Patents Examined by Christopher Wait
  • Patent number: 11070701
    Abstract: The present disclosure relates generally to signal encoding for product packaging and other printed objects. One implementation utilizes a target reflectance value for image content combined with an encoded signal at or around 660 nm to guide color changes. Luminance change is controlled through opposing color shifts, while maintaining the target reflectance value. Other implementations are provided.
    Type: Grant
    Filed: December 4, 2019
    Date of Patent: July 20, 2021
    Assignee: Digimarc Corporation
    Inventor: Jerry Allen McMahan, Jr.
  • Patent number: 11070705
    Abstract: A method includes obtaining a dynamic range representation of an image including multiple color channels. The dynamic range representation includes dynamic range information of pixels of the image in the color channels. The method further includes decomposing the dynamic range representation into a smooth portion, a color portion, and a detail portion. The smooth portion includes low frequency information of the pixels in the color channels. The color portion includes color intensity information of the pixels in the color channels. The detail portion includes high frequency information of the pixels in the color channels. The method also includes adjusting the smooth portion, the color portion, and the detail portion, respectively, to obtain an adjusted smooth portion, an adjusted color portion, and an adjusted detail portion, and combining the adjusted smooth portion, the adjusted color portion, and the adjusted detail portion to generate an output image.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: July 20, 2021
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventor: Zisheng Cao
  • Patent number: 11062419
    Abstract: An image processing system comprises one or more image sensors configured to take images, one or more image processors configured to process images taken by the one or more image sensors to produce output images, and one or more circuits configured to use output images. The one or more image processors comprise a set of one or more image processing stages, and each stage is configured to process images using a respective image processing operation. Processing circuitry is configured to verify image processing performed by one or more image processing stages, by inserting one or more probes into one or more images prior to the one or more images being processed by the one or more image processing stages, and attempting to identify the one or more probes in an output of the one or more processing stages.
    Type: Grant
    Filed: July 15, 2020
    Date of Patent: July 13, 2021
    Assignee: Arm Limited
    Inventor: Robin Paul Fell
  • Patent number: 11055805
    Abstract: The present disclosure relates generally to signal encoding for printed objects. One implementation selects an embed direction based on a minimal visibility axis of a 1 JND ellipse at a certain color center. Other technology provided.
    Type: Grant
    Filed: November 12, 2019
    Date of Patent: July 6, 2021
    Assignee: Digimarc Corporation
    Inventors: Alastair M. Reed, Kristyn R. Falkenstern
  • Patent number: 11057544
    Abstract: An image forming apparatus includes a feeder having a tray and configured to convey a sheet, a reader including a platen, an image forming unit configured to form a test pattern, and a controller. The controller adjusts, based on a result of reading the sheet having the test pattern formed thereon, a quality of an image to be formed by the image forming unit. In a case where a sheet of a first type having the test pattern formed thereon is placed on the tray, the feeder conveys the sheet. In a case where a sheet of a second type having the test pattern formed thereon is placed on the tray, the controller is configured to display a notification representing that the sheet is not to be conveyed by the feeder.
    Type: Grant
    Filed: May 4, 2020
    Date of Patent: July 6, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventor: Toyomi Hirao
  • Patent number: 11042778
    Abstract: A method, computer system, and a computer program product for generating one or more realistic x-ray angiography (XA) images for deep learning is provided. The present invention may include generating at least one three-dimensional (3D) model associated with a subject. The present invention may then include projecting the generated 3D model associated with the subject into one or more two-dimensional (2D) images associated with the subject. The present invention may also include creating the one or more realistic XA images of the subject from the one or more 2D images associated with the subject by utilizing a trained deep convolutional neural network.
    Type: Grant
    Filed: November 29, 2018
    Date of Patent: June 22, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventor: Omid Bonakdar Sakhi
  • Patent number: 11032442
    Abstract: An image processing apparatus of an embodiment includes an image processing unit to convert a color image to a monochrome image. The color image comprises pixels with a plurality of color components. The image processing unit is configured to generate a histogram from the monochrome image showing a color intensity gradation in the monochrome image by pixel frequency. A processor is configured to obtain a first threshold value based on the histogram, determine for each color component of each pixel in the color image whether or not each color component of the pixel is light based on the first threshold value, and generate a corrected color image by removing a background coloring from the color image by correcting each pixel for which all the color components are determined to be light.
