Robust video-based handwriting and gesture recognition for in-car applications

1. A method of receiving input from a user, said method comprising the steps of:

capturing images of a gesture made by a hand of the user with a surface of the vehicle in a background of the images, the surface being located on a steering wheel or on an armrest of a motor vehicle, the surface having a color;

identifying at least two separate and unconnected shapes in each of the captured images, the shapes having a first color, a background behind the hand in the visual images having a second color, the identifying including distinguishing the first color from the second color;

modifying the captured images by merging the separate and unconnected shapes into a single continuous shape corresponding to the user's hand in each of the captured images;

detecting a center of mass of the continuous shape of the hand in the captured images;

detecting a finger tip of the continuous shape of the hand in the captured images;

determining a first trajectory for the center of mass of the hand detected in the captured images;

determining a second trajectory for the finger tip of the hand detected in the captured images; and

determining an alphanumeric character represented by the gesture made by the hand, the determining being dependent upon both the first trajectory and the second trajectory.

2. The method of claim 1 wherein the surface has a vibration due to vibration of the motor vehicle, the sensing steps being dependent upon the vibration.

3. The method of claim 1 wherein the determining step comprises using a lookup table or algorithm relating the first and the second trajectories to the determined alphanumeric character.

4. The method of claim 1 comprising the further steps of:

informing the user of the alphanumeric character and/or a word in which the alphanumeric character is included; and

receiving feedback from the user regarding whether the alphanumeric character and/or word is an alphanumeric character and/or word that the user intended to be represented by the gesture made by the hand.

5. The method of claim 4 comprising the further step, in response to receiving feedback from the user that the alphanumeric character or word is correct, of transmitting an input to an electronic system, the input being dependent upon the alphanumeric character or word.

6. The method of claim 4 wherein the sensing and determining steps are repeated until a word formed by the alphanumeric characters is identified, the informing step comprising audibly or visually informing the user of the identified word.