Patents by Inventor Vuong Le

Vuong Le has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 9286717
    Abstract: According to an example, 3D modeling motion parameters may be simultaneously determined for video frames according to different first and second motion estimation techniques. In response to detecting a failure of the first motion estimation technique, the 3D modeling motion parameters determined according to the second motion estimation technique may be used to re-determine the 3D modeling motion parameters according to the first motion estimation technique.
    Type: Grant
    Filed: July 30, 2013
    Date of Patent: March 15, 2016
    Assignee: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
    Inventors: Vuong Le, Wei Hong, Kar-Han Tan, John Apostolopoulos
  • Patent number: 9202138
    Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. A profile model and a shape model may be applied to an object in an image to determine locations of feature points for each object component. Input may be received to move one of the feature points to a fixed location. Other ones of the feature points may be automatically adjusted to different locations based on the moved feature point.
    Type: Grant
    Filed: October 4, 2012
    Date of Patent: December 1, 2015
    Assignee: Adobe Systems Incorporated
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le, Lubomir D. Bourdev
  • Patent number: 9158963
    Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. An object in an input image may be detected. A profile model may be applied to determine feature point locations for each object component of the detected object. Applying the profile model may include globally optimizing the feature points for each object component to find a global energy minimum. A component-based shape model may be applied to update the respective feature point locations for each object component.
    Type: Grant
    Filed: October 4, 2012
    Date of Patent: October 13, 2015
    Assignee: Adobe Systems Incorporated
    Inventors: Jonathan W. Brandt, Zhe Lin, Lubomir D. Bourdev, Vuong Le
  • Publication number: 20150035820
    Abstract: According to an example, 3D modeling motion parameters may be simultaneously determined for video frames according to different first and second motion estimation techniques. In response to detecting a failure of the first motion estimation technique, the 3D modeling motion parameters determined according to the second motion estimation technique may be used to re-determine the 3D modeling motion parameters according to the first motion estimation technique.
    Type: Application
    Filed: July 30, 2013
    Publication date: February 5, 2015
    Applicant: Hewlett-Packard Development Company, L.P.
    Inventors: Vuong Le, Wei Hong, Kar-Han Tan, John Apostolopoulos
  • Patent number: 8824808
    Abstract: Various embodiments of methods and apparatus for facial retouching are disclosed. In one embodiment, a face in an input image is detected. One or more transformation parameters for the detected face are estimated based on a profile model. The profile model is applied to obtain a set of feature points for each facial component of the detected face. Global and component-based shape models are applied to generate feature point locations of each facial component of the detected face.
    Type: Grant
    Filed: July 31, 2012
    Date of Patent: September 2, 2014
    Assignee: Adobe Systems Incorporated
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le
  • Patent number: 8811686
    Abstract: Various embodiments of methods and apparatus for facial retouching are disclosed. In one embodiment, a face in an input image is detected. Independent sets of feature points are detected for respective facial feature components. A plurality of masks for each of the facial feature components is generated. Using the plurality of masks, retouch effects are performed to the facial feature components. Some embodiments provide for user interaction to constrain the mask generation.
    Type: Grant
    Filed: July 31, 2012
    Date of Patent: August 19, 2014
    Assignee: Adobe Systems Incorporated
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le
  • Publication number: 20140099031
    Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. A profile model and a shape model may be applied to an object in an image to determine locations of feature points for each object component. Input may be received to move one of the feature points to a fixed location. Other ones of the feature points may be automatically adjusted to different locations based on the moved feature point.
    Type: Application
    Filed: October 4, 2012
    Publication date: April 10, 2014
    Applicant: ADOBE SYSTEMS INCORPORATED
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le, Lubomir D. Bourdev
  • Publication number: 20140098988
    Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. An object in an input image may be detected. A profile model may be applied to determine feature point locations for each object component of the detected object. Applying the profile model may include globally optimizing the feature points for each object component to find a global energy minimum. A component-based shape model may be applied to update the respective feature point locations for each object component.
    Type: Application
    Filed: October 4, 2012
    Publication date: April 10, 2014
    Applicant: ADOBE SYSTEMS INCORPORATED
    Inventors: Jonathan W. Brandt, Zhe Lin, Lubomir D. Bourdev, Vuong Le
  • Publication number: 20130044947
    Abstract: Various embodiments of methods and apparatus for facial retouching are disclosed. In one embodiment, a face in an input image is detected. Independent sets of feature points are detected for respective facial feature components. A plurality of masks for each of the facial feature components is generated. Using the plurality of masks, retouch effects are performed to the facial feature components. Some embodiments provide for user interaction to constrain the mask generation.
    Type: Application
    Filed: July 31, 2012
    Publication date: February 21, 2013
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le
  • Publication number: 20130044958
    Abstract: Various embodiments of methods and apparatus for facial retouching are disclosed. In one embodiment, a face in an input image is detected. One or more transformation parameters for the detected face are estimated based on a profile model. The profile model is applied to obtain a set of feature points for each facial component of the detected face. Global and component-based shape models are applied to generate feature point locations of each facial component of the detected face.
    Type: Application
    Filed: July 31, 2012
    Publication date: February 21, 2013
    Inventors: Jonathan W. Brandt, Zhe Lin, Vuong Le
  • Patent number: 7209533
    Abstract: The present invention prevents the DLL from locking into the wrong phase, harmonic lock and hang. The detection is independent of temperature, voltage and process that the DLL is running. Including these mechanisms in the DLL design, the operating frequency range of the DLL can be extended significantly. Also many design blocks in the main loop can be reused for these additional circuitries, the design time of this DLL is much faster than to design a whole new hang or harmonic lock prevention circuitries.
    Type: Grant
    Filed: May 13, 2003
    Date of Patent: April 24, 2007
    Assignee: National Semiconductor Corporation
    Inventors: Hai Nguyen, Yu-Sheng (Stephen) Yang, Vuong Le