairs can be determined from the standardized 2D and 3D pairs where the 2D and 3D images correspond based on a common attribute, such as a similar timestamp or time value. The enhanced prediction can use separate underlying 2D and 3D prediction models where the 2D and 3D images of a 2D3D pair are each input to the respective underlying 2D and 3D prediction models to generate respective 2D and 3D predict actions.
    Type: Grant
    Filed: May 16, 2017
    Date of Patent: April 16, 2019
    Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
    Inventors: Elizabeth Flowers, Puneit Dua, Eric Balota, Shanna L. Phillips
  • Patent number: 10249048
    Abstract: The present disclosure is directed to a method and system for automatically predicting a blood flow feature based on a medical image. The method may include acquiring, by a processor, image patches and a vessel related feature of a vessel tree. Then, the blood flow feature of the vessel tree may be calculated, by the processor, using a learning network based on both the image patches and the vessel related feature of the vessel tree. The learning network includes a multi-model neural network and a tree structure recurrent neural network connected in series. The method and system of present disclosure can perform a quick and accurate prediction for the blood flow feature, such as FFR, of the vessel tree of a target object (such as certain site of human body or animal body) based on both the medical images and vessel related features of the vessel tree of the target object. The predicted FFR may assist the user in pathological diagnosis or other treatment of the target object.
    Type: Grant
    Filed: October 26, 2018
    Date of Patent: April 2, 2019
    Assignee: Beijing Curacloud Technology Co., Ltd.
    Inventors: Xin Wang, Youbing Yin, Dan Wu, Kunlin Cao, Yuwei Li
  • Patent number: 10249028
    Abstract: An optical system has the entire angle of view at a wide-angle end of not smaller than 90 degrees. A spatial frequency at which an MTF of the optical system acquired using an evaluation wavelength in a region of an image formation plane in which the distance from the center of the image formation plane is not less than 80% and less than 95% of half of the length of a diagonal line of an imaging surface of an imaging element image is not more than 30% is higher at the wide-angle end than at a telephoto end. When F??(Fw×Ft) is satisfied (where F indicates the focal length of the optical system when the target image is captured, Fw indicates the focal length at the wide-angle end, and Ft indicates the focal length at the telephoto end), a sharpening processing unit performs a restoration process based on an optical transfer function of the optical system as a sharpening process.
    Type: Grant
    Filed: October 13, 2017
    Date of Patent: April 2, 2019
    Assignee: FUJIFILM Corporation
    Inventors: Takashi Kunugise, Yousuke Naruse
  • Patent number: 10241000
    Abstract: A method for checking the plausibility of detected features of a light distribution of a headlamp of a motor vehicle includes irradiating, by the headlamp, a scene in surroundings of the motor vehicle; capturing, by a camera of the motor vehicle, the irradiated scene in an image; dynamically seeking and identifying at least one initial optical feature in the image, adaptively producing and analyzing local surroundings of the at least one initial optical feature; dynamically extracting at least one further optical feature from the local surroundings; and carrying out, using a learned algorithm and on the basis of the at least one initial optical feature and the at least one further optical feature, an adaptive check as to whether the at least one initial optical feature and the at least one further optical feature are plausibly arranged in the local surroundings.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: March 26, 2019
    Assignee: DR. ING. H.C. F. PORSCHE AKTIENGESELLSCHAFT
    Inventors: Sascha Saralajew, Sebastian Soehner, Steffen Strebel
  • Patent number: 10242442
    Abstract: A method for image analysis comprises receiving one or more images of a plurality of lesions captured from a body of a person, extracting one or more features of the plurality of lesions from the one or more images, analyzing the extracted one or more features, wherein the analyzing comprises determining a distance between at least two lesions with respect to the extracted one or more features, and determining whether any of the plurality of lesions is an outlier based on the analyzing.
    Type: Grant
    Filed: October 27, 2016
    Date of Patent: March 26, 2019
    Assignee: International Business Machines Corporation
    Inventors: Mani Abedini, Adrian Bowling, Rajib Chakravorty, Sergey Demyanov, Rahil Garnavi
  • Patent number: 10242251
    Abstract: An online system matches a user across multiple online systems based on image data for the user (e.g., profile photo) regardless whether the image data is from the online system, a different but related online system or a third party system. For example, to match the user across a social networking system and INSTAGRAM™ system, the online system compares the similarity between images of the user from both systems in addition to similarity of textual information in the user profiles on both systems. The similarity of image data and the similarity of textual information associated with the user are used by the online system as indicators of matched user accounts belonging to the same user across both systems. The online system applies models trained using deep learning techniques to match a user across multiple online systems based on the image data and textual information associated with the user.
    Type: Grant
    Filed: April 26, 2017
    Date of Patent: March 26, 2019
    Assignee: Facebook, Inc.
    Inventors: Aleksey Sergeyevich Fadeev, Li Zhou, Yimin Song, Goran Predovic, Chaochao Cai, Liang Xu
  • Patent number: 10235746
    Abstract: Disclosed herein are a method and apparatus for fusing a panchromatic image and an infrared image. The apparatus includes: an image acquisition unit configured to acquire a panchromatic image and an infrared image having the same coordinate system; a filtering unit configured to generate a low-frequency panchromatic image by performing low-frequency filtering on the panchromatic image, and to generate a high-frequency panchromatic image by subtracting the low-frequency panchromatic image from the panchromatic image; an image correction unit configured to generate a corrected high-frequency panchromatic image, to construct a linear regression equation, and to generate a corrected infrared image by using the constructed linear regression equation; a scaling factor determination unit configured to determine the ratio at which the panchromatic image and the infrared image are fused together; and a fused image generation unit configured to generate a fused image through multiplication and addition.
    Type: Grant
    Filed: June 2, 2017
    Date of Patent: March 19, 2019
    Assignee: University of Seoul Industry Cooperation Foundation
    Inventors: Hyung Sup Jung, Sung Hwan Park
  • Patent number: 10237470
    Abstract: A focusing device comprises: an image capturing unit that captures a subject image formed via an optical system including a lens for executing focus adjustment and outputs an output signal; an edge detection unit that detects an edge signal among the output signal in correspondence to each color component among a plurality of color components contained in an image based upon the output signal; a calculation unit that calculates edge differential values each of which is a differential value of the edge signal in correspondence to the each color component; and a control unit that controls a moving direction along which the lens is to move based upon a comparison of the edge differential values.
    Type: Grant
    Filed: August 1, 2017
    Date of Patent: March 19, 2019
    Assignee: NIKON CORPORATION
    Inventors: Souichi Ueta, Yoshiyuki Suzuki
  • Patent number: 10235768
    Abstract: In an image processing device (120), an extraction unit (121) extracts a plurality of objects from a captured image (101). A prediction unit (122) predicts a future distance between the plurality of objects extracted by the extraction unit (121). A classification unit (123) classifies into groups the plurality of objects extracted by the extraction unit (121) based on the future distance predicted by the prediction unit (122). A processing unit (124) processes the captured image (101) into a highlight image (102). The highlight image (102) is an image in which the plurality of objects classified by the classification unit (123) are highlighted separately for each group.
    Type: Grant
    Filed: December 10, 2014
    Date of Patent: March 19, 2019
    Assignee: Mitsubishi Electric Corporation
    Inventor: Ryosuke Sasaki