Using A Facial Characteristic Patents (Class 382/118)
  • Patent number: 10129460
    Abstract: A method of recoding a photograph for use in a personal photo identification document such as a passport includes using a digital image capture system, including a digital camera, a computer processor, and memory to store specifications and requirements for a photo print in order to be compliant for use in a user selected photo ID such as a passport for a selected country or jurisdiction, using the digital image capture system to capture a facial image, using facial image processing techniques to provide automatic detection of a face and facial feature points on the facial image, processing the facial image and generating a visual indication of compliance, and when compliant, generating the photograph based on the compliant facial image.
    Type: Grant
    Filed: March 18, 2016
    Date of Patent: November 13, 2018
    Assignee: KODAK ALARIS INC.
    Inventors: Peter Stubler, David Kloosterman, Joseph A. Manico
  • Patent number: 10127475
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying images.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: November 13, 2018
    Assignee: Google LLC
    Inventors: Gregory S. Corrado, Jeffrey A. Dean, Samy Bengio, Andrea L. Frome, Jonathon Shlens
  • Patent number: 10129459
    Abstract: An image capturing method includes detecting a predetermined target, the predetermined target includes an object that is positioned on a user. A camera device is controlled to capture an image or a video, when the predetermined target is detected.
    Type: Grant
    Filed: February 23, 2016
    Date of Patent: November 13, 2018
    Assignees: Fu Tai Hua Industry (Shenzhen) Co., Ltd., HON HAI PRECISION INDUSTRY CO., LTD.
    Inventor: Feng Li
  • Patent number: 10127945
    Abstract: Implementations relate to visualizations including images based on image content. In some implementations, a computer-implemented method includes obtaining a set of images, determining one or more pixel characteristics of the set of images, and determining one or more faces depicted in the plurality of images based on one or more pixel characteristics. The method selects a group of images of the set of images, where each image in the group of images depicts a different group of faces than depicted in the other images in the set of images. The method generates a visualization including the group of images, and provides the visualization to a user device in response to a user request to cause the group of images to be displayed by the user device.
    Type: Grant
    Filed: March 15, 2016
    Date of Patent: November 13, 2018
    Assignee: Google LLC
    Inventors: Bo-Jhang Ho, Sevket Derin Babacan
  • Patent number: 10120879
    Abstract: Retrieval of images of objects from a large-scale database of object images, based on a query image. The database may, for example, contain images of objects such as faces, vehicles, people and luggage. Semantic attributes such as doors or windows in the case of vehicles are used as high level semantic cues to determine identities of objects in the images. Salient visual characteristics of the images are labeled with attribute information, and a transformation is learned so as to transform the labeled visual characteristics into a discrimination vector that discriminates between the labels. A similarity metric is learned using the discrimination vectors, such that different images depicting the same object are determined to be close while those having different objects are determined to be far apart. Candidates are retrieved based on a query image, and a re-ranking step may be applied to improve results. Validation experiments are described.
    Type: Grant
    Filed: November 26, 2014
    Date of Patent: November 6, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Le An, Changjian Zou, Liyan Zhang, Bradley Scott Denney, Dariusz Dusberger
  • Patent number: 10121060
    Abstract: Disclosed is a method and system for automatically forming a group to share a media file or adding the media file to an existing group. The method and system includes receiving, by a processor, a media file comprising an image, identifying, by the processor, the face of a first person in the image and the face of a second person in the image, identifying, by the processor, a first profile of the first person from the face of the first person and a second profile of the second person from the face of the second person, automatically forming, by the processor, a group of recipients in a messaging application, the forming of the group of recipients based on the first profile and the second profile, the group of recipients comprising the first person and the second person; and sharing, by the processor, the media file with the group.
    Type: Grant
    Filed: February 13, 2015
    Date of Patent: November 6, 2018
    Assignee: OATH INC.
    Inventors: Austin Shoemaker, Howard Law, Hamoun Parvizi, Venkat Krishnaraj, Soujanya Bhumkar
  • Patent number: 10123360
    Abstract: A system and method for secure wireless communication for transferring or sharing data between at least two devices over a wireless network. A set of pictures are displayed on a source device from which a picture is selected either manually by a user or automatically by the system. Information related to the selected picture is transmitted to a target device. A set of pictures are displayed on the target device. On the target device, a particular picture is selected either manually by a user of the target device or automatically by the system, and further transmitted back to the source device. At the source device, the picture received from the target device is matched with the selected picture previously transmitted by the source device. Upon a successful match, the source device transmits an authentication confirmation for pairing the source device and the target device and enables data transfer.
    Type: Grant
    Filed: January 21, 2015
    Date of Patent: November 6, 2018
    Inventors: Vijeth Pandit, Pratap Singh, Nagappan Arunachalam, Yogendra Patel, Valliappan Letchumanan
  • Patent number: 10114957
    Abstract: A content management system for collecting files from one or more submitters in a collection folder. A collector, who generates the collection folder, can invite one or more submitters to submit one or more files to the collection folder. Facial recognition is applied to the submitted files. The one or more submitters have limited rights to the collection folder. The limited rights can include uploading rights and prohibiting a submitter from viewing files that other submitters associated with the collection folder submitted. Thus, the collection folder is able to store files from the one or more submitters, but prevent them from viewing other's submissions.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: October 30, 2018
    Assignee: DROPBOX, INC.
    Inventors: Mindy Zhang, Pranav Piyush, Jan Senderek
  • Patent number: 10115004
    Abstract: Identifying a masked suspect is one of the toughest challenges in biometrics that exist. This is an important problem faced in many law-enforcement applications on almost a daily basis. In such situations, investigators often only have access to the periocular region of a suspect's face and, unfortunately, conventional commercial matchers are unable to process these images in such a way that the suspect can be identified. Herein, a practical method to hallucinate a full frontal face given only a periocular region of a face is presented. This approach reconstructs the entire frontal face based on an image of an individual's periocular region. By using an approach based on a modified sparsifying dictionary learning algorithm, faces can be effectively reconstructed more accurately than with conventional methods. Further, various methods presented herein are open set, and thus can reconstruct faces even if the algorithms are not specifically trained using those faces.
    Type: Grant
    Filed: June 17, 2015
    Date of Patent: October 30, 2018
    Assignee: Carnegie Mellon University
    Inventors: Felix Juefei-Xu, Dipan K. Pal, Marios Savvides
  • Patent number: 10108961
    Abstract: A user can be authenticated to any of a number of computing devices using an authentication process that recognizes the user and verifies that an actual human being is attempting to be authenticated, in order to minimize the ability of another person to spoof the authentication process. A model of a user can be generated and stored in the cloud, enabling that model to be synchronized across various devices. A user accessing one of these devices can have image information captured, which can be used with a facial recognition process, to recognize the user, and with a human verification process, to verify that the facial information corresponds to a human user. Various approaches such as visual analysis, three-dimensional imaging, and thermal imaging can be used to verify that the human user being recognized is interactive with the device.
    Type: Grant
    Filed: March 27, 2018
    Date of Patent: October 23, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Yicong Wang, Haizhi Xu
  • Patent number: 10108871
    Abstract: Spoof-detection and liveness analysis is performed using a software-based solution on a user device, such as a smartphone having a camera, audio output component (e.g., earpiece), and audio input component (e.g., microphone). One or more audio signals are emitted from the audio output component of the user device, reflect off a target, and are received back at the audio input component of the device. Based on the reflections, a determination is made as to whether the target is comprised of a three-dimensional face-like structure and/or face-like tissue. Using at least this determination, a finding is made as to whether the target is likely to be spoofed, rather than a legitimate, live person.
    Type: Grant
    Filed: April 27, 2017
    Date of Patent: October 23, 2018
    Assignee: EyeVerify Inc.
    Inventors: Reza R. Derakhshani, Joel Teply
  • Patent number: 10102505
    Abstract: A server-implemented method, a terminal-implemented method and a device for acquiring business card information are provided. The server-implemented method includes: receiving a request for acquiring business card information sent by a terminal of a first user, and the request for acquiring business card information includes facial feature information of a target user; determining identity information of the target user according to the facial feature information of the target user; verifying the request for acquiring business card information sent by the terminal of the first user; sending business card information corresponding to the identity information of the target user to the terminal of the first user if the request for acquiring business card information sent by the terminal of the first user is verified successfully.
    Type: Grant
    Filed: November 3, 2016
    Date of Patent: October 16, 2018
    Assignee: XIAOMI INC.
    Inventors: Zhijun Chen, Wendi Hou, Qiuping Qin
  • Patent number: 10096089
    Abstract: In one embodiment, a method includes accessing an original image of a person's face to be smoothed. A second image may be generated to include color information corresponding to those of the original image. The color information of the second image may be blurred. A filter image may be generated and may include an Alpha channel and color channels. The Alpha channel may include a mask representing opaque and transparent information, and the color channels may include a smoothed original image. High frequency color information may be determined from the color information of the original image and used to modify the color information of the filter image. A display may be outputted based on an overlay of the modified filter image over the original image.
    Type: Grant
    Filed: January 4, 2017
    Date of Patent: October 9, 2018
    Assignee: Facebook, Inc.
    Inventor: Andrei Igorevich Kopysov
  • Patent number: 10095913
    Abstract: A user authentication method includes matching an input image, comprising biometric information of a user, to a grid, selecting a reference cell from a database that stores respective location and image information of a plurality of cells previously randomly extracted from a reference biometric image, identifying a target image in the input image corresponding to the reference cell using the grid, comparing the target image to image information of the reference cell, and authenticating the user based on a result of the comparing.
    Type: Grant
    Filed: May 11, 2016
    Date of Patent: October 9, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Jonghan Kim
  • Patent number: 10095917
    Abstract: Systems, methods, and non-transitory computer readable media can align face images, classify face images, and verify face images by employing a deep neural network (DNN). A 3D-aligned face image can be generated from a 2D face image. An identity of the 2D face image can be classified based on provision of the 3D-aligned face image to the DNN. The identity of the 2D face image can comprise a feature vector.
    Type: Grant
    Filed: October 31, 2014
    Date of Patent: October 9, 2018
    Assignee: Facebook, Inc.
    Inventors: Yaniv Taigman, Ming Yang, Marc′Aurelio Ranzato
  • Patent number: 10089521
    Abstract: Technologies are provided herein for verifying identities of individuals via facial recognition and a graph database. Images of individuals to be identified can be can be captured with multiple mobile devices, such as by crowdsourcing, and transmitted to an identity verification server for identification. The identity verification server can maintain a graph database and locate a potential identity for an individual via facial recognition. Confirmation can be achieved by transmitting an image already in the database. A wide variety of validation techniques can be employed to filter out low quality data and improve the quality of matching. The identity verification server can manage profile information for the verified identity by creating and analyzing nodes and relationship records in the graph database. The identity verification server can update the graph database to track associations between verified identities.
    Type: Grant
    Filed: September 2, 2016
    Date of Patent: October 2, 2018
    Assignee: VeriHelp, Inc.
    Inventor: Bhushan Kolleri
  • Patent number: 10091436
    Abstract: An electronic device is provided. The electronic device includes a camera module and an image processing module. The image processing module may obtains a first image and a second image for the scene including a first object and a second object, identifies a first motion amount corresponding to the first object and a second motion amount corresponding to the second object using the first image and the second image, and applies different effects to a first image area corresponding to the first object and a second image area corresponding to the second object, at least, based on the first motion amount and the second motion amount.
    Type: Grant
    Filed: May 13, 2016
    Date of Patent: October 2, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ki-Huk Lee, Parijat Prakash Prabhudesai, Sabari Raju Shanmugam, Jin-Hee Na, Kshitij Dwivedi, Sanket Deshmukh, Siddarth Reddy Malreddy, Jong-Min Hyun
  • Patent number: 10091552
    Abstract: Methods and systems for a media guidance application that can identify and display a portion of a media asset that is of interest to a user. In some embodiments, the media guidance application may extract a portion of the media asset that encompasses a particular main action sequence. The extracted portion may also include an amount of additional content (e.g., content immediately before or after the main action sequence) that the media guidance application determines is necessary for the user to understand the main action sequence. In some embodiments, the media guidance application may extract several media assets, so that a user may graze through the extracted portions in series.
    Type: Grant
    Filed: September 19, 2012
    Date of Patent: October 2, 2018
    Assignee: Rovi Guides, Inc.
    Inventor: Michael Papish
  • Patent number: 10082664
    Abstract: Exemplary embodiments provide a tracking optics system for mobile devices. The tracking optics system may comprise a telescope longitudinally disposed in a case of the mobile device, wherein a length of the telescope is greater than a depth of the mobile device; an illuminator that emits a light source and low-power mode through the telescope towards a target of image capture; a two-axis gimbal mirror that is adjusted to steer the light source towards the target until the target is within a field of view of the telescope; and an image sensor that captures an image of the target in response to the illuminator emitting the light source in high power mode to flash the target.
    Type: Grant
    Filed: September 22, 2014
    Date of Patent: September 25, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Dirk Smits
  • Patent number: 10083490
    Abstract: Disclosed is a system, method, and computer program product for implementing a marketing automation tool that provides an improved approach for an integrated and/or customized workspace for a social relationship management system. The present invention provides a mechanism to allow the user of a SRM system to configure a workspace for the SRM product, to choose the specific functionality from the SRM suite to be displayed and executed for the user and to post a message while simultaneously viewing the workspace.
    Type: Grant
    Filed: August 17, 2015
    Date of Patent: September 25, 2018
    Assignee: ORACLE INTERNATIONAL CORPORATION
    Inventors: Horace Williams, II, John Benjamin Nolt
  • Patent number: 10083344
    Abstract: A facial recognition apparatus comprises a photographing parameter input unit that receives a photographing parameter(s); a lighting information estimation unit that estimates lighting information based on the photographing parameter(s); and a recognition accuracy control unit that controls a recognition accuracy parameter(s) based on the lighting information.
    Type: Grant
    Filed: November 27, 2013
    Date of Patent: September 25, 2018
    Assignee: NEC CORPORATION
    Inventor: Yuusuke Tomita
  • Patent number: 10076705
    Abstract: A system and method for conditioning execution of a control function on a determination of whether or not a person's attention is directed toward a predetermined device. The method involves acquiring data concerning the activity of a person who is in the proximity of the device, the data being in the form of one or more temporal samples. One or more of the temporal samples is then analyzed to determine if the person's activity during the time of the analyzed samples indicates that the person's attention is not directed toward the device. The results of the determination are used to ascertain whether or not the control function should be performed.
    Type: Grant
    Filed: January 7, 2014
    Date of Patent: September 18, 2018
    Assignee: Sony Interactive Entertainment Inc.
    Inventors: Hrishikesh R. Deshpande, Ruxin Chen
  • Patent number: 10073030
    Abstract: In order to accurately detect a subject to be detected and reduce manufacturing or maintenance costs, this optical detection device determines whether there is a subject to be detected by determining a correction coefficient for correcting data from an image captured by a capturing sensor through a filter unit with an image data estimation value from when an image is captured without the filter unit, and comparing an image data estimation value obtained through correction using the correction coefficient from the image data with captured data obtained by capturing a detection area in a state where the filter unit is not in front of the capturing sensor.
    Type: Grant
    Filed: December 1, 2015
    Date of Patent: September 11, 2018
    Assignee: KONICA MINOLTA, INC.
    Inventor: Takashi Morimoto
  • Patent number: 10075846
    Abstract: Systems and methods for continuous and transparent verification, authentication, and identification of individuals are provided. A method can include detecting a signal from a sensor embedded in a wearable device, determining a set of features unique to the wearer of the wearable device, creating a user profile of that individual, detecting a signal from a sensor of an unknown individual, determining a set of features unique to the unknown individual, and comparing the features of the unknown individual to the previously created user profile.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: September 11, 2018
    Assignee: The Florida International University Board of Trustees
    Inventors: Abbas Acar, Hidayet Aksu, Kemal Akkaya, A. Selcuk Uluagac
  • Patent number: 10074030
    Abstract: A device comprising: an input for receiving images captured by a camera, of an environment illuminated by light from a light source; an image processing module; and a verification module. The image processing module is configured to process one or more of the images to decode a timestamp modulated into the light, and to output an indication of the decoded timestamp. The verification module is arranged to receive the indication of the decoded timestamp output by the image processing module, and based thereon to perform an at least partially automated verification of a time at which the one or more images were captured.
    Type: Grant
    Filed: April 28, 2015
    Date of Patent: September 11, 2018
    Assignee: PHILIPS LIGHTING HOLDING B.V.
    Inventors: Alexander Henricus Waltherus Van Eeuwijk, William Nathan Chelton
  • Patent number: 10069967
    Abstract: Disclosed is a secure telephone call management system for authenticating users of a telephone system in an institutional facility. Authentication of the users is accomplished by using a personal identification number, preferably in conjunction with speaker independent voice recognition and speaker dependent voice identification. When a user first enters the system, the user speaks his or her name which is used as a sample voice print. During each subsequent use of the system, the user is required to speak his or her name. Voice identification software is used to verify that the provided speech matches the sample voice print. The secure system includes accounting software to limit access based on funds in a user's account or other related limitations. Management software implements widespread or local changes to the system and can modify or set any number of user account parameters.
    Type: Grant
    Filed: September 25, 2015
    Date of Patent: September 4, 2018
    Assignee: Global Tel*Link Corporation
    Inventor: Stephen Lee Hodge
  • Patent number: 10068324
    Abstract: A 3D profiling system of a semiconductor chip is provided and includes a storage unit that receives scanning electron microscope (SEM) images of a plurality of semiconductor devices having respective data with respect to a plurality of different components and gray levels of each SEM image. An extraction unit that performs principal component analysis (PCA) on the gray level of the SEM image and separates principal components from among the plurality of different components is also part of the system. Additionally, a calculation unit receives provision of actually measured values of the plurality of semiconductor devices, and applies a multiple linear regression to the principal components based on the measured values to complete a 3D profile of the semiconductor chip.
    Type: Grant
    Filed: October 12, 2016
    Date of Patent: September 4, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jung Soo Kim, Jin Kwan Kim, Chung Sam Jun, Yu sin Yang, Soo Seok Lee
  • Patent number: 10061976
    Abstract: The disclosure relates to a device for capturing person-specific data of a person, wherein the person-specific data comprises a facial image of the person, wherein the device has a camera for recording the facial image of the person, a lighting apparatus, and a semi-transparent mirror, wherein the semi-transparent mirror is arranged between the person and the camera, wherein the semi-transparent mirror is oriented such that, on the side of the semi-transparent mirror facing towards the person, the optical path of light incident on the semi-transparent mirror is parallel to the optical path of the portion of this light reflected back by the semi-transparent mirror, wherein the lighting apparatus is used to illuminate the person from the front, wherein the device also has a control unit for capturing an image, by generating light by means of the lighting apparatus in order to illuminate the face of the person and, during the illumination, capturing a first image of the face of the person by means of the camera,
    Type: Grant
    Filed: February 14, 2014
    Date of Patent: August 28, 2018
    Assignee: Bundesdruckerei GmbH
    Inventors: Alexander Bludau, Gerhard Lueth, Wolfgang Duemchen
  • Patent number: 10062170
    Abstract: According to one general aspect, an apparatus for extracting an object includes an image receiver configured to receive an image; a coupled saliency-map generator configured to generate a coupled saliency-map which is the sum of the product of a global saliency-map of the image and a predetermined weight value and a local saliency-map; an adaptive tri-map generator configured to generate an adaptive tri-map corresponding to the coupled saliency-map; an alpha matte generator configured to generate an alpha matte based on the adaptive tri-map; and an object detector configured to extract an object according to transparency of the alpha matte to generate an object image.
    Type: Grant
    Filed: August 5, 2016
    Date of Patent: August 28, 2018
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventor: Jae-Hwan Kim
  • Patent number: 10055646
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying people depicted in images. In one aspect, a process includes receiving an image from a camera. A face of a person is detected in the image. The image is compared to a set of images stored in a local cache. A determination is made whether the face of the person matches a face of a person depicted by at least one image of the set of images. In response to determining that the face of the person does not match a face of a person depicted by at least one image of the set of images, a selection is made of a highest quality image of the face of the person. A server system compares the highest quality image to images from data for the multiple people to identify the person.
    Type: Grant
    Filed: May 31, 2016
    Date of Patent: August 21, 2018
    Assignee: Accenture Global Solutions Limited
    Inventors: Cyrille Bataller, Anders Astrom, Vitalie Schiopu, Hakim Khalafi
  • Patent number: 10055880
    Abstract: The specification describes methods and systems for increasing a dimensional depth of a two-dimensional image of a face to yield a face image that appears three dimensional. The methods and systems identify key points on the 2-D image, obtain a texture map for the 2-D image, determines one or more proportions within the 2-D image, and adjusts the texture map of the 3-D model based on the determined one or more proportions within the 2-D image.
    Type: Grant
    Filed: December 6, 2016
    Date of Patent: August 21, 2018
    Assignee: Activision Publishing, Inc.
    Inventors: Paul D Yan, Thitikun Vorachart
  • Patent number: 10052553
    Abstract: An example system includes: a contactless communication part that performs contactless communication with a data storage medium having a contactless communication function; a data writing part that writes data to the data storage medium by the contactless communication part; a storage part that stores the data written by the data writing part; and a corruption determination part that determines whether the data stored in the data storage medium is corrupted or not. When the corruption determination part determines that the data is corrupted, the data writing part writes the data stored in the storage part, to the data storage medium.
    Type: Grant
    Filed: April 24, 2014
    Date of Patent: August 21, 2018
    Assignees: NINTENDO CO., LTD., AMBRELLA CO., LTD., THE POKÉMON COMPANY
    Inventors: Hiroshi Momose, Kaori Ando, Hideaki Araki, Takayuki Ito, Nayuta Taga, Yoshihiro Hatta
  • Patent number: 10055783
    Abstract: Systems and methods for identifying products in video are disclosed. A video containing at least one object is received, and video frames are extracted from the video for analysis. At least one object is extracted from one or more of the video frames to determine whether it corresponds to a product. Hyperlinks can be generated and embedded in a user interface to allow a user to purchase the product and/or retrieve additional information about the product.
    Type: Grant
    Filed: February 10, 2014
    Date of Patent: August 21, 2018
    Assignee: Amazon Technologies, Inc.
    Inventor: Brian J. Feinstein
  • Patent number: 10049516
    Abstract: A guest engagement system and associated methods provide seamless engagement with guests of facilities through the use of wireless sensing technologies. The system makes use of individual guest devices which are carried by guests and used to automatically identify and authenticate the guests throughout the facility. Services can thereby be seamlessly provided to the guests throughout the facility. The services include automatic unlocking of doors, including hotel or state room doors, based on the guests' immediate proximity to their assigned room's door. The services also include automated payment services provided at checkout or vending terminals, and automated log-on to interactive displays and portals, among others, based on secure wireless authentication of the guest devices.
    Type: Grant
    Filed: March 16, 2017
    Date of Patent: August 14, 2018
    Assignee: CARNIVAL CORPORATION
    Inventors: John Padgett, Michael G. Jungen, Douglas Steele, Kyle Prestenback, Richard J. Criado, Vince Ball, Adam Leonards, Glenn Curtis, Manny Vellon, Patrick Mendiuk, Sander Lam
  • Patent number: 10049262
    Abstract: A method for extracting a characteristic of a three-dimensional face image includes: performing face area division, to obtain a group of face areas; projecting each face area onto a corresponding regional bounding sphere; obtaining an indication of the corresponding face area according to the regional bounding sphere, and recording the indication as a regional bounding spherical descriptor of the face area; calculating a weight of the regional bounding spherical descriptor of the face area for each face area; and obtaining a characteristic of a three-dimensional face image according to the indication of the face area and the corresponding weight.
    Type: Grant
    Filed: July 11, 2016
    Date of Patent: August 14, 2018
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Yue Ming, Jie Jiang, Tingting Liu, Juhong Wang
  • Patent number: 10049433
    Abstract: The invention provides a facial image adjustment system and a facial image adjustment method. The facial image adjustment method comprises following steps: obtaining a image file; storing at least one known facial image and at least one adjustment parameter set corresponding to the at least one known facial image; and adjusting a first initial facial image corresponding to the at least one known facial image according to the at least one adjustment parameter set of the at least one known facial image in respond to recognize the image file comprising the first initial facial image corresponding to the at least one known facial image, so as to output a post-production facial image.
    Type: Grant
    Filed: March 17, 2016
    Date of Patent: August 14, 2018
    Assignee: HTC Corporation
    Inventor: Cheng-Hang Lin
  • Patent number: 10048748
    Abstract: A user device is enabled by an audio-visual assistant for audio-visual interaction with a user. The audio-visual assistant enables the user device to track the user's eyes and face to determine objects on the screen that the user is currently observing. Various tasks can be executed on the objects based on further input provided by the user. The user can provide further inputs via facial gestures, voice or combinations thereof for executing the various tasks.
    Type: Grant
    Filed: November 12, 2013
    Date of Patent: August 14, 2018
    Assignee: EXCALIBUR IP, LLC
    Inventors: Venkatraman Sridharan, Robert Jacob Kirk
  • Patent number: 10049263
    Abstract: A computer-implemented method of digital image analysis includes obtaining first digital video of a human subject that indicates facial expressions of the human subject; performing micro-expression analysis on the human subject using the first digital video; comparing results of the performed micro-expression analysis with content of a presentation determined to have been provided to the human subject at the same time that particular portions of the digital video were initially captured; and modifying a manner of performing interaction with the human subject or other human subjects based on the comparing of results.
    Type: Grant
    Filed: June 15, 2016
    Date of Patent: August 14, 2018
    Inventor: Stephan Hau
  • Patent number: 10049425
    Abstract: Techniques for merging multiple filters into a single GPU program is described. The system includes a filtering engine, which receives an input to apply a plurality of filters to a source image. The filtering engine identifies a first type of filter and a second type of filter from the input. The filtering engine identifies a supplemental transformation filter from the input, implements the supplemental transformation filter using a custom function to generate a color value at the source image and merges the first type of filter and the second type of filter based on the supplemental transformation filter. Finally, the filtering engine may apply the merged filter on the source image to generate a destination image.
    Type: Grant
    Filed: May 23, 2016
    Date of Patent: August 14, 2018
    Assignee: Google LLC
    Inventor: Brian Cornell
  • Patent number: 10042820
    Abstract: A method for converting an electronic document (ED) having a first format includes comparing an original width of the ED with a predetermined width and an original length of the ED with a predetermined length; splitting the ED into pieces in a width direction when the original width is greater than the predetermined width, and splitting the ED into pieces in a length direction when the original length is greater than the predetermined length, wherein each piece has a width and length less than or equal to the predetermined width and length; storing information representing geometric relationships of the pieces; converting the pieces from the first format into a second format; outputting the converted pieces as first output EDs; and outputting a second output ED having the second format, wherein the second output ED incorporates the first output EDs according to the information when displayed by a viewer application.
    Type: Grant
    Filed: July 31, 2015
    Date of Patent: August 7, 2018
    Assignee: Konica Minolta Laboratory U.S.A., Inc.
    Inventor: Paul Bosma
  • Patent number: 10043184
    Abstract: A system or method is provided to facilitate a payment transaction by utilizing facial recognition to identify the payee of the payment transaction. In particular, the system may remember a particular list of individuals to which a user has been or are frequently making payments. The facial profiles of the individuals in the particular list may be stored and referenced for identification. When the user is ready to transfer money to any of the frequent payees, the user may use any of the payee's pictures locally, anywhere on social platforms, or just by clicking the person. After the image is selected for payment, the system may analyze the image to match the image with existing face profiles of respective frequent payees. Once the payee is identified, the system may process the payment to the identified payee.
    Type: Grant
    Filed: May 30, 2014
    Date of Patent: August 7, 2018
    Assignee: PAYPAL, INC.
    Inventors: Priyanshu Agarwal, Prasanna Annamalai
  • Patent number: 10043034
    Abstract: A security code input may be obfuscated from a thermal imaging device by randomly heating a random set of inputs of an input device. The security code is inputted on an input device, which communicates with a security system to grant or deny access to a user based on an entry of the security code. The input device includes a plurality of hearing elements. The input device may receive an input from the user. A random set of heating elements including one or more heating elements, are generated from the plurality of heating elements. A temperature is determined for the one or more heating elements of the random set of heating elements. The temperature is then applied to the one or more heating elements of the random set of heating elements of the input device.
    Type: Grant
    Filed: October 19, 2016
    Date of Patent: August 7, 2018
    Assignee: International Business Machines Corporation
    Inventor: Brendan Murray
  • Patent number: 10037176
    Abstract: An image processing system includes a portable terminal and an image processing apparatus. The portable terminal includes a transmission processing unit that transmits each of the image data in units of the page of the document. The image processing apparatus includes a reception processing unit, a determination processing unit, and an output processing unit. The reception processing unit receives each of the image data in units of the page of the document transmitted from the portable terminal. The determination processing unit determines a page sequence of each of the image data in units of the page of the document based on each of the image data in units of the page of the document received by the reception processing unit. The output processing unit outputs each of the image data in units of the page of the document received by the reception processing unit in accordance with the page sequence.
    Type: Grant
    Filed: April 26, 2017
    Date of Patent: July 31, 2018
    Assignee: Kyocera Document Solutions Inc.
    Inventor: Masato Mori
  • Patent number: 10037481
    Abstract: The invention provides a system and a method for an otitis media database constructing. The steps of method comprise: First, receiving a plurality of tympanic membrane images, wherein the tympanic membrane images are ear infection in different types. Second, choosing one of the tympanic membrane images, then classifying into a plurality of anatomic regions based on a plurality of tissue types. Coding each of anatomic regions with a numerical number to describe its morbid condition, and obtaining an eigenvalue through collecting the numerical number of each anatomic region. Furthermore, repeatedly choosing other one of tympanic membrane images until each tympanic membrane image obtaining the eigenvalue. And obtaining a matrix through collecting the eigenvalue of each tympanic membrane image, then generating an otitis media database.
    Type: Grant
    Filed: July 14, 2016
    Date of Patent: July 31, 2018
    Assignee: National Central University
    Inventors: Men-Tzung Lo, Te-Yung Fang, Van-Truong Pham, Thi-Thao Tran, Pa-Chun Wang
  • Patent number: 10029176
    Abstract: A data processing apparatus that controls a screen displayed by a body-mounted data display device, includes a measurement unit that measures a viewing direction or a focal length of a user, based on a motion data of a head and eyes of the user who wears the data display device; an object display control unit that controls a viewing direction or a focal length of an object that moves in a virtual space displayed in the screen by an operation of the user to correspond to the viewing direction or the focal length of the user obtained from the measurement unit, respectively; and a content generation unit that generates a content to be displayed in a screen, in which the motion of the object obtained from the object display control unit is displayed, that is displayed by the data display device.
    Type: Grant
    Filed: September 12, 2016
    Date of Patent: July 24, 2018
    Assignee: KOEI TECMO GAMES CO., LTD.
    Inventor: Yosuke Aizawa
  • Patent number: 10032327
    Abstract: An access control system with facial recognition comprising a casing, a door handle, an interaction unit, a locking unit, a triggering unit controlling an unlock/lock state of the locking unit and a facial recognition unit. The interaction unit has an operation panel arranged above the door handle and protruded from the casing at an inclined acute angle relative to a vertical surface of the casing. The facial recognition unit comprises a data storage module, an image collection module comprising an infrared camera and an optical camera for user face scanning, an image processing module and a determination module. The infrared camera and the optical camera are fixed on the operation panel of the interaction unit, which enables authentication for users of different heights. Furthermore, the access control system can also be unlocked by passcode and/or a RFID card.
    Type: Grant
    Filed: April 7, 2017
    Date of Patent: July 24, 2018
    Assignee: BEIJING JIALAN TECHNOLOGY CO., LTD.
    Inventor: Mingjiang Xin
  • Patent number: 10032091
    Abstract: A collection of photos is organized by arranging a limited number of clusters of the photos on a predefined topology, so that similar photos are placed in the same cluster or a nearby cluster. Similarity is measured in attribute space. The attributes may include automatically recognized facial expression attributes.
    Type: Grant
    Filed: June 5, 2014
    Date of Patent: July 24, 2018
    Assignee: Emotient, Inc.
    Inventors: Javier Movellan, Joshua Susskind, Ken Denman
  • Patent number: 10032302
    Abstract: A sub-image of data of a first full image may be selected. The sub-image of data may at least partially obscure an object within the first full image. A request to replace the sub-image of data may be transmitted over a network. The request may include transmitting the full image and transmitting metadata associated with the first full image to one or more of a server computing device. The server computing device may analyze a history of images and select one or more images of the history of images that match one or more attributes of the metadata. The server computing device may replace the sub-image of data using the one or more images to generate at least a second full image that includes the object, wherein the object is not obscured. The second full image may be received over the network.
    Type: Grant
    Filed: February 12, 2018
    Date of Patent: July 24, 2018
    Assignee: International Business Machines Corporation
    Inventors: Swaminathan Balasubramanian, Radha M. De, Ashley D. Delport, Indrajit Poddar, Cheranellore Vasudevan
  • Patent number: 10032076
    Abstract: A method for displaying images includes clustering similar images in an album into a plurality of image groups when receiving an instruction for opening the album, selecting representative images from the image groups, and displaying the representative images.
    Type: Grant
    Filed: July 14, 2016
    Date of Patent: July 24, 2018
    Assignee: Xiaomi Inc.
    Inventors: Tao Zhang, Fei Long, Zhijun Chen
  • Patent number: 10032067
    Abstract: A system to recognize objects in an image includes an object detection network outputs a first hierarchical-calculated feature for a detected object. A face alignment regression network determines a regression loss for alignment parameters based on the first hierarchical-calculated feature. A detection box regression network determines a regression loss for detected boxes based on the first hierarchical-calculated feature. The object detection network further includes a weighted loss generator to generate a weighted loss for the first hierarchical-calculated feature, the regression loss for the alignment parameters and the regression loss of the detected boxes. A backpropagator backpropagates the generated weighted loss.
    Type: Grant
    Filed: July 29, 2016
    Date of Patent: July 24, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Mostafa El-Khamy, Arvind Yedla, Marcel Nassar, Jungwon Lee