Method of fusing multiple information sources in image-based gesture recognition system

摘要

A method of interpreting input from a user includes providing a surface within reach of a hand of the user. A plurality of locations on the surface that are touched by the user are sensed. An alphanumeric character having a shape most similar to the plurality of touched locations on the surface is determined. The determining includes collecting information associated with hand region localized modules, and modeling the information using statistical models. The user is informed of the alphanumeric character and/or a word in which the alphanumeric character is included. Feedback is received from the user regarding whether the alphanumeric character and/or word is an alphanumeric character and/or word that the user intended to be determined in the determining step.

主权项

1. A method of interpreting input from a user, said method comprising:
providing a surface within reach of a hand of the user; sensing a plurality of locations on the surface that are touched by the user; determining an alphanumeric character having a shape most similar to the plurality of touched locations on the surface, the determining including:
collecting information associated with a plurality of hand localized modules corresponding to skin on the hand of the user and a background corresponding to the surface;generating a first score corresponding to a likelihood that a portion of the collected information corresponds to the skin on the hand of the user using a first lower level statistical model;generating a second score corresponding to a likelihood that a portion of the collected information corresponds to the background using a second lower level statistical model;generating a combined score based on the first score and the second score using a higher level statistical model;identifying the alphanumeric character using combined scores from the first and second lower level statistical models and the higher level statistical model; andgenerating an output for the user including the alphanumeric character; and receiving feedback from the user regarding whether the alphanumeric character included in the output corresponds to the plurality of touched locations on the surface.