Patents Examined by Jingge Wu
  • Patent number: 11132777
    Abstract: A method for generating a composite image includes receiving a first image that includes an eyeglass lens illuminated by a first illumination source radiating electromagnetic radiation in a first polarization state, and receiving a second image that includes the eyeglass lens illuminated by a second illumination source radiating electromagnetic radiation in a second polarization state. The second polarization state is different from the first polarization state, and the second illumination source is spatially separated from the first illumination source. The method also includes identifying, in the first image, a first portion that represents a reflection of the first illumination source on the eyeglass lens, and generating the composite image in which the first portion is replaced by a corresponding second portion from the second image. The first portion and the second portion represent substantially a same portion of the eyeglass lens.
    Type: Grant
    Filed: December 21, 2020
    Date of Patent: September 28, 2021
    Assignee: Advanced New Technologies Co., Ltd.
    Inventors: Reza R. Derakhshani, Raghunandan Pasula
  • Patent number: 11126883
    Abstract: A character string recognition apparatus includes a prediction unit that computes an attention single character certainty factor from a single character certainty factor, computed for a sequence of a partial pattern of an input pattern that is a character string serving as a recognition target, and from attention information computed by a recurrent neural network. The prediction unit shares a parameter among labels serving as recognition results, and uses the attention single character certainty factor as a feature value.
    Type: Grant
    Filed: March 27, 2019
    Date of Patent: September 21, 2021
    Assignee: FUJIFILM Business Innovation Corp.
    Inventor: Eiichi Tanaka
  • Patent number: 11120303
    Abstract: A reinforcement learning method and apparatus includes storing video frames in a video memory, performing a first preprocessing step of retrieving a sequence of n image frames of the stored video frames, and merging the n image frames in a fading-in fashion by incrementally increasing the intensity of each frame up to the most recent frame having full intensity to obtain a merged frame; and performing a training step of inputting the merged frame to the DQN and training the DQN to learn Q-values for all possible actions from a state represented by the merged frame with only a single forward pass through the network. The learning method and apparatus includes a second preprocessing step of removing the background from the merged frame. The method can be applied to any DQN learning method that uses a convolution neural network as its core value function approximator.
    Type: Grant
    Filed: October 24, 2019
    Date of Patent: September 14, 2021
    Inventors: Anas Mohammed Albaghajati, Lahouari Ghouti
  • Patent number: 11113857
    Abstract: The present disclosure provides a display method. The display method includes displaying a first image based on a first scene; detecting whether a first condition is satisfied; and displaying a second image based on the first condition being satisfied. The first image is an image corresponding to a first portion of the first scene, the second image includes a character image of a viewer and an image of a second portion of the first scene, and the first portion is different from the second portion.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: September 7, 2021
    Assignee: LENOVO (BEIJING) CO., LTD.
    Inventor: Yanyan Tong
  • Patent number: 11113507
    Abstract: One embodiment provides a method comprising identifying a salient part of an object in an input image based on processing of a region of interest (RoI) in the input image at an electronic device. The method further comprises determining an estimated full appearance of the object in the input image based on the salient part and a relationship between the salient part and the object. The electronic device is operated based on the estimated full appearance of the object.
    Type: Grant
    Filed: May 22, 2018
    Date of Patent: September 7, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Heming Zhang, Xiaolong Wang, Jingwen Zhu
  • Patent number: 11094048
    Abstract: An image inspection device which enables the user to know the cause of an abnormality in a read image. The image inspection device includes: an image reader outputting a read image generated by reading an image formed on a sheet of paper by an image forming device; an image inspection section inspecting the read image and outputting an inspection result which takes the read image determined not to have an abnormality as a normal image and the read image determined to have the abnormality as an abnormal image; an inspection result report generator generating an inspection result report according to the read image and the inspection result; an inspection result report output section outputting the inspection result report; and a controller performing control to cause the inspection result report output section to output the normal image and the abnormal image in a comparable manner.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: August 17, 2021
    Assignee: Konica Minolta, Inc.
    Inventor: Yasumasa Tsukamoto
  • Patent number: 11083428
    Abstract: A medical image diagnosis apparatus according to an embodiment includes setting circuitry and image generating circuitry. The setting circuitry is configured to obtain position information with respect to a landmark of a patient in a first image generated by performing a first scan on the patient and to set a scan range to be used during a second scan by using the obtained position information, the position information being determined on a basis of the first image and expressed in an image taking system used during the first scan. The image generating circuitry is configured to generate a second image by performing the second scan on the scan range.
    Type: Grant
    Filed: February 27, 2018
    Date of Patent: August 10, 2021
    Inventors: Shinsuke Tsukagoshi, Takahiro Goto, Go Mukumoto
  • Patent number: 11087146
    Abstract: A lane-line recognizing apparatus includes an acquiring unit, an extractor, and an identifier including a storage and an estimator. The acquiring unit acquires a traveling environment information on a traveling environment in front of an own vehicle. The extractor extracts feature quantities of lane-line components of lane lines from each frame image on a basis of the traveling environment information acquired by the acquiring unit. The identifier identifies the lane lines on the basis of the feature quantities extracted by the extractor. The storage stores the feature quantities extracted by the extractor. When the feature quantities are extracted again after a transition from a condition where the lane lines are identifiable to a condition where the lane lines are unidentifiable, the estimator estimates, on the basis of the feature quantities stored in the storage, the lane lines after the transition to the condition where the lane lines are unidentifiable.
