Patents Examined by Kenny Cese
  • Patent number: 10297049
    Abstract: An image processing system (IPS) and related method to transform different multi-modal or multi-contrast input images (u,v) into respective transformed images (U,V). The transformation may proceed iteratively to improve a regularized objective function. The regularization is via a regularizer function (R). The regularizer function (R) is computed from noise normalized gradients of the two or more transformed images (u,v).
    Type: Grant
    Filed: November 26, 2015
    Date of Patent: May 21, 2019
    Inventors: Thomas Koehler, Bernhard Johannes Brendel, Frank Bergner
  • Patent number: 10282622
    Abstract: A system detects a candidate for an object which intrudes based on images of a visible light camera and a far-infrared camera that monitor the sea, further derives a size, a velocity, an intrusion direction, and linearity, and identifies the object to some extent. Also, the system distinguishes between a boat, a human, and a floating matter based on the luminances or the like in a far-infrared image. In addition, the system observes the periodicity of normal waves on the sea surface at a location without any object by performing the Fourier transform on the image. The accuracy of identification of an object is improved based on the correlation between the motion of waves in a normal state and the motion of the object.
    Type: Grant
    Filed: December 9, 2016
    Date of Patent: May 7, 2019
    Assignee: Hitachi Kokusai Electric Inc.
    Inventors: Junichi Togashi, Wataru Ito, Masaya Okada, Kazunari Iwanaga, Miyuki Fujii
  • Patent number: 10274711
    Abstract: A microscopic image recognition system for detecting a protein-based molecule by presenting a recognition image is provided. The protein-based molecule has a state of a monomer. The microscopic image recognition system includes an image capturing unit, a monomer tracking module and a texture mask. The image capturing unit is configured to capture an original image of the protein-based molecule. The monomer tracking module is configured to capture a monomer image from the original image based on a predetermined size and a predetermined brightness. The predetermined size and the predetermined brightness correspond to the monomer. The texture mask is configured to perform a two-dimensional masking process on the monomer image to form at least two texture images. The recognition image is formed by superimposing the at least two texture images. A microscopic image recognition method is also provided.
    Type: Grant
    Filed: July 19, 2017
    Date of Patent: April 30, 2019
    Inventors: Ching-Fen Chiang, Ming-Hung Tsai
  • Patent number: 10275870
    Abstract: A computer-based system and method for taking clarity measurements of a gem, and a computer-readable medium having computer-executable instructions, are provided and include receiving a pixilated image of a gem and identifying pixels representing an inclusion. The method and medium further include determining characteristics of the inclusion as a function of the pixels representing the inclusion, and providing a clarity grade based upon the determined characteristics. Also provided is a method for mapping a gem, and a computer-readable medium having computer-executable instructions, which include receiving a pixilated image of a gem having facet edges, and identifying pixels representing the facet edges. The method and medium further include generating a diagram of the gem, such that the diagram is a function of the pixels representing the facet edges, and superimposing the diagram onto the pixilated image.
    Type: Grant
    Filed: March 12, 2018
    Date of Patent: April 30, 2019
    Assignee: Gemological Institute of America, Inc. (GIA)
    Inventors: Marc Verboven, Troy Blodgett, Dirk Nuyts
  • Patent number: 10269175
    Abstract: A three dimensional (3D) content generating apparatus includes an inputter configured to receive a plurality of images of an object captured from different locations; a detector configured to identify the object and detect a predetermined feature point of the object from each of the plurality of images; a map former configured to extract 3D location information of the detected feature point, and configured to form at least one depth map with respect to a surface of the object based on the extracted 3D location information of the feature point; and a content generator configured to generate a 3D content of the object using the at least one depth map and the plurality of images.
    Type: Grant
    Filed: June 17, 2016
    Date of Patent: April 23, 2019
    Inventors: Jae-yun Jeong, Alexander Limonov
  • Patent number: 10268802
    Abstract: According to one embodiment, a medical image processing apparatus and a medical image processing system includes at least a position detecting unit, a human body chart storage unit, a mapping chart generating unit, and a display. A position detecting unit detects a position of a characteristic local structure in a human body from the medical image. A human body chart storage unit stores a human body chart that represents the human body. A mapping chart generating unit generates a mapping chart that is the human body chart to which a mark indicating a position of the local structure detected by the position detecting unit is added. A display displays the mapping chart.
    Type: Grant
    Filed: March 2, 2015
    Date of Patent: April 23, 2019
    Inventors: Yosuke Yanagida, Junichi Tashiro, Jyunichi Yoshida, Kousuke Sakaue, Masashi Yoshida, Shigeyuki Ishii, Satoshi Ikeda, Hitoshi Yamagata, Takashi Masuzawa, Naoki Sugiyama, Muneyasu Kazuno
  • Patent number: 10262229
    Abstract: Described is a system for detecting multiple salient objects in an image using low power hardware. From consecutive pair of image frames of a set of input image frames, image channels are generated. The image channels are resized into multiple image scales that specify a relative size of a salient object in the image frames. A patch-based spectral transform is applied to overlapping image patches in the resized image channel, generating salient patches. Saliency patches are combined into a saliency map for each resized image channel, resulting in multiple saliency maps. The saliency maps are combined into an aggregate saliency map. An adaptive threshold is applied to the aggregate saliency map to determine which pixels in the aggregate saliency map correspond to a detected salient object region including a salient object. An object bounding box is generated for each salient object and output to a display.
