Patents Assigned to Ezel Incorporated
  • Patent number: 5506915
    Abstract: An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an object sensing unit. The system also includes a memory for storing a matrix. A matrix calculation unit is included for performing matrix calculations and producing weighted data. A quantizer unit for quantizing the weighted data is included within the system. An adder unit and a maximum limiting unit are also included within the system. The adder unit adds matrices and the limiting unit limits values of an output matrix. Finally, the system includes a recognition unit for recognizing the sensed object based upon the output matrix.
    Type: Grant
    Filed: September 16, 1994
    Date of Patent: April 9, 1996
    Assignee: Ezel Incorporated
    Inventors: Sunao Takstori, Ryohei Kumagai, Makoto Yamamoto
  • Patent number: 5416850
    Abstract: An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an image input portion, an image processing portion and a recognition portion. The image processing portion includes a process unit for extracting characteristics and a frame memory for holding image data. The recognition portion, which includes a component for the learning of data to be associated, obtains the extracted characteristics from the image processing portion and performs associative pattern conversion from the image input portion. The system of the present invention may be applied to any neural network, preferably a matrix calculation type neural network.
    Type: Grant
    Filed: March 18, 1993
    Date of Patent: May 16, 1995
    Assignee: Ezel, Incorporated
    Inventors: Sunao Takatori, Ryohei Kumagai, Makoto Yamamoto
  • Patent number: 5040230
    Abstract: An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an image input portion, an image processing portion and a recognition portion. The image processing portion includes a process unit for extracting characteristics and a frame memory for holding image data. The recognition portion, which includes a component for the learning of data to be associated, obtains the extracted characteristics from the image processing portion and performs associative pattern conversion from the image input portion. The system of the present invention may be applied to any neutral network, preferably a matrix calculation type neural network.
    Type: Grant
    Filed: January 11, 1989
    Date of Patent: August 13, 1991
    Assignee: Ezel Incorporated
    Inventors: Sunao Takatori, Ryohei Kumagai, Makoto Yamamoto