    Type: Grant
    Filed: July 17, 2019
    Date of Patent: August 10, 2021
    Inventor: Akihiro Watanabe
  • Patent number: 11076675
    Abstract: A method of camouflaging a tonal imperfection comprising the steps of: identifying a skin tone of a user comprising a tonal imperfection; instructing the user to select a pigmented cosmetic composition adapted to camouflage the tonal imperfection based on the user's skin tone; selecting the pigmented cosmetic composition; and selectively targeting and depositing the pigmented cosmetic composition substantially only onto the tonal imperfection; wherein the pigmented cosmetic composition comprises an average composition L* value of about 10 to about 40 units greater than an average skin L* value of the user. The pigmented cosmetic composition can comprise a particular set of L*C*h* values such that when deposited onto tonal imperfections, it can result in natural, flawless looking skin, while still remaining substantially undetectable to the naked eye.
    Type: Grant
    Filed: June 13, 2018
    Date of Patent: August 3, 2021
    Assignee: The Procter & Gamble Company
    Inventors: Janette Villalobos Lingoes, Thomas Elliot Rabe, Lissette D Schorsch, Timothy Edward Nolan, Faiz Feisal Sherman, Stephan Gary Bush, Stephan James Andreas Meschkat
  • Patent number: 11080881
    Abstract: Some systems include an illuminator configured to illuminate a scene, a detector configured to receive electromagnetic radiation from the scene, one or more retroreflective tags, and an image processor. Each of the one or more retroreflective tags is attached to or positioned near a corresponding target and is configured to reflect electromagnetic radiation from the illuminator toward the detector. The image processor can identify electromagnetic radiation reflected by one or more retroreflective tags to determine the presence of one or more retroreflective tags and corresponding targets in the scene. Retroreflective tags can include retroreflective portions and non-retroreflective portions such that, when electromagnetic radiation is incident upon the retroreflective tag, the retroreflective tag reflects the electromagnetic radiation in a pattern that corresponds to a code uniquely corresponding to the target.
    Type: Grant
    Filed: June 20, 2019
    Date of Patent: August 3, 2021
    Assignee: Infrared Integrated Systems Limited
    Inventors: Stuart Andrew Holliday, Timothy J. Wheatley, Neil Johnson
  • Patent number: 11062163
    Abstract: Techniques for binarization and extraction of information from image data are disclosed. The inventive concepts include independently binarizing portions of the image data on the basis of individual features, e.g. per connected component, and using multiple different binarization thresholds to obtain the best possible binarization result for each portion of the image data. Determining the quality of each binarization result may be based on attempted recognition and/or extraction of information therefrom. Independently binarized portions may be assembled into a contiguous result. In one embodiment, a method includes: identifying a region of interest within a digital image; generating a plurality of binarized images based on the region of interest using different binarization thresholds; subjecting the region of interest within a digital image to a plurality of thresholding and extraction iterations; and extracting data from some or all of the plurality of binarized images.
    Type: Grant
    Filed: February 4, 2019
    Date of Patent: July 13, 2021
    Assignee: KOFAX, INC.
    Inventors: Christopher W. Thrasher, Alexander Shustorovich, Stephen Michael Thompson, Jan W. Amtrup, Anthony Macciola
  • Patent number: 11055827
    Abstract: The invention relates to an image processing apparatus for generating an HDR image associated with a first view on the basis of a plurality of LDR images, including a first LDR image and a second LDR image. The first LDR image is associated with the first view and a first exposure, i.e. a first dynamic range, and the second LDR image is associated with a second view and a second exposure, i.e. a second dynamic range. The image processing apparatus comprises a processor configured to provide a neural network having a plurality of neural subnetworks including a first neural subnetwork. The first neural subnetwork is configured to generate the HDR image on the basis of: (i) the first LDR image, (ii) the second LDR image, and (iii) a modified first LDR image. The modified first LDR image is associated with the first view and the second exposure.
    Type: Grant
    Filed: December 27, 2019
    Date of Patent: July 6, 2021
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Fahd Bouzaraa, Onay Urfalioglu, Ibrahim Halfaoui
  • Patent number: 11055511
    Abstract: A biological pattern information processing device includes: a biological pattern information acquisition unit that acquires biological pattern information indicating a biological pattern; and a singular region detection unit that detects a singular region including damage, from the biological pattern indicated by the acquired biological pattern information.
    Type: Grant
    Filed: March 30, 2016
    Date of Patent: July 6, 2021
    Inventors: Kan Satou, Yoshinori Suzuki, Masanori Mizoguchi, Masanori Hara
  • Patent number: 11049212
    Abstract: Provided is a data processing device and a method of operating the same. The data processing device includes: a plurality of preprocessors configured to perform correction processing on a plurality of sensor data; a first switching circuit configured to selectively map and input the plurality of sensor data from at least two sensors to at least two preprocessors among the plurality of preprocessors; and a hybrid data processing engine configured to perform at least one of image enhancement and depth information determination on the plurality of sensor data received, via an on-the-fly method, from the at least two preprocessors.
    Type: Grant
    Filed: September 16, 2019
    Date of Patent: June 29, 2021
    Inventors: Young Jun Kim, Jin Aeon Lee
  • Patent number: 11051032
    Abstract: An electronic device for encoding a picture is described. The electronic device includes a processor and instructions stored in memory that are in electronic communication with the processor. The instructions are executable to encode a gradual temporal layer access (GTLA) picture. The instructions are further executable to send the GTLA picture.
    Type: Grant
    Filed: September 11, 2019
    Date of Patent: June 29, 2021
    Inventor: Sachin G. Deshpande
  • Patent number: 11043006
    Abstract: Some embodiments of the invention provide a novel multi-layer node network to determine a set of misalignment values for a set of cameras that may be arranged with deviations from an ideal alignment or placement based on images captured by the set of cameras. A set of misalignment values for a set of cameras, in some embodiments, takes the form of translation vectors indicating the offsets between the centers of projection of the cameras relative to some useful coordinate system, and quaternions indicating the orientations of the cameras' optical axes and reference vectors associated with the cameras. Some embodiments train the multi-layer network using a set of inputs generated with random misalignments incorporated into the training set.
    Type: Grant
    Filed: January 12, 2018
    Date of Patent: June 22, 2021
    Inventors: Andrew Mihal, Steven Teig
  • Patent number: 11042783
    Abstract: Techniques described herein relate to generating a posteriori knowledge about where objects are typically located within environments to improve object location. In various implementations, output from vision sensor(s) of a robot may include visual frame(s) that capture at least a portion of an environment in which a robot operates/will operate. The visual frame(s) may be applied as input across a machine learning model to generate output that identifies potential location(s) of an object of interest. The robot's position/pose may be altered based on the output to relocate one or more of the vision sensors. One or more subsequent visual frames that capture at least a not-previously-captured portion of the environment may be applied as input across the machine learning model to generate subsequent output identifying the object of interest. The robot may perform task(s) that relate to the object of interest.
    Type: Grant
    Filed: January 3, 2020
    Date of Patent: June 22, 2021
    Inventor: Alexa Greenberg
  • Patent number: 11042986
    Abstract: A method for thinning and connection in linear object extraction from an image and including the following steps: 1. extracting direction features using various sliding windows from the binary image obtained of linear objects. 2. decomposing the binary image into several binary image layers according to the direction features. 3. extracting thinned curves and endpoints of each binary image layer by conducting curve fitting on each connected component using coordinate information. 4. connecting the thinned curves by computing spatial distances between the endpoints belonging to different thinned curves, angles between the tangential direction and connected direction vectors of the connected points. Finally, the road network image is constructed by overlaying image layers with the thinned curves.
    Type: Grant
    Filed: November 29, 2019
    Date of Patent: June 22, 2021
    Assignee: University of Electronic Science and Technology of China
    Inventors: Ling Tong, Fanghong Xiao
  • Patent number: 11030443
    Abstract: An information processing apparatus (2000) includes a determination unit (2020) and a notification unit (2040). The determination unit (2020) determines whether a field of view of a second camera is correct, on the basis of a first captured image (40), a second captured image (50), and relationship information (information indicating the relationship to be satisfied between a field of view of a first camera and the field of view of the second camera). In a case in which the field of view of the second camera is not correct, the notification unit (2040) notifies that the field of view of the second camera is not correct. The first camera is provided in a head-mounted display worn by a person. The second camera is provided in a part other than the head-mounted display.
    Type: Grant
    Filed: April 26, 2019
    Date of Patent: June 8, 2021
    Inventors: Ryoma Oami, Katsuhiko Takahashi, Yuusuke Konishi, Hiroshi Yamada, Hiroo Ikeda, Junko Nakagawa, Kosuke Yoshimi, Ryo Kawai, Takuya Ogawa
  • Patent number: 11030442
    Abstract: In a materials handling facility, events may be associated with users based on imaging data captured from multiple fields of view. When an event is detected at a location within the fields of view of multiple cameras, two or more of the cameras may be identified as having captured images of the location at a time of the event. Users within the materials handling facility may be identified from images captured prior to, during or after the event, and visual representations of the respective actors may be generated from the images. The event may be associated with one of the users based on distances between the users' hands and the location of the event, as determined from the visual representations, or based on imaging data captured from the users' hands, which may be processed to determine which, if any, of such hands includes an item associated with the event.
    Type: Grant
    Filed: December 13, 2017
    Date of Patent: June 8, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Alessandro Bergamo, Pahal Kamlesh Dalal, Nishitkumar Ashokkumar Desai, Jayakrishnan Kumar Eledath, Marian Nasr Amin George, Jean Laurent Guigues, Gerard Guy Medioni, Kartik Muktinutalapati, Robert Matthias Steele, Lu Xia