    Type: Grant
    Filed: September 21, 2016
    Date of Patent: April 16, 2019
    Assignee: HRL Laboratories, LLC
    Inventors: Shankar R. Rao, Narayan Srinivasa
  • Patent number: 10235595
    Abstract: Provided is a value bill identifying method, which includes: step 1, collecting, by a color collection device including multiple color sensors, color data of a to-be-detected value bill and preprocessing the collected color data; step 2, extracting a feature from the preprocessed color data; step 3, matching the extracted feature with feature template sets corresponding to each type of value bills, to obtain matching scores, and regarding a feature template with the highest score as a matched template of the color data; and step 4, determining a type of the value bill based on a matching result.
    Type: Grant
    Filed: April 6, 2016
    Date of Patent: March 19, 2019
    Assignee: GRG Banking Equipment Co., Ltd.
    Inventors: Xuyao Yue, Zhuming Xiao, Dandan Wang, Xiaoqun Huang
  • Patent number: 10229305
    Abstract: The present invention provides a touch screen, a control method thereof and a display device. The touch screen comprises a touch area used for touch display. A plurality of fingerprint identification elements are provided in the touch area and are configured to identify a fingerprint. The touch area includes a plurality of sub-areas, and the fingerprint identification elements located in each sub-area independently identify a fingerprint or a part of a fingerprint in the sub-area.
    Type: Grant
    Filed: January 22, 2016
    Date of Patent: March 12, 2019
    Inventor: Lin Zhu
  • Patent number: 10210414
    Abstract: According to an embodiment, an object detection system includes an obtaining unit, an estimating unit, a setting unit, a calculating unit, and a detecting unit. The obtaining unit is configured to obtain an image in which an object is captured. The estimating unit is configured to estimate a condition of the object. The setting unit is configured to set, in the image, a plurality of areas that have at least one of a relative positional relationship altered according to the condition and a shape altered according to the condition. The calculating unit is configured to calculate a feature value of an image covering the areas. The detecting unit is configured to compare the calculated feature value with a feature value of a predetermined registered object, and detect the registered object corresponding to the object.
    Type: Grant
    Filed: June 12, 2013
    Date of Patent: February 19, 2019
    Inventors: Hidetaka Ohira, Masahiro Sekine, Masashi Nishiyama
  • Patent number: 10210371
    Abstract: Method, means, portable terminal accessory and system for calibrating a sensor device comprising a positioning unit detecting the position of the electronic device, an image capturing unit capturing an image of the environment around the electronic device, a processing unit detecting the presence of at least one identifiable object in the image captured and from a comparison of the position of the object in relation to the position of the user determining the heading of a user of the electronic device. Once the heading of the user is determined, it is used to calibrate one or more sensor devices or sensor functionalities in the electronic device.
    Type: Grant
    Filed: October 30, 2012
    Date of Patent: February 19, 2019
    Inventors: Magnus Abrahamsson, Gunnar Klinghult, Andreas Kristensson, Martin Nystrom
  • Patent number: 10192131
    Abstract: An image identification system may identify key points on a known image, variations of the known image in different levels of blur, and an unidentified image. One or more geometric shapes may be formed from the key points. A match between the unidentified image and either the known image or a blurred variation of the known image may be determined by comparison of the respective geometric shapes.
    Type: Grant
    Filed: August 7, 2018
    Date of Patent: January 29, 2019
    Assignee: Blinkfire Analytics, Inc.
    Inventors: Stephen Joseph Olechowski, III, Nan Jiang, Alejandro Tatay de Pascual
  • Patent number: 10181186
    Abstract: The invention is a system designed to assist a hospital pharmacy in the compounding of medications comprising hazardous drugs. The system comprising: a safety cabinet, at least two robotic arm assemblies configured to simultaneously move vials and syringes within the safety cabinet, a plurality of cameras each installed at a specific location in the safety cabinet or on the robotic arm assemblies, and a processor. Each of the cameras is dedicated to provide real time digital images of the stage of the preparation process carried out at its location. Dedicated software and algorithms in the system processor allow almost all steps in the compounding process to be carried out automatically by the robotic arm assemblies without intervention by the operator or a supervisor and the cameras and imaging process algorithms are adapted to provide real-time feedback control of all stages of the compounding process.
    Type: Grant
    Filed: August 24, 2014
    Date of Patent: January 15, 2019
    Inventors: Marino Kriheli, Eric Shem-Tov, Gonen Daskal
  • Patent number: 10169656
    Abstract: Systems and devices including an imaging sensor to capture video sequences in an environment having safety concerns therein. The systems and devices further including a processor to generate driving series based on observations from the video sequences, and generate predictions of future events based on the observations using a dual-stage attention-based recurrent neural network (DA-RNN). The DA-RNN includes an input attention mechanism to extract relevant driving series, an encoder to encode the extracted relevant driving series into hidden states, a temporal attention mechanism to extract relevant hidden states, and a decoder to decode the relevant hidden states. The processor further generates a signal for initiating an action to machines to mitigate harm to items.
