Method and apparatus for identifying input features for later recognition
First Claim
1. A method, comprising:
- defining an actor input for an actor;
defining a command associated with said actor input;
defining a region for said actor input;
detecting said actor input in said region;
executing said command in response to said actor input;
identifying at least one structural geometric salient feature of said actor from said actor input associated with said executed command;
defining a structural geometric actor model of said actor from said at least one structural geometric salient feature;
retaining a data set comprising at least one of said at least one structural geometric salient feature or said structural geometric actor model; and
using said data set to identify subsequent actor inputs without requiring further training process from said actor for identifying said salient features of said actor.
3 Assignments
0 Petitions
Accused Products
Abstract
Disclosed are method and apparatus to recognize actors during normal system operation. The method includes defining actor input such as hand gestures, executing and detecting input, and identifying salient features of the actor therein. A model is defined from salient features, and a data set of salient features and/or model are retained, and may be used to identify actors for other inputs. A command such as “unlock” may be executed in response to actor input. Parameters may be applied to further define where, when, how, etc. actor input is executed, such as defining a region for a gesture. The apparatus includes a processor and sensor, the processor defining actor input, identifying salient features, defining a model therefrom, and retaining a data set. A display may also be used to show actor input, a defined region, relevant information, and/or an environment. A stylus or other non-human actor may be used.
-
Citations
22 Claims
-
1. A method, comprising:
-
defining an actor input for an actor; defining a command associated with said actor input; defining a region for said actor input; detecting said actor input in said region; executing said command in response to said actor input; identifying at least one structural geometric salient feature of said actor from said actor input associated with said executed command; defining a structural geometric actor model of said actor from said at least one structural geometric salient feature; retaining a data set comprising at least one of said at least one structural geometric salient feature or said structural geometric actor model; and using said data set to identify subsequent actor inputs without requiring further training process from said actor for identifying said salient features of said actor.
-
-
2. A method, comprising:
-
establishing in a processor of a mobile device an imaging field of view for an imager in communication with said processor; defining an input region in said processor within said imaging field of view, said input region being smaller than and substantially fully within said field of view; defining an input in said processor comprising at least one of a hand posture and a hand gesture; defining in said processor an unlock command adapted to unlock said mobile device for a user to interface therewith; associating said unlock command with said input in said processor; outputting said imaging field of view to said user via a display; outputting to said display a visible two-dimensional virtual object occupying at least a portion of said region; obtaining with said imager at least one image of at least a portion of said field of view with said hand delivering said input in said region therein, and communicating said image to said processor; identifying in said processor a plurality of salient features of said hand comprising a structure of said hand from said input delivered by said hand in said region in said image, said structure comprising a plurality of fingertips of said hand, a plurality of fingers of said hand, and a geometry of said hand; executing said unlock command in said processor in response to said input so as to unlock said mobile device for said user to interface therewith; defining a model of said hand in said processor from said salient features, said hand model comprising said fingertips, said fingers, and said geometry thereof; retaining said hand model; and using said hand model to identify said hand in said processor in subsequent images. - View Dependent Claims (3, 4)
-
-
5. A method, comprising:
-
establishing in a processor an imaging field of view; defining an input region in said processor within said field of view; defining a user actor input in said processor; defining in said processor a command; associating said command with said input in said processor; outputting said imaging field of view to a display; outputting to said display a virtual object occupying at least a portion of said region; obtaining at least one image of at least a portion of said field of view with said input in said region; identifying in said processor a plurality of salient features of said user actor comprising a structure of said user actor from said input delivered by said user actor in said region in said image, said structure comprising a geometry of said user actor; executing said command in said processor in response to said input; defining a model of said user actor in said processor from said salient features, said user actor model comprising said geometry thereof; retaining said user actor model; and using said user actor model to identify said user actor in said processor in subsequent images. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. An apparatus, comprising:
-
a processor; an imager in communication with said processor; a display in communication with said processor wherein; said processor is adapted to establish an imaging field of view for said imager; said processor is adapted to define an input region within said field of view, said input region being smaller than and substantially fully within said field of view; said processor is adapted to define an input comprising at least one of a hand posture and a hand gesture; said processor is adapted to define an unlock command adapted to unlock said apparatus for a user to interface therewith; said processor is adapted to associate said unlock command with said input; said display is adapted to output said imaging field of view to said user; said display is adapted to output a visible two-dimensional virtual object occupying at least a portion of said region; said imager is adapted to obtain at least one image of at least a portion of said imaging field of view with said hand delivering said input in said region therein, and to communicate said image to said processor; said processor is adapted to identify a plurality of salient features of said hand comprising a structure of said hand from said input delivered by said hand in said region in said image, said structure comprising a plurality of fingertips of said hand, a plurality of fingers of said hand, and a geometry of said hand; said processor is adapted to execute said unlock command in response to said input so as to unlock said apparatus for said user to interface therewith; said processor is adapted define a model of said hand from said salient features, said hand model comprising said fingertips, said fingers, and said geometry thereof; said processor is adapted to retain said hand model; and said processor is adapted to use said hand model to identify said hand in subsequent images. - View Dependent Claims (20, 21, 22)
-
Specification