Patents by Inventor Williams J. F. Paquier

Williams J. F. Paquier 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 and apparatus for creating a pattern recognizer
    Patent number: 8290250
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Grant
    Filed: December 26, 2008
    Date of Patent: October 16, 2012
    Assignee: Five Apes, Inc.
    Inventor: Williams J. F. Paquier
  • MULTI-STAGE IMAGE PATTERN RECOGNIZER
    Publication number: 20120207394
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Application
    Filed: April 16, 2012
    Publication date: August 16, 2012
    Applicant: Five Apes, Inc.
    Inventor: Williams J. F. Paquier
  • Neural network based pattern recognizer
    Patent number: 8229209
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Grant
    Filed: December 26, 2008
    Date of Patent: July 24, 2012
    Assignee: Five Apes, Inc.
    Inventor: Williams J. F. Paquier
  • Multi-stage image pattern recognizer
    Patent number: 8160354
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Grant
    Filed: December 26, 2008
    Date of Patent: April 17, 2012
    Assignee: Five Apes, Inc.
    Inventor: Williams J. F. Paquier
  • METHOD AND APPARATUS FOR CREATING A PATTERN RECOGNIZER
    Publication number: 20100166315
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Application
    Filed: December 26, 2008
    Publication date: July 1, 2010
    Inventor: Williams J. F. Paquier
  • MULTI-STAGE IMAGE PATTERN RECOGNIZER
    Publication number: 20100166320
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Application
    Filed: December 26, 2008
    Publication date: July 1, 2010
    Inventor: Williams J. F. Paquier
  • NEURAL NETWORK BASED PATTERN RECOGNIZER
    Publication number: 20100166298
    Abstract: An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.
    Type: Application
    Filed: December 26, 2008
    Publication date: July 1, 2010
    Inventor: Williams J. F. Paquier