    Type: Grant
    Filed: August 28, 2017
    Date of Patent: January 1, 2019
    Assignee: NEC Corporation
    Inventors: Dongjin Song, Haifeng Chen, Guofei Jiang, Yao Qin
  • Patent number: 10157475
    Abstract: According the present invention there is provided a method for adjusting a component handling assembly, the component handling assembly comprising, a plurality of stations at least some of which have a nest which can receive a component, and a rotatable turret having a plurality of component handling heads, and wherein the turret can rotate to transport components between the plurality of stations, the method comprising the steps of, capturing a first image of a reference element located at a first station, using a camera which is located on the rotatable turret; identifying the position in the first image of the center of the reference element; rotating the turret so that the camera on the turret is in a position where it can capture a second image of nest of a second station; capturing a second image of the nest of the second station, using said camera; identifying the position in the second image of the center of the nest of the second station; superimposing a marker on the second image at the same positio
    Type: Grant
    Filed: April 12, 2016
    Date of Patent: December 18, 2018
    Inventors: Pierrick Abrial, Damien Coste, Marco Oberli, Patrice Schwindenhammer
  • Patent number: 10157477
    Abstract: Systems and methods are provided for estimating head pose data from a sequence of depth images of a human subject, and processing the data to generate a continuous estimate of the head pose in a 3-dimensional (3D) space, and to generate a 3D head model for display and further use. The subject is provided instructions to rotate their head in a first direction until a threshold angle of rotation is reached and then are provided instructions to rotate their head in a second direction. The depth camera provides a sequence of captured images which are processed to extract head meshes. After capture is complete the head meshes are merged to generate a 3D model of the subject's head.
    Type: Grant
    Filed: June 5, 2017
    Date of Patent: December 18, 2018
    Inventor: Shenchang Eric Chen
  • Patent number: 10151781
    Abstract: Systems and methods for detecting, decoupling and quantifying unresolved signals in trace signal data in the presence of noise with no prior knowledge of the signal characteristics (e.g., signal peak location, intensity and width) of the unresolved signals. The systems and methods are useful for analyzing any trace data signals having one or multiple constituent signals, including overlapping constituent signals, and particularly useful for analyzing data signals which often contain an unknown number of constituent signals with varying signal characteristics, such as peak location, peak intensity and peak width, and varying resolutions. A general signal model function is assumed for each unknown, constituent signal in the trace signal data.
    Type: Grant
    Filed: March 7, 2018
    Date of Patent: December 11, 2018
    Inventor: Patrick G. Humphrey
  • Patent number: 10147136
    Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR A VIDEO REMOTE DEPOSIT CAPTURE PLATFORM (hereinafter “RDC-Video”) provides a platform for remote deposit by obtaining images of a check from streaming video captured by a video camera, wherein the RDC-Video transforms captured check images and/or entered check deposit information inputs via RDC-Video components into deposit confirmation outputs. For example, in one embodiment, a user may employ a personal computer connected to a web camera, and/or a smartphone with a built-in camera to initiate the remote deposit by holding a check in front of the camera, and the RDC-Video may capture images of the check and send them to a financial institution for deposit processing.
    Type: Grant
    Filed: November 7, 2016
    Date of Patent: December 4, 2018
    Assignee: United Services Automobile Association (USAA)
    Inventors: Teddy Voutour, Bharat Prasad
  • Patent number: 10132735
    Abstract: There is provided a microparticle sorting device that automatically optimizes a fluid stream. There is provided a microparticle sorting device that includes a voltage supply unit that supplies a driving voltage to a vibratory element that applies vibration to an orifice that produces a fluid stream, a charge unit that imparts charge to at least some droplets ejected from the orifice, deflecting plates, arranged opposing each other with the fluid stream S therebetween, that vary a travel direction of the droplets, and a first image sensor that acquires an image of the droplets passing between the deflecting plates.
    Type: Grant
    Filed: June 11, 2015
    Date of Patent: November 20, 2018
    Assignee: Sony Corporation
    Inventor: Yosuke Muraki
  • Patent number: 10127675
    Abstract: Systems and methods for generating a locally adaptive threshold image for foreground detection performing operations including creating a saliency edge strength image or layer indicating edge or border pixels of the nuclei by performing tensor voting on pixels neighboring the initial edge pixels within an image region to refine true edges are featured. Further, for each of a plurality of regions or blocks of the image, an adaptive threshold image is determined by sampling a foreground pixel and a background pixel for each initial edge pixel or refined edge pixel, generating histograms for both background and foreground saliency (or gradient magnitude) modulated histograms, determining a threshold range for each block of the image, and interpolating the threshold at each pixel based on the threshold range at each block. Comparing the input image with the resulting locally adaptive threshold image enables extraction of significantly improved foreground.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: November 13, 2018
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Christophe Chefd'hotel, Srinivas Chukka, Xiuzhong Wang