Information recognition system and control system using same

• US 5,619,619 A
• Filed: 03/11/1994
• Issued: 04/08/1997
• Est. Priority Date: 03/11/1993
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hayashi, Shinji, Murai, Masahiko, Ohya, Junko, Chida, Yuichi, Takagi, Yasuo, Iino, Yutaka, Shinohara, Wataro
• Primary Examiner(s): Davis, George B.
• Application Number:
  US08/208,584
• Time in Patent Office: 1,124 Days
• Field of Search: 395/24, 395/11, 395/27
• US Class Current: 706/28
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

An information recognition circuit comprises a plurality of recognition processing units each composed of a neural network. Teacher signals and information signals to be processed are supplied to a plurality of the units, individually so as to obtain output signals by executing individual learning. Thereafter, the plural units are connected to each other so as to construct a large scale information recognition system. Further, in the man-machine interface system, a plurality of operating instruction data are prepared. An operator'"'"'s face is sensed by a TV camera to extract the factors related to the operator'"'"'s facial expression. The neural network analogizes operator'"'"'s feeling on the basis of the extracted factors. In accordance with the guessed results, a specific sort of the operating instruction is selected from a plurality of sorts of the operating instructions, and the selected instruction is displayed as an appropriate instruction for the operator. Further, the one-loop controller for automatizing operation comprises an input interface section for acquiring image information, an image recognition section for recognizing the image using the acquired image information, a control section for calculating control commands according to the image recognition results, and an output interface for outputting control commands to process actuators or subordinate controllers, respectively.

Claims

1. An information recognition system, comprising:

a plurality of recognition processing units arranged in a predetermined order, each composed of a neural network;

a plurality of teaching signal transmission lines through which teaching signals are individually supplied to each of said plurality of said recognition processing units;

a plurality of data transmission lines through which data to be learned are individually supplied to each of said plurality of said recognition processing units, said plurality of said recognition processing units generating output signals in response to said teaching signals and said data;

a plurality of output signal transmission lines through which said output signals are individually supplied as said data to succeeding recognition processing units among said recognition processing units;

a plurality of output signal external-transmission lines for transmitting output signals of said plurality of said recognition processing units externally to check the output signals thereof; and

switching means for selectively connecting each of said plurality of said output signal transmission lines to at least one of said plurality of said data transmission lines or to at least one of said plurality of said output signal external-transmission lines.