Gesture recognition from depth and distortion analysis

A non-transitory computer-readable media storing computer-executable instructions that, when executed by a processor, cause the processor to perform acts comprising:

• analyzing depth information to determine when a selection tool touches or is within a threshold distance of a surface on which content is projected;
• acquiring a color image after the selection tool touches or is within the threshold distance of the surface;
• comparing the color image acquired after the selection tool touches or is within the threshold distance of the surface to a color image of the surface acquired prior to the selection tool touching or being within the threshold distance of the surface;
• identifying a distortion in the color image acquired after the selection tool touches or is within the threshold distance of the surface based at least in part on the comparing;
• and
• determining which portion of the content the selection tool is selecting based at least in part on the distortion.

A method comprising:

• under control of one or more computing systems configured with executable instructions,
• analyzing information acquired by a first camera to determine that a hand or finger of a user touches or is within a threshold distance of a surface on which content is projected;
• and
• analyzing information acquired by a second camera to identify a gesture of the hand or finger, the second camera being configured to generate one or more color images, and the analyzing the information acquired by the second camera comprising identifying distortion in a first of the one or more color images by comparing the first color image with a second of the one or more color images or a pre-stored image associated with the projected content.