    Type: Grant
    Filed: March 15, 2019
    Date of Patent: June 8, 2021
    Assignee: TOSHIBA TEC KABUSHIKI KAISHA
    Inventor: Keiko Kanamori
  • Patent number: 11030493
    Abstract: A method, computer system, and a computer program product for predicting a variation of sequential blood glucose levels by using deep learning is provided. The present invention may include training a predictor associated with a user by using a deep learning network. The present invention may further include predicting a plurality of sequential blood glucose levels by the trained predictor based on at least one meal image, at least one time-period, and at least one set of data associated with a plurality of blood glucose levels of the user.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: June 8, 2021
    Assignee: International Business Machines Corporation
    Inventors: Takuya Goto, Yutaka Oishi, Chiaki Oishi, Shuji Umehara, Masaki Saitoh
  • Patent number: 11017203
    Abstract: This disclosure describes techniques for identifying users that are enrolled for use of a user-recognition system and updating enrollment data of these users over time. To enroll in the user-recognition system, the user may initially scan his or her palm. The resulting image data may later be used when the user requests to be identified by the system by again scanning his or her palm. However, because the characteristics of user palms may change over the time, the user-recognition system may continue to build more and more data for use in recognizing the user, in addition to removing older data that may no longer accurately represent current characteristics of respective user palms.
    Type: Grant
    Filed: June 19, 2019
    Date of Patent: May 25, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Manoj Aggarwal, Jason Garfield, Korwin Jon Smith, Jordan Tyler Williams
  • Patent number: 11017260
    Abstract: A text region positioning method and device, and a computer readable storage medium, which relate to the field of image processing. The text region positioning method includes acquiring a variance graph on the basis of an original image; acquiring an edge image of the variance graph; if a difference value among distances between edge points of opposing positions in two adjacent edge lines in the edge image is within a preset distance difference range, then the region between the two adjacent edge lines is determined as a text region.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: May 25, 2021
    Assignees: BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO., LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.
    Inventors: Yongliang Wang, Qingze Wang, Biaolong Chen
  • Patent number: 11010913
    Abstract: A method is presented for determining a weight of all of the grains of an ear of a grain stalk. The method comprises providing a digital image of the ear in a spindle step view of the ear, wherein the ear is located in front of a reference card as a background, and determining the length of the ear by means of a comparison with the reference card. Furthermore, the method comprises determining a number of spindle steps of the ear by means of a template matching method, determining a number of grains of the ear and determining of the weight of all of the grains of the ear.
    Type: Grant
    Filed: October 12, 2017
    Date of Patent: May 18, 2021
    Assignee: BASF Agro Trademarks GmbH
    Inventors: Klaus Ruelberg, Gregor Fischer
  • Patent number: 11003965
    Abstract: An image is printed by using a first, second and third ink. A surface tension difference between a first ink and a third ink is smaller than a surface tension difference between the first ink and a second ink. A first gradation value for the first ink, a second gradation value for the second ink and a third gradation value for the third ink are quantized to generate a first quantized value, a second quantized value, and a third quantized value respectively. This quantization processing is performed such that, the number of pixels for each of which the first quantized value indicates printing, a the second quantized value indicates non-printing and the third quantized value indicates non-printing is greater than the number of pixels for each of which the first quantized value indicates printing and at least the second quantized value indicates printing or the third quantized value indicates printing.
    Type: Grant
    Filed: April 8, 2020
    Date of Patent: May 11, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventors: Shoei Moribe, Yumi Yanai
  • Patent number: 11004194
    Abstract: An inspection device includes: an image acquirer that acquires an inspection target image; an edge extractor that extracts an edge from each of the inspection target image and a reference image to be used in inspecting the output image; a defect candidate region extractor that extracts a defect candidate region having a possibility of a defect by comparing the inspection target image with the reference image; an edge direction calculator that calculates a direction of the edge in the inspection target image and a direction of the edge in the reference image; and a defect determiner that determines whether the defect candidate region is a defect, on a basis of the direction of the edge in the inspection target image and the direction of the edge in the reference image at a position corresponding to the defect candidate region.
    Type: Grant
    Filed: August 16, 2019
    Date of Patent: May 11, 2021
    Assignee: KONICA MINOLTA, INC.
    Inventors: Yusuke Mimura, Makoto Oki
  • Patent number: 11004169
    Abstract: Methods and apparatus, including computer program products, are provided for watermarking neural networks. In some embodiments, there may be provided a method. The method may include determining, for a neural network, an activation layer output by a hidden layer of the neural network. The method may include selecting a watermarking process. The method may include applying the selected watermarking process to the activation layer output to generate a key. The method may include storing, for the neural network to enable detection of copying of the neural network, the selected watermarking process and the key. Related systems, methods, and articles of manufacture are also described.
    Type: Grant
    Filed: August 27, 2019
    Date of Patent: May 11, 2021
    Assignee: Nokia Technologies Oy
    Inventors: Csaba Nemes, Sándor Jordán
  • Patent number: 10999475
    Abstract: The occurrence of more and the deterioration of performance are suppressed. A data compression unit stores identification data indicating the presence or absence of periodicity, and printing data correlated with the identification data in a first memory area of a RAM. A color conversion processing unit that performs speculation processing stores printing data that has undergone color conversion processing corresponding to printing by a printer in a second memory area of the RAM. A screen processing unit that performs speculation processing performs AM screen processing on printing data. The screen processing unit confirms the identification data stored in the first memory area of the RAM by the data compression unit, and in a case where the identification data indicates there is periodicity, instructs to perform color conversion processing corresponding to printing by a copier on printing data, and performs FM screen processing on the printing data.
    Type: Grant
    Filed: October 12, 2018
    Date of Patent: May 4, 2021
    Assignee: KYOCERA Document Solutions Inc.
    Inventors: Norifumi Miyahara, Kunihiko Shimamoto, Satoshi Hayama
  • Patent number: 10992840
    Abstract: An example is provided to calculate calibration data for or print quality data of a printer, in one example, image data on printed elements of a plurality of patches printed at different powers or intensities by a print device may be determined.
    Type: Grant
    Filed: October 20, 2016
    Date of Patent: April 27, 2021
    Assignee: HP Indigo B.V.
    Inventors: Uri Lidai, Rivay Mor, Lior Katz, Iliya Shahamov, Pavel Blinchuk
  • Patent number: 10992841
    Abstract: An information processing apparatus for managing a printing apparatus in a print site including at least one printing apparatus includes a memory that stores a set of instructions, and at least one processor that executes the instruction to determine a custom color that is used in a color verification operation of the at least one printing apparatus, obtain an input profile of a color verification setting of the determined custom color, display a screen for selecting whether or not to add a standard color corresponding to the obtained input profile to the color verification operation, and according to having received an instruction, via the screen, for adding the standard color to the color verification operation, instruct the at least one printing apparatus to perform printing in accordance with the color verification setting, including the input profile, for the custom color and the standard color.
    Type: Grant
    Filed: February 15, 2019
    Date of Patent: April 27, 2021
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Hiroyuki Toriyabe
  • Patent number: 10979603
    Abstract: The inventive plastic card permits a scuba diver to photograph underwater such as at 100 feet, without using external lighting, and to achieve quality photographic images as if external lighting actually had been used during the underwater photography.
    Type: Grant
    Filed: July 25, 2019
    Date of Patent: April 13, 2021
    Inventor: Steven Scagnelli
  • Patent number: 10977504
    Abstract: A vehicle-mounted image processing device 1000 acquires an image around a host vehicle 10, senses a feature amount of a target object present on a road surface from the image, and relative position coordinates with respect to the host vehicle 10, acquires information of a three-dimensional object around the host vehicle 10 and relative position coordinates of the three-dimensional object, distinguishes whether the feature amount is a feature amount of a feature on the road surface or a feature amount of a feature on the three-dimensional object by using a positional relationship between the feature amount and the three-dimensional object, and recognizes the target object by using a feature on the road surface. As a result, a vehicle-mounted image processing device, which is capable of avoiding misrecognition of a part of a three-dimensional object as a target object when sensing the target object present on a road surface such as a parking bay by using a camera image, is provided.
    Type: Grant
    Filed: August 31, 2017
    Date of Patent: April 13, 2021
    Assignee: Clarion Co., Ltd.
    Inventors: Takehito Ogata, Masahiro Kiyohara, Daisuke Fukuda, Yoshitaka Uchida
  • Patent number: 10977798
    Abstract: In some implementations a neural network is trained to perform to directly predict thin boundaries of objects in images based on image characteristics. A neural network can be trained to predict thin boundaries of objects without requiring subsequent computations to reduce the thickness of the boundary prediction. Instead, the network is trained to make the predicted boundaries thin by effectively suppressing non-maximum values in normal directions along what might otherwise be a thick predicted boundary. To do so, the neural network can be trained to determine normal directions and suppress non-maximum values based on those determined normal directions.
    Type: Grant
    Filed: August 20, 2019
    Date of Patent: April 13, 2021
    Assignee: Apple Inc.
    Inventors: Amit Kumar Kc, Daniel Ulbricht