Patents Examined by Brenda C Bernardi
-
Patent number: 10769501Abstract: The present disclosure relates to analysis of perturbed subjects using semantic embeddings. One example embodiment includes a method. The method includes applying a respective perturbation to each of a plurality of subjects in a controlled environment. The method also includes producing a respective visual representation for each of the perturbed subjects using at least one imaging modality. Further, the method includes obtaining, by a computing device for each of the respective visual representations, a corresponding semantic embedding associated with the respective visual representation. The semantic embedding associated with the respective visual representation is generated using a machine-learned, deep metric network model. In addition, the method includes classifying, by the computing device based on the corresponding semantic embedding, each of the visual representations into one or more groups.Type: GrantFiled: September 17, 2018Date of Patent: September 8, 2020Assignee: Google LLCInventors: Dale M. Ando, Marc Berndl, Lusann Yang, Michelle Dimon
-
Patent number: 10762486Abstract: There is provided a checkout apparatus (10) including an image data acquisition unit (11) which acquires data on an image, an image analysis unit (12) which recognizes a product in the image, using a feature value of appearance of each of a plurality of products registered in a feature value storage unit (14) and the image data; a registration unit (13) which registers the product recognized by the image analysis unit (12) as a checkout target, and a projection unit (15) which projects an image related to a checkout process on the product and/or a placement surface of a placement platform of the product.Type: GrantFiled: December 13, 2016Date of Patent: September 1, 2020Assignee: NEC CorporationInventors: Dai Kinno, Kota Iwamoto, Shinichi Matsumoto, Yoshihiro Itou, Shinya Yamasaki, Kanako Taga
-
Patent number: 10762360Abstract: Aspects of the disclosure relate to detecting unmapped drivable road surfaces. In one instance, sensor data captured by a sensor of an autonomous vehicle may be projected onto a grid having a plurality of cells. The plurality of cells may be classified by generating a label for each of the plurality of cells. Each label may identifies whether or not a corresponding cell contains a drivable surface. Ones of the plurality of cells may be clustered based on the labels to form a cluster of cells. An area of the cluster of cells may be compared to a map. Whether the area of the cluster of cells is an unmapped drivable road surface may be determined based on the comparison.Type: GrantFiled: November 19, 2018Date of Patent: September 1, 2020Assignee: Waymo LLCInventors: David Harrison Silver, Ivan Bogun, Romain Thibaux
-
Patent number: 10758171Abstract: Methods for tracking gum line changes by comparing digital 3D models of teeth and gingiva taken at different times. The digital 3D models are segmented to digitally identify the teeth from the gingiva, and the segmented digital 3D models are compared to detect gum line changes by determining differences between them relating to the gum line. Gum line changes can also be estimated by comparing one of the digital 3D models with a 3D model having a predicted original location of the gum line. Gum line change maps can be displayed to show the gum line changes determined through the tracking or estimating of changes. The digital 3D models can also be displayed with periodontal measurements placed upon them.Type: GrantFiled: May 7, 2019Date of Patent: September 1, 2020Assignee: 3M INNOVATIVE PROPERTIES COMPANYInventors: Alexandra R. Cunliffe, Guruprasad Somasundaram, Benjamin D. Zimmer, Steve Lastavich, Peter See, Kelly L. Stein
-
Patent number: 10755089Abstract: There is provided a framework including systems and methods for analyzing skin parameters from images or videos showing skin. Using a series of Hierarchical Differential Image Filters (HDIF), it becomes possible to detect different skin features such as wrinkles, spots, and roughness. The hierarchical differential image filter computes two enhancements to an image showing skin at two different levels of enhancement, determines a differential image using the two enhancements and computes the skin analysis rating using the differential image. These skin ratings are comparably accurate to actual ratings by dermatologists.Type: GrantFiled: June 18, 2019Date of Patent: August 25, 2020Assignee: L'OREALInventors: Parham Aarabi, Angel Jing Yi Zhang
-
Patent number: 10747996Abstract: An identification method includes acquiring image data, acquiring a photography condition for the image data, selecting a classifier corresponding to the acquired photography condition from a plurality of classifiers, each of which was created for one of a plurality of different photography conditions, and identifying a target in the acquired image data by using the selected classifier.Type: GrantFiled: November 2, 2017Date of Patent: August 18, 2020Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICAInventors: Yukie Shoda, Toru Tanigawa
-
Patent number: 10740636Abstract: A method, a system and a terminal for identity authentication, and a computer readable storage medium are provided. The method for identity authentication includes: acquiring a facial image of a person to be authenticated, and determining from the facial image facial feature information of the person to be authenticated; determining a suspected object using a face authentication platform according to the facial feature information of the person to be authenticated; acquiring a human body image of the person to be authenticated, and determining from the human body image a plurality of skeleton key points of the person to be authenticated; converting the skeleton key points into feature data; and recognizing an identity of the person to be authenticated according to the feature data of the person to be authenticated and information of the suspected object.Type: GrantFiled: October 5, 2018Date of Patent: August 11, 2020Assignee: Baidu Online Nework Technology (Beijing) Co., Ltd.Inventors: Wenbin Xie, Weiqing He, Fanping Liu, Xiangli Chen
-
Patent number: 10740655Abstract: A system and method automatically predicts an evolution of a cognitive score for a subject by classifying a cognitive data set for the subject into a first or second class by determining the cognitive set of data for each subject of a group, acquiring for each subject a neuropsychological score used for classifying each subject in the first or second class, and training a two-class machine learning classification algorithm on the cognitive data sets of all subjects. For each subject, the cognitive data set is used as input of the algorithm and the obtained classification of the subject as output target of the algorithm. The algorithm classifies each cognitive data set in the first or second class. The evolution of the cognitive score of a subject is predicted by the trained algorithm for automatically classifying a new cognitive dataset for the subject into the first or second class.Type: GrantFiled: July 2, 2018Date of Patent: August 11, 2020Assignees: Centre Hospitalier Universitaire Vaudois, Siemens Healthcare GmbHInventors: Jonas Richiardi, Tobias Kober, Julius Popp
-
Patent number: 10733450Abstract: Multiple video files that are captured by calibrated imaging devices may be annotated based on a single annotation of an image frame of one of the video files. An operator may enter an annotation to an image frame via a user interface, and the annotation may be replicated from the image frame to other image frames that were captured at the same time and are included in other video files. Annotations may be updated by the operator and/or tracked in subsequent image frames. Predicted locations of the annotations in subsequent image frames within each of the video files may be determined, e.g., by a tracker, and a confidence level associated with any of the annotations may be calculated. Where the confidence level falls below a predetermined threshold, the operator may be prompted to delete or update the annotation, or the annotation may be deleted.Type: GrantFiled: March 4, 2019Date of Patent: August 4, 2020Assignee: Amazon Technologies, Inc.Inventors: Roman Goldenberg, Gerard Guy Medioni, Ofer Meidan, Ehud Benyamin Rivlin, Dilip Kumar
-
Patent number: 10731864Abstract: A cooking appliance, in particular a commercial cooking appliance, with a housing, in which a cooking chamber is arranged, which has a cooking chamber opening, which can be opened and closed using a cooking chamber door; with an optical system, which has at least one optical capturing device above the cooking chamber opening; and with a protection against contamination for the optical system, wherein the protection against contamination has a catching surface, which can be moved using a drive unit and which, seen in the capturing direction of the optical system, is arranged in front thereof.Type: GrantFiled: June 1, 2018Date of Patent: August 4, 2020Assignee: CONVOTHERM ELEKTROGERAETE GMBHInventor: Hannes Wild
-
Patent number: 10733770Abstract: A method for performing fault-tolerant reconstruction of an image of an object is provided. The method includes acquiring a dataset corresponding to the object via a plurality of sensors, and detecting anomalous data within the dataset based at least in part on a statistical difference between the anomalous data and reference data within the dataset. The anomalous data is acquired by at least a first sensor of the plurality, and the reference data is acquired by at least a second sensor of the plurality that neighbors the first sensor.Type: GrantFiled: January 30, 2018Date of Patent: August 4, 2020Assignee: GENERAL ELECTRIC COMPANYInventors: Michel Souheil Tohme, Floribertus P. Heukensfeldt Jansen, Timothy Wayne Deller
-
Patent number: 10735878Abstract: Example techniques may involve a first playback device forming a stereo pair with a second playback device while the first playback device is placed onto a device base, and conversely, playing in mono while the first playback device is removed from the device base. In an example implementation, while a first playback device is placed onto a device base, the first playback device plays back audio content as a stereo pair with a second playback device. The first playback device detects, via a sensor, removal of the first playback device from the device base. When the first playback device is removed from the device base, the first playback device is configured to play back audio content in mono. Configuring the first playback device to play back audio content in mono removes the first playback device from the stereo pair with the second playback device.Type: GrantFiled: March 28, 2019Date of Patent: August 4, 2020Assignee: Sonos, Inc.Inventor: Benjamin Rappoport
-
Patent number: 10726264Abstract: Techniques for localizing a device based on images captured by the device. The techniques include receiving, from a device via a data communication network, image frame data for frames captured by an imaging camera included in the device, the frames including a first frame, automatically detecting real-world objects captured in the image frame data, automatically classifying the detected real-world objects as being associated with respective object classes, automatically identifying object class and instance dependent keypoints for the real-world objects based on the object classes associated with the real-world objects, and estimating a pose of the device for the first frame based on at least the identified object class and instance dependent keypoints.Type: GrantFiled: June 25, 2018Date of Patent: July 28, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Harpreet Singh Sawhney, Marc André Léon Pollefeys
-
Patent number: 10713484Abstract: A farming machine including a number of treatment mechanisms treats plants according to a treatment plan as the farming machine moves through the field. The control system of the farming machine executes a plant identification model configured to identify plants in the field for treatment. The control system generates a treatment map identifying which treatment mechanisms to actuate to treat the plants in the field. To generate a treatment map, the farming machine captures an image of plants, processes the image to identify plants, and generates a treatment map. The plant identification model can be a convolutional neural network having an input layer, an identification layer, and an output layer. The input layer has the dimensionality of the image, the identification layer has a greatly reduced dimensionality, and the output layer has the dimensionality of the treatment mechanisms.Type: GrantFiled: September 10, 2018Date of Patent: July 14, 2020Assignee: Blue River Technology Inc.Inventors: Andrei Polzounov, James Patrick Ostrowski, Lee Kamp Redden, Olgert Denas, Chia-Chun Fu, Chris Padwick
-
Patent number: 10702220Abstract: The invention relates to a tomography system (TA) comprising a first (QD1) and a second (QD2) beam source-detector pair for capturing one series (A1, A2) of projection image data sets (PB1, PB2) each from one projection angle (W1, W2) each and a volume image production system (VE) for producing a series (AV) of volume images (VB) of a vascular system (GS) while taking into account first confidence values (VW1) of the first pixel values (PW1) and/or while taking into account second confidence values (VW2) of the second pixel values (PW2). The confidence value (VW1, VW2) of a pixel value (PW1, PW2) depends on a pixel-specific traversing length (L) that a projection beam (PS1, PS2) traverses on a path through parts (Gi) of the vascular system (GS) from the first (Q1) or the second (Q2) beam source to a pixel-specific sensor element (S) of the associated first (D1) or second (D2) detector.Type: GrantFiled: December 9, 2015Date of Patent: July 7, 2020Assignee: Siemens Healthcare GmbHInventors: Klaus Klingenbeck, Markus Kowarschik, Christopher Rohkohl, Kevin Royalty, Sebastian Schafer
-
Patent number: 10706543Abstract: A method includes accessing a set of model points of a model of one or more passageways of a patient; detecting a point collection condition in image data obtained from an image-capture device of a catheter based upon machine vision; automatically initiating collection of a set of measured points based on detection of the point collection condition in the image data obtained from the image-capture device; performing a point set registration algorithm using the set of model points of the model of one or more passageways of the patient and the set of measured points to produce a registered set of model points; and displaying a visual representation of the registered set of model points in a user interface provided by a display system.Type: GrantFiled: August 11, 2016Date of Patent: July 7, 2020Assignee: INTUITIVE SURGICAL OPERATIONS, INC.Inventors: Caitlin Q. Donhowe, Vincent Duindam, Timothy D. Soper, Tao Zhao
-
Patent number: 10699111Abstract: Disclosed systems and methods generate page segmented documents from unstructured vector graphics documents. The page segmentation application executing on a computing device receives as input an unstructured vector graphics document. The application generates an element proposal for each of many areas on a page of the input document tentatively identified as being page elements. The page segmentation application classifies each of the element proposals into one of a plurality of defined type of categories of page elements. The page segmentation application may further refine at least one of the element proposals and select a final element proposal for each element within the unstructured vector document. One or more of the page segmentation steps may be performed using a neural network.Type: GrantFiled: January 18, 2019Date of Patent: June 30, 2020Assignee: Adobe Inc.Inventors: Scott Cohen, Brian Lynn Price, Dafang He, Michael F. Kraley, Paul Asente
-
Patent number: 10699104Abstract: The present disclosure provides a method, computer system and computer program product for obtaining an image. According to the method, an emotional status of a user is determined, at least one character can be determined based on a preference of the user, and at least one image comprising the at least one character can be obtained based on the emotional status of the user.Type: GrantFiled: May 3, 2018Date of Patent: June 30, 2020Assignee: International Business Machines CorporationInventors: Cheng Xu, Su Liu, Bing Fang, Li Ya Feng
-
Patent number: 10685254Abstract: The present invention relates to a device for encoding an anatomical shape (13) of a living being, comprising a receiving unit (12) for receiving an anatomical shape (13); a shape representation generating unit (14) for generating a shape representation of the anatomical shape (13) by using one or more shape representation models and determining the value of one or more shape representation coefficients of the one or more shape representation models; and a conversion unit (16) for converting the determined value of the one or more shape representation coefficients into a human-readable code comprising one or more human-readable characters.Type: GrantFiled: October 20, 2016Date of Patent: June 16, 2020Assignee: KONINKLIJKE PHILIPS N.V.Inventors: Frank Michael Weber, Irina Waechter-Stehle, Rafael Wiemker
-
Patent number: 10685233Abstract: Provided are methods, systems, and devices for generating semantic objects and an output based on the detection or recognition of the state of an environment that includes objects. State data, based in part on sensor output, can be received from one or more sensors that detect a state of an environment including objects. Based in part on the state data, semantic objects are generated. The semantic objects can correspond to the objects and include a set of attributes. Based in part on the set of attributes of the semantic objects, one or more operating modes, associated with the semantic objects can be determined. Based in part on the one or more operating modes, object outputs associated with the semantic objects can be generated. The object outputs can include one or more visual indications or one or more audio indications.Type: GrantFiled: October 24, 2017Date of Patent: June 16, 2020Assignee: Google LLCInventors: Tim Wantland, Donald A. Barnett, David Matthew Jones
