Patents by Inventor Ara V. Nefian

Ara V. Nefian 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: 20120173549
    Abstract: A processing system may receive an example image for use in querying a collection of digital images. The processing system may use local and global feature descriptors to perform a content-based image comparison of the digital images with the example image, to automatically rank the digital images with respect to similarity to the example image. A local feature descriptor may represent a portion of the contents of a digital image. A global feature descriptor may represent substantially all of the contents of that digital image. The global feature descriptor may be content based, not keyword based. Intermediate and final classifiers may be used to perform the automatic ranking. Different intermediate classifiers may generate intermediate relevance metrics with respect to different modalities. The final classifier may use results from the intermediate classifiers to produce a final relevance metric for the digital images. Other embodiments are described and claimed.
    Type: Application
    Filed: March 15, 2012
    Publication date: July 5, 2012
    Inventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
  • Patent number: 8200027
    Abstract: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.
    Type: Grant
    Filed: November 23, 2010
    Date of Patent: June 12, 2012
    Assignee: Intel Corporation
    Inventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
  • Publication number: 20110081090
    Abstract: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.
    Type: Application
    Filed: November 23, 2010
    Publication date: April 7, 2011
    Inventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
  • Patent number: 7840076
    Abstract: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.
    Type: Grant
    Filed: November 22, 2006
    Date of Patent: November 23, 2010
    Assignee: Intel Corporation
    Inventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
  • Patent number: 7472063
    Abstract: A speech recognition method includes several embodiments describing application of support vector machine analysis to a mouth region. Lip position can be accurately determined and used in conjunction with synchronous or asynchronous audio data to enhance speech recognition probabilities.
    Type: Grant
    Filed: December 19, 2002
    Date of Patent: December 30, 2008
    Assignee: Intel Corporation
    Inventors: Ara V. Nefian, Xiaobo Pi, Luhong Liang, Xiaoxing Liu, Yibao Zhao
  • Patent number: 7389502
    Abstract: A method, apparatus and system including selecting a phase threshold value, receiving a plurality of sequenced buffers, determining a distance between centers of at least two consecutive histogram bins, comparing the distance with the selected threshold value, and determining major execution phases of an executable process based on the comparison.
    Type: Grant
    Filed: March 31, 2004
    Date of Patent: June 17, 2008
    Assignee: Intel Corporation
    Inventors: Ara V. Nefian, Ali-Reza Adl-Tabatabai
  • Publication number: 20080118151
    Abstract: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.
    Type: Application
    Filed: November 22, 2006
    Publication date: May 22, 2008
    Inventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
  • Patent number: 7224830
    Abstract: Human gestures are detected and/or tracked from a pair of digital video images. The pair of images may be used to provide a set of observation vectors that provide a three dimensional position of a subject's upper body. The likelihood of each observation vector representing an upper body component may be determined. Initialization of the model for detecting and tracking gestures may include a set of assumptions regarding the initial position of the subject in a set of foreground observation vectors.
    Type: Grant
    Filed: February 4, 2003
    Date of Patent: May 29, 2007
    Assignee: Intel Corporation
    Inventors: Ara V. Nefian, Robert D. Cavin
  • Patent number: 7209883
    Abstract: A speech recognition method includes use of synchronous or asynchronous audio and a video data to enhance speech recognition probabilities. A two stream factorial hidden Markov model is trained and used to identify speech. At least one stream is derived from audio data and a second stream is derived from mouth pattern data. Gestural or other suitable data streams can optionally be combined to reduce speech recognition error rates in noisy environments.
    Type: Grant
    Filed: May 9, 2002
    Date of Patent: April 24, 2007
    Assignee: Intel Corporation
    Inventor: Ara V. Nefian
  • Patent number: 7203368
    Abstract: A pattern recognition procedure forms a hierarchical statistical model using a hidden Markov model and a coupled hidden Markov model. The hierarchical statistical model supports a pa 20 layer having multiple supernodes and a child layer having multiple nodes associated with each supernode of the parent layer. After training, the hierarchical statistical model uses observation vectors extracted from a data set to find a substantially optimal state sequence segmentation.
    Type: Grant
    Filed: January 6, 2003
    Date of Patent: April 10, 2007
    Assignee: Intel Corporation
    Inventor: Ara V. Nefian
  • Patent number: 7171043
    Abstract: An image processing system useful for facial recognition and security identification obtains an array of observation vectors from a facial image to be identified. A Viterbi algorithm is applied to the observation vectors given the parameters of a hierarchical statistical model for each object, and a face is identified by finding a highest matching score between an observation sequence and the hierarchical statistical model.
    Type: Grant
    Filed: October 11, 2002
    Date of Patent: January 30, 2007
    Assignee: Intel Corporation
    Inventor: Ara V. Nefian
  • Patent number: 7165029
    Abstract: A speech recognition method includes use of synchronous or asynchronous audio and a video data to enhance speech recognition probabilities. A two stream coupled hidden Markov model is trained and used to identify speech. At least one stream is derived from audio data and a second stream is derived from mouth pattern data. Gestural or other suitable data streams can optionally be combined to reduce speech recognition error rates in noisy environments.
    Type: Grant
    Filed: May 9, 2002
    Date of Patent: January 16, 2007
    Assignee: Intel Corporation
    Inventor: Ara V. Nefian
  • Patent number: 7089185
    Abstract: An arrangement is provided for embedded coupled hidden Markov model. To train an embedded coupled hidden Markov model, training data is first segmented into uniform segments at different layers of the embedded coupled hidden Markov model. At each layer, a uniform segment corresponds to a state of a coupled hidden Markov model at that layer. An optimal segmentation is generated at the lower layer based on the uniform segmentation and is then used to update parameters of models associated with the states of coupled hidden Markov models at lower layer. The updated model parameters at the lower layer are then used to update the model parameters associated with states at the super layer.
    Type: Grant
    Filed: June 27, 2002
    Date of Patent: August 8, 2006
    Assignee: Intel Corporation
    Inventor: Ara V Nefian
  • Publication number: 20040151366
    Abstract: Human gestures are detected and/or tracked from a pair of digital video images. The pair of images may be used to provide a set of observation vectors that provide a three dimensional position of a subject's upper body. The likelihood of each observation vector representing an upper body component may be determined. Initialization of the model for detecting and tracking gestures may include a set of assumptions regarding the initial position of the subject in a set of foreground observation vectors.
    Type: Application
    Filed: February 4, 2003
    Publication date: August 5, 2004
    Inventors: Ara V. Nefian, Robert D. Cavin
  • Publication number: 20040131259
    Abstract: A pattern recognition procedure forms a hierarchical statistical model using a hidden Markov model and a coupled hidden Markov model. The hierarchical statistical model supports a pa20 layer having multiple supernodes and a child layer having multiple nodes associated with each supernode of the parent layer. After training, the hierarchical statistical model uses observation vectors extracted from a data set to find a substantially optimal state sequence segmentation.
    Type: Application
    Filed: January 6, 2003
    Publication date: July 8, 2004
    Inventor: Ara V. Nefian
  • Publication number: 20040071338
    Abstract: An image processing system useful for facial recognition and security identification obtains an array of observation vectors from a facial image to be identified. A Viterbi algorithm is applied to the observation vectors given the parameters of a hierarchical statistical model for each object, and a face is identified by finding a highest matching score between an observation sequence and the hierarchical statistical model.
    Type: Application
    Filed: October 11, 2002
    Publication date: April 15, 2004
    Inventor: Ara V. Nefian
  • Publication number: 20040002863
    Abstract: An arrangement is provided for embedded coupled hidden Markov model. To train an embedded coupled hidden Markov model, training data is first segmented into uniform segments at different layers of the embedded coupled hidden Markov model. At each layer, a uniform segment corresponds to a state of a coupled hidden Markov model at that layer. An optimal segmentation is generated at the lower layer based on the uniform segmentation and is then used to update parameters of models associated with the states of coupled hidden Markov models at lower layer. The updated model parameters at the lower layer are then used to update the model parameters associated with states at the super layer.
    Type: Application
    Filed: June 27, 2002
    Publication date: January 1, 2004
    Applicant: Intel Corporation
    Inventor: Ara V. Nefian
  • Publication number: 20030212557
    Abstract: A speech recognition method includes use of synchronous or asynchronous audio and a video data to enhance speech recognition probabilities. A two stream coupled hidden Markov model is trained and used to identify speech. At least one stream is derived from audio data and a second stream is derived from mouth pattern data. Gestural or other suitable data streams can optionally be combined to reduce speech recognition error rates in noisy environments.
    Type: Application
    Filed: May 9, 2002
    Publication date: November 13, 2003
    Inventor: Ara V. Nefian
  • Publication number: 20030212552
    Abstract: A visual feature extraction method includes application of multiclass linear discriminant analysis to the mouth region. Lip position can be accurately determined and used in conjunction with synchronous or asynchronous audio data to enhance speech recognition probabilities.
    Type: Application
    Filed: May 9, 2002
    Publication date: November 13, 2003
    Inventors: Lu Hong Liang, Xiaobo Pi, Xiaoxing Liu, Crusoe Mao, Ara V. Nefian
  • Publication number: 20030212556
    Abstract: A speech recognition method includes use of synchronous or asynchronous audio and a video data to enhance speech recognition probabilities. A two stream factorial hidden Markov model is trained and used to identify speech. At least one stream is derived from audio data and a second stream is derived from mouth pattern data. Gestural or other suitable data streams can optionally be combined to reduce speech recognition error rates in noisy environments.
    Type: Application
    Filed: May 9, 2002
    Publication date: November 13, 2003
    Inventor: Ara V. Nefian