Patents by Inventor Albert Peter Blicher

Albert Peter Blicher 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).

  • Method for matching a two dimensional image to one of a plurality of three dimensional candidate models contained in a database
    Patent number: 6956569
    Abstract: A method for matching a two dimensional image to one of a plurality of three dimensional candidate models.
    Type: Grant
    Filed: March 30, 2000
    Date of Patent: October 18, 2005
    Assignee: NEC Corporation
    Inventors: Sebastien Roy, Albert Peter Blicher
  • Fast optimal linear approximation of the images of variably illuminated solid objects for recognition
    Patent number: 6888960
    Abstract: An efficient computation of low-dimensional linear subspaces that optimally contain the set of images that are generated by varying the illumination impinging on the surface of a three-dimensional object for many different relative positions of that object and the viewing camera. The matrix elements of the spatial covariance matrix for an object are calculated for an arbitrary pre-determined distribution of illumination conditions. The maximum complexity is reduced for the model by approximating any pair of normal-vector and albedo from the set of all such pairs of albedo and normals with the centers of the clusters that are the result of the vector quantization of this set. For an object, a viewpoint-independent covariance matrix whose complexity is large, but practical, is constructed and diagonalized off-line. A viewpoint-dependent covariance matrix is computed from the viewpoint-independent diagonalization results and is diagonalized online in real time.
    Type: Grant
    Filed: July 31, 2001
    Date of Patent: May 3, 2005
    Assignee: NEC Corporation
    Inventors: Penio S. Penev, Albert Peter Blicher, Rui Ishiyama
  • Fast optimal linear approximation of the images of variably illuminated solid objects for recognition
    Publication number: 20020186880
    Abstract: An efficient computation of low-dimensional linear subspaces that optimally contain the set of images that are generated by varying the illumination impinging on the surface of a three-dimensional object for many different relative positions of that object and the viewing camera. The matrix elements of the spatial covariance matrix for an object are calculated for an arbitrary pre-determined distribution of illumination conditions. The maximum complexity is reduced for the model by approximating any pair of normal-vector and albedo from the set of all such pairs of albedo and normals with the centers of the clusters that are the result of the vector quantization of this set. For an object, a viewpoint-independent covariance matrix whose complexity is large, but practical, is constructed and diagonalized off-line. A viewpoint-dependent covariance matrix is computed from the viewpoint-independent diagonalization results and is diagonalized online in real time.
    Type: Application
    Filed: July 31, 2001
    Publication date: December 12, 2002
    Inventors: Penio S. Penev, Albert Peter Blicher, Rui Ishiyama