Search

Eric Pavie

from Rochester, NY

Eric Pavie Phones & Addresses

  • 22 Strathallan Park, Rochester, NY 14607
  • 42 Atkinson St, Rochester, NY 14608

Us Patents

  • Method For Automatically Classifying Images Into Events

    view source
  • US Patent:
    6606411, Aug 12, 2003
  • Filed:
    Sep 30, 1998
  • Appl. No.:
    09/163618
  • Inventors:
    Alexander C. Loui - Penfield NY
    Eric S. Pavie - Rochester NY
  • Assignee:
    Eastman Kodak Company - Rochester NY
  • International Classification:
    G06K 962
  • US Classification:
    382224, 382165, 382170
  • Abstract:
    A method for automatically classifying images into events, the method includes the steps of: receiving a plurality of images having either or both date and/or time of image capture; determining one or more largest time differences of the plurality of images based on clustering of the images; and separating the plurality of images into the events based on having one or more boundaries between events which one or more boundaries correspond to the one or more largest time differences.
  • Method Of Detecting Duplicate Pictures In An Automatic Albuming System

    view source
  • US Patent:
    6961463, Nov 1, 2005
  • Filed:
    Mar 29, 2000
  • Appl. No.:
    09/537334
  • Inventors:
    Alexander C. Loui - Penfield NY, US
    Eric S. Pavie - Rochester NY, US
  • Assignee:
    Eastman Kodak Company - Rochester NY
  • International Classification:
    G06K009/00
  • US Classification:
    382170, 382305
  • Abstract:
    Duplicate images are detected by providing at least two images captured at determinable times; computing an indication of the image content for each image; determining the time of capture of each of the images; and evaluating the indication of image content and the time of capture to determine whether the images are duplicate images. The images are divided into blocks and the indication of image content is computed from a histogram for each block. Thereafter, the step of evaluating the indication of image content and the time of capture comprises comparing one or more blocks of one image, using a histogram intersection metric, to corresponding blocks of another image and using the time difference between capture of the two images to determine whether the images are duplicate images.
  • Method For Automatically Classifying Images Into Events

    view source
  • US Patent:
    20030198390, Oct 23, 2003
  • Filed:
    Apr 15, 2003
  • Appl. No.:
    10/413673
  • Inventors:
    Alexander Loui - Penfield NY, US
    Eric Pavie - Rochester NY, US
  • Assignee:
    Eastman Kodak Company
  • International Classification:
    G06K009/62
  • US Classification:
    382/224000, 348/231200
  • Abstract:
    A method for automatically classifying images into events, the method includes the steps of: receiving a plurality of images having either or both date and/or time of image capture; determining one or more largest time differences of the plurality of images based on clustering of the images; and separating the plurality of images into the events based on having one or more boundaries between events which one or more boundaries correspond to the one or more largest time differences.
  • Method For Automatically Comparing Content Of Images For Classification Into Events

    view source
  • US Patent:
    6351556, Feb 26, 2002
  • Filed:
    Nov 20, 1998
  • Appl. No.:
    09/197363
  • Inventors:
    Alexander C. Loui - Penfield NY
    Eric S. Pavie - Rochester NY
  • Assignee:
    Eastman Kodak Company - Rochester NY
  • International Classification:
    G06K 934
  • US Classification:
    382164, 382168
  • Abstract:
    A method for comparing image content of first and second images, the method comprises the steps of extracting a portion of both the first and second images both of which portions are determined to include a main subject area of each image; dividing the main subject area of the images into a plurality of blocks; computing a color histogram for one block in each image; computing a histogram intersection value between the block of the first image and the block of the second image; and determining a first threshold value for the computed histogram intersection value that determines similarity between the block in the first image and the block in the second image.

Get Report for Eric Pavie from Rochester, NY
Control profile