Patents by Inventor Mihai Ciuc

Mihai Ciuc 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).

  • Publication number: 20210089831
    Abstract: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.
    Type: Application
    Filed: March 12, 2020
    Publication date: March 25, 2021
    Applicant: FotoNation Limited
    Inventors: Alexandru MALAESCU, Adrian Dorin CAPATA, Mihai CIUC, Alina SULTANA, Dan FILIP, Liviu-Cristian DUTU
  • Publication number: 20200334853
    Abstract: Tracking units for facial features with advanced training for natural rendering of human faces in real-time are provided. An example device receives a video stream, and upon detecting a visual face, selects a 3D model from a comprehensive set of head orientation classes. The device determines modifications to the selected 3D model to describe the face, then projects a 2D model of tracking points of facial features based on the 3D model, and controls, actuates, or animates hardware based on the facial features tracking points. The device can switch among an example comprehensive set of 35 different head orientation classes for each video frame, based on suggestions computed from a previous video frame or from yaw and pitch angles of the visual head orientation. Each class of the comprehensive set is trained separately based on a respective collection of automatically marked images for that head orientation class.
    Type: Application
    Filed: July 6, 2020
    Publication date: October 22, 2020
    Inventors: Mihai CIUC, Stefan PETRESCU, Emanuela HALLER, Florin OPREA, Alexandru NICOLAESCU, Florin NANU, Iulian PALADE
  • Patent number: 10706577
    Abstract: Tracking units for facial features with advanced training for natural rendering of human faces in real-time are provided. An example device receives a video stream, and upon detecting a visual face, selects a 3D model from a comprehensive set of head orientation classes. The device determines modifications to the selected 3D model to describe the face, then projects a 2D model of tracking points of facial features based on the 3D model, and controls, actuates, or animates hardware based on the facial features tracking points. The device can switch among an example comprehensive set of 35 different head orientation classes for each video frame, based on suggestions computed from a previous video frame or from yaw and pitch angles of the visual head orientation. Each class of the comprehensive set is trained separately based on a respective collection of automatically marked images for that head orientation class.
    Type: Grant
    Filed: March 6, 2018
    Date of Patent: July 7, 2020
    Assignee: FotoNation Limited
    Inventors: Mihai Ciuc, Stefan Petrescu, Emanuela Haller, Florin Oprea, Alexandru Nicolaescu, Florin Nanu, Iulian Palade
  • Publication number: 20190279393
    Abstract: Tracking units for facial features with advanced training for natural rendering of human faces in real-time are provided. An example device receives a video stream, and upon detecting a visual face, selects a 3D model from a comprehensive set of head orientation classes. The device determines modifications to the selected 3D model to describe the face, then projects a 2D model of tracking points of facial features based on the 3D model, and controls, actuates, or animates hardware based on the facial features tracking points. The device can switch among an example comprehensive set of 35 different head orientation classes for each video frame, based on suggestions computed from a previous video frame or from yaw and pitch angles of the visual head orientation. Each class of the comprehensive set is trained separately based on a respective collection of automatically marked images for that head orientation class.
    Type: Application
    Filed: March 6, 2018
    Publication date: September 12, 2019
    Inventors: Mihai CIUC, Stefan PETRESCU, Emanuela HALLER, Florin OPREA, Alexandru NICOLAESCU, Florin NANU, Iulian PALADE
  • Patent number: 10346677
    Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: July 9, 2019
    Assignee: FotoNation Limited
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Vertan
  • Patent number: 10304166
    Abstract: Sub-regions within one or more face images are identified within a digital image, and enhanced by applying an artificial glint symmetrically and/or synchronously to image data corresponding to sub-regions of eyes within the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more eye regions of the face with the artificial glint.
    Type: Grant
    Filed: June 21, 2017
    Date of Patent: May 28, 2019
    Assignee: FotoNation Limited
    Inventors: Corneliu Florea, Cosmin Nicolae Stan, Mihai Ciuc, Adrian Capata
  • Publication number: 20180025218
    Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.
    Type: Application
    Filed: September 29, 2017
    Publication date: January 25, 2018
    Inventors: Eran STEINBERG, Peter CORCORAN, Yury PRILUTSKY, Petronel BIGIOI, Mihai CIUC, Stefanita CIUREL, Constantin VERTAN
  • Publication number: 20170352135
    Abstract: Sub-regions within one or more face images are identified within a digital image, and enhanced by applying an artificial glint symmetrically and/or synchronously to image data corresponding to sub-regions of eyes within the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more eye regions of the face with the artificial glint.
    Type: Application
    Filed: June 21, 2017
    Publication date: December 7, 2017
    Inventors: Corneliu FLOREA, Cosmin Nicolae STAN, Mihai CIUC, Adrian CAPATA
  • Patent number: 9779287
    Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.
    Type: Grant
    Filed: November 14, 2014
    Date of Patent: October 3, 2017
    Assignee: FotoNation Limited
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Verlan
  • Patent number: 9691136
    Abstract: Sub-regions within one or more face images are identified within a digital image, and enhanced by applying an artificial glint symmetrically and/or synchronously to image data corresponding to sub-regions of eyes within the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more eye regions of the face with the artificial glint.
    Type: Grant
    Filed: June 8, 2015
    Date of Patent: June 27, 2017
    Assignee: FOTONATION LIMITED
    Inventors: Corneliu Florea, Cosmin Nicolae Stan, Mihai Ciuc, Adrian Capata
  • Patent number: 9684966
    Abstract: A method for providing improved foreground/background separation in a digital image of a scene is disclosed. The method comprises providing a first map comprising one or more regions provisionally defined as one of foreground or background within the digital image; and providing a subject profile corresponding to a region of interest of the digital image. The provisionally defined regions are compared with the subject profile to determine if any of the regions intersect with the profile region. The definition of one or more of the regions in the map is changed based on the comparison.
    Type: Grant
    Filed: August 24, 2015
    Date of Patent: June 20, 2017
    Assignee: FotoNation Limited
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Alexei Pososin, Mihai Ciuc, Adrian Zamfir, Adrian Capata
  • Publication number: 20170070649
    Abstract: A digital camera has an integral flash and stores and displays a digital image. Under certain conditions, a flash photograph taken with the camera may result in a red-eye phenomenon due to a reflection within an eye of a subject of the photograph. A digital apparatus has a red-eye filter which analyzes at least one partial face region identified within the digital image for the red-eye phenomenon and modifies the image to eliminate the red-eye phenomenon by changing the red area to black. The modification of the image is enabled when a photograph is taken under conditions indicative of the red-eye phenomenon. The modification is subject to anti-falsing analysis which further examines the area around the red-eye area for indicia of the eye of the subject. The detection and correction can be optimized for performance and quality by operating on subsample versions of the image when appropriate.
    Type: Application
    Filed: August 9, 2016
    Publication date: March 9, 2017
    Inventors: Florin NANU, Eran STEINBERG, Stefan PETRESCU, Mihnea GANGEA, Adrian CAPATA, Mihai CIUC, Adrian ZAMFIR, Peter CORCORAN, Alexei POSOSIN, Petronel BIGIOI, Alexandru DRIMBAREAN
  • Patent number: 9412007
    Abstract: A digital camera has an integral flash and stores and displays a digital image. Under certain conditions, a flash photograph taken with the camera may result in a red-eye phenomenon due to a reflection within an eye of a subject of the photograph. A digital apparatus has a red-eye filter which analyzes at least one partial face region identified within the digital image for the red-eye phenomenon and modifies the image to eliminate the red-eye phenomenon by changing the red area to black. The modification of the image is enabled when a photograph is taken under conditions indicative of the red-eye phenomenon. The modification is subject to anti-falsing analysis which further examines the area around the red-eye area for indicia of the eye of the subject. The detection and correction can be optimized for performance and quality by operating on subsample versions of the image when appropriate.
    Type: Grant
    Filed: August 31, 2009
    Date of Patent: August 9, 2016
    Assignee: FOTONATION LIMITED
    Inventors: Florin Nanu, Eran Steinberg, Peter Corcoran, Alexei Pososin, Petronel Bigioi, Alexandru Drimbarean, Stefan Petrescu, Mihnea Gangea, Adrian Capata, Mihai Ciuc, Adrian Zamfir
  • Publication number: 20160078630
    Abstract: A method for providing improved foreground/background separation in a digital image of a scene is disclosed. The method comprises providing a first map comprising one or more regions provisionally defined as one of foreground or background within the digital image; and providing a subject profile corresponding to a region of interest of the digital image. The provisionally defined regions are compared with the subject profile to determine if any of the regions intersect with the profile region. The definition of one or more of the regions in the map is changed based on the comparison.
    Type: Application
    Filed: August 24, 2015
    Publication date: March 17, 2016
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Alexei Pososin, Mihai Ciuc, Adrian Zamfir, Adrian Capata
  • Publication number: 20150358535
    Abstract: Sub-regions within a face image are identified to be enhanced by applying a localized smoothing kernel to luminance data corresponding to the sub-regions of the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more enhanced sub-regions of the face.
    Type: Application
    Filed: April 13, 2015
    Publication date: December 10, 2015
    Inventors: Mihai Ciuc, Adrian Capata, Valentin Mocanu, Corneliu Florea, Alexei Pososin, Peter Corcoran
  • Publication number: 20150269712
    Abstract: Sub-regions within one or more face images are identified within a digital image, and enhanced by applying an artificial glint symmetrically and/or synchronously to image data corresponding to sub-regions of eyes within the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more eye regions of the face with the artificial glint.
    Type: Application
    Filed: June 8, 2015
    Publication date: September 24, 2015
    Inventors: Corneliu Florea, Cosmin Nicolae Stan, Mihai Ciuc, Adrian Capata
  • Patent number: 9117282
    Abstract: A method for providing improved foreground/background separation in a digital image of a scene is disclosed. The method comprises providing a first map comprising one or more regions provisionally defined as one of foreground or background within the digital image; and providing a subject profile corresponding to a region of interest of the digital image. The provisionally defined regions are compared with the subject profile to determine if any of the regions intersect with the profile region. The definition of one or more of the regions in the map is changed based on the comparison.
    Type: Grant
    Filed: January 28, 2013
    Date of Patent: August 25, 2015
    Assignee: FotoNation Limited
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Alexei Pososin, Mihai Ciuc, Adrian Zamfir, Adrian Capata
  • Patent number: 9053524
    Abstract: Sub-regions within one or more face images are identified within a digital image, and enhanced by applying an artificial glint symmetrically and/or synchronously to image data corresponding to sub-regions of eyes within the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more eye regions of the face with the artificial glint.
    Type: Grant
    Filed: August 17, 2013
    Date of Patent: June 9, 2015
    Assignee: FOTONATION LIMITED
    Inventors: Corneliu Florea, Cosmin Nicolae Stan, Mihai Ciuc, Adrian Capata
  • Patent number: 9007480
    Abstract: Sub-regions within a face image are identified to be enhanced by applying a localized smoothing kernel to luminance data corresponding to the sub-regions of the face image. An enhanced face image is generated including an enhanced version of the face that includes certain original pixels in combination with pixels corresponding to the one or more enhanced sub-regions of the face.
    Type: Grant
    Filed: July 30, 2009
    Date of Patent: April 14, 2015
    Assignee: FotoNation Limited
    Inventors: Mihai Ciuc, Adrian Capata, Valentin Mocanu, Alexei Pososin, Corneliu Florea, Peter Corcoran
  • Publication number: 20150067600
    Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.
    Type: Application
    Filed: November 14, 2014
    Publication date: March 5, 2015
    Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Verlan