Dynamic and static hand gesture recognition through low-level image analysis

• US 5,454,043 A
• Filed: 07/30/1993
• Issued: 09/26/1995
• Est. Priority Date: 07/30/1993
• Status: Expired due to Term

• Current Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Inventors: Freeman, William T.
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Bella, Matthew C.
• Application Number:
  US08/099,944
• Time in Patent Office: 788 Days
• Field of Search: 382/18, 382/1, 382/16, 382/51, 358/105, 358/125, 358/126, 348/169, 348/214, 348/578, 348/700, 395/152, 395/155, 395/119, 395/161, 395/100, 345/122, 345/158
• US Class Current: 382/168
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/1122 of movement trajectories
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06V 10/421 by analysing segments intersecting the pattern
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

A low-level model-free dynamic and static hand gesture recognition system utilizes either a 1-D histogram of frequency of occurrence vs. spatial orientation angle for static gestures or a 2-D histogram of frequency of occurrence vs. space-time orientation for dynamic gestures. In each case the histogram constitutes the signature of the gesture which is used for gesture recognition. For moving gesture detection, a 3-D space-time orientation map is merged or converted into the 2-D space-time orientation histogram which graphs frequency of occurrence vs. both orientation and movement. It is against this representation or template that an incoming moving gesture is matched.

Claims

1. A machine for detecting a dynamic gesture comprising:

means for providing a training histogram corresponding to a predetermined gesture;

means for generating a video image of a gesturing object;

means for generating a 3-D dynamic gesturing object map corresponding to said video image, points on said image of said dynamic gesturing object each having a local spario-temporal image orientation, said 3-D map including vectors graphing frequency of occurance vs. spatio-temporal orientation;

means for converting said 3-D map into a 2-D histogram graphing angular orientation of the vectors of said 3-D map against position;

means for comparing said histograms; and

,

means for indicating a match between said histograms, thereby to detect said gesture.

2. The machine of claim 1, wherein said histogram generating means includes means for taking the derivative of the intensity of the video image of said gesture with respect to two orthogonal directions.

3. The machine of claim 2, wherein said histogram generating means further includes means for taking the derivative of the intensity of the video image with respect to time.

4. The machine of claim 2, and further including means for taking the arc tangent of said derivatives to obtain the dominant angle of said video image.

5. The machine of claim 2, and further including means for taking the sum of the squares of said derivatives to provide a gradient strength measurement and means for rejecting from the generation of a histogram gradient strength below a predetermined threshhold.

6. The machine of claim 1, and further including means for blurring said histograms to provide a smooth histogram signature.

7. The machine of claim 1, and further including means for applying local gain control to said histograms.