Image recognition apparatus and method

• US 6,504,944 B2
• Filed: 02/01/1999
• Issued: 01/07/2003
• Est. Priority Date: 01/30/1998
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Mihara, Isao, Doi, Miwako
• Primary Examiner(s): Couso, Jose L.
• Assistant Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US09/241,078
• Publication Number:
  US 20020126879A1
• Time in Patent Office: 1,436 Days
• Field of Search: 382/118, 382/203, 382/100, 382/190, 382/154, 382/173, 382/195, 382/206, 382/285, 704/231, 704/235, 704/248, 704/270, 704/238, 704/200, 704/246
• US Class Current: 382/118
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

An image recognition apparatus and method in which an image capture device captures a distance image stream of an object body. A mouth portion extraction mechanism extracts a mouth portion from the distance image stream that has been extracted by the image capture device. An image recognition mechanism recognizes at least one of a lip shape and a lip movement based on a mouth portion distance image stream that has been extracted by the mouth portion extraction mechanism. Instructions for causing a computer to perform the method may be stored in a computer readable memory.

Claims

1. An image recognition apparatus comprising:

an image capturing device which captures a distance image having a depth value that represents a three-dimensional shape of an object;

a mouth portion extracting mechanism configured to extract a mouth portion from the distance image captured by the image capturing device;

an image recognizing mechanism configured to recognize a lip shape based on a mouth portion distance image extracted by the mouth portion extracting mechanism;

a direction recognizing mechanism configured to recognize a direction of a face of a speaker based on the mouth shape obtained by the image recognition mechanism;

a speech recognizing mechanism configured to recognize an input voice; and

a control mechanism configured to perform at least one of a control of causing the speech recognizing mechanism to start speech recognition when a recognition results of the direction recognizing mechanism is a square direction and a control of causing the speech recognizing mechanism to terminate speech recognition based on a recognition result of the direction recognizing mechanism.

2. An image recognition apparatus comprising:

image capturing device which captures a distance image stream having a depth value represents a three-dimensional shape of an object;

a mouth portion extracting mechanism configured to extract a mouth portion from the distance image stream captured by the image capturing device;

an image recognizing mechanism configured to recognize a lip movement based on a mouth portion distance image stream extracted by the mouth portion extracting mechanism;

a direction recognizing mechanism configured to recognize a direction of a face of a speaker based on the mouth movement obtained by the image recognition mechanism;

a speech recognizing mechanism configured to recognize an input voice; and

a control mechanism configured to perform at least one of a control of causing the speech recognizing mechanism to start speech recognition when a recognition results of the direction recognizing mechanism is a square direction and a control of causing the speech recognizing mechanism to terminate speech recognition when a recognition result of the direction recognizing mechanism is not a